summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool-net.rst139
-rw-r--r--tools/bpf/bpftool/Documentation/bpftool.rst6
-rw-r--r--tools/bpf/bpftool/bash-completion/bpftool17
-rw-r--r--tools/bpf/bpftool/main.c3
-rw-r--r--tools/bpf/bpftool/main.h8
-rw-r--r--tools/bpf/bpftool/map.c45
-rw-r--r--tools/bpf/bpftool/net.c272
-rw-r--r--tools/bpf/bpftool/netlink_dumper.c174
-rw-r--r--tools/bpf/bpftool/netlink_dumper.h95
-rw-r--r--tools/bpf/bpftool/prog.c1
-rw-r--r--tools/include/uapi/linux/bpf.h26
-rw-r--r--tools/include/uapi/linux/if_link.h2
-rw-r--r--tools/lib/bpf/Build2
-rw-r--r--tools/lib/bpf/bpf.c129
-rw-r--r--tools/lib/bpf/libbpf.c4
-rw-r--r--tools/lib/bpf/libbpf.h16
-rw-r--r--tools/lib/bpf/libbpf_errno.c1
-rw-r--r--tools/lib/bpf/netlink.c331
-rw-r--r--tools/lib/bpf/nlattr.c33
-rw-r--r--tools/lib/bpf/nlattr.h38
-rw-r--r--tools/testing/selftests/bpf/.gitignore6
-rw-r--r--tools/testing/selftests/bpf/Makefile8
-rw-r--r--tools/testing/selftests/bpf/bpf_flow.c373
-rw-r--r--tools/testing/selftests/bpf/config1
-rw-r--r--tools/testing/selftests/bpf/flow_dissector_load.c140
-rw-r--r--tools/testing/selftests/bpf/test_btf.c179
-rw-r--r--tools/testing/selftests/bpf/test_flow_dissector.c782
-rwxr-xr-xtools/testing/selftests/bpf/test_flow_dissector.sh115
-rw-r--r--tools/testing/selftests/bpf/test_progs.c20
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c56
-rw-r--r--tools/testing/selftests/bpf/test_tcpbpf_kern.c38
-rw-r--r--tools/testing/selftests/bpf/test_tcpbpf_user.c31
-rwxr-xr-xtools/testing/selftests/bpf/with_addr.sh54
-rwxr-xr-xtools/testing/selftests/bpf/with_tunnels.sh36
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh347
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/Makefile4
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh69
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh25
-rw-r--r--tools/testing/selftests/net/ip_defrag.c394
-rwxr-xr-xtools/testing/selftests/net/ip_defrag.sh39
-rw-r--r--tools/testing/selftests/net/tls.c57
42 files changed, 3861 insertions, 256 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
new file mode 100644
index 000000000000..408ec30d8872
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -0,0 +1,139 @@
+================
+bpftool-net
+================
+-------------------------------------------------------------------------------
+tool for inspection of netdev/tc related bpf prog attachments
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+ **bpftool** [*OPTIONS*] **net** *COMMAND*
+
+ *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] }
+
+ *COMMANDS* :=
+ { **show** | **list** } [ **dev** name ] | **help**
+
+NET COMMANDS
+============
+
+| **bpftool** **net { show | list } [ dev name ]**
+| **bpftool** **net help**
+
+DESCRIPTION
+===========
+ **bpftool net { show | list } [ dev name ]**
+ List bpf program attachments in the kernel networking subsystem.
+
+ Currently, only device driver xdp attachments and tc filter
+ classification/action attachments are implemented, i.e., for
+ program types **BPF_PROG_TYPE_SCHED_CLS**,
+ **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**.
+ For programs attached to a particular cgroup, e.g.,
+ **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**,
+ **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ users can use **bpftool cgroup** to dump cgroup attachments.
+ For sk_{filter, skb, msg, reuseport} and lwt/seg6
+ bpf programs, users should consult other tools, e.g., iproute2.
+
+ The current output will start with all xdp program attachments, followed by
+ all tc class/qdisc bpf program attachments. Both xdp programs and
+ tc programs are ordered based on ifindex number. If multiple bpf
+ programs attached to the same networking device through **tc filter**,
+ the order will be first all bpf programs attached to tc classes, then
+ all bpf programs attached to non clsact qdiscs, and finally all
+ bpf programs attached to root and clsact qdisc.
+
+ **bpftool net help**
+ Print short help message.
+
+OPTIONS
+=======
+ -h, --help
+ Print short generic help message (similar to **bpftool help**).
+
+ -v, --version
+ Print version number (similar to **bpftool version**).
+
+ -j, --json
+ Generate JSON output. For commands that cannot produce JSON, this
+ option has no effect.
+
+ -p, --pretty
+ Generate human-readable JSON output. Implies **-j**.
+
+EXAMPLES
+========
+
+| **# bpftool net**
+
+::
+
+ xdp:
+ eth0(2) driver id 198
+
+ tc:
+ eth0(2) htb name prefix_matcher.o:[cls_prefix_matcher_htb] id 111727 act []
+ eth0(2) clsact/ingress fbflow_icmp id 130246 act []
+ eth0(2) clsact/egress prefix_matcher.o:[cls_prefix_matcher_clsact] id 111726
+ eth0(2) clsact/egress cls_fg_dscp id 108619 act []
+ eth0(2) clsact/egress fbflow_egress id 130245
+
+|
+| **# bpftool -jp net**
+
+::
+
+ [{
+ "xdp": [{
+ "devname": "eth0",
+ "ifindex": 2,
+ "mode": "driver",
+ "id": 198
+ }
+ ],
+ "tc": [{
+ "devname": "eth0",
+ "ifindex": 2,
+ "kind": "htb",
+ "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
+ "id": 111727,
+ "act": []
+ },{
+ "devname": "eth0",
+ "ifindex": 2,
+ "kind": "clsact/ingress",
+ "name": "fbflow_icmp",
+ "id": 130246,
+ "act": []
+ },{
+ "devname": "eth0",
+ "ifindex": 2,
+ "kind": "clsact/egress",
+ "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
+ "id": 111726,
+ },{
+ "devname": "eth0",
+ "ifindex": 2,
+ "kind": "clsact/egress",
+ "name": "cls_fg_dscp",
+ "id": 108619,
+ "act": []
+ },{
+ "devname": "eth0",
+ "ifindex": 2,
+ "kind": "clsact/egress",
+ "name": "fbflow_egress",
+ "id": 130245,
+ }
+ ]
+ }
+ ]
+
+
+SEE ALSO
+========
+ **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index b6f5d560460d..8dda77daeda9 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -16,7 +16,7 @@ SYNOPSIS
**bpftool** **version**
- *OBJECT* := { **map** | **program** | **cgroup** | **perf** }
+ *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** }
*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
@@ -32,6 +32,8 @@ SYNOPSIS
*PERF-COMMANDS* := { **show** | **list** | **help** }
+ *NET-COMMANDS* := { **show** | **list** | **help** }
+
DESCRIPTION
===========
*bpftool* allows for inspection and simple modification of BPF objects
@@ -58,4 +60,4 @@ OPTIONS
SEE ALSO
========
**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
- **bpftool-perf**\ (8)
+ **bpftool-perf**\ (8), **bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 598066c40191..df1060b852c1 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -494,10 +494,10 @@ _bpftool()
_filedir
return 0
;;
- tree)
- _filedir
- return 0
- ;;
+ tree)
+ _filedir
+ return 0
+ ;;
attach|detach)
local ATTACH_TYPES='ingress egress sock_create sock_ops \
device bind4 bind6 post_bind4 post_bind6 connect4 \
@@ -552,6 +552,15 @@ _bpftool()
;;
esac
;;
+ net)
+ case $command in
+ *)
+ [[ $prev == $object ]] && \
+ COMPREPLY=( $( compgen -W 'help \
+ show list' -- "$cur" ) )
+ ;;
+ esac
+ ;;
esac
} &&
complete -F _bpftool bpftool
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d15a62be6cf0..79dc3f193547 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -85,7 +85,7 @@ static int do_help(int argc, char **argv)
" %s batch file FILE\n"
" %s version\n"
"\n"
- " OBJECT := { prog | map | cgroup | perf }\n"
+ " OBJECT := { prog | map | cgroup | perf | net }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, bin_name, bin_name);
@@ -215,6 +215,7 @@ static const struct cmd cmds[] = {
{ "map", do_map },
{ "cgroup", do_cgroup },
{ "perf", do_perf },
+ { "net", do_net },
{ "version", do_version },
{ 0 }
};
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 238e734d75b3..40492cdc4e53 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -136,6 +136,7 @@ int do_map(int argc, char **arg);
int do_event_pipe(int argc, char **argv);
int do_cgroup(int argc, char **arg);
int do_perf(int argc, char **arg);
+int do_net(int argc, char **arg);
int prog_parse_fd(int *argc, char ***argv);
int map_parse_fd(int *argc, char ***argv);
@@ -165,4 +166,11 @@ struct btf_dumper {
*/
int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
const void *data);
+
+struct nlattr;
+struct ifinfomsg;
+struct tcmsg;
+int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
+int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
+ const char *devname, int ifindex);
#endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index b455930a3eaf..e22fbe8b975f 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -71,6 +71,7 @@ static const char * const map_type_name[] = {
[BPF_MAP_TYPE_XSKMAP] = "xskmap",
[BPF_MAP_TYPE_SOCKHASH] = "sockhash",
[BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage",
+ [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
};
static bool map_is_per_cpu(__u32 type)
@@ -170,9 +171,28 @@ static int do_dump_btf(const struct btf_dumper *d,
if (ret)
goto err_end_obj;
- jsonw_name(d->jw, "value");
+ if (!map_is_per_cpu(map_info->type)) {
+ jsonw_name(d->jw, "value");
+ ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+ } else {
+ unsigned int i, n, step;
- ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+ jsonw_name(d->jw, "values");
+ jsonw_start_array(d->jw);
+ n = get_possible_cpus();
+ step = round_up(map_info->value_size, 8);
+ for (i = 0; i < n; i++) {
+ jsonw_start_object(d->jw);
+ jsonw_int_field(d->jw, "cpu", i);
+ jsonw_name(d->jw, "value");
+ ret = btf_dumper_type(d, map_info->btf_value_type_id,
+ value + i * step);
+ jsonw_end_object(d->jw);
+ if (ret)
+ break;
+ }
+ jsonw_end_array(d->jw);
+ }
err_end_obj:
/* end of key-value pair */
@@ -299,6 +319,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
jsonw_end_object(json_wtr);
}
jsonw_end_array(json_wtr);
+ if (btf) {
+ struct btf_dumper d = {
+ .btf = btf,
+ .jw = json_wtr,
+ .is_plain_text = false,
+ };
+
+ jsonw_name(json_wtr, "formatted");
+ do_dump_btf(&d, info, key, value);
+ }
}
jsonw_end_object(json_wtr);
@@ -644,12 +674,6 @@ static int do_dump(int argc, char **argv)
if (fd < 0)
return -1;
- if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
- p_err("Dumping maps of maps and program maps not supported");
- close(fd);
- return -1;
- }
-
key = malloc(info.key_size);
value = alloc_value(&info);
if (!key || !value) {
@@ -703,7 +727,9 @@ static int do_dump(int argc, char **argv)
} else {
print_entry_plain(&info, key, value);
}
- } else {
+ num_elems++;
+ } else if (!map_is_map_of_maps(info.type) &&
+ !map_is_map_of_progs(info.type)) {
if (json_output) {
jsonw_name(json_wtr, "key");
print_hex_data_json(key, info.key_size);
@@ -720,7 +746,6 @@ static int do_dump(int argc, char **argv)
}
prev_key = key;
- num_elems++;
}
if (json_output)
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
new file mode 100644
index 000000000000..ed205ee57655
--- /dev/null
+++ b/tools/bpf/bpftool/net.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <libbpf.h>
+#include <net/if.h>
+#include <linux/if.h>
+#include <linux/rtnetlink.h>
+#include <linux/tc_act/tc_bpf.h>
+#include <sys/socket.h>
+
+#include <bpf.h>
+#include <nlattr.h>
+#include "main.h"
+#include "netlink_dumper.h"
+
+struct ip_devname_ifindex {
+ char devname[64];
+ int ifindex;
+};
+
+struct bpf_netdev_t {
+ struct ip_devname_ifindex *devices;
+ int used_len;
+ int array_len;
+ int filter_idx;
+};
+
+struct tc_kind_handle {
+ char kind[64];
+ int handle;
+};
+
+struct bpf_tcinfo_t {
+ struct tc_kind_handle *handle_array;
+ int used_len;
+ int array_len;
+ bool is_qdisc;
+};
+
+struct bpf_filter_t {
+ const char *kind;
+ const char *devname;
+ int ifindex;
+};
+
+static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+ struct bpf_netdev_t *netinfo = cookie;
+ struct ifinfomsg *ifinfo = msg;
+
+ if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index)
+ return 0;
+
+ if (netinfo->used_len == netinfo->array_len) {
+ netinfo->devices = realloc(netinfo->devices,
+ (netinfo->array_len + 16) *
+ sizeof(struct ip_devname_ifindex));
+ if (!netinfo->devices)
+ return -ENOMEM;
+
+ netinfo->array_len += 16;
+ }
+ netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index;
+ snprintf(netinfo->devices[netinfo->used_len].devname,
+ sizeof(netinfo->devices[netinfo->used_len].devname),
+ "%s",
+ tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : "");
+ netinfo->used_len++;
+
+ return do_xdp_dump(ifinfo, tb);
+}
+
+static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+ struct bpf_tcinfo_t *tcinfo = cookie;
+ struct tcmsg *info = msg;
+
+ if (tcinfo->is_qdisc) {
+ /* skip clsact qdisc */
+ if (tb[TCA_KIND] &&
+ strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0)
+ return 0;
+ if (info->tcm_handle == 0)
+ return 0;
+ }
+
+ if (tcinfo->used_len == tcinfo->array_len) {
+ tcinfo->handle_array = realloc(tcinfo->handle_array,
+ (tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
+ if (!tcinfo->handle_array)
+ return -ENOMEM;
+
+ tcinfo->array_len += 16;
+ }
+ tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
+ snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
+ sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
+ "%s",
+ tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
+ tcinfo->used_len++;
+
+ return 0;
+}
+
+static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+ const struct bpf_filter_t *filter_info = cookie;
+
+ return do_filter_dump((struct tcmsg *)msg, tb, filter_info->kind,
+ filter_info->devname, filter_info->ifindex);
+}
+
+static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
+ struct ip_devname_ifindex *dev)
+{
+ struct bpf_filter_t filter_info;
+ struct bpf_tcinfo_t tcinfo;
+ int i, handle, ret = 0;
+
+ tcinfo.handle_array = NULL;
+ tcinfo.used_len = 0;
+ tcinfo.array_len = 0;
+
+ tcinfo.is_qdisc = false;
+ ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
+ &tcinfo);
+ if (ret)
+ goto out;
+
+ tcinfo.is_qdisc = true;
+ ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
+ &tcinfo);
+ if (ret)
+ goto out;
+
+ filter_info.devname = dev->devname;
+ filter_info.ifindex = dev->ifindex;
+ for (i = 0; i < tcinfo.used_len; i++) {
+ filter_info.kind = tcinfo.handle_array[i].kind;
+ ret = nl_get_filter(sock, nl_pid, dev->ifindex,
+ tcinfo.handle_array[i].handle,
+ dump_filter_nlmsg,
+ &filter_info);
+ if (ret)
+ goto out;
+ }
+
+ /* root, ingress and egress handle */
+ handle = TC_H_ROOT;
+ filter_info.kind = "root";
+ ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+ dump_filter_nlmsg, &filter_info);
+ if (ret)
+ goto out;
+
+ handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
+ filter_info.kind = "clsact/ingress";
+ ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+ dump_filter_nlmsg, &filter_info);
+ if (ret)
+ goto out;
+
+ handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
+ filter_info.kind = "clsact/egress";
+ ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+ dump_filter_nlmsg, &filter_info);
+ if (ret)
+ goto out;
+
+out:
+ free(tcinfo.handle_array);
+ return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+ int i, sock, ret, filter_idx = -1;
+ struct bpf_netdev_t dev_array;
+ unsigned int nl_pid;
+ char err_buf[256];
+
+ if (argc == 2) {
+ if (strcmp(argv[0], "dev") != 0)
+ usage();
+ filter_idx = if_nametoindex(argv[1]);
+ if (filter_idx == 0) {
+ fprintf(stderr, "invalid dev name %s\n", argv[1]);
+ return -1;
+ }
+ } else if (argc != 0) {
+ usage();
+ }
+
+ sock = bpf_netlink_open(&nl_pid);
+ if (sock < 0) {
+ fprintf(stderr, "failed to open netlink sock\n");
+ return -1;
+ }
+
+ dev_array.devices = NULL;
+ dev_array.used_len = 0;
+ dev_array.array_len = 0;
+ dev_array.filter_idx = filter_idx;
+
+ if (json_output)
+ jsonw_start_array(json_wtr);
+ NET_START_OBJECT;
+ NET_START_ARRAY("xdp", "%s:\n");
+ ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
+ NET_END_ARRAY("\n");
+
+ if (!ret) {
+ NET_START_ARRAY("tc", "%s:\n");
+ for (i = 0; i < dev_array.used_len; i++) {
+ ret = show_dev_tc_bpf(sock, nl_pid,
+ &dev_array.devices[i]);
+ if (ret)
+ break;
+ }
+ NET_END_ARRAY("\n");
+ }
+ NET_END_OBJECT;
+ if (json_output)
+ jsonw_end_array(json_wtr);
+
+ if (ret) {
+ if (json_output)
+ jsonw_null(json_wtr);
+ libbpf_strerror(ret, err_buf, sizeof(err_buf));
+ fprintf(stderr, "Error: %s\n", err_buf);
+ }
+ free(dev_array.devices);
+ close(sock);
+ return ret;
+}
+
+static int do_help(int argc, char **argv)
+{
+ if (json_output) {
+ jsonw_null(json_wtr);
+ return 0;
+ }
+
+ fprintf(stderr,
+ "Usage: %s %s { show | list } [dev <devname>]\n"
+ " %s %s help\n"
+ "Note: Only xdp and tc attachments are supported now.\n"
+ " For progs attached to cgroups, use \"bpftool cgroup\"\n"
+ " to dump program attachments. For program types\n"
+ " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n"
+ " consult iproute2.\n",
+ bin_name, argv[-2], bin_name, argv[-2]);
+
+ return 0;
+}
+
+static const struct cmd cmds[] = {
+ { "show", do_show },
+ { "list", do_show },
+ { "help", do_help },
+ { 0 }
+};
+
+int do_net(int argc, char **argv)
+{
+ return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
new file mode 100644
index 000000000000..6f5e9cc6836c
--- /dev/null
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#include <stdlib.h>
+#include <string.h>
+#include <libbpf.h>
+#include <linux/rtnetlink.h>
+#include <linux/tc_act/tc_bpf.h>
+
+#include <nlattr.h>
+#include "main.h"
+#include "netlink_dumper.h"
+
+static void xdp_dump_prog_id(struct nlattr **tb, int attr,
+ const char *mode,
+ bool new_json_object)
+{
+ if (!tb[attr])
+ return;
+
+ if (new_json_object)
+ NET_START_OBJECT
+ NET_DUMP_STR("mode", " %s", mode);
+ NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr]))
+ if (new_json_object)
+ NET_END_OBJECT
+}
+
+static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
+ const char *name)
+{
+ struct nlattr *tb[IFLA_XDP_MAX + 1];
+ unsigned char mode;
+
+ if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
+ return -1;
+
+ if (!tb[IFLA_XDP_ATTACHED])
+ return 0;
+
+ mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
+ if (mode == XDP_ATTACHED_NONE)
+ return 0;
+
+ NET_START_OBJECT;
+ if (name)
+ NET_DUMP_STR("devname", "%s", name);
+ NET_DUMP_UINT("ifindex", "(%d)", ifindex);
+
+ if (mode == XDP_ATTACHED_MULTI) {
+ if (json_output) {
+ jsonw_name(json_wtr, "multi_attachments");
+ jsonw_start_array(json_wtr);
+ }
+ xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic", true);
+ xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "driver", true);
+ xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload", true);
+ if (json_output)
+ jsonw_end_array(json_wtr);
+ } else if (mode == XDP_ATTACHED_DRV) {
+ xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "driver", false);
+ } else if (mode == XDP_ATTACHED_SKB) {
+ xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "generic", false);
+ } else if (mode == XDP_ATTACHED_HW) {
+ xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "offload", false);
+ }
+
+ NET_END_OBJECT_FINAL;
+ return 0;
+}
+
+int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
+{
+ if (!tb[IFLA_XDP])
+ return 0;
+
+ return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index,
+ nla_getattr_str(tb[IFLA_IFNAME]));
+}
+
+static int do_bpf_dump_one_act(struct nlattr *attr)
+{
+ struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+
+ if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ if (!tb[TCA_ACT_BPF_PARMS])
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ NET_START_OBJECT_NESTED2;
+ if (tb[TCA_ACT_BPF_NAME])
+ NET_DUMP_STR("name", "%s",
+ nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+ if (tb[TCA_ACT_BPF_ID])
+ NET_DUMP_UINT("id", " id %u",
+ nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
+ NET_END_OBJECT_NESTED;
+ return 0;
+}
+
+static int do_dump_one_act(struct nlattr *attr)
+{
+ struct nlattr *tb[TCA_ACT_MAX + 1];
+
+ if (!attr)
+ return 0;
+
+ if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
+ return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]);
+
+ return 0;
+}
+
+static int do_bpf_act_dump(struct nlattr *attr)
+{
+ struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
+ int act, ret;
+
+ if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ NET_START_ARRAY("act", " %s [");
+ for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) {
+ ret = do_dump_one_act(tb[act]);
+ if (ret)
+ break;
+ }
+ NET_END_ARRAY("] ");
+
+ return ret;
+}
+
+static int do_bpf_filter_dump(struct nlattr *attr)
+{
+ struct nlattr *tb[TCA_BPF_MAX + 1];
+ int ret;
+
+ if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ if (tb[TCA_BPF_NAME])
+ NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME]));
+ if (tb[TCA_BPF_ID])
+ NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID]));
+ if (tb[TCA_BPF_ACT]) {
+ ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind,
+ const char *devname, int ifindex)
+{
+ int ret = 0;
+
+ if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
+ NET_START_OBJECT;
+ if (devname[0] != '\0')
+ NET_DUMP_STR("devname", "%s", devname);
+ NET_DUMP_UINT("ifindex", "(%u)", ifindex);
+ NET_DUMP_STR("kind", " %s", kind);
+ ret = do_bpf_filter_dump(tb[TCA_OPTIONS]);
+ NET_END_OBJECT_FINAL;
+ }
+
+ return ret;
+}
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
new file mode 100644
index 000000000000..0788cfbbed0e
--- /dev/null
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#ifndef _NETLINK_DUMPER_H_
+#define _NETLINK_DUMPER_H_
+
+#define NET_START_OBJECT \
+{ \
+ if (json_output) \
+ jsonw_start_object(json_wtr); \
+}
+
+#define NET_START_OBJECT_NESTED(name) \
+{ \
+ if (json_output) { \
+ jsonw_name(json_wtr, name); \
+ jsonw_start_object(json_wtr); \
+ } else { \
+ fprintf(stderr, "%s {", name); \
+ } \
+}
+
+#define NET_START_OBJECT_NESTED2 \
+{ \
+ if (json_output) \
+ jsonw_start_object(json_wtr); \
+ else \
+ fprintf(stderr, "{"); \
+}
+
+#define NET_END_OBJECT_NESTED \
+{ \
+ if (json_output) \
+ jsonw_end_object(json_wtr); \
+ else \
+ fprintf(stderr, "}"); \
+}
+
+#define NET_END_OBJECT \
+{ \
+ if (json_output) \
+ jsonw_end_object(json_wtr); \
+}
+
+#define NET_END_OBJECT_FINAL \
+{ \
+ if (json_output) \
+ jsonw_end_object(json_wtr); \
+ else \
+ fprintf(stderr, "\n"); \
+}
+
+#define NET_START_ARRAY(name, fmt_str) \
+{ \
+ if (json_output) { \
+ jsonw_name(json_wtr, name); \
+ jsonw_start_array(json_wtr); \
+ } else { \
+ fprintf(stderr, fmt_str, name); \
+ } \
+}
+
+#define NET_END_ARRAY(endstr) \
+{ \
+ if (json_output) \
+ jsonw_end_array(json_wtr); \
+ else \
+ fprintf(stderr, "%s", endstr); \
+}
+
+#define NET_DUMP_UINT(name, fmt_str, val) \
+{ \
+ if (json_output) \
+ jsonw_uint_field(json_wtr, name, val); \
+ else \
+ fprintf(stderr, fmt_str, val); \
+}
+
+#define NET_DUMP_STR(name, fmt_str, str) \
+{ \
+ if (json_output) \
+ jsonw_string_field(json_wtr, name, str);\
+ else \
+ fprintf(stderr, fmt_str, str); \
+}
+
+#define NET_DUMP_STR_ONLY(str) \
+{ \
+ if (json_output) \
+ jsonw_string(json_wtr, str); \
+ else \
+ fprintf(stderr, "%s ", str); \
+}
+
+#endif
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index dce960d22106..b1cd3bc8db70 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint",
[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
[BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2",
+ [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector",
};
static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 66917a4eba27..aa5ccd2385ed 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -152,6 +152,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LWT_SEG6LOCAL,
BPF_PROG_TYPE_LIRC_MODE2,
BPF_PROG_TYPE_SK_REUSEPORT,
+ BPF_PROG_TYPE_FLOW_DISSECTOR,
};
enum bpf_attach_type {
@@ -172,6 +173,7 @@ enum bpf_attach_type {
BPF_CGROUP_UDP4_SENDMSG,
BPF_CGROUP_UDP6_SENDMSG,
BPF_LIRC_MODE2,
+ BPF_FLOW_DISSECTOR,
__MAX_BPF_ATTACH_TYPE
};
@@ -2333,6 +2335,7 @@ struct __sk_buff {
/* ... here. */
__u32 data_meta;
+ struct bpf_flow_keys *flow_keys;
};
struct bpf_tunnel_key {
@@ -2778,4 +2781,27 @@ enum bpf_task_fd_type {
BPF_FD_TYPE_URETPROBE, /* filename + offset */
};
+struct bpf_flow_keys {
+ __u16 nhoff;
+ __u16 thoff;
+ __u16 addr_proto; /* ETH_P_* of valid addrs */
+ __u8 is_frag;
+ __u8 is_first_frag;
+ __u8 is_encap;
+ __u8 ip_proto;
+ __be16 n_proto;
+ __be16 sport;
+ __be16 dport;
+ union {
+ struct {
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ };
+ struct {
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+ };
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 43391e2d1153..58faab897201 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -161,6 +161,7 @@ enum {
IFLA_EVENT,
IFLA_NEW_NETNSID,
IFLA_IF_NETNSID,
+ IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
IFLA_CARRIER_UP_COUNT,
IFLA_CARRIER_DOWN_COUNT,
IFLA_NEW_IFINDEX,
@@ -554,6 +555,7 @@ enum {
IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
IFLA_GENEVE_LABEL,
+ IFLA_GENEVE_TTL_INHERIT,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6eb9bacd1948..7bc31c905018 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 60aa4ca8b2c5..3878a26a2071 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -28,16 +28,8 @@
#include <linux/bpf.h>
#include "bpf.h"
#include "libbpf.h"
-#include "nlattr.h"
-#include <linux/rtnetlink.h>
-#include <linux/if_link.h>
-#include <sys/socket.h>
#include <errno.h>
-#ifndef SOL_NETLINK
-#define SOL_NETLINK 270
-#endif
-
/*
* When building perf, unistd.h is overridden. __NR_bpf is
* required to be defined explicitly.
@@ -499,127 +491,6 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
}
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
- struct sockaddr_nl sa;
- int sock, seq = 0, len, ret = -1;
- char buf[4096];
- struct nlattr *nla, *nla_xdp;
- struct {
- struct nlmsghdr nh;
- struct ifinfomsg ifinfo;
- char attrbuf[64];
- } req;
- struct nlmsghdr *nh;
- struct nlmsgerr *err;
- socklen_t addrlen;
- int one = 1;
-
- memset(&sa, 0, sizeof(sa));
- sa.nl_family = AF_NETLINK;
-
- sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
- if (sock < 0) {
- return -errno;
- }
-
- if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
- &one, sizeof(one)) < 0) {
- fprintf(stderr, "Netlink error reporting not supported\n");
- }
-
- if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- addrlen = sizeof(sa);
- if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- if (addrlen != sizeof(sa)) {
- ret = -LIBBPF_ERRNO__INTERNAL;
- goto cleanup;
- }
-
- memset(&req, 0, sizeof(req));
- req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
- req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
- req.nh.nlmsg_type = RTM_SETLINK;
- req.nh.nlmsg_pid = 0;
- req.nh.nlmsg_seq = ++seq;
- req.ifinfo.ifi_family = AF_UNSPEC;
- req.ifinfo.ifi_index = ifindex;
-
- /* started nested attribute for XDP */
- nla = (struct nlattr *)(((char *)&req)
- + NLMSG_ALIGN(req.nh.nlmsg_len));
- nla->nla_type = NLA_F_NESTED | IFLA_XDP;
- nla->nla_len = NLA_HDRLEN;
-
- /* add XDP fd */
- nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
- nla_xdp->nla_type = IFLA_XDP_FD;
- nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
- memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
- nla->nla_len += nla_xdp->nla_len;
-
- /* if user passed in any flags, add those too */
- if (flags) {
- nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
- nla_xdp->nla_type = IFLA_XDP_FLAGS;
- nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
- memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
- nla->nla_len += nla_xdp->nla_len;
- }
-
- req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
- if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- len = recv(sock, buf, sizeof(buf), 0);
- if (len < 0) {
- ret = -errno;
- goto cleanup;
- }
-
- for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
- nh = NLMSG_NEXT(nh, len)) {
- if (nh->nlmsg_pid != sa.nl_pid) {
- ret = -LIBBPF_ERRNO__WRNGPID;
- goto cleanup;
- }
- if (nh->nlmsg_seq != seq) {
- ret = -LIBBPF_ERRNO__INVSEQ;
- goto cleanup;
- }
- switch (nh->nlmsg_type) {
- case NLMSG_ERROR:
- err = (struct nlmsgerr *)NLMSG_DATA(nh);
- if (!err->error)
- continue;
- ret = err->error;
- nla_dump_errormsg(nh);
- goto cleanup;
- case NLMSG_DONE:
- break;
- default:
- break;
- }
- }
-
- ret = 0;
-
-cleanup:
- close(sock);
- return ret;
-}
-
int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
bool do_log)
{
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bdb94939fd60..4f8d43ae20d2 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1502,6 +1502,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
case BPF_PROG_TYPE_LIRC_MODE2:
case BPF_PROG_TYPE_SK_REUSEPORT:
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
return false;
case BPF_PROG_TYPE_UNSPEC:
case BPF_PROG_TYPE_KPROBE:
@@ -2121,6 +2122,7 @@ static const struct {
BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB),
BPF_PROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG),
BPF_PROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2),
+ BPF_PROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR),
BPF_SA_PROG_SEC("cgroup/bind4", BPF_CGROUP_INET4_BIND),
BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND),
BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
@@ -2336,7 +2338,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
bpf_program__set_expected_attach_type(prog,
expected_attach_type);
- if (!bpf_program__is_function_storage(prog, obj) && !first_prog)
+ if (!first_prog)
first_prog = prog;
}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 96c55fac54c3..e3b00e23e181 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -46,6 +46,7 @@ enum libbpf_errno {
LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */
LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */
LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */
+ LIBBPF_ERRNO__NLPARSE, /* netlink parsing error */
__LIBBPF_ERRNO__END,
};
@@ -297,4 +298,19 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
unsigned long page_size,
void **buf, size_t *buf_len,
bpf_perf_event_print_t fn, void *priv);
+
+struct nlmsghdr;
+struct nlattr;
+typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
+ void *cookie);
+int bpf_netlink_open(unsigned int *nl_pid);
+int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
+ void *cookie);
+int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+ dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+ dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+ dump_nlmsg_t dump_filter_nlmsg, void *cookie);
#endif
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index d9ba851bd7f9..2464ade3b326 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -42,6 +42,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
[ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
[ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
[ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
+ [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing",
};
int libbpf_strerror(int err, char *buf, size_t size)
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
new file mode 100644
index 000000000000..fde1d7bf8199
--- /dev/null
+++ b/tools/lib/bpf/netlink.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: LGPL-2.1
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <memory.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+#include <time.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
+int bpf_netlink_open(__u32 *nl_pid)
+{
+ struct sockaddr_nl sa;
+ socklen_t addrlen;
+ int one = 1, ret;
+ int sock;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.nl_family = AF_NETLINK;
+
+ sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (sock < 0)
+ return -errno;
+
+ if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+ &one, sizeof(one)) < 0) {
+ fprintf(stderr, "Netlink error reporting not supported\n");
+ }
+
+ if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+ ret = -errno;
+ goto cleanup;
+ }
+
+ addrlen = sizeof(sa);
+ if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
+ ret = -errno;
+ goto cleanup;
+ }
+
+ if (addrlen != sizeof(sa)) {
+ ret = -LIBBPF_ERRNO__INTERNAL;
+ goto cleanup;
+ }
+
+ *nl_pid = sa.nl_pid;
+ return sock;
+
+cleanup:
+ close(sock);
+ return ret;
+}
+
+static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+ __dump_nlmsg_t _fn, dump_nlmsg_t fn,
+ void *cookie)
+{
+ bool multipart = true;
+ struct nlmsgerr *err;
+ struct nlmsghdr *nh;
+ char buf[4096];
+ int len, ret;
+
+ while (multipart) {
+ multipart = false;
+ len = recv(sock, buf, sizeof(buf), 0);
+ if (len < 0) {
+ ret = -errno;
+ goto done;
+ }
+
+ if (len == 0)
+ break;
+
+ for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+ nh = NLMSG_NEXT(nh, len)) {
+ if (nh->nlmsg_pid != nl_pid) {
+ ret = -LIBBPF_ERRNO__WRNGPID;
+ goto done;
+ }
+ if (nh->nlmsg_seq != seq) {
+ ret = -LIBBPF_ERRNO__INVSEQ;
+ goto done;
+ }
+ if (nh->nlmsg_flags & NLM_F_MULTI)
+ multipart = true;
+ switch (nh->nlmsg_type) {
+ case NLMSG_ERROR:
+ err = (struct nlmsgerr *)NLMSG_DATA(nh);
+ if (!err->error)
+ continue;
+ ret = err->error;
+ nla_dump_errormsg(nh);
+ goto done;
+ case NLMSG_DONE:
+ return 0;
+ default:
+ break;
+ }
+ if (_fn) {
+ ret = _fn(nh, fn, cookie);
+ if (ret)
+ return ret;
+ }
+ }
+ }
+ ret = 0;
+done:
+ return ret;
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+ int sock, seq = 0, ret;
+ struct nlattr *nla, *nla_xdp;
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg ifinfo;
+ char attrbuf[64];
+ } req;
+ __u32 nl_pid;
+
+ sock = bpf_netlink_open(&nl_pid);
+ if (sock < 0)
+ return sock;
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_type = RTM_SETLINK;
+ req.nh.nlmsg_pid = 0;
+ req.nh.nlmsg_seq = ++seq;
+ req.ifinfo.ifi_family = AF_UNSPEC;
+ req.ifinfo.ifi_index = ifindex;
+
+ /* started nested attribute for XDP */
+ nla = (struct nlattr *)(((char *)&req)
+ + NLMSG_ALIGN(req.nh.nlmsg_len));
+ nla->nla_type = NLA_F_NESTED | IFLA_XDP;
+ nla->nla_len = NLA_HDRLEN;
+
+ /* add XDP fd */
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = IFLA_XDP_FD;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+ nla->nla_len += nla_xdp->nla_len;
+
+ /* if user passed in any flags, add those too */
+ if (flags) {
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = IFLA_XDP_FLAGS;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+ nla->nla_len += nla_xdp->nla_len;
+ }
+
+ req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+ if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ ret = -errno;
+ goto cleanup;
+ }
+ ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
+
+cleanup:
+ close(sock);
+ return ret;
+}
+
+static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
+ void *cookie)
+{
+ struct nlattr *tb[IFLA_MAX + 1], *attr;
+ struct ifinfomsg *ifi = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+ attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+ if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_link_nlmsg(cookie, ifi, tb);
+}
+
+int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
+ void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct ifinfomsg ifm;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+ .nlh.nlmsg_type = RTM_GETLINK,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .ifm.ifi_family = AF_PACKET,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
+ dump_link_nlmsg, cookie);
+}
+
+static int __dump_class_nlmsg(struct nlmsghdr *nlh,
+ dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+ struct nlattr *tb[TCA_MAX + 1], *attr;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+ attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+ if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_class_nlmsg(cookie, t, tb);
+}
+
+int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+ dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct tcmsg t;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+ .nlh.nlmsg_type = RTM_GETTCLASS,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .t.tcm_family = AF_UNSPEC,
+ .t.tcm_ifindex = ifindex,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg,
+ dump_class_nlmsg, cookie);
+}
+
+static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
+ dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+ struct nlattr *tb[TCA_MAX + 1], *attr;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+ attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+ if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_qdisc_nlmsg(cookie, t, tb);
+}
+
+int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+ dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct tcmsg t;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+ .nlh.nlmsg_type = RTM_GETQDISC,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .t.tcm_family = AF_UNSPEC,
+ .t.tcm_ifindex = ifindex,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg,
+ dump_qdisc_nlmsg, cookie);
+}
+
+static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
+ dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+ struct nlattr *tb[TCA_MAX + 1], *attr;
+ struct tcmsg *t = NLMSG_DATA(nlh);
+ int len;
+
+ len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+ attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+ if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+ return -LIBBPF_ERRNO__NLPARSE;
+
+ return dump_filter_nlmsg(cookie, t, tb);
+}
+
+int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+ dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+ struct {
+ struct nlmsghdr nlh;
+ struct tcmsg t;
+ } req = {
+ .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+ .nlh.nlmsg_type = RTM_GETTFILTER,
+ .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+ .t.tcm_family = AF_UNSPEC,
+ .t.tcm_ifindex = ifindex,
+ .t.tcm_parent = handle,
+ };
+ int seq = time(NULL);
+
+ req.nlh.nlmsg_seq = seq;
+ if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+ return -errno;
+
+ return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg,
+ dump_filter_nlmsg, cookie);
+}
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 4719434278b2..49f514119bdb 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -26,11 +26,6 @@ static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
[NLA_FLAG] = 0,
};
-static int nla_len(const struct nlattr *nla)
-{
- return nla->nla_len - NLA_HDRLEN;
-}
-
static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
{
int totlen = NLA_ALIGN(nla->nla_len);
@@ -46,11 +41,6 @@ static int nla_ok(const struct nlattr *nla, int remaining)
nla->nla_len <= remaining;
}
-static void *nla_data(const struct nlattr *nla)
-{
- return (char *) nla + NLA_HDRLEN;
-}
-
static int nla_type(const struct nlattr *nla)
{
return nla->nla_type & NLA_TYPE_MASK;
@@ -114,8 +104,8 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
* @see nla_validate
* @return 0 on success or a negative error code.
*/
-static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
- struct nla_policy *policy)
+int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+ struct nla_policy *policy)
{
struct nlattr *nla;
int rem, err;
@@ -146,6 +136,25 @@ errout:
return err;
}
+/**
+ * Create attribute index based on nested attribute
+ * @arg tb Index array to be filled (maxtype+1 elements).
+ * @arg maxtype Maximum attribute type expected and accepted.
+ * @arg nla Nested Attribute.
+ * @arg policy Attribute validation policy.
+ *
+ * Feeds the stream of attributes nested into the specified attribute
+ * to nla_parse().
+ *
+ * @see nla_parse
+ * @return 0 on success or a negative error code.
+ */
+int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+ struct nla_policy *policy)
+{
+ return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+}
+
/* dump netlink extended ack error message */
int nla_dump_errormsg(struct nlmsghdr *nlh)
{
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 931a71f68f93..a6e2396bce7c 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -67,6 +67,44 @@ struct nla_policy {
nla_ok(pos, rem); \
pos = nla_next(pos, &(rem)))
+/**
+ * nla_data - head of payload
+ * @nla: netlink attribute
+ */
+static inline void *nla_data(const struct nlattr *nla)
+{
+ return (char *) nla + NLA_HDRLEN;
+}
+
+static inline uint8_t nla_getattr_u8(const struct nlattr *nla)
+{
+ return *(uint8_t *)nla_data(nla);
+}
+
+static inline uint32_t nla_getattr_u32(const struct nlattr *nla)
+{
+ return *(uint32_t *)nla_data(nla);
+}
+
+static inline const char *nla_getattr_str(const struct nlattr *nla)
+{
+ return (const char *)nla_data(nla);
+}
+
+/**
+ * nla_len - length of payload
+ * @nla: netlink attribute
+ */
+static inline int nla_len(const struct nlattr *nla)
+{
+ return nla->nla_len - NLA_HDRLEN;
+}
+
+int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+ struct nla_policy *policy);
+int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+ struct nla_policy *policy);
+
int nla_dump_errormsg(struct nlmsghdr *nlh);
#endif /* __NLATTR_H */
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 49938d72cf63..8a60c9b9892d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -19,3 +19,9 @@ test_btf
test_sockmap
test_lirc_mode2_user
get_cgroup_id_user
+test_skb_cgroup_id_user
+test_socket_cookie
+test_cgroup_storage
+test_select_reuseport
+test_flow_dissector
+flow_dissector_load
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fff7fb1285fc..fd3851d5c079 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -35,7 +35,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
- test_skb_cgroup_id_kern.o
+ test_skb_cgroup_id_kern.o bpf_flow.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@@ -47,10 +47,12 @@ TEST_PROGS := test_kmod.sh \
test_tunnel.sh \
test_lwt_seg6local.sh \
test_lirc_mode2.sh \
- test_skb_cgroup_id.sh
+ test_skb_cgroup_id.sh \
+ test_flow_dissector.sh
# Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
+ flow_dissector_load test_flow_dissector
include ../lib.mk
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
new file mode 100644
index 000000000000..107350a7821d
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <limits.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/icmp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_packet.h>
+#include <sys/socket.h>
+#include <linux/if_tunnel.h>
+#include <linux/mpls.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+#define PROG(F) SEC(#F) int bpf_func_##F
+
+/* These are the identifiers of the BPF programs that will be used in tail
+ * calls. Name is limited to 16 characters, with the terminating character and
+ * bpf_func_ above, we have only 6 to work with, anything after will be cropped.
+ */
+enum {
+ IP,
+ IPV6,
+ IPV6OP, /* Destination/Hop-by-Hop Options IPv6 Extension header */
+ IPV6FR, /* Fragmentation IPv6 Extension Header */
+ MPLS,
+ VLAN,
+};
+
+#define IP_MF 0x2000
+#define IP_OFFSET 0x1FFF
+#define IP6_MF 0x0001
+#define IP6_OFFSET 0xFFF8
+
+struct vlan_hdr {
+ __be16 h_vlan_TCI;
+ __be16 h_vlan_encapsulated_proto;
+};
+
+struct gre_hdr {
+ __be16 flags;
+ __be16 proto;
+};
+
+struct frag_hdr {
+ __u8 nexthdr;
+ __u8 reserved;
+ __be16 frag_off;
+ __be32 identification;
+};
+
+struct bpf_map_def SEC("maps") jmp_table = {
+ .type = BPF_MAP_TYPE_PROG_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u32),
+ .max_entries = 8
+};
+
+static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb,
+ __u16 hdr_size,
+ void *buffer)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ __u16 nhoff = skb->flow_keys->nhoff;
+ __u8 *hdr;
+
+ /* Verifies this variable offset does not overflow */
+ if (nhoff > (USHRT_MAX - hdr_size))
+ return NULL;
+
+ hdr = data + nhoff;
+ if (hdr + hdr_size <= data_end)
+ return hdr;
+
+ if (bpf_skb_load_bytes(skb, nhoff, buffer, hdr_size))
+ return NULL;
+
+ return buffer;
+}
+
+/* Dispatches on ETHERTYPE */
+static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
+{
+ struct bpf_flow_keys *keys = skb->flow_keys;
+
+ keys->n_proto = proto;
+ switch (proto) {
+ case bpf_htons(ETH_P_IP):
+ bpf_tail_call(skb, &jmp_table, IP);
+ break;
+ case bpf_htons(ETH_P_IPV6):
+ bpf_tail_call(skb, &jmp_table, IPV6);
+ break;
+ case bpf_htons(ETH_P_MPLS_MC):
+ case bpf_htons(ETH_P_MPLS_UC):
+ bpf_tail_call(skb, &jmp_table, MPLS);
+ break;
+ case bpf_htons(ETH_P_8021Q):
+ case bpf_htons(ETH_P_8021AD):
+ bpf_tail_call(skb, &jmp_table, VLAN);
+ break;
+ default:
+ /* Protocol not supported */
+ return BPF_DROP;
+ }
+
+ return BPF_DROP;
+}
+
+SEC("dissect")
+int _dissect(struct __sk_buff *skb)
+{
+ if (!skb->vlan_present)
+ return parse_eth_proto(skb, skb->protocol);
+ else
+ return parse_eth_proto(skb, skb->vlan_proto);
+}
+
+/* Parses on IPPROTO_* */
+static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
+{
+ struct bpf_flow_keys *keys = skb->flow_keys;
+ void *data_end = (void *)(long)skb->data_end;
+ struct icmphdr *icmp, _icmp;
+ struct gre_hdr *gre, _gre;
+ struct ethhdr *eth, _eth;
+ struct tcphdr *tcp, _tcp;
+ struct udphdr *udp, _udp;
+
+ keys->ip_proto = proto;
+ switch (proto) {
+ case IPPROTO_ICMP:
+ icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp);
+ if (!icmp)
+ return BPF_DROP;
+ return BPF_OK;
+ case IPPROTO_IPIP:
+ keys->is_encap = true;
+ return parse_eth_proto(skb, bpf_htons(ETH_P_IP));
+ case IPPROTO_IPV6:
+ keys->is_encap = true;
+ return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6));
+ case IPPROTO_GRE:
+ gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre);
+ if (!gre)
+ return BPF_DROP;
+
+ if (bpf_htons(gre->flags & GRE_VERSION))
+ /* Only inspect standard GRE packets with version 0 */
+ return BPF_OK;
+
+ keys->nhoff += sizeof(*gre); /* Step over GRE Flags and Proto */
+ if (GRE_IS_CSUM(gre->flags))
+ keys->nhoff += 4; /* Step over chksum and Padding */
+ if (GRE_IS_KEY(gre->flags))
+ keys->nhoff += 4; /* Step over key */
+ if (GRE_IS_SEQ(gre->flags))
+ keys->nhoff += 4; /* Step over sequence number */
+
+ keys->is_encap = true;
+
+ if (gre->proto == bpf_htons(ETH_P_TEB)) {
+ eth = bpf_flow_dissect_get_header(skb, sizeof(*eth),
+ &_eth);
+ if (!eth)
+ return BPF_DROP;
+
+ keys->nhoff += sizeof(*eth);
+
+ return parse_eth_proto(skb, eth->h_proto);
+ } else {
+ return parse_eth_proto(skb, gre->proto);
+ }
+ case IPPROTO_TCP:
+ tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp);
+ if (!tcp)
+ return BPF_DROP;
+
+ if (tcp->doff < 5)
+ return BPF_DROP;
+
+ if ((__u8 *)tcp + (tcp->doff << 2) > data_end)
+ return BPF_DROP;
+
+ keys->thoff = keys->nhoff;
+ keys->sport = tcp->source;
+ keys->dport = tcp->dest;
+ return BPF_OK;
+ case IPPROTO_UDP:
+ case IPPROTO_UDPLITE:
+ udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp);
+ if (!udp)
+ return BPF_DROP;
+
+ keys->thoff = keys->nhoff;
+ keys->sport = udp->source;
+ keys->dport = udp->dest;
+ return BPF_OK;
+ default:
+ return BPF_DROP;
+ }
+
+ return BPF_DROP;
+}
+
+static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)
+{
+ struct bpf_flow_keys *keys = skb->flow_keys;
+
+ keys->ip_proto = nexthdr;
+ switch (nexthdr) {
+ case IPPROTO_HOPOPTS:
+ case IPPROTO_DSTOPTS:
+ bpf_tail_call(skb, &jmp_table, IPV6OP);
+ break;
+ case IPPROTO_FRAGMENT:
+ bpf_tail_call(skb, &jmp_table, IPV6FR);
+ break;
+ default:
+ return parse_ip_proto(skb, nexthdr);
+ }
+
+ return BPF_DROP;
+}
+
+PROG(IP)(struct __sk_buff *skb)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ struct bpf_flow_keys *keys = skb->flow_keys;
+ void *data = (void *)(long)skb->data;
+ struct iphdr *iph, _iph;
+ bool done = false;
+
+ iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph);
+ if (!iph)
+ return BPF_DROP;
+
+ /* IP header cannot be smaller than 20 bytes */
+ if (iph->ihl < 5)
+ return BPF_DROP;
+
+ keys->addr_proto = ETH_P_IP;
+ keys->ipv4_src = iph->saddr;
+ keys->ipv4_dst = iph->daddr;
+
+ keys->nhoff += iph->ihl << 2;
+ if (data + keys->nhoff > data_end)
+ return BPF_DROP;
+
+ if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) {
+ keys->is_frag = true;
+ if (iph->frag_off & bpf_htons(IP_OFFSET))
+ /* From second fragment on, packets do not have headers
+ * we can parse.
+ */
+ done = true;
+ else
+ keys->is_first_frag = true;
+ }
+
+ if (done)
+ return BPF_OK;
+
+ return parse_ip_proto(skb, iph->protocol);
+}
+
+PROG(IPV6)(struct __sk_buff *skb)
+{
+ struct bpf_flow_keys *keys = skb->flow_keys;
+ struct ipv6hdr *ip6h, _ip6h;
+
+ ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
+ if (!ip6h)
+ return BPF_DROP;
+
+ keys->addr_proto = ETH_P_IPV6;
+ memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr));
+
+ keys->nhoff += sizeof(struct ipv6hdr);
+
+ return parse_ipv6_proto(skb, ip6h->nexthdr);
+}
+
+PROG(IPV6OP)(struct __sk_buff *skb)
+{
+ struct ipv6_opt_hdr *ip6h, _ip6h;
+
+ ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
+ if (!ip6h)
+ return BPF_DROP;
+
+ /* hlen is in 8-octets and does not include the first 8 bytes
+ * of the header
+ */
+ skb->flow_keys->nhoff += (1 + ip6h->hdrlen) << 3;
+
+ return parse_ipv6_proto(skb, ip6h->nexthdr);
+}
+
+PROG(IPV6FR)(struct __sk_buff *skb)
+{
+ struct bpf_flow_keys *keys = skb->flow_keys;
+ struct frag_hdr *fragh, _fragh;
+
+ fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh);
+ if (!fragh)
+ return BPF_DROP;
+
+ keys->nhoff += sizeof(*fragh);
+ keys->is_frag = true;
+ if (!(fragh->frag_off & bpf_htons(IP6_OFFSET)))
+ keys->is_first_frag = true;
+
+ return parse_ipv6_proto(skb, fragh->nexthdr);
+}
+
+PROG(MPLS)(struct __sk_buff *skb)
+{
+ struct mpls_label *mpls, _mpls;
+
+ mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls);
+ if (!mpls)
+ return BPF_DROP;
+
+ return BPF_OK;
+}
+
+PROG(VLAN)(struct __sk_buff *skb)
+{
+ struct bpf_flow_keys *keys = skb->flow_keys;
+ struct vlan_hdr *vlan, _vlan;
+ __be16 proto;
+
+ /* Peek back to see if single or double-tagging */
+ if (bpf_skb_load_bytes(skb, keys->nhoff - sizeof(proto), &proto,
+ sizeof(proto)))
+ return BPF_DROP;
+
+ /* Account for double-tagging */
+ if (proto == bpf_htons(ETH_P_8021AD)) {
+ vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
+ if (!vlan)
+ return BPF_DROP;
+
+ if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
+ return BPF_DROP;
+
+ keys->nhoff += sizeof(*vlan);
+ }
+
+ vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
+ if (!vlan)
+ return BPF_DROP;
+
+ keys->nhoff += sizeof(*vlan);
+ /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
+ if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
+ vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
+ return BPF_DROP;
+
+ return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index b4994a94968b..3655508f95fd 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -18,3 +18,4 @@ CONFIG_CRYPTO_HMAC=m
CONFIG_CRYPTO_SHA256=m
CONFIG_VXLAN=y
CONFIG_GENEVE=y
+CONFIG_NET_CLS_FLOWER=m
diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
new file mode 100644
index 000000000000..d3273b5b3173
--- /dev/null
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <errno.h>
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
+const char *cfg_map_name = "jmp_table";
+bool cfg_attach = true;
+char *cfg_section_name;
+char *cfg_path_name;
+
+static void load_and_attach_program(void)
+{
+ struct bpf_program *prog, *main_prog;
+ struct bpf_map *prog_array;
+ int i, fd, prog_fd, ret;
+ struct bpf_object *obj;
+ int prog_array_fd;
+
+ ret = bpf_prog_load(cfg_path_name, BPF_PROG_TYPE_FLOW_DISSECTOR, &obj,
+ &prog_fd);
+ if (ret)
+ error(1, 0, "bpf_prog_load %s", cfg_path_name);
+
+ main_prog = bpf_object__find_program_by_title(obj, cfg_section_name);
+ if (!main_prog)
+ error(1, 0, "bpf_object__find_program_by_title %s",
+ cfg_section_name);
+
+ prog_fd = bpf_program__fd(main_prog);
+ if (prog_fd < 0)
+ error(1, 0, "bpf_program__fd");
+
+ prog_array = bpf_object__find_map_by_name(obj, cfg_map_name);
+ if (!prog_array)
+ error(1, 0, "bpf_object__find_map_by_name %s", cfg_map_name);
+
+ prog_array_fd = bpf_map__fd(prog_array);
+ if (prog_array_fd < 0)
+ error(1, 0, "bpf_map__fd %s", cfg_map_name);
+
+ i = 0;
+ bpf_object__for_each_program(prog, obj) {
+ fd = bpf_program__fd(prog);
+ if (fd < 0)
+ error(1, 0, "bpf_program__fd");
+
+ if (fd != prog_fd) {
+ printf("%d: %s\n", i, bpf_program__title(prog, false));
+ bpf_map_update_elem(prog_array_fd, &i, &fd, BPF_ANY);
+ ++i;
+ }
+ }
+
+ ret = bpf_prog_attach(prog_fd, 0 /* Ignore */, BPF_FLOW_DISSECTOR, 0);
+ if (ret)
+ error(1, 0, "bpf_prog_attach %s", cfg_path_name);
+
+ ret = bpf_object__pin(obj, cfg_pin_path);
+ if (ret)
+ error(1, 0, "bpf_object__pin %s", cfg_pin_path);
+
+}
+
+static void detach_program(void)
+{
+ char command[64];
+ int ret;
+
+ ret = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+ if (ret)
+ error(1, 0, "bpf_prog_detach");
+
+ /* To unpin, it is necessary and sufficient to just remove this dir */
+ sprintf(command, "rm -r %s", cfg_pin_path);
+ ret = system(command);
+ if (ret)
+ error(1, errno, command);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ bool attach = false;
+ bool detach = false;
+ int c;
+
+ while ((c = getopt(argc, argv, "adp:s:")) != -1) {
+ switch (c) {
+ case 'a':
+ if (detach)
+ error(1, 0, "attach/detach are exclusive");
+ attach = true;
+ break;
+ case 'd':
+ if (attach)
+ error(1, 0, "attach/detach are exclusive");
+ detach = true;
+ break;
+ case 'p':
+ if (cfg_path_name)
+ error(1, 0, "only one prog name can be given");
+
+ cfg_path_name = optarg;
+ break;
+ case 's':
+ if (cfg_section_name)
+ error(1, 0, "only one section can be given");
+
+ cfg_section_name = optarg;
+ break;
+ }
+ }
+
+ if (detach)
+ cfg_attach = false;
+
+ if (cfg_attach && !cfg_path_name)
+ error(1, 0, "must provide a path to the BPF program");
+
+ if (cfg_attach && !cfg_section_name)
+ error(1, 0, "must provide a section name");
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+ if (cfg_attach)
+ load_and_attach_program();
+ else
+ detach_program();
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 6b5cfeb7a9cc..f42b3396d622 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -4,6 +4,7 @@
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
+#include <linux/kernel.h>
#include <bpf/bpf.h>
#include <sys/resource.h>
#include <libelf.h>
@@ -45,7 +46,6 @@ static int count_result(int err)
return err;
}
-#define min(a, b) ((a) < (b) ? (a) : (b))
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
@@ -130,6 +130,7 @@ struct btf_raw_test {
bool map_create_err;
bool ordered_map;
bool lossless_map;
+ bool percpu_map;
int hdr_len_delta;
int type_off_delta;
int str_off_delta;
@@ -2157,6 +2158,7 @@ static struct btf_pprint_test_meta {
const char *map_name;
bool ordered_map;
bool lossless_map;
+ bool percpu_map;
} pprint_tests_meta[] = {
{
.descr = "BTF pretty print array",
@@ -2164,6 +2166,7 @@ static struct btf_pprint_test_meta {
.map_name = "pprint_test_array",
.ordered_map = true,
.lossless_map = true,
+ .percpu_map = false,
},
{
@@ -2172,6 +2175,7 @@ static struct btf_pprint_test_meta {
.map_name = "pprint_test_hash",
.ordered_map = false,
.lossless_map = true,
+ .percpu_map = false,
},
{
@@ -2180,30 +2184,83 @@ static struct btf_pprint_test_meta {
.map_name = "pprint_test_lru_hash",
.ordered_map = false,
.lossless_map = false,
+ .percpu_map = false,
+},
+
+{
+ .descr = "BTF pretty print percpu array",
+ .map_type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .map_name = "pprint_test_percpu_array",
+ .ordered_map = true,
+ .lossless_map = true,
+ .percpu_map = true,
+},
+
+{
+ .descr = "BTF pretty print percpu hash",
+ .map_type = BPF_MAP_TYPE_PERCPU_HASH,
+ .map_name = "pprint_test_percpu_hash",
+ .ordered_map = false,
+ .lossless_map = true,
+ .percpu_map = true,
+},
+
+{
+ .descr = "BTF pretty print lru percpu hash",
+ .map_type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ .map_name = "pprint_test_lru_percpu_hash",
+ .ordered_map = false,
+ .lossless_map = false,
+ .percpu_map = true,
},
};
-static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
+static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i,
+ int num_cpus, int rounded_value_size)
{
- v->ui32 = i;
- v->si32 = -i;
- v->unused_bits2a = 3;
- v->bits28 = i;
- v->unused_bits2b = 3;
- v->ui64 = i;
- v->aenum = i & 0x03;
+ int cpu;
+
+ for (cpu = 0; cpu < num_cpus; cpu++) {
+ v->ui32 = i + cpu;
+ v->si32 = -i;
+ v->unused_bits2a = 3;
+ v->bits28 = i;
+ v->unused_bits2b = 3;
+ v->ui64 = i;
+ v->aenum = i & 0x03;
+ v = (void *)v + rounded_value_size;
+ }
}
+static int check_line(const char *expected_line, int nexpected_line,
+ int expected_line_len, const char *line)
+{
+ if (CHECK(nexpected_line == expected_line_len,
+ "expected_line is too long"))
+ return -1;
+
+ if (strcmp(expected_line, line)) {
+ fprintf(stderr, "unexpected pprint output\n");
+ fprintf(stderr, "expected: %s", expected_line);
+ fprintf(stderr, " read: %s", line);
+ return -1;
+ }
+
+ return 0;
+}
+
+
static int do_test_pprint(void)
{
const struct btf_raw_test *test = &pprint_test_template;
struct bpf_create_map_attr create_attr = {};
+ bool ordered_map, lossless_map, percpu_map;
+ int err, ret, num_cpus, rounded_value_size;
+ struct pprint_mapv *mapv = NULL;
unsigned int key, nr_read_elems;
- bool ordered_map, lossless_map;
int map_fd = -1, btf_fd = -1;
- struct pprint_mapv mapv = {};
unsigned int raw_btf_size;
char expected_line[255];
FILE *pin_file = NULL;
@@ -2212,7 +2269,6 @@ static int do_test_pprint(void)
char *line = NULL;
uint8_t *raw_btf;
ssize_t nread;
- int err, ret;
fprintf(stderr, "%s......", test->descr);
raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
@@ -2261,9 +2317,18 @@ static int do_test_pprint(void)
if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno))
goto done;
+ percpu_map = test->percpu_map;
+ num_cpus = percpu_map ? bpf_num_possible_cpus() : 1;
+ rounded_value_size = round_up(sizeof(struct pprint_mapv), 8);
+ mapv = calloc(num_cpus, rounded_value_size);
+ if (CHECK(!mapv, "mapv allocation failure")) {
+ err = -1;
+ goto done;
+ }
+
for (key = 0; key < test->max_entries; key++) {
- set_pprint_mapv(&mapv, key);
- bpf_map_update_elem(map_fd, &key, &mapv, 0);
+ set_pprint_mapv(mapv, key, num_cpus, rounded_value_size);
+ bpf_map_update_elem(map_fd, &key, mapv, 0);
}
pin_file = fopen(pin_path, "r");
@@ -2286,33 +2351,74 @@ static int do_test_pprint(void)
ordered_map = test->ordered_map;
lossless_map = test->lossless_map;
do {
+ struct pprint_mapv *cmapv;
ssize_t nexpected_line;
unsigned int next_key;
+ int cpu;
next_key = ordered_map ? nr_read_elems : atoi(line);
- set_pprint_mapv(&mapv, next_key);
- nexpected_line = snprintf(expected_line, sizeof(expected_line),
- "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
- next_key,
- mapv.ui32, mapv.si32,
- mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
- mapv.ui64,
- mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3],
- mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7],
- pprint_enum_str[mapv.aenum]);
-
- if (CHECK(nexpected_line == sizeof(expected_line),
- "expected_line is too long")) {
- err = -1;
- goto done;
+ set_pprint_mapv(mapv, next_key, num_cpus, rounded_value_size);
+ cmapv = mapv;
+
+ for (cpu = 0; cpu < num_cpus; cpu++) {
+ if (percpu_map) {
+ /* for percpu map, the format looks like:
+ * <key>: {
+ * cpu0: <value_on_cpu0>
+ * cpu1: <value_on_cpu1>
+ * ...
+ * cpun: <value_on_cpun>
+ * }
+ *
+ * let us verify the line containing the key here.
+ */
+ if (cpu == 0) {
+ nexpected_line = snprintf(expected_line,
+ sizeof(expected_line),
+ "%u: {\n",
+ next_key);
+
+ err = check_line(expected_line, nexpected_line,
+ sizeof(expected_line), line);
+ if (err == -1)
+ goto done;
+ }
+
+ /* read value@cpu */
+ nread = getline(&line, &line_len, pin_file);
+ if (nread < 0)
+ break;
+ }
+
+ nexpected_line = snprintf(expected_line, sizeof(expected_line),
+ "%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
+ "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
+ percpu_map ? "\tcpu" : "",
+ percpu_map ? cpu : next_key,
+ cmapv->ui32, cmapv->si32,
+ cmapv->unused_bits2a,
+ cmapv->bits28,
+ cmapv->unused_bits2b,
+ cmapv->ui64,
+ cmapv->ui8a[0], cmapv->ui8a[1],
+ cmapv->ui8a[2], cmapv->ui8a[3],
+ cmapv->ui8a[4], cmapv->ui8a[5],
+ cmapv->ui8a[6], cmapv->ui8a[7],
+ pprint_enum_str[cmapv->aenum]);
+
+ err = check_line(expected_line, nexpected_line,
+ sizeof(expected_line), line);
+ if (err == -1)
+ goto done;
+
+ cmapv = (void *)cmapv + rounded_value_size;
}
- if (strcmp(expected_line, line)) {
- err = -1;
- fprintf(stderr, "unexpected pprint output\n");
- fprintf(stderr, "expected: %s", expected_line);
- fprintf(stderr, " read: %s", line);
- goto done;
+ if (percpu_map) {
+ /* skip the last bracket for the percpu map */
+ nread = getline(&line, &line_len, pin_file);
+ if (nread < 0)
+ break;
}
nread = getline(&line, &line_len, pin_file);
@@ -2334,6 +2440,8 @@ static int do_test_pprint(void)
err = 0;
done:
+ if (mapv)
+ free(mapv);
if (!err)
fprintf(stderr, "OK");
if (*btf_log_buf && (err || args.always_log))
@@ -2361,6 +2469,7 @@ static int test_pprint(void)
pprint_test_template.map_name = pprint_tests_meta[i].map_name;
pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
+ pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map;
err |= count_result(do_test_pprint());
}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.c b/tools/testing/selftests/bpf/test_flow_dissector.c
new file mode 100644
index 000000000000..12b784afba31
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_flow_dissector.c
@@ -0,0 +1,782 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Inject packets with all sorts of encapsulation into the kernel.
+ *
+ * IPv4/IPv6 outer layer 3
+ * GRE/GUE/BARE outer layer 4, where bare is IPIP/SIT/IPv4-in-IPv6/..
+ * IPv4/IPv6 inner layer 3
+ */
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <asm/byteorder.h>
+#include <error.h>
+#include <errno.h>
+#include <linux/if_packet.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <netinet/ip.h>
+#include <netinet/in.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define CFG_PORT_INNER 8000
+
+/* Add some protocol definitions that do not exist in userspace */
+
+struct grehdr {
+ uint16_t unused;
+ uint16_t protocol;
+} __attribute__((packed));
+
+struct guehdr {
+ union {
+ struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u8 hlen:5,
+ control:1,
+ version:2;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+ __u8 version:2,
+ control:1,
+ hlen:5;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ __u8 proto_ctype;
+ __be16 flags;
+ };
+ __be32 word;
+ };
+};
+
+static uint8_t cfg_dsfield_inner;
+static uint8_t cfg_dsfield_outer;
+static uint8_t cfg_encap_proto;
+static bool cfg_expect_failure = false;
+static int cfg_l3_extra = AF_UNSPEC; /* optional SIT prefix */
+static int cfg_l3_inner = AF_UNSPEC;
+static int cfg_l3_outer = AF_UNSPEC;
+static int cfg_num_pkt = 10;
+static int cfg_num_secs = 0;
+static char cfg_payload_char = 'a';
+static int cfg_payload_len = 100;
+static int cfg_port_gue = 6080;
+static bool cfg_only_rx;
+static bool cfg_only_tx;
+static int cfg_src_port = 9;
+
+static char buf[ETH_DATA_LEN];
+
+#define INIT_ADDR4(name, addr4, port) \
+ static struct sockaddr_in name = { \
+ .sin_family = AF_INET, \
+ .sin_port = __constant_htons(port), \
+ .sin_addr.s_addr = __constant_htonl(addr4), \
+ };
+
+#define INIT_ADDR6(name, addr6, port) \
+ static struct sockaddr_in6 name = { \
+ .sin6_family = AF_INET6, \
+ .sin6_port = __constant_htons(port), \
+ .sin6_addr = addr6, \
+ };
+
+INIT_ADDR4(in_daddr4, INADDR_LOOPBACK, CFG_PORT_INNER)
+INIT_ADDR4(in_saddr4, INADDR_LOOPBACK + 2, 0)
+INIT_ADDR4(out_daddr4, INADDR_LOOPBACK, 0)
+INIT_ADDR4(out_saddr4, INADDR_LOOPBACK + 1, 0)
+INIT_ADDR4(extra_daddr4, INADDR_LOOPBACK, 0)
+INIT_ADDR4(extra_saddr4, INADDR_LOOPBACK + 1, 0)
+
+INIT_ADDR6(in_daddr6, IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER)
+INIT_ADDR6(in_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(out_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(out_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(extra_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(extra_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+
+static unsigned long util_gettime(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void util_printaddr(const char *msg, struct sockaddr *addr)
+{
+ unsigned long off = 0;
+ char nbuf[INET6_ADDRSTRLEN];
+
+ switch (addr->sa_family) {
+ case PF_INET:
+ off = __builtin_offsetof(struct sockaddr_in, sin_addr);
+ break;
+ case PF_INET6:
+ off = __builtin_offsetof(struct sockaddr_in6, sin6_addr);
+ break;
+ default:
+ error(1, 0, "printaddr: unsupported family %u\n",
+ addr->sa_family);
+ }
+
+ if (!inet_ntop(addr->sa_family, ((void *) addr) + off, nbuf,
+ sizeof(nbuf)))
+ error(1, errno, "inet_ntop");
+
+ fprintf(stderr, "%s: %s\n", msg, nbuf);
+}
+
+static unsigned long add_csum_hword(const uint16_t *start, int num_u16)
+{
+ unsigned long sum = 0;
+ int i;
+
+ for (i = 0; i < num_u16; i++)
+ sum += start[i];
+
+ return sum;
+}
+
+static uint16_t build_ip_csum(const uint16_t *start, int num_u16,
+ unsigned long sum)
+{
+ sum += add_csum_hword(start, num_u16);
+
+ while (sum >> 16)
+ sum = (sum & 0xffff) + (sum >> 16);
+
+ return ~sum;
+}
+
+static void build_ipv4_header(void *header, uint8_t proto,
+ uint32_t src, uint32_t dst,
+ int payload_len, uint8_t tos)
+{
+ struct iphdr *iph = header;
+
+ iph->ihl = 5;
+ iph->version = 4;
+ iph->tos = tos;
+ iph->ttl = 8;
+ iph->tot_len = htons(sizeof(*iph) + payload_len);
+ iph->id = htons(1337);
+ iph->protocol = proto;
+ iph->saddr = src;
+ iph->daddr = dst;
+ iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0);
+}
+
+static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield)
+{
+ uint16_t val, *ptr = (uint16_t *)ip6h;
+
+ val = ntohs(*ptr);
+ val &= 0xF00F;
+ val |= ((uint16_t) dsfield) << 4;
+ *ptr = htons(val);
+}
+
+static void build_ipv6_header(void *header, uint8_t proto,
+ struct sockaddr_in6 *src,
+ struct sockaddr_in6 *dst,
+ int payload_len, uint8_t dsfield)
+{
+ struct ipv6hdr *ip6h = header;
+
+ ip6h->version = 6;
+ ip6h->payload_len = htons(payload_len);
+ ip6h->nexthdr = proto;
+ ip6h->hop_limit = 8;
+ ipv6_set_dsfield(ip6h, dsfield);
+
+ memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr));
+ memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr));
+}
+
+static uint16_t build_udp_v4_csum(const struct iphdr *iph,
+ const struct udphdr *udph,
+ int num_words)
+{
+ unsigned long pseudo_sum;
+ int num_u16 = sizeof(iph->saddr); /* halfwords: twice byte len */
+
+ pseudo_sum = add_csum_hword((void *) &iph->saddr, num_u16);
+ pseudo_sum += htons(IPPROTO_UDP);
+ pseudo_sum += udph->len;
+ return build_ip_csum((void *) udph, num_words, pseudo_sum);
+}
+
+static uint16_t build_udp_v6_csum(const struct ipv6hdr *ip6h,
+ const struct udphdr *udph,
+ int num_words)
+{
+ unsigned long pseudo_sum;
+ int num_u16 = sizeof(ip6h->saddr); /* halfwords: twice byte len */
+
+ pseudo_sum = add_csum_hword((void *) &ip6h->saddr, num_u16);
+ pseudo_sum += htons(ip6h->nexthdr);
+ pseudo_sum += ip6h->payload_len;
+ return build_ip_csum((void *) udph, num_words, pseudo_sum);
+}
+
+static void build_udp_header(void *header, int payload_len,
+ uint16_t dport, int family)
+{
+ struct udphdr *udph = header;
+ int len = sizeof(*udph) + payload_len;
+
+ udph->source = htons(cfg_src_port);
+ udph->dest = htons(dport);
+ udph->len = htons(len);
+ udph->check = 0;
+ if (family == AF_INET)
+ udph->check = build_udp_v4_csum(header - sizeof(struct iphdr),
+ udph, len >> 1);
+ else
+ udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr),
+ udph, len >> 1);
+}
+
+static void build_gue_header(void *header, uint8_t proto)
+{
+ struct guehdr *gueh = header;
+
+ gueh->proto_ctype = proto;
+}
+
+static void build_gre_header(void *header, uint16_t proto)
+{
+ struct grehdr *greh = header;
+
+ greh->protocol = htons(proto);
+}
+
+static int l3_length(int family)
+{
+ if (family == AF_INET)
+ return sizeof(struct iphdr);
+ else
+ return sizeof(struct ipv6hdr);
+}
+
+static int build_packet(void)
+{
+ int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0;
+ int el3_len = 0;
+
+ if (cfg_l3_extra)
+ el3_len = l3_length(cfg_l3_extra);
+
+ /* calculate header offsets */
+ if (cfg_encap_proto) {
+ ol3_len = l3_length(cfg_l3_outer);
+
+ if (cfg_encap_proto == IPPROTO_GRE)
+ ol4_len = sizeof(struct grehdr);
+ else if (cfg_encap_proto == IPPROTO_UDP)
+ ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr);
+ }
+
+ il3_len = l3_length(cfg_l3_inner);
+ il4_len = sizeof(struct udphdr);
+
+ if (el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len >=
+ sizeof(buf))
+ error(1, 0, "packet too large\n");
+
+ /*
+ * Fill packet from inside out, to calculate correct checksums.
+ * But create ip before udp headers, as udp uses ip for pseudo-sum.
+ */
+ memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len,
+ cfg_payload_char, cfg_payload_len);
+
+ /* add zero byte for udp csum padding */
+ buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len] = 0;
+
+ switch (cfg_l3_inner) {
+ case PF_INET:
+ build_ipv4_header(buf + el3_len + ol3_len + ol4_len,
+ IPPROTO_UDP,
+ in_saddr4.sin_addr.s_addr,
+ in_daddr4.sin_addr.s_addr,
+ il4_len + cfg_payload_len,
+ cfg_dsfield_inner);
+ break;
+ case PF_INET6:
+ build_ipv6_header(buf + el3_len + ol3_len + ol4_len,
+ IPPROTO_UDP,
+ &in_saddr6, &in_daddr6,
+ il4_len + cfg_payload_len,
+ cfg_dsfield_inner);
+ break;
+ }
+
+ build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len,
+ cfg_payload_len, CFG_PORT_INNER, cfg_l3_inner);
+
+ if (!cfg_encap_proto)
+ return il3_len + il4_len + cfg_payload_len;
+
+ switch (cfg_l3_outer) {
+ case PF_INET:
+ build_ipv4_header(buf + el3_len, cfg_encap_proto,
+ out_saddr4.sin_addr.s_addr,
+ out_daddr4.sin_addr.s_addr,
+ ol4_len + il3_len + il4_len + cfg_payload_len,
+ cfg_dsfield_outer);
+ break;
+ case PF_INET6:
+ build_ipv6_header(buf + el3_len, cfg_encap_proto,
+ &out_saddr6, &out_daddr6,
+ ol4_len + il3_len + il4_len + cfg_payload_len,
+ cfg_dsfield_outer);
+ break;
+ }
+
+ switch (cfg_encap_proto) {
+ case IPPROTO_UDP:
+ build_gue_header(buf + el3_len + ol3_len + ol4_len -
+ sizeof(struct guehdr),
+ cfg_l3_inner == PF_INET ? IPPROTO_IPIP
+ : IPPROTO_IPV6);
+ build_udp_header(buf + el3_len + ol3_len,
+ sizeof(struct guehdr) + il3_len + il4_len +
+ cfg_payload_len,
+ cfg_port_gue, cfg_l3_outer);
+ break;
+ case IPPROTO_GRE:
+ build_gre_header(buf + el3_len + ol3_len,
+ cfg_l3_inner == PF_INET ? ETH_P_IP
+ : ETH_P_IPV6);
+ break;
+ }
+
+ switch (cfg_l3_extra) {
+ case PF_INET:
+ build_ipv4_header(buf,
+ cfg_l3_outer == PF_INET ? IPPROTO_IPIP
+ : IPPROTO_IPV6,
+ extra_saddr4.sin_addr.s_addr,
+ extra_daddr4.sin_addr.s_addr,
+ ol3_len + ol4_len + il3_len + il4_len +
+ cfg_payload_len, 0);
+ break;
+ case PF_INET6:
+ build_ipv6_header(buf,
+ cfg_l3_outer == PF_INET ? IPPROTO_IPIP
+ : IPPROTO_IPV6,
+ &extra_saddr6, &extra_daddr6,
+ ol3_len + ol4_len + il3_len + il4_len +
+ cfg_payload_len, 0);
+ break;
+ }
+
+ return el3_len + ol3_len + ol4_len + il3_len + il4_len +
+ cfg_payload_len;
+}
+
+/* sender transmits encapsulated over RAW or unencap'd over UDP */
+static int setup_tx(void)
+{
+ int family, fd, ret;
+
+ if (cfg_l3_extra)
+ family = cfg_l3_extra;
+ else if (cfg_l3_outer)
+ family = cfg_l3_outer;
+ else
+ family = cfg_l3_inner;
+
+ fd = socket(family, SOCK_RAW, IPPROTO_RAW);
+ if (fd == -1)
+ error(1, errno, "socket tx");
+
+ if (cfg_l3_extra) {
+ if (cfg_l3_extra == PF_INET)
+ ret = connect(fd, (void *) &extra_daddr4,
+ sizeof(extra_daddr4));
+ else
+ ret = connect(fd, (void *) &extra_daddr6,
+ sizeof(extra_daddr6));
+ if (ret)
+ error(1, errno, "connect tx");
+ } else if (cfg_l3_outer) {
+ /* connect to destination if not encapsulated */
+ if (cfg_l3_outer == PF_INET)
+ ret = connect(fd, (void *) &out_daddr4,
+ sizeof(out_daddr4));
+ else
+ ret = connect(fd, (void *) &out_daddr6,
+ sizeof(out_daddr6));
+ if (ret)
+ error(1, errno, "connect tx");
+ } else {
+ /* otherwise using loopback */
+ if (cfg_l3_inner == PF_INET)
+ ret = connect(fd, (void *) &in_daddr4,
+ sizeof(in_daddr4));
+ else
+ ret = connect(fd, (void *) &in_daddr6,
+ sizeof(in_daddr6));
+ if (ret)
+ error(1, errno, "connect tx");
+ }
+
+ return fd;
+}
+
+/* receiver reads unencapsulated UDP */
+static int setup_rx(void)
+{
+ int fd, ret;
+
+ fd = socket(cfg_l3_inner, SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket rx");
+
+ if (cfg_l3_inner == PF_INET)
+ ret = bind(fd, (void *) &in_daddr4, sizeof(in_daddr4));
+ else
+ ret = bind(fd, (void *) &in_daddr6, sizeof(in_daddr6));
+ if (ret)
+ error(1, errno, "bind rx");
+
+ return fd;
+}
+
+static int do_tx(int fd, const char *pkt, int len)
+{
+ int ret;
+
+ ret = write(fd, pkt, len);
+ if (ret == -1)
+ error(1, errno, "send");
+ if (ret != len)
+ error(1, errno, "send: len (%d < %d)\n", ret, len);
+
+ return 1;
+}
+
+static int do_poll(int fd, short events, int timeout)
+{
+ struct pollfd pfd;
+ int ret;
+
+ pfd.fd = fd;
+ pfd.events = events;
+
+ ret = poll(&pfd, 1, timeout);
+ if (ret == -1)
+ error(1, errno, "poll");
+ if (ret && !(pfd.revents & POLLIN))
+ error(1, errno, "poll: unexpected event 0x%x\n", pfd.revents);
+
+ return ret;
+}
+
+static int do_rx(int fd)
+{
+ char rbuf;
+ int ret, num = 0;
+
+ while (1) {
+ ret = recv(fd, &rbuf, 1, MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ break;
+ if (ret == -1)
+ error(1, errno, "recv");
+ if (rbuf != cfg_payload_char)
+ error(1, 0, "recv: payload mismatch");
+ num++;
+ };
+
+ return num;
+}
+
+static int do_main(void)
+{
+ unsigned long tstop, treport, tcur;
+ int fdt = -1, fdr = -1, len, tx = 0, rx = 0;
+
+ if (!cfg_only_tx)
+ fdr = setup_rx();
+ if (!cfg_only_rx)
+ fdt = setup_tx();
+
+ len = build_packet();
+
+ tcur = util_gettime();
+ treport = tcur + 1000;
+ tstop = tcur + (cfg_num_secs * 1000);
+
+ while (1) {
+ if (!cfg_only_rx)
+ tx += do_tx(fdt, buf, len);
+
+ if (!cfg_only_tx)
+ rx += do_rx(fdr);
+
+ if (cfg_num_secs) {
+ tcur = util_gettime();
+ if (tcur >= tstop)
+ break;
+ if (tcur >= treport) {
+ fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
+ tx = 0;
+ rx = 0;
+ treport = tcur + 1000;
+ }
+ } else {
+ if (tx == cfg_num_pkt)
+ break;
+ }
+ }
+
+ /* read straggler packets, if any */
+ if (rx < tx) {
+ tstop = util_gettime() + 100;
+ while (rx < tx) {
+ tcur = util_gettime();
+ if (tcur >= tstop)
+ break;
+
+ do_poll(fdr, POLLIN, tstop - tcur);
+ rx += do_rx(fdr);
+ }
+ }
+
+ fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
+
+ if (fdr != -1 && close(fdr))
+ error(1, errno, "close rx");
+ if (fdt != -1 && close(fdt))
+ error(1, errno, "close tx");
+
+ /*
+ * success (== 0) only if received all packets
+ * unless failure is expected, in which case none must arrive.
+ */
+ if (cfg_expect_failure)
+ return rx != 0;
+ else
+ return rx != tx;
+}
+
+
+static void __attribute__((noreturn)) usage(const char *filepath)
+{
+ fprintf(stderr, "Usage: %s [-e gre|gue|bare|none] [-i 4|6] [-l len] "
+ "[-O 4|6] [-o 4|6] [-n num] [-t secs] [-R] [-T] "
+ "[-s <osrc> [-d <odst>] [-S <isrc>] [-D <idst>] "
+ "[-x <otos>] [-X <itos>] [-f <isport>] [-F]\n",
+ filepath);
+ exit(1);
+}
+
+static void parse_addr(int family, void *addr, const char *optarg)
+{
+ int ret;
+
+ ret = inet_pton(family, optarg, addr);
+ if (ret == -1)
+ error(1, errno, "inet_pton");
+ if (ret == 0)
+ error(1, 0, "inet_pton: bad string");
+}
+
+static void parse_addr4(struct sockaddr_in *addr, const char *optarg)
+{
+ parse_addr(AF_INET, &addr->sin_addr, optarg);
+}
+
+static void parse_addr6(struct sockaddr_in6 *addr, const char *optarg)
+{
+ parse_addr(AF_INET6, &addr->sin6_addr, optarg);
+}
+
+static int parse_protocol_family(const char *filepath, const char *optarg)
+{
+ if (!strcmp(optarg, "4"))
+ return PF_INET;
+ if (!strcmp(optarg, "6"))
+ return PF_INET6;
+
+ usage(filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "d:D:e:f:Fhi:l:n:o:O:Rs:S:t:Tx:X:")) != -1) {
+ switch (c) {
+ case 'd':
+ if (cfg_l3_outer == AF_UNSPEC)
+ error(1, 0, "-d must be preceded by -o");
+ if (cfg_l3_outer == AF_INET)
+ parse_addr4(&out_daddr4, optarg);
+ else
+ parse_addr6(&out_daddr6, optarg);
+ break;
+ case 'D':
+ if (cfg_l3_inner == AF_UNSPEC)
+ error(1, 0, "-D must be preceded by -i");
+ if (cfg_l3_inner == AF_INET)
+ parse_addr4(&in_daddr4, optarg);
+ else
+ parse_addr6(&in_daddr6, optarg);
+ break;
+ case 'e':
+ if (!strcmp(optarg, "gre"))
+ cfg_encap_proto = IPPROTO_GRE;
+ else if (!strcmp(optarg, "gue"))
+ cfg_encap_proto = IPPROTO_UDP;
+ else if (!strcmp(optarg, "bare"))
+ cfg_encap_proto = IPPROTO_IPIP;
+ else if (!strcmp(optarg, "none"))
+ cfg_encap_proto = IPPROTO_IP; /* == 0 */
+ else
+ usage(argv[0]);
+ break;
+ case 'f':
+ cfg_src_port = strtol(optarg, NULL, 0);
+ break;
+ case 'F':
+ cfg_expect_failure = true;
+ break;
+ case 'h':
+ usage(argv[0]);
+ break;
+ case 'i':
+ if (!strcmp(optarg, "4"))
+ cfg_l3_inner = PF_INET;
+ else if (!strcmp(optarg, "6"))
+ cfg_l3_inner = PF_INET6;
+ else
+ usage(argv[0]);
+ break;
+ case 'l':
+ cfg_payload_len = strtol(optarg, NULL, 0);
+ break;
+ case 'n':
+ cfg_num_pkt = strtol(optarg, NULL, 0);
+ break;
+ case 'o':
+ cfg_l3_outer = parse_protocol_family(argv[0], optarg);
+ break;
+ case 'O':
+ cfg_l3_extra = parse_protocol_family(argv[0], optarg);
+ break;
+ case 'R':
+ cfg_only_rx = true;
+ break;
+ case 's':
+ if (cfg_l3_outer == AF_INET)
+ parse_addr4(&out_saddr4, optarg);
+ else
+ parse_addr6(&out_saddr6, optarg);
+ break;
+ case 'S':
+ if (cfg_l3_inner == AF_INET)
+ parse_addr4(&in_saddr4, optarg);
+ else
+ parse_addr6(&in_saddr6, optarg);
+ break;
+ case 't':
+ cfg_num_secs = strtol(optarg, NULL, 0);
+ break;
+ case 'T':
+ cfg_only_tx = true;
+ break;
+ case 'x':
+ cfg_dsfield_outer = strtol(optarg, NULL, 0);
+ break;
+ case 'X':
+ cfg_dsfield_inner = strtol(optarg, NULL, 0);
+ break;
+ }
+ }
+
+ if (cfg_only_rx && cfg_only_tx)
+ error(1, 0, "options: cannot combine rx-only and tx-only");
+
+ if (cfg_encap_proto && cfg_l3_outer == AF_UNSPEC)
+ error(1, 0, "options: must specify outer with encap");
+ else if ((!cfg_encap_proto) && cfg_l3_outer != AF_UNSPEC)
+ error(1, 0, "options: cannot combine no-encap and outer");
+ else if ((!cfg_encap_proto) && cfg_l3_extra != AF_UNSPEC)
+ error(1, 0, "options: cannot combine no-encap and extra");
+
+ if (cfg_l3_inner == AF_UNSPEC)
+ cfg_l3_inner = AF_INET6;
+ if (cfg_l3_inner == AF_INET6 && cfg_encap_proto == IPPROTO_IPIP)
+ cfg_encap_proto = IPPROTO_IPV6;
+
+ /* RFC 6040 4.2:
+ * on decap, if outer encountered congestion (CE == 0x3),
+ * but inner cannot encode ECN (NoECT == 0x0), then drop packet.
+ */
+ if (((cfg_dsfield_outer & 0x3) == 0x3) &&
+ ((cfg_dsfield_inner & 0x3) == 0x0))
+ cfg_expect_failure = true;
+}
+
+static void print_opts(void)
+{
+ if (cfg_l3_inner == PF_INET6) {
+ util_printaddr("inner.dest6", (void *) &in_daddr6);
+ util_printaddr("inner.source6", (void *) &in_saddr6);
+ } else {
+ util_printaddr("inner.dest4", (void *) &in_daddr4);
+ util_printaddr("inner.source4", (void *) &in_saddr4);
+ }
+
+ if (!cfg_l3_outer)
+ return;
+
+ fprintf(stderr, "encap proto: %u\n", cfg_encap_proto);
+
+ if (cfg_l3_outer == PF_INET6) {
+ util_printaddr("outer.dest6", (void *) &out_daddr6);
+ util_printaddr("outer.source6", (void *) &out_saddr6);
+ } else {
+ util_printaddr("outer.dest4", (void *) &out_daddr4);
+ util_printaddr("outer.source4", (void *) &out_saddr4);
+ }
+
+ if (!cfg_l3_extra)
+ return;
+
+ if (cfg_l3_outer == PF_INET6) {
+ util_printaddr("extra.dest6", (void *) &extra_daddr6);
+ util_printaddr("extra.source6", (void *) &extra_saddr6);
+ } else {
+ util_printaddr("extra.dest4", (void *) &extra_daddr4);
+ util_printaddr("extra.source4", (void *) &extra_saddr4);
+ }
+
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+ print_opts();
+ return do_main();
+}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
new file mode 100755
index 000000000000..c0fb073b5eab
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Load BPF flow dissector and verify it correctly dissects traffic
+export TESTNAME=test_flow_dissector
+unmount=0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
+# This test needs to be run in a network namespace with in_netns.sh. Check if
+# this is the case and run it with in_netns.sh if it is being run in the root
+# namespace.
+if [[ -z $(ip netns identify $$) ]]; then
+ ../net/in_netns.sh "$0" "$@"
+ exit $?
+fi
+
+# Determine selftest success via shell exit code
+exit_handler()
+{
+ if (( $? == 0 )); then
+ echo "selftests: $TESTNAME [PASS]";
+ else
+ echo "selftests: $TESTNAME [FAILED]";
+ fi
+
+ set +e
+
+ # Cleanup
+ tc filter del dev lo ingress pref 1337 2> /dev/null
+ tc qdisc del dev lo ingress 2> /dev/null
+ ./flow_dissector_load -d 2> /dev/null
+ if [ $unmount -ne 0 ]; then
+ umount bpffs 2> /dev/null
+ fi
+}
+
+# Exit script immediately (well catched by trap handler) if any
+# program/thing exits with a non-zero status.
+set -e
+
+# (Use 'trap -l' to list meaning of numbers)
+trap exit_handler 0 2 3 6 9
+
+# Mount BPF file system
+if /bin/mount | grep /sys/fs/bpf > /dev/null; then
+ echo "bpffs already mounted"
+else
+ echo "bpffs not mounted. Mounting..."
+ unmount=1
+ /bin/mount bpffs /sys/fs/bpf -t bpf
+fi
+
+# Attach BPF program
+./flow_dissector_load -p bpf_flow.o -s dissect
+
+# Setup
+tc qdisc add dev lo ingress
+
+echo "Testing IPv4..."
+# Drops all IP/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \
+ udp src_port 9 action drop
+
+# Send 10 IPv4/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 4 -f 8
+# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 4 -f 9 -F
+# Send 10 IPv4/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 4 -f 10
+
+echo "Testing IPIP..."
+# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+ -D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+ -D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+ -D 192.168.0.1 -S 1.1.1.1 -f 10
+
+echo "Testing IPv4 + GRE..."
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+ -D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+ -D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+ -D 192.168.0.1 -S 1.1.1.1 -f 10
+
+tc filter del dev lo ingress pref 1337
+
+echo "Testing IPv6..."
+# Drops all IPv6/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \
+ udp src_port 9 action drop
+
+# Send 10 IPv6/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 6 -f 8
+# Send 10 IPv6/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 6 -f 9 -F
+# Send 10 IPv6/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 6 -f 10
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 0ef68204c84b..63a671803ed6 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -112,13 +112,13 @@ static void test_pkt_access(void)
err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
NULL, NULL, &retval, &duration);
- CHECK(err || errno || retval, "ipv4",
+ CHECK(err || retval, "ipv4",
"err %d errno %d retval %d duration %d\n",
err, errno, retval, duration);
err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6),
NULL, NULL, &retval, &duration);
- CHECK(err || errno || retval, "ipv6",
+ CHECK(err || retval, "ipv6",
"err %d errno %d retval %d duration %d\n",
err, errno, retval, duration);
bpf_object__close(obj);
@@ -153,14 +153,14 @@ static void test_xdp(void)
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != XDP_TX || size != 74 ||
+ CHECK(err || retval != XDP_TX || size != 74 ||
iph->protocol != IPPROTO_IPIP, "ipv4",
"err %d errno %d retval %d size %d\n",
err, errno, retval, size);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != XDP_TX || size != 114 ||
+ CHECK(err || retval != XDP_TX || size != 114 ||
iph6->nexthdr != IPPROTO_IPV6, "ipv6",
"err %d errno %d retval %d size %d\n",
err, errno, retval, size);
@@ -185,13 +185,13 @@ static void test_xdp_adjust_tail(void)
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != XDP_DROP,
+ CHECK(err || retval != XDP_DROP,
"ipv4", "err %d errno %d retval %d size %d\n",
err, errno, retval, size);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != XDP_TX || size != 54,
+ CHECK(err || retval != XDP_TX || size != 54,
"ipv6", "err %d errno %d retval %d size %d\n",
err, errno, retval, size);
bpf_object__close(obj);
@@ -254,14 +254,14 @@ static void test_l4lb(const char *file)
err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+ CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
*magic != MAGIC_VAL, "ipv4",
"err %d errno %d retval %d size %d magic %x\n",
err, errno, retval, size, *magic);
err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+ CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
*magic != MAGIC_VAL, "ipv6",
"err %d errno %d retval %d size %d magic %x\n",
err, errno, retval, size, *magic);
@@ -343,14 +343,14 @@ static void test_xdp_noinline(void)
err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != 1 || size != 54 ||
+ CHECK(err || retval != 1 || size != 54 ||
*magic != MAGIC_VAL, "ipv4",
"err %d errno %d retval %d size %d magic %x\n",
err, errno, retval, size, *magic);
err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
- CHECK(err || errno || retval != 1 || size != 74 ||
+ CHECK(err || retval != 1 || size != 74 ||
*magic != MAGIC_VAL, "ipv6",
"err %d errno %d retval %d size %d magic %x\n",
err, errno, retval, size, *magic);
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 0c7d9e556b47..ac7de38e5c63 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -469,8 +469,6 @@ static int sendmsg_test(struct sockmap_options *opt)
fprintf(stderr,
"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
iov_count, iov_buf, cnt, err);
- shutdown(p2, SHUT_RDWR);
- shutdown(p1, SHUT_RDWR);
if (s.end.tv_sec - s.start.tv_sec) {
sent_Bps = sentBps(s);
recvd_Bps = recvdBps(s);
@@ -500,7 +498,6 @@ static int sendmsg_test(struct sockmap_options *opt)
fprintf(stderr,
"msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
iov_count, iov_buf, cnt, err);
- shutdown(c1, SHUT_RDWR);
if (s.end.tv_sec - s.start.tv_sec) {
sent_Bps = sentBps(s);
recvd_Bps = recvdBps(s);
@@ -1348,9 +1345,9 @@ static int populate_progs(char *bpf_file)
return 0;
}
-static int __test_suite(char *bpf_file)
+static int __test_suite(int cg_fd, char *bpf_file)
{
- int cg_fd, err;
+ int err, cleanup = cg_fd;
err = populate_progs(bpf_file);
if (err < 0) {
@@ -1358,22 +1355,24 @@ static int __test_suite(char *bpf_file)
return err;
}
- if (setup_cgroup_environment()) {
- fprintf(stderr, "ERROR: cgroup env failed\n");
- return -EINVAL;
- }
-
- cg_fd = create_and_get_cgroup(CG_PATH);
if (cg_fd < 0) {
- fprintf(stderr,
- "ERROR: (%i) open cg path failed: %s\n",
- cg_fd, optarg);
- return cg_fd;
- }
+ if (setup_cgroup_environment()) {
+ fprintf(stderr, "ERROR: cgroup env failed\n");
+ return -EINVAL;
+ }
+
+ cg_fd = create_and_get_cgroup(CG_PATH);
+ if (cg_fd < 0) {
+ fprintf(stderr,
+ "ERROR: (%i) open cg path failed: %s\n",
+ cg_fd, optarg);
+ return cg_fd;
+ }
- if (join_cgroup(CG_PATH)) {
- fprintf(stderr, "ERROR: failed to join cgroup\n");
- return -EINVAL;
+ if (join_cgroup(CG_PATH)) {
+ fprintf(stderr, "ERROR: failed to join cgroup\n");
+ return -EINVAL;
+ }
}
/* Tests basic commands and APIs with range of iov values */
@@ -1394,20 +1393,24 @@ static int __test_suite(char *bpf_file)
out:
printf("Summary: %i PASSED %i FAILED\n", passed, failed);
- cleanup_cgroup_environment();
- close(cg_fd);
+ if (cleanup < 0) {
+ cleanup_cgroup_environment();
+ close(cg_fd);
+ }
return err;
}
-static int test_suite(void)
+static int test_suite(int cg_fd)
{
int err;
- err = __test_suite(BPF_SOCKMAP_FILENAME);
+ err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME);
if (err)
goto out;
- err = __test_suite(BPF_SOCKHASH_FILENAME);
+ err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME);
out:
+ if (cg_fd > -1)
+ close(cg_fd);
return err;
}
@@ -1420,7 +1423,7 @@ int main(int argc, char **argv)
int test = PING_PONG;
if (argc < 2)
- return test_suite();
+ return test_suite(-1);
while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
long_options, &longindex)) != -1) {
@@ -1486,6 +1489,9 @@ int main(int argc, char **argv)
}
}
+ if (argc <= 3 && cg_fd)
+ return test_suite(cg_fd);
+
if (!cg_fd) {
fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
argv[0]);
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 4b7fd540cea9..74f73b33a7b0 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -5,6 +5,7 @@
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
+#include <linux/ipv6.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/tcp.h>
@@ -17,6 +18,13 @@ struct bpf_map_def SEC("maps") global_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct tcpbpf_globals),
+ .max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") sockopt_results = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(int),
.max_entries = 2,
};
@@ -45,11 +53,14 @@ int _version SEC("version") = 1;
SEC("sockops")
int bpf_testcb(struct bpf_sock_ops *skops)
{
- int rv = -1;
- int bad_call_rv = 0;
+ char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
+ struct tcphdr *thdr;
int good_call_rv = 0;
- int op;
+ int bad_call_rv = 0;
+ int save_syn = 1;
+ int rv = -1;
int v = 0;
+ int op;
op = (int) skops->op;
@@ -82,6 +93,21 @@ int bpf_testcb(struct bpf_sock_ops *skops)
v = 0xff;
rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
sizeof(v));
+ if (skops->family == AF_INET6) {
+ v = bpf_getsockopt(skops, IPPROTO_TCP, TCP_SAVED_SYN,
+ header, (sizeof(struct ipv6hdr) +
+ sizeof(struct tcphdr)));
+ if (!v) {
+ int offset = sizeof(struct ipv6hdr);
+
+ thdr = (struct tcphdr *)(header + offset);
+ v = thdr->syn;
+ __u32 key = 1;
+
+ bpf_map_update_elem(&sockopt_results, &key, &v,
+ BPF_ANY);
+ }
+ }
break;
case BPF_SOCK_OPS_RTO_CB:
break;
@@ -111,6 +137,12 @@ int bpf_testcb(struct bpf_sock_ops *skops)
break;
case BPF_SOCK_OPS_TCP_LISTEN_CB:
bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+ v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN,
+ &save_syn, sizeof(save_syn));
+ /* Update global map w/ result of setsock opt */
+ __u32 key = 0;
+
+ bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY);
break;
default:
rv = -1;
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index a275c2971376..e6eebda7d112 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -54,6 +54,26 @@ err:
return -1;
}
+int verify_sockopt_result(int sock_map_fd)
+{
+ __u32 key = 0;
+ int res;
+ int rv;
+
+ /* check setsockopt for SAVE_SYN */
+ rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
+ EXPECT_EQ(0, rv, "d");
+ EXPECT_EQ(0, res, "d");
+ key = 1;
+ /* check getsockopt for SAVED_SYN */
+ rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
+ EXPECT_EQ(0, rv, "d");
+ EXPECT_EQ(1, res, "d");
+ return 0;
+err:
+ return -1;
+}
+
static int bpf_find_map(const char *test, struct bpf_object *obj,
const char *name)
{
@@ -70,11 +90,11 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
int main(int argc, char **argv)
{
const char *file = "test_tcpbpf_kern.o";
+ int prog_fd, map_fd, sock_map_fd;
struct tcpbpf_globals g = {0};
const char *cg_path = "/foo";
int error = EXIT_FAILURE;
struct bpf_object *obj;
- int prog_fd, map_fd;
int cg_fd = -1;
__u32 key = 0;
int rv;
@@ -110,6 +130,10 @@ int main(int argc, char **argv)
if (map_fd < 0)
goto err;
+ sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results");
+ if (sock_map_fd < 0)
+ goto err;
+
rv = bpf_map_lookup_elem(map_fd, &key, &g);
if (rv != 0) {
printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
@@ -121,6 +145,11 @@ int main(int argc, char **argv)
goto err;
}
+ if (verify_sockopt_result(sock_map_fd)) {
+ printf("FAILED: Wrong sockopt stats\n");
+ goto err;
+ }
+
printf("PASSED!\n");
error = 0;
err:
diff --git a/tools/testing/selftests/bpf/with_addr.sh b/tools/testing/selftests/bpf/with_addr.sh
new file mode 100755
index 000000000000..ffcd3953f94c
--- /dev/null
+++ b/tools/testing/selftests/bpf/with_addr.sh
@@ -0,0 +1,54 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# add private ipv4 and ipv6 addresses to loopback
+
+readonly V6_INNER='100::a/128'
+readonly V4_INNER='192.168.0.1/32'
+
+if getopts ":s" opt; then
+ readonly SIT_DEV_NAME='sixtofourtest0'
+ readonly V6_SIT='2::/64'
+ readonly V4_SIT='172.17.0.1/32'
+ shift
+fi
+
+fail() {
+ echo "error: $*" 1>&2
+ exit 1
+}
+
+setup() {
+ ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address'
+ ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address'
+
+ if [[ -n "${V6_SIT}" ]]; then
+ ip link add "${SIT_DEV_NAME}" type sit remote any local any \
+ || fail 'failed to add sit'
+ ip link set dev "${SIT_DEV_NAME}" up \
+ || fail 'failed to bring sit device up'
+ ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \
+ || fail 'failed to setup v6 SIT address'
+ ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \
+ || fail 'failed to setup v4 SIT address'
+ fi
+
+ sleep 2 # avoid race causing bind to fail
+}
+
+cleanup() {
+ if [[ -n "${V6_SIT}" ]]; then
+ ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}"
+ ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}"
+ ip link del "${SIT_DEV_NAME}"
+ fi
+
+ ip -4 addr del "${V4_INNER}" dev lo
+ ip -6 addr del "${V6_INNER}" dev lo
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"
diff --git a/tools/testing/selftests/bpf/with_tunnels.sh b/tools/testing/selftests/bpf/with_tunnels.sh
new file mode 100755
index 000000000000..e24949ed3a20
--- /dev/null
+++ b/tools/testing/selftests/bpf/with_tunnels.sh
@@ -0,0 +1,36 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# setup tunnels for flow dissection test
+
+readonly SUFFIX="test_$(mktemp -u XXXX)"
+CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo"
+
+setup() {
+ ip link add "ipip_${SUFFIX}" type ipip ${CONFIG}
+ ip link add "gre_${SUFFIX}" type gre ${CONFIG}
+ ip link add "sit_${SUFFIX}" type sit ${CONFIG}
+
+ echo "tunnels before test:"
+ ip tunnel show
+
+ ip link set "ipip_${SUFFIX}" up
+ ip link set "gre_${SUFFIX}" up
+ ip link set "sit_${SUFFIX}" up
+}
+
+
+cleanup() {
+ ip tunnel del "ipip_${SUFFIX}"
+ ip tunnel del "gre_${SUFFIX}"
+ ip tunnel del "sit_${SUFFIX}"
+
+ echo "tunnels after test:"
+ ip tunnel show
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
new file mode 100644
index 000000000000..0150bb2741eb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -0,0 +1,347 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# A test for switch behavior under MC overload. An issue in Spectrum chips
+# causes throughput of UC traffic to drop severely when a switch is under heavy
+# MC load. This issue can be overcome by putting the switch to MC-aware mode.
+# This test verifies that UC performance stays intact even as the switch is
+# under MC flood, and therefore that the MC-aware mode is enabled and correctly
+# configured.
+#
+# Because mlxsw throttles CPU port, the traffic can't actually reach userspace
+# at full speed. That makes it impossible to use iperf3 to simply measure the
+# throughput, because many packets (that reach $h3) don't get to the kernel at
+# all even in UDP mode (the situation is even worse in TCP mode, where one can't
+# hope to see more than a couple Mbps).
+#
+# So instead we send traffic with mausezahn and use RX ethtool counters at $h3.
+# Multicast traffic is untagged, unicast traffic is tagged with PCP 1. Therefore
+# each gets a different priority and we can use per-prio ethtool counters to
+# measure the throughput. In order to avoid prioritizing unicast traffic, prio
+# qdisc is installed on $swp3 and maps all priorities to the same band #7 (and
+# thus TC 0).
+#
+# Mausezahn can't actually saturate the links unless it's using large frames.
+# Thus we set MTU to 10K on all involved interfaces. Then both unicast and
+# multicast traffic uses 8K frames.
+#
+# +-----------------------+ +----------------------------------+
+# | H1 | | H2 |
+# | | | unicast --> + $h2.111 |
+# | | | traffic | 192.0.2.129/28 |
+# | multicast | | | e-qos-map 0:1 |
+# | traffic | | | |
+# | $h1 + <----- | | + $h2 |
+# +-----|-----------------+ +--------------|-------------------+
+# | |
+# +-----|-------------------------------------------------|-------------------+
+# | + $swp1 + $swp2 |
+# | | >1Gbps | >1Gbps |
+# | +---|----------------+ +----------|----------------+ |
+# | | + $swp1.1 | | + $swp2.111 | |
+# | | BR1 | SW | BR111 | |
+# | | + $swp3.1 | | + $swp3.111 | |
+# | +---|----------------+ +----------|----------------+ |
+# | \_________________________________________________/ |
+# | | |
+# | + $swp3 |
+# | | 1Gbps bottleneck |
+# | | prio qdisc: {0..7} -> 7 |
+# +------------------------------------|--------------------------------------+
+# |
+# +--|-----------------+
+# | + $h3 H3 |
+# | | |
+# | + $h3.111 |
+# | 192.0.2.130/28 |
+# +--------------------+
+
+ALL_TESTS="
+ ping_ipv4
+ test_mc_aware
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+ mtu_set $h1 10000
+}
+
+h1_destroy()
+{
+ mtu_restore $h1
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2
+ mtu_set $h2 10000
+
+ vlan_create $h2 111 v$h2 192.0.2.129/28
+ ip link set dev $h2.111 type vlan egress-qos-map 0:1
+}
+
+h2_destroy()
+{
+ vlan_destroy $h2 111
+
+ mtu_restore $h2
+ simple_if_fini $h2
+}
+
+h3_create()
+{
+ simple_if_init $h3
+ mtu_set $h3 10000
+
+ vlan_create $h3 111 v$h3 192.0.2.130/28
+}
+
+h3_destroy()
+{
+ vlan_destroy $h3 111
+
+ mtu_restore $h3
+ simple_if_fini $h3
+}
+
+switch_create()
+{
+ ip link set dev $swp1 up
+ mtu_set $swp1 10000
+
+ ip link set dev $swp2 up
+ mtu_set $swp2 10000
+
+ ip link set dev $swp3 up
+ mtu_set $swp3 10000
+
+ vlan_create $swp2 111
+ vlan_create $swp3 111
+
+ ethtool -s $swp3 speed 1000 autoneg off
+ tc qdisc replace dev $swp3 root handle 3: \
+ prio bands 8 priomap 7 7 7 7 7 7 7 7
+
+ ip link add name br1 type bridge vlan_filtering 0
+ ip link set dev br1 up
+ ip link set dev $swp1 master br1
+ ip link set dev $swp3 master br1
+
+ ip link add name br111 type bridge vlan_filtering 0
+ ip link set dev br111 up
+ ip link set dev $swp2.111 master br111
+ ip link set dev $swp3.111 master br111
+}
+
+switch_destroy()
+{
+ ip link del dev br111
+ ip link del dev br1
+
+ tc qdisc del dev $swp3 root handle 3:
+ ethtool -s $swp3 autoneg on
+
+ vlan_destroy $swp3 111
+ vlan_destroy $swp2 111
+
+ mtu_restore $swp3
+ ip link set dev $swp3 down
+
+ mtu_restore $swp2
+ ip link set dev $swp2 down
+
+ mtu_restore $swp1
+ ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ h3mac=$(mac_get $h3)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ h3_create
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+ h3_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h2 192.0.2.130
+}
+
+humanize()
+{
+ local speed=$1; shift
+
+ for unit in bps Kbps Mbps Gbps; do
+ if (($(echo "$speed < 1024" | bc))); then
+ break
+ fi
+
+ speed=$(echo "scale=1; $speed / 1024" | bc)
+ done
+
+ echo "$speed${unit}"
+}
+
+rate()
+{
+ local t0=$1; shift
+ local t1=$1; shift
+ local interval=$1; shift
+
+ echo $((8 * (t1 - t0) / interval))
+}
+
+check_rate()
+{
+ local rate=$1; shift
+ local min=$1; shift
+ local what=$1; shift
+
+ if ((rate > min)); then
+ return 0
+ fi
+
+ echo "$what $(humanize $ir) < $(humanize $min_ingress)" > /dev/stderr
+ return 1
+}
+
+measure_uc_rate()
+{
+ local what=$1; shift
+
+ local interval=10
+ local i
+ local ret=0
+
+ # Dips in performance might cause momentary ingress rate to drop below
+ # 1Gbps. That wouldn't saturate egress and MC would thus get through,
+ # seemingly winning bandwidth on account of UC. Demand at least 2Gbps
+ # average ingress rate to somewhat mitigate this.
+ local min_ingress=2147483648
+
+ mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+ -a own -b $h3mac -t udp -q &
+ sleep 1
+
+ for i in {5..0}; do
+ local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
+ local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+ sleep $interval
+ local t1=$(ethtool_stats_get $h3 rx_octets_prio_1)
+ local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+
+ local ir=$(rate $u0 $u1 $interval)
+ local er=$(rate $t0 $t1 $interval)
+
+ if check_rate $ir $min_ingress "$what ingress rate"; then
+ break
+ fi
+
+ # Fail the test if we can't get the throughput.
+ if ((i == 0)); then
+ ret=1
+ fi
+ done
+
+ # Suppress noise from killing mausezahn.
+ { kill %% && wait; } 2>/dev/null
+
+ echo $ir $er
+ exit $ret
+}
+
+test_mc_aware()
+{
+ RET=0
+
+ local -a uc_rate
+ uc_rate=($(measure_uc_rate "UC-only"))
+ check_err $? "Could not get high enough UC-only ingress rate"
+ local ucth1=${uc_rate[1]}
+
+ mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
+
+ local d0=$(date +%s)
+ local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
+ local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0)
+
+ local -a uc_rate_2
+ uc_rate_2=($(measure_uc_rate "UC+MC"))
+ check_err $? "Could not get high enough UC+MC ingress rate"
+ local ucth2=${uc_rate_2[1]}
+
+ local d1=$(date +%s)
+ local t1=$(ethtool_stats_get $h3 rx_octets_prio_0)
+ local u1=$(ethtool_stats_get $swp1 rx_octets_prio_0)
+
+ local deg=$(bc <<< "
+ scale=2
+ ret = 100 * ($ucth1 - $ucth2) / $ucth1
+ if (ret > 0) { ret } else { 0 }
+ ")
+ check_err $(bc <<< "$deg > 10")
+
+ local interval=$((d1 - d0))
+ local mc_ir=$(rate $u0 $u1 $interval)
+ local mc_er=$(rate $t0 $t1 $interval)
+
+ # Suppress noise from killing mausezahn.
+ { kill %% && wait; } 2>/dev/null
+
+ log_test "UC performace under MC overload"
+
+ echo "UC-only throughput $(humanize $ucth1)"
+ echo "UC+MC throughput $(humanize $ucth2)"
+ echo "Degradation $deg %"
+ echo
+ echo "Full report:"
+ echo " UC only:"
+ echo " ingress UC throughput $(humanize ${uc_rate[0]})"
+ echo " egress UC throughput $(humanize ${uc_rate[1]})"
+ echo " UC+MC:"
+ echo " ingress UC throughput $(humanize ${uc_rate_2[0]})"
+ echo " egress UC throughput $(humanize ${uc_rate_2[1]})"
+ echo " ingress MC throughput $(humanize $mc_ir)"
+ echo " egress MC throughput $(humanize $mc_er)"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 78b24cf76f40..8cf22b3c2563 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -14,3 +14,4 @@ udpgso_bench_rx
udpgso_bench_tx
tcp_inq
tls
+ip_defrag
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 919aa2ac00af..256d82d5fa87 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,13 +5,13 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
-TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
diff --git a/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
new file mode 100755
index 000000000000..1f8ef0eff862
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="sticky"
+NUM_NETIFS=4
+TEST_MAC=de:ad:be:ef:13:37
+source lib.sh
+
+switch_create()
+{
+ ip link add dev br0 type bridge
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+
+ ip link set dev br0 up
+ ip link set dev $h1 up
+ ip link set dev $swp1 up
+ ip link set dev $h2 up
+ ip link set dev $swp2 up
+}
+
+switch_destroy()
+{
+ ip link set dev $swp2 down
+ ip link set dev $h2 down
+ ip link set dev $swp1 down
+ ip link set dev $h1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+ h2=${NETIFS[p3]}
+ swp2=${NETIFS[p4]}
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+ switch_destroy
+}
+
+sticky()
+{
+ bridge fdb add $TEST_MAC dev $swp1 master static sticky
+ check_err $? "Could not add fdb entry"
+ bridge fdb del $TEST_MAC dev $swp1 vlan 1 master static sticky
+ $MZ $h2 -c 1 -a $TEST_MAC -t arp "request" -q
+ bridge -j fdb show br br0 brport $swp1\
+ | jq -e ".[] | select(.mac == \"$TEST_MAC\")" &> /dev/null
+ check_err $? "Did not find FDB record when should"
+
+ log_test "Sticky fdb entry"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ca53b539aa2d..0e73698b2048 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -494,6 +494,14 @@ tc_rule_stats_get()
| jq '.[1].options.actions[].stats.packets'
}
+ethtool_stats_get()
+{
+ local dev=$1; shift
+ local stat=$1; shift
+
+ ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2
+}
+
mac_get()
{
local if_name=$1
@@ -541,6 +549,23 @@ forwarding_restore()
sysctl_restore net.ipv4.conf.all.forwarding
}
+declare -A MTU_ORIG
+mtu_set()
+{
+ local dev=$1; shift
+ local mtu=$1; shift
+
+ MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu')
+ ip link set dev $dev mtu $mtu
+}
+
+mtu_restore()
+{
+ local dev=$1; shift
+
+ ip link set dev $dev mtu ${MTU_ORIG["$dev"]}
+}
+
tc_offload_check()
{
local num_netifs=${1:-$NUM_NETIFS}
diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
new file mode 100644
index 000000000000..2366dc6bce71
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -0,0 +1,394 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+static bool cfg_do_ipv4;
+static bool cfg_do_ipv6;
+static bool cfg_verbose;
+static bool cfg_overlap;
+static unsigned short cfg_port = 9000;
+
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+
+#define IP4_HLEN (sizeof(struct iphdr))
+#define IP6_HLEN (sizeof(struct ip6_hdr))
+#define UDP_HLEN (sizeof(struct udphdr))
+
+/* IPv6 fragment header lenth. */
+#define FRAG_HLEN 8
+
+static int payload_len;
+static int max_frag_len;
+
+#define MSG_LEN_MAX 60000 /* Max UDP payload length. */
+
+#define IP4_MF (1u << 13) /* IPv4 MF flag. */
+#define IP6_MF (1) /* IPv6 MF flag. */
+
+#define CSUM_MANGLED_0 (0xffff)
+
+static uint8_t udp_payload[MSG_LEN_MAX];
+static uint8_t ip_frame[IP_MAXPACKET];
+static uint32_t ip_id = 0xabcd;
+static int msg_counter;
+static int frag_counter;
+static unsigned int seed;
+
+/* Receive a UDP packet. Validate it matches udp_payload. */
+static void recv_validate_udp(int fd_udp)
+{
+ ssize_t ret;
+ static uint8_t recv_buff[MSG_LEN_MAX];
+
+ ret = recv(fd_udp, recv_buff, payload_len, 0);
+ msg_counter++;
+
+ if (cfg_overlap) {
+ if (ret != -1)
+ error(1, 0, "recv: expected timeout; got %d",
+ (int)ret);
+ if (errno != ETIMEDOUT && errno != EAGAIN)
+ error(1, errno, "recv: expected timeout: %d",
+ errno);
+ return; /* OK */
+ }
+
+ if (ret == -1)
+ error(1, errno, "recv: payload_len = %d max_frag_len = %d",
+ payload_len, max_frag_len);
+ if (ret != payload_len)
+ error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len);
+ if (memcmp(udp_payload, recv_buff, payload_len))
+ error(1, 0, "recv: wrong data");
+}
+
+static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum)
+{
+ int i;
+
+ for (i = 0; i < (len & ~1U); i += 2) {
+ sum += (u_int16_t)ntohs(*((u_int16_t *)(buf + i)));
+ if (sum > 0xffff)
+ sum -= 0xffff;
+ }
+
+ if (i < len) {
+ sum += buf[i] << 8;
+ if (sum > 0xffff)
+ sum -= 0xffff;
+ }
+
+ return sum;
+}
+
+static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr)
+{
+ uint32_t sum = 0;
+ uint16_t res;
+
+ sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src),
+ IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len));
+ sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+ sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+ res = 0xffff & ~sum;
+ if (res)
+ return htons(res);
+ else
+ return CSUM_MANGLED_0;
+}
+
+static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr)
+{
+ uint32_t sum = 0;
+ uint16_t res;
+
+ sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src),
+ IPPROTO_UDP);
+ sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum);
+ sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+ sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+ res = 0xffff & ~sum;
+ if (res)
+ return htons(res);
+ else
+ return CSUM_MANGLED_0;
+}
+
+static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
+ int offset, bool ipv6)
+{
+ int frag_len;
+ int res;
+ int payload_offset = offset > 0 ? offset - UDP_HLEN : 0;
+ uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN :
+ ip_frame + IP4_HLEN;
+
+ if (offset == 0) {
+ struct udphdr udphdr;
+ udphdr.source = htons(cfg_port + 1);
+ udphdr.dest = htons(cfg_port);
+ udphdr.len = htons(UDP_HLEN + payload_len);
+ udphdr.check = 0;
+ if (ipv6)
+ udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr);
+ else
+ udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr);
+ memcpy(frag_start, &udphdr, UDP_HLEN);
+ }
+
+ if (ipv6) {
+ struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
+ struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+ if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+ /* This is the last fragment. */
+ frag_len = FRAG_HLEN + payload_len - payload_offset;
+ fraghdr->ip6f_offlg = htons(offset);
+ } else {
+ frag_len = FRAG_HLEN + max_frag_len;
+ fraghdr->ip6f_offlg = htons(offset | IP6_MF);
+ }
+ ip6hdr->ip6_plen = htons(frag_len);
+ if (offset == 0)
+ memcpy(frag_start + UDP_HLEN, udp_payload,
+ frag_len - FRAG_HLEN - UDP_HLEN);
+ else
+ memcpy(frag_start, udp_payload + payload_offset,
+ frag_len - FRAG_HLEN);
+ frag_len += IP6_HLEN;
+ } else {
+ struct ip *iphdr = (struct ip *)ip_frame;
+ if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+ /* This is the last fragment. */
+ frag_len = IP4_HLEN + payload_len - payload_offset;
+ iphdr->ip_off = htons(offset / 8);
+ } else {
+ frag_len = IP4_HLEN + max_frag_len;
+ iphdr->ip_off = htons(offset / 8 | IP4_MF);
+ }
+ iphdr->ip_len = htons(frag_len);
+ if (offset == 0)
+ memcpy(frag_start + UDP_HLEN, udp_payload,
+ frag_len - IP4_HLEN - UDP_HLEN);
+ else
+ memcpy(frag_start, udp_payload + payload_offset,
+ frag_len - IP4_HLEN);
+ }
+
+ res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+ if (res < 0)
+ error(1, errno, "send_fragment");
+ if (res != frag_len)
+ error(1, 0, "send_fragment: %d vs %d", res, frag_len);
+
+ frag_counter++;
+}
+
+static void send_udp_frags(int fd_raw, struct sockaddr *addr,
+ socklen_t alen, bool ipv6)
+{
+ struct ip *iphdr = (struct ip *)ip_frame;
+ struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
+ struct udphdr udphdr;
+ int res;
+ int offset;
+ int frag_len;
+
+ /* Send the UDP datagram using raw IP fragments: the 0th fragment
+ * has the UDP header; other fragments are pieces of udp_payload
+ * split in chunks of frag_len size.
+ *
+ * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then
+ * even fragments (0th, 2nd, etc.) are sent out.
+ */
+ if (ipv6) {
+ struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+ ((struct sockaddr_in6 *)addr)->sin6_port = 0;
+ memset(ip6hdr, 0, sizeof(*ip6hdr));
+ ip6hdr->ip6_flow = htonl(6<<28); /* Version. */
+ ip6hdr->ip6_nxt = IPPROTO_FRAGMENT;
+ ip6hdr->ip6_hops = 255;
+ ip6hdr->ip6_src = addr6;
+ ip6hdr->ip6_dst = addr6;
+ fraghdr->ip6f_nxt = IPPROTO_UDP;
+ fraghdr->ip6f_reserved = 0;
+ fraghdr->ip6f_ident = htonl(ip_id++);
+ } else {
+ memset(iphdr, 0, sizeof(*iphdr));
+ iphdr->ip_hl = 5;
+ iphdr->ip_v = 4;
+ iphdr->ip_tos = 0;
+ iphdr->ip_id = htons(ip_id++);
+ iphdr->ip_ttl = 0x40;
+ iphdr->ip_p = IPPROTO_UDP;
+ iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
+ iphdr->ip_dst = addr4;
+ iphdr->ip_sum = 0;
+ }
+
+ /* Odd fragments. */
+ offset = max_frag_len;
+ while (offset < (UDP_HLEN + payload_len)) {
+ send_fragment(fd_raw, addr, alen, offset, ipv6);
+ offset += 2 * max_frag_len;
+ }
+
+ if (cfg_overlap) {
+ /* Send an extra random fragment. */
+ offset = rand() % (UDP_HLEN + payload_len - 1);
+ /* sendto() returns EINVAL if offset + frag_len is too small. */
+ if (ipv6) {
+ struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+ frag_len = max_frag_len + rand() % 256;
+ /* In IPv6 if !!(frag_len % 8), the fragment is dropped. */
+ frag_len &= ~0x7;
+ fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF);
+ ip6hdr->ip6_plen = htons(frag_len);
+ frag_len += IP6_HLEN;
+ } else {
+ frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
+ iphdr->ip_off = htons(offset / 8 | IP4_MF);
+ iphdr->ip_len = htons(frag_len);
+ }
+ res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+ if (res < 0)
+ error(1, errno, "sendto overlap");
+ if (res != frag_len)
+ error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len);
+ frag_counter++;
+ }
+
+ /* Event fragments. */
+ offset = 0;
+ while (offset < (UDP_HLEN + payload_len)) {
+ send_fragment(fd_raw, addr, alen, offset, ipv6);
+ offset += 2 * max_frag_len;
+ }
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6)
+{
+ int fd_tx_raw, fd_rx_udp;
+ struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 };
+ int idx;
+ int min_frag_len = ipv6 ? 1280 : 8;
+
+ /* Initialize the payload. */
+ for (idx = 0; idx < MSG_LEN_MAX; ++idx)
+ udp_payload[idx] = idx % 256;
+
+ /* Open sockets. */
+ fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW);
+ if (fd_tx_raw == -1)
+ error(1, errno, "socket tx_raw");
+
+ fd_rx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fd_rx_udp == -1)
+ error(1, errno, "socket rx_udp");
+ if (bind(fd_rx_udp, addr, alen))
+ error(1, errno, "bind");
+ /* Fail fast. */
+ if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcv timeout");
+
+ for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX;
+ payload_len += (rand() % 4096)) {
+ if (cfg_verbose)
+ printf("payload_len: %d\n", payload_len);
+ max_frag_len = min_frag_len;
+ do {
+ send_udp_frags(fd_tx_raw, addr, alen, ipv6);
+ recv_validate_udp(fd_rx_udp);
+ max_frag_len += 8 * (rand() % 8);
+ } while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len);
+ }
+
+ /* Cleanup. */
+ if (close(fd_tx_raw))
+ error(1, errno, "close tx_raw");
+ if (close(fd_rx_udp))
+ error(1, errno, "close rx_udp");
+
+ if (cfg_verbose)
+ printf("processed %d messages, %d fragments\n",
+ msg_counter, frag_counter);
+
+ fprintf(stderr, "PASS\n");
+}
+
+
+static void run_test_v4(void)
+{
+ struct sockaddr_in addr = {0};
+
+ addr.sin_family = AF_INET;
+ addr.sin_port = htons(cfg_port);
+ addr.sin_addr = addr4;
+
+ run_test((void *)&addr, sizeof(addr), false /* !ipv6 */);
+}
+
+static void run_test_v6(void)
+{
+ struct sockaddr_in6 addr = {0};
+
+ addr.sin6_family = AF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = addr6;
+
+ run_test((void *)&addr, sizeof(addr), true /* ipv6 */);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "46ov")) != -1) {
+ switch (c) {
+ case '4':
+ cfg_do_ipv4 = true;
+ break;
+ case '6':
+ cfg_do_ipv6 = true;
+ break;
+ case 'o':
+ cfg_overlap = true;
+ break;
+ case 'v':
+ cfg_verbose = true;
+ break;
+ default:
+ error(1, 0, "%s: parse error", argv[0]);
+ }
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+ seed = time(NULL);
+ srand(seed);
+ /* Print the seed to track/reproduce potential failures. */
+ printf("seed = %d\n", seed);
+
+ if (cfg_do_ipv4)
+ run_test_v4();
+ if (cfg_do_ipv6)
+ run_test_v6();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
new file mode 100755
index 000000000000..3a4042d918f0
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -0,0 +1,39 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a couple of IP defragmentation tests.
+
+set +x
+set -e
+
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+setup() {
+ ip netns add "${NETNS}"
+ ip -netns "${NETNS}" link set lo up
+ ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+ ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+ ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null
+ ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null
+}
+
+cleanup() {
+ ip netns del "${NETNS}"
+}
+
+trap cleanup EXIT
+setup
+
+echo "ipv4 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -4
+
+
+echo "ipv4 defrag with overlaps"
+ip netns exec "${NETNS}" ./ip_defrag -4o
+
+echo "ipv6 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -6
+
+echo "ipv6 defrag with overlaps"
+ip netns exec "${NETNS}" ./ip_defrag -6o
+
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 8fdfeafaf8c0..fac68d710f35 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile)
buf = (char *)malloc(st.st_size);
EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
- EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+ EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send);
EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
- EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+ EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size);
}
TEST_F(tls, recv_max)
@@ -160,7 +160,7 @@ TEST_F(tls, msg_more)
EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
- EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+ EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL),
send_len * 2);
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
@@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single)
msg.msg_iov = &vec;
msg.msg_iovlen = 1;
EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
- EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
@@ -288,7 +288,7 @@ TEST_F(tls, splice_from_pipe)
ASSERT_GE(pipe(p), 0);
EXPECT_GE(write(p[1], mem_send, send_len), 0);
EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
- EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+ EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
}
@@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2)
EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
- EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+ EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
}
@@ -322,13 +322,13 @@ TEST_F(tls, send_and_splice)
ASSERT_GE(pipe(p), 0);
EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
- EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+ EXPECT_EQ(recv(self->cfd, buf, send_len2, MSG_WAITALL), send_len2);
EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
EXPECT_GE(write(p[1], mem_send, send_len), send_len);
EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
- EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+ EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
}
@@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv)
EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
memset(recv_mem, 0, total_len);
- EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+ EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len);
EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
@@ -516,17 +516,17 @@ TEST_F(tls, recv_peek_multiple_records)
len = strlen(test_str_second) + 1;
EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
- len = sizeof(buf);
+ len = strlen(test_str_first);
memset(buf, 0, len);
- EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+ EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
/* MSG_PEEK can only peek into the current record. */
- len = strlen(test_str_first) + 1;
+ len = strlen(test_str_first);
EXPECT_EQ(memcmp(test_str_first, buf, len), 0);
- len = sizeof(buf);
+ len = strlen(test_str) + 1;
memset(buf, 0, len);
- EXPECT_NE(recv(self->cfd, buf, len, 0), -1);
+ EXPECT_EQ(recv(self->cfd, buf, len, MSG_WAITALL), len);
/* Non-MSG_PEEK will advance strparser (and therefore record)
* however.
@@ -543,6 +543,28 @@ TEST_F(tls, recv_peek_multiple_records)
len = strlen(test_str_second) + 1;
EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+ len = strlen(test_str) + 1;
+ memset(buf, 0, len);
+ EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
+
+ len = strlen(test_str) + 1;
+ EXPECT_EQ(memcmp(test_str, buf, len), 0);
+}
+
+TEST_F(tls, recv_peek_large_buf_mult_recs)
+{
+ char const *test_str = "test_read_peek_mult_recs";
+ char const *test_str_first = "test_read_peek";
+ char const *test_str_second = "_mult_recs";
+ int len;
+ char buf[64];
+
+ len = strlen(test_str_first);
+ EXPECT_EQ(send(self->fd, test_str_first, len, 0), len);
+
+ len = strlen(test_str_second) + 1;
+ EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+
len = sizeof(buf);
memset(buf, 0, len);
EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
@@ -551,6 +573,7 @@ TEST_F(tls, recv_peek_multiple_records)
EXPECT_EQ(memcmp(test_str, buf, len), 0);
}
+
TEST_F(tls, pollin)
{
char const *test_str = "test_poll";
@@ -564,7 +587,7 @@ TEST_F(tls, pollin)
EXPECT_EQ(poll(&fd, 1, 20), 1);
EXPECT_EQ(fd.revents & POLLIN, 1);
- EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
/* Test timing out */
EXPECT_EQ(poll(&fd, 1, 20), 0);
}
@@ -582,7 +605,7 @@ TEST_F(tls, poll_wait)
/* Set timeout to inf. secs */
EXPECT_EQ(poll(&fd, 1, -1), 1);
EXPECT_EQ(fd.revents & POLLIN, 1);
- EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len);
}
TEST_F(tls, blocking)
@@ -728,7 +751,7 @@ TEST_F(tls, control_msg)
EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
vec.iov_base = buf;
- EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+ EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len);
cmsg = CMSG_FIRSTHDR(&msg);
EXPECT_NE(cmsg, NULL);
EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);