diff options
Diffstat (limited to 'tools/testing/selftests/net')
99 files changed, 7442 insertions, 253 deletions
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c709523c99c6..a275ed584026 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_PROGS := \ big_tcp.sh \ bind_bhash.sh \ bpf_offload.py \ + bridge_stp_mode.sh \ bridge_vlan_dump.sh \ broadcast_ether_dst.sh \ broadcast_pmtu.sh \ @@ -45,6 +46,7 @@ TEST_PROGS := \ io_uring_zerocopy_tx.sh \ ioam6.sh \ ip6_gre_headroom.sh \ + ip6_tunnel.sh \ ip_defrag.sh \ ip_local_port_range.sh \ ipv6_flowlabel.sh \ @@ -55,6 +57,7 @@ TEST_PROGS := \ l2tp.sh \ link_netns.py \ lwt_dst_cache_ref_loop.sh \ + macvlan_mcast_shared_mac.sh \ msg_zerocopy.sh \ nat6to4.sh \ ndisc_unsolicited_na_test.sh \ @@ -62,7 +65,9 @@ TEST_PROGS := \ netdevice.sh \ netns-name.sh \ netns-sysctl.sh \ + nk_qlease.py \ nl_netdev.py \ + nl_nlctrl.py \ pmtu.sh \ psock_snd.sh \ reuseaddr_ports_exhausted.sh \ @@ -121,6 +126,7 @@ TEST_PROGS := \ vrf_route_leaking.sh \ vrf_strict_mode_test.sh \ xfrm_policy.sh \ + xfrm_state.sh \ # end of TEST_PROGS TEST_PROGS_EXTENDED := \ diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c index 86e7b0fb522d..f6466a717f49 100644 --- a/tools/testing/selftests/net/af_unix/so_peek_off.c +++ b/tools/testing/selftests/net/af_unix/so_peek_off.c @@ -76,6 +76,19 @@ FIXTURE_TEARDOWN(so_peek_off) ASSERT_STREQ(str, buf); \ } while (0) +#define peekoffeq(fd, expected) \ + do { \ + socklen_t optlen = sizeof(int); \ + int off = -1; \ + int ret; \ + \ + ret = getsockopt(fd, SOL_SOCKET, SO_PEEK_OFF, \ + &off, &optlen); \ + ASSERT_EQ(0, ret); \ + ASSERT_EQ((socklen_t)sizeof(off), optlen); \ + ASSERT_EQ(expected, off); \ + } while (0) + #define async \ for (pid_t pid = (pid = fork(), \ pid < 0 ? \ @@ -91,7 +104,12 @@ TEST_F(so_peek_off, single_chunk) sendeq(self->fd[0], "aaaabbbb", 0); recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + peekoffeq(self->fd[1], 4); recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + peekoffeq(self->fd[1], 8); + + recveq(self->fd[1], "aaaabbbb", 8, 0); + peekoffeq(self->fd[1], 0); } TEST_F(so_peek_off, two_chunks) @@ -100,7 +118,13 @@ TEST_F(so_peek_off, two_chunks) sendeq(self->fd[0], "bbbb", 0); recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + peekoffeq(self->fd[1], 4); recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + peekoffeq(self->fd[1], 8); + + recveq(self->fd[1], "aaaa", 4, 0); + recveq(self->fd[1], "bbbb", 4, 0); + peekoffeq(self->fd[1], 0); } TEST_F(so_peek_off, two_chunks_blocking) @@ -111,6 +135,7 @@ TEST_F(so_peek_off, two_chunks_blocking) } recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + peekoffeq(self->fd[1], 4); async { usleep(1000); @@ -119,24 +144,38 @@ TEST_F(so_peek_off, two_chunks_blocking) /* goto again; -> goto redo; in unix_stream_read_generic(). */ recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + peekoffeq(self->fd[1], 8); + + recveq(self->fd[1], "aaaa", 4, 0); + recveq(self->fd[1], "bbbb", 4, 0); + peekoffeq(self->fd[1], 0); } TEST_F(so_peek_off, two_chunks_overlap) { sendeq(self->fd[0], "aaaa", 0); recveq(self->fd[1], "aa", 2, MSG_PEEK); + peekoffeq(self->fd[1], 2); sendeq(self->fd[0], "bbbb", 0); if (variant->type == SOCK_STREAM) { /* SOCK_STREAM tries to fill the buffer. */ recveq(self->fd[1], "aabb", 4, MSG_PEEK); + peekoffeq(self->fd[1], 6); recveq(self->fd[1], "bb", 100, MSG_PEEK); + peekoffeq(self->fd[1], 8); } else { /* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */ recveq(self->fd[1], "aa", 100, MSG_PEEK); + peekoffeq(self->fd[1], 4); recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + peekoffeq(self->fd[1], 8); } + + recveq(self->fd[1], "aaaa", 4, 0); + recveq(self->fd[1], "bbbb", 4, 0); + peekoffeq(self->fd[1], 0); } TEST_F(so_peek_off, two_chunks_overlap_blocking) @@ -147,6 +186,7 @@ TEST_F(so_peek_off, two_chunks_overlap_blocking) } recveq(self->fd[1], "aa", 2, MSG_PEEK); + peekoffeq(self->fd[1], 2); async { usleep(1000); @@ -155,8 +195,14 @@ TEST_F(so_peek_off, two_chunks_overlap_blocking) /* Even SOCK_STREAM does not wait if at least one byte is read. */ recveq(self->fd[1], "aa", 100, MSG_PEEK); + peekoffeq(self->fd[1], 4); recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + peekoffeq(self->fd[1], 8); + + recveq(self->fd[1], "aaaa", 4, 0); + recveq(self->fd[1], "bbbb", 4, 0); + peekoffeq(self->fd[1], 0); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/bridge_stp_mode.sh b/tools/testing/selftests/net/bridge_stp_mode.sh new file mode 100755 index 000000000000..0c81fd029d79 --- /dev/null +++ b/tools/testing/selftests/net/bridge_stp_mode.sh @@ -0,0 +1,288 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2034,SC2154,SC2317,SC2329 +# +# Test for bridge STP mode selection (IFLA_BR_STP_MODE). +# +# Verifies that: +# - stp_mode defaults to auto on new bridges +# - stp_mode can be toggled between user, kernel, and auto +# - stp_mode change is rejected while STP is active (-EBUSY) +# - stp_mode user in a netns yields userspace STP (stp_state=2) +# - stp_mode kernel forces kernel STP (stp_state=1) +# - stp_mode auto preserves traditional fallback to kernel STP +# - stp_mode and stp_state can be set atomically in one message +# - stp_mode persists across STP disable/enable cycles + +source lib.sh + +require_command jq + +ALL_TESTS=" + test_default_auto + test_set_modes + test_reject_change_while_stp_active + test_idempotent_mode_while_stp_active + test_user_mode_in_netns + test_kernel_mode + test_auto_mode + test_atomic_mode_and_state + test_mode_persistence +" + +bridge_info_get() +{ + ip -n "$NS1" -d -j link show "$1" | \ + jq -r ".[0].linkinfo.info_data.$2" +} + +check_stp_mode() +{ + local br=$1; shift + local expected=$1; shift + local msg=$1; shift + local val + + val=$(bridge_info_get "$br" stp_mode) + [ "$val" = "$expected" ] + check_err $? "$msg: expected $expected, got $val" +} + +check_stp_state() +{ + local br=$1; shift + local expected=$1; shift + local msg=$1; shift + local val + + val=$(bridge_info_get "$br" stp_state) + [ "$val" = "$expected" ] + check_err $? "$msg: expected $expected, got $val" +} + +# Create a bridge in NS1, bring it up, and defer its deletion. +bridge_create() +{ + ip -n "$NS1" link add "$1" type bridge + ip -n "$NS1" link set "$1" up + defer ip -n "$NS1" link del "$1" +} + +setup_prepare() +{ + setup_ns NS1 +} + +cleanup() +{ + defer_scopes_cleanup + cleanup_all_ns +} + +# Check that stp_mode defaults to auto when creating a bridge. +test_default_auto() +{ + RET=0 + + ip -n "$NS1" link add br-test type bridge + defer ip -n "$NS1" link del br-test + + check_stp_mode br-test auto "stp_mode default" + + log_test "stp_mode defaults to auto" +} + +# Test setting stp_mode to user, kernel, and back to auto. +test_set_modes() +{ + RET=0 + + ip -n "$NS1" link add br-test type bridge + defer ip -n "$NS1" link del br-test + + ip -n "$NS1" link set dev br-test type bridge stp_mode user + check_err $? "Failed to set stp_mode to user" + check_stp_mode br-test user "after set user" + + ip -n "$NS1" link set dev br-test type bridge stp_mode kernel + check_err $? "Failed to set stp_mode to kernel" + check_stp_mode br-test kernel "after set kernel" + + ip -n "$NS1" link set dev br-test type bridge stp_mode auto + check_err $? "Failed to set stp_mode to auto" + check_stp_mode br-test auto "after set auto" + + log_test "stp_mode set user/kernel/auto" +} + +# Verify that stp_mode cannot be changed while STP is active. +test_reject_change_while_stp_active() +{ + RET=0 + + bridge_create br-test + + ip -n "$NS1" link set dev br-test type bridge stp_mode kernel + check_err $? "Failed to set stp_mode to kernel" + + ip -n "$NS1" link set dev br-test type bridge stp_state 1 + check_err $? "Failed to enable STP" + + # Changing stp_mode while STP is active should fail. + ip -n "$NS1" link set dev br-test type bridge stp_mode auto 2>/dev/null + check_fail $? "Changing stp_mode should fail while STP is active" + + check_stp_mode br-test kernel "mode unchanged after rejected change" + + # Disable STP, then change should succeed. + ip -n "$NS1" link set dev br-test type bridge stp_state 0 + check_err $? "Failed to disable STP" + + ip -n "$NS1" link set dev br-test type bridge stp_mode auto + check_err $? "Changing stp_mode should succeed after STP is disabled" + + log_test "reject stp_mode change while STP is active" +} + +# Verify that re-setting the same stp_mode while STP is active succeeds. +test_idempotent_mode_while_stp_active() +{ + RET=0 + + bridge_create br-test + + ip -n "$NS1" link set dev br-test type bridge stp_mode user stp_state 1 + check_err $? "Failed to enable STP with user mode" + + # Re-setting the same mode while STP is active should succeed. + ip -n "$NS1" link set dev br-test type bridge stp_mode user + check_err $? "Idempotent stp_mode set should succeed while STP is active" + + check_stp_state br-test 2 "stp_state after idempotent set" + + # Changing mode while disabling STP in the same message should succeed. + ip -n "$NS1" link set dev br-test type bridge stp_mode auto stp_state 0 + check_err $? "Mode change with simultaneous STP disable should succeed" + + check_stp_mode br-test auto "mode changed after disable+change" + check_stp_state br-test 0 "stp_state after disable+change" + + log_test "idempotent and simultaneous mode change while STP active" +} + +# Test that stp_mode user in a non-init netns yields userspace STP +# (stp_state == 2). This is the key use case: userspace STP without +# needing /sbin/bridge-stp or being in init_net. +test_user_mode_in_netns() +{ + RET=0 + + bridge_create br-test + + ip -n "$NS1" link set dev br-test type bridge stp_mode user + check_err $? "Failed to set stp_mode to user" + + ip -n "$NS1" link set dev br-test type bridge stp_state 1 + check_err $? "Failed to enable STP" + + check_stp_state br-test 2 "stp_state with user mode" + + log_test "stp_mode user in netns yields userspace STP" +} + +# Test that stp_mode kernel forces kernel STP (stp_state == 1) +# regardless of whether /sbin/bridge-stp exists. +test_kernel_mode() +{ + RET=0 + + bridge_create br-test + + ip -n "$NS1" link set dev br-test type bridge stp_mode kernel + check_err $? "Failed to set stp_mode to kernel" + + ip -n "$NS1" link set dev br-test type bridge stp_state 1 + check_err $? "Failed to enable STP" + + check_stp_state br-test 1 "stp_state with kernel mode" + + log_test "stp_mode kernel forces kernel STP" +} + +# Test that stp_mode auto preserves traditional behavior: in a netns +# (non-init_net), bridge-stp is not called and STP falls back to +# kernel mode (stp_state == 1). +test_auto_mode() +{ + RET=0 + + bridge_create br-test + + # Auto mode is the default; enable STP in a netns. + ip -n "$NS1" link set dev br-test type bridge stp_state 1 + check_err $? "Failed to enable STP" + + # In a netns with auto mode, bridge-stp is skipped (init_net only), + # so STP should fall back to kernel mode (stp_state == 1). + check_stp_state br-test 1 "stp_state with auto mode in netns" + + log_test "stp_mode auto preserves traditional behavior" +} + +# Test that stp_mode and stp_state can be set in a single netlink +# message. This is the intended atomic usage pattern. +test_atomic_mode_and_state() +{ + RET=0 + + bridge_create br-test + + # Set both stp_mode and stp_state in one command. + ip -n "$NS1" link set dev br-test type bridge stp_mode user stp_state 1 + check_err $? "Failed to set stp_mode user and stp_state 1 atomically" + + check_stp_state br-test 2 "stp_state after atomic set" + + log_test "atomic stp_mode user + stp_state 1 in single message" +} + +# Test that stp_mode persists across STP disable/enable cycles. +test_mode_persistence() +{ + RET=0 + + bridge_create br-test + + # Set user mode and enable STP. + ip -n "$NS1" link set dev br-test type bridge stp_mode user + ip -n "$NS1" link set dev br-test type bridge stp_state 1 + check_err $? "Failed to enable STP with user mode" + + # Disable STP. + ip -n "$NS1" link set dev br-test type bridge stp_state 0 + check_err $? "Failed to disable STP" + + # Verify mode is still user. + check_stp_mode br-test user "stp_mode after STP disable" + + # Re-enable STP -- should use user mode again. + ip -n "$NS1" link set dev br-test type bridge stp_state 1 + check_err $? "Failed to re-enable STP" + + check_stp_state br-test 2 "stp_state after re-enable" + + log_test "stp_mode persists across STP disable/enable cycles" +} + +# Check iproute2 support before setting up resources. +if ! ip link add type bridge help 2>&1 | grep -q "stp_mode"; then + echo "SKIP: iproute2 too old, missing stp_mode support" + exit "$ksft_skip" +fi + +trap cleanup EXIT + +setup_prepare +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cd49b7dfe216..2a390cae41bf 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,6 +43,8 @@ CONFIG_IPV6_ILA=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_IPV6_MROUTE=y CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_RPL_LWTUNNEL=y CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SIT=y diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 829f72c8ee07..af64f93bb2e1 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -545,7 +545,7 @@ fib4_nexthop() fib6_nexthop() { local lldummy=$(get_linklocal dummy0) - local llv1=$(get_linklocal dummy0) + local llv1=$(get_linklocal veth1) if [ -z "$lldummy" ]; then echo "Failed to get linklocal address for dummy0" @@ -1589,6 +1589,23 @@ fib6_ra_to_static() log_test $ret 0 "ipv6 promote RA route to static" + # Prepare for RA route with gateway + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_ra_rt_info_max_plen=64 + + # Add initial route to cause ECMP merging + $IP -6 route add 2001:12::/64 via fe80::dead:beef dev veth1 + + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -R 2001:12::/64#1#120 + + # Routes are not merged as RA routes are not elegible for ECMP + check_rt_num 2 "$($IP -6 route list | grep -c "2001:12::/64 via")" + + $IP -6 route append 2001:12::/64 via fe80::dead:feeb dev veth1 + + check_rt_num 2 "$($IP -6 route list | grep -c "nexthop via")" + + log_test "$ret" 0 "ipv6 RA route with nexthop do not merge into ECMP with static" + set +e cleanup &> /dev/null diff --git a/tools/testing/selftests/net/forwarding/.gitignore b/tools/testing/selftests/net/forwarding/.gitignore index 2dea317f12e7..418ff96c52ef 100644 --- a/tools/testing/selftests/net/forwarding/.gitignore +++ b/tools/testing/selftests/net/forwarding/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only forwarding.config +ipmr diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index ff4a00d91a26..bbaf4d937dd8 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -133,6 +133,10 @@ TEST_FILES := \ tc_common.sh \ # end of TEST_FILES +TEST_GEN_PROGS := \ + ipmr +# end of TEST_GEN_PROGS + TEST_INCLUDES := \ $(wildcard ../lib/sh/*.sh) \ ../lib.sh \ diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index 57531c1d884d..ce4ae74843d9 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -65,7 +65,7 @@ source lib.sh h1_create() { - simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + simple_if_init $h1 192.0.2.1/28 ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2 } diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh index 7d5b2b9cc133..c667b81da37f 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh @@ -80,7 +80,7 @@ h1_destroy() { ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2 - simple_if_fini $h1 192.0.2.1/28 + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 } sw1_create() diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh index 370f9925302d..d04bad58a96a 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh @@ -80,7 +80,7 @@ h1_destroy() { ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2 - simple_if_fini $h1 192.0.2.1/28 + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 } sw1_create() diff --git a/tools/testing/selftests/net/forwarding/ipip_lib.sh b/tools/testing/selftests/net/forwarding/ipip_lib.sh index 01e62c4ac94d..b255646b737a 100644 --- a/tools/testing/selftests/net/forwarding/ipip_lib.sh +++ b/tools/testing/selftests/net/forwarding/ipip_lib.sh @@ -144,7 +144,7 @@ h1_create() { - simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + simple_if_init $h1 192.0.2.1/28 ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2 } diff --git a/tools/testing/selftests/net/forwarding/ipmr.c b/tools/testing/selftests/net/forwarding/ipmr.c new file mode 100644 index 000000000000..df870aad9ead --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ipmr.c @@ -0,0 +1,455 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2026 Google LLC */ + +#include <linux/if.h> +#include <linux/mroute.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <linux/socket.h> +#include <sched.h> +#include <sys/ioctl.h> +#include <sys/socket.h> + +#include "kselftest_harness.h" + +FIXTURE(ipmr) +{ + int netlink_sk; + int raw_sk; + int veth_ifindex; +}; + +FIXTURE_VARIANT(ipmr) +{ + int family; + int protocol; + int level; + int opts[MRT_MAX - MRT_BASE + 1]; +}; + +FIXTURE_VARIANT_ADD(ipmr, ipv4) +{ + .family = AF_INET, + .protocol = IPPROTO_IGMP, + .level = IPPROTO_IP, + .opts = { + MRT_INIT, + MRT_DONE, + MRT_ADD_VIF, + MRT_DEL_VIF, + MRT_ADD_MFC, + MRT_DEL_MFC, + MRT_VERSION, + MRT_ASSERT, + MRT_PIM, + MRT_TABLE, + MRT_ADD_MFC_PROXY, + MRT_DEL_MFC_PROXY, + MRT_FLUSH, + }, +}; + +struct mfc_attr { + int table; + __u32 origin; + __u32 group; + int ifindex; + bool proxy; +}; + +static struct rtattr *nl_add_rtattr(struct nlmsghdr *nlmsg, struct rtattr *rta, + int type, const void *data, int len) +{ + int unused = 0; + + rta->rta_type = type; + rta->rta_len = RTA_LENGTH(len); + memcpy(RTA_DATA(rta), data, len); + + nlmsg->nlmsg_len += NLMSG_ALIGN(rta->rta_len); + + return RTA_NEXT(rta, unused); +} + +static int nl_sendmsg_mfc(struct __test_metadata *_metadata, FIXTURE_DATA(ipmr) *self, + __u16 nlmsg_type, struct mfc_attr *mfc_attr) +{ + struct { + struct nlmsghdr nlmsg; + struct rtmsg rtm; + char buf[4096]; + } req = { + .nlmsg = { + .nlmsg_len = NLMSG_LENGTH(sizeof(req.rtm)), + /* ipmr does not care about NLM_F_CREATE and NLM_F_EXCL ... */ + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK, + .nlmsg_type = nlmsg_type, + }, + .rtm = { + /* hard requirements in rtm_to_ipmr_mfcc() */ + .rtm_family = RTNL_FAMILY_IPMR, + .rtm_dst_len = 32, + .rtm_type = RTN_MULTICAST, + .rtm_scope = RT_SCOPE_UNIVERSE, + .rtm_protocol = RTPROT_MROUTED, + }, + }; + struct nlmsghdr *nlmsg = &req.nlmsg; + struct nlmsgerr *errmsg; + struct rtattr *rta; + int err; + + rta = (struct rtattr *)&req.buf; + rta = nl_add_rtattr(nlmsg, rta, RTA_TABLE, &mfc_attr->table, sizeof(mfc_attr->table)); + rta = nl_add_rtattr(nlmsg, rta, RTA_SRC, &mfc_attr->origin, sizeof(mfc_attr->origin)); + rta = nl_add_rtattr(nlmsg, rta, RTA_DST, &mfc_attr->group, sizeof(mfc_attr->group)); + if (mfc_attr->ifindex) + rta = nl_add_rtattr(nlmsg, rta, RTA_IIF, &mfc_attr->ifindex, sizeof(mfc_attr->ifindex)); + if (mfc_attr->proxy) + rta = nl_add_rtattr(nlmsg, rta, RTA_PREFSRC, NULL, 0); + + err = send(self->netlink_sk, &req, req.nlmsg.nlmsg_len, 0); + ASSERT_EQ(err, req.nlmsg.nlmsg_len); + + memset(&req, 0, sizeof(req)); + + err = recv(self->netlink_sk, &req, sizeof(req), 0); + ASSERT_TRUE(NLMSG_OK(nlmsg, err)); + ASSERT_EQ(NLMSG_ERROR, nlmsg->nlmsg_type); + + errmsg = (struct nlmsgerr *)NLMSG_DATA(nlmsg); + return errmsg->error; +} + +FIXTURE_SETUP(ipmr) +{ + struct ifreq ifr = { + .ifr_name = "veth0", + }; + int err; + + err = unshare(CLONE_NEWNET); + ASSERT_EQ(0, err); + + self->netlink_sk = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + ASSERT_LE(0, self->netlink_sk); + + self->raw_sk = socket(variant->family, SOCK_RAW, variant->protocol); + ASSERT_LT(0, self->raw_sk); + + err = system("ip link add veth0 type veth peer veth1"); + ASSERT_EQ(0, err); + + err = ioctl(self->raw_sk, SIOCGIFINDEX, &ifr); + ASSERT_EQ(0, err); + + self->veth_ifindex = ifr.ifr_ifindex; +} + +FIXTURE_TEARDOWN(ipmr) +{ + close(self->raw_sk); + close(self->netlink_sk); +} + +TEST_F(ipmr, mrt_init) +{ + int err, val = 0; /* any value is ok, but size must be int for MRT_INIT. */ + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_INIT - MRT_BASE], + &val, sizeof(val)); + ASSERT_EQ(0, err); + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_DONE - MRT_BASE], + &val, sizeof(val)); + ASSERT_EQ(0, err); +} + +TEST_F(ipmr, mrt_add_vif_register) +{ + struct vifctl vif = { + .vifc_vifi = 0, + .vifc_flags = VIFF_REGISTER, + }; + int err; + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); + + err = system("cat /proc/net/ip_mr_vif | grep -q pimreg"); + ASSERT_EQ(0, err); + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_DEL_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); +} + +TEST_F(ipmr, mrt_del_vif_unreg) +{ + struct vifctl vif = { + .vifc_vifi = 0, + .vifc_flags = VIFF_USE_IFINDEX, + .vifc_lcl_ifindex = self->veth_ifindex, + }; + int err; + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); + + err = system("cat /proc/net/ip_mr_vif | grep -q veth0"); + ASSERT_EQ(0, err); + + /* VIF is removed along with its device. */ + err = system("ip link del veth0"); + ASSERT_EQ(0, err); + + /* mrt->vif_table[veth_ifindex]->dev is NULL. */ + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_DEL_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(-1, err); + ASSERT_EQ(EADDRNOTAVAIL, errno); +} + +TEST_F(ipmr, mrt_del_vif_netns_dismantle) +{ + struct vifctl vif = { + .vifc_vifi = 0, + .vifc_flags = VIFF_USE_IFINDEX, + .vifc_lcl_ifindex = self->veth_ifindex, + }; + int err; + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); + + /* Let cleanup_net() remove veth0 and VIF. */ +} + +TEST_F(ipmr, mrt_add_mfc) +{ + struct mfcctl mfc = {}; + int err; + + /* MRT_ADD_MFC / MRT_ADD_MFC_PROXY does not need vif to exist (unlike netlink). */ + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_MFC - MRT_BASE], + &mfc, sizeof(mfc)); + ASSERT_EQ(0, err); + + /* (0.0.0.0 -> 0.0.0.0) */ + err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' "); + ASSERT_EQ(0, err); + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_DEL_MFC - MRT_BASE], + &mfc, sizeof(mfc)); +} + +TEST_F(ipmr, mrt_add_mfc_proxy) +{ + struct mfcctl mfc = {}; + int err; + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_MFC_PROXY - MRT_BASE], + &mfc, sizeof(mfc)); + ASSERT_EQ(0, err); + + err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' "); + ASSERT_EQ(0, err); + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_DEL_MFC_PROXY - MRT_BASE], + &mfc, sizeof(mfc)); +} + +TEST_F(ipmr, mrt_add_mfc_netlink) +{ + struct vifctl vif = { + .vifc_vifi = 0, + .vifc_flags = VIFF_USE_IFINDEX, + .vifc_lcl_ifindex = self->veth_ifindex, + }; + struct mfc_attr mfc_attr = { + .table = RT_TABLE_DEFAULT, + .origin = 0, + .group = 0, + .ifindex = self->veth_ifindex, + .proxy = false, + }; + int err; + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); + + err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr); + ASSERT_EQ(0, err); + + err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' "); + ASSERT_EQ(0, err); + + err = nl_sendmsg_mfc(_metadata, self, RTM_DELROUTE, &mfc_attr); + ASSERT_EQ(0, err); +} + +TEST_F(ipmr, mrt_add_mfc_netlink_proxy) +{ + struct vifctl vif = { + .vifc_vifi = 0, + .vifc_flags = VIFF_USE_IFINDEX, + .vifc_lcl_ifindex = self->veth_ifindex, + }; + struct mfc_attr mfc_attr = { + .table = RT_TABLE_DEFAULT, + .origin = 0, + .group = 0, + .ifindex = self->veth_ifindex, + .proxy = true, + }; + int err; + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); + + err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr); + ASSERT_EQ(0, err); + + err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' "); + ASSERT_EQ(0, err); + + err = nl_sendmsg_mfc(_metadata, self, RTM_DELROUTE, &mfc_attr); + ASSERT_EQ(0, err); +} + +TEST_F(ipmr, mrt_add_mfc_netlink_no_vif) +{ + struct mfc_attr mfc_attr = { + .table = RT_TABLE_DEFAULT, + .origin = 0, + .group = 0, + .proxy = false, + }; + int err; + + /* netlink always requires RTA_IIF of an existing vif. */ + mfc_attr.ifindex = 0; + err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr); + ASSERT_EQ(-ENFILE, err); + + /* netlink always requires RTA_IIF of an existing vif. */ + mfc_attr.ifindex = self->veth_ifindex; + err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr); + ASSERT_EQ(-ENFILE, err); +} + +TEST_F(ipmr, mrt_del_mfc_netlink_netns_dismantle) +{ + struct vifctl vifs[2] = { + { + .vifc_vifi = 0, + .vifc_flags = VIFF_USE_IFINDEX, + .vifc_lcl_ifindex = self->veth_ifindex, + }, + { + .vifc_vifi = 1, + .vifc_flags = VIFF_REGISTER, + } + }; + struct mfc_attr mfc_attr = { + .table = RT_TABLE_DEFAULT, + .origin = 0, + .group = 0, + .ifindex = self->veth_ifindex, + .proxy = false, + }; + int i, err; + + for (i = 0; i < 2; i++) { + /* Create 2 VIFs just to avoid -ENFILE later. */ + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vifs[i], sizeof(vifs[i])); + ASSERT_EQ(0, err); + } + + /* Create a MFC for mrt->vif_table[0]. */ + err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr); + ASSERT_EQ(0, err); + + err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' "); + ASSERT_EQ(0, err); + + /* Remove mrt->vif_table[0]. */ + err = system("ip link del veth0"); + ASSERT_EQ(0, err); + + /* MFC entry is NOT removed even if the tied VIF is removed... */ + err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' "); + ASSERT_EQ(0, err); + + /* ... and netlink is not capable of removing such an entry + * because netlink always requires a valid RTA_IIF ... :/ + */ + err = nl_sendmsg_mfc(_metadata, self, RTM_DELROUTE, &mfc_attr); + ASSERT_EQ(-ENODEV, err); + + /* It can be removed by setsockopt(), but let cleanup_net() remove this time. */ +} + +TEST_F(ipmr, mrt_table_flush) +{ + struct vifctl vif = { + .vifc_vifi = 0, + .vifc_flags = VIFF_USE_IFINDEX, + .vifc_lcl_ifindex = self->veth_ifindex, + }; + struct mfc_attr mfc_attr = { + .origin = 0, + .group = 0, + .ifindex = self->veth_ifindex, + .proxy = false, + }; + int table_id = 92; + int err, flags; + + /* Set a random table id rather than RT_TABLE_DEFAULT. + * Note that /proc/net/ip_mr_{vif,cache} only supports RT_TABLE_DEFAULT. + */ + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_TABLE - MRT_BASE], + &table_id, sizeof(table_id)); + ASSERT_EQ(0, err); + + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE], + &vif, sizeof(vif)); + ASSERT_EQ(0, err); + + mfc_attr.table = table_id; + err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr); + ASSERT_EQ(0, err); + + /* Flush mrt->vif_table[] and all caches. */ + flags = MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | + MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC; + err = setsockopt(self->raw_sk, + variant->level, variant->opts[MRT_FLUSH - MRT_BASE], + &flags, sizeof(flags)); + ASSERT_EQ(0, err); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index a9034f0bb58b..ac8358bcb22c 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1,5 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +#shellcheck disable=SC2034 # SC doesn't see our uses of global variables ############################################################################## # Topology description. p1 looped back to p2, p3 to p4 and so on. @@ -340,17 +341,145 @@ fi ############################################################################## # Command line options handling -count=0 +check_env() { + if [[ ! (( -n "$LOCAL_V4" && -n "$REMOTE_V4") || + ( -n "$LOCAL_V6" && -n "$REMOTE_V6" )) ]]; then + echo "SKIP: Invalid environment, missing or inconsistent LOCAL_V4/REMOTE_V4/LOCAL_V6/REMOTE_V6" + echo "Please see tools/testing/selftests/drivers/net/README.rst" + exit "$ksft_skip" + fi + + if [[ -z "$REMOTE_TYPE" ]]; then + echo "SKIP: Invalid environment, missing REMOTE_TYPE" + exit "$ksft_skip" + fi + + if [[ -z "$REMOTE_ARGS" ]]; then + echo "SKIP: Invalid environment, missing REMOTE_ARGS" + exit "$ksft_skip" + fi +} + +__run_on() +{ + local target=$1; shift + local type args + + IFS=':' read -r type args <<< "$target" + + case "$type" in + netns) + # Execute command in network namespace + # args contains the namespace name + ip netns exec "$args" "$@" + ;; + ssh) + # Execute command via SSH args contains user@host + ssh -n "$args" "$@" + ;; + local|*) + # Execute command locally. This is also the fallback + # case for when the interface's target is not found in + # the TARGETS array. + "$@" + ;; + esac +} + +run_on() +{ + local iface=$1; shift + local target="local:" + + if [ "${DRIVER_TEST_CONFORMANT}" = "yes" ]; then + target="${TARGETS[$iface]}" + fi + + __run_on "$target" "$@" +} + +get_ifname_by_ip() +{ + local target=$1; shift + local ip_addr=$1; shift + + __run_on "$target" ip -j addr show to "$ip_addr" | jq -r '.[].ifname' +} + +# Whether the test is conforming to the requirements and usage described in +# drivers/net/README.rst. +: "${DRIVER_TEST_CONFORMANT:=no}" + +declare -A TARGETS + +# Based on DRIVER_TEST_CONFORMANT, decide if to source drivers/net/net.config +# or not. In the "yes" case, the test expects to pass the arguments through the +# variables specified in drivers/net/README.rst file. If not, fallback on +# parsing the script arguments for interface names. +if [ "${DRIVER_TEST_CONFORMANT}" = "yes" ]; then + if [[ -f $net_forwarding_dir/../../drivers/net/net.config ]]; then + source "$net_forwarding_dir/../../drivers/net/net.config" + fi + + if (( NUM_NETIFS > 2)); then + echo "SKIP: DRIVER_TEST_CONFORMANT=yes and NUM_NETIFS is bigger than 2" + exit "$ksft_skip" + fi -while [[ $# -gt 0 ]]; do - if [[ "$count" -eq "0" ]]; then + check_env + + # Populate the NETIFS and TARGETS arrays automatically based on the + # environment variables. The TARGETS array is indexed by the network + # interface name keeping track of the target on which the interface + # resides. Values will be strings of the following format - + # <type>:<args>. + # + # TARGETS[eth0]="local:" - meaning that the eth0 interface is + # accessible locally + # TARGETS[eth1]="netns:foo" - eth1 is in the foo netns + # TARGETS[eth2]="ssh:root@10.0.0.2" - eth2 is accessible through + # running the 'ssh root@10.0.0.2' command. + + unset NETIFS + declare -A NETIFS + + NETIFS[p1]="$NETIF" + TARGETS[$NETIF]="local:" + + # Locate the name of the remote interface + remote_target="$REMOTE_TYPE:$REMOTE_ARGS" + if [[ -v REMOTE_V4 ]]; then + remote_netif=$(get_ifname_by_ip "$remote_target" "$REMOTE_V4") + else + remote_netif=$(get_ifname_by_ip "$remote_target" "$REMOTE_V6") + fi + if [[ ! -n "$remote_netif" ]]; then + echo "SKIP: cannot find remote interface" + exit "$ksft_skip" + fi + + if [[ "$NETIF" == "$remote_netif" ]]; then + echo "SKIP: local and remote interfaces cannot have the same name" + exit "$ksft_skip" + fi + + NETIFS[p2]="$remote_netif" + TARGETS[$remote_netif]="$REMOTE_TYPE:$REMOTE_ARGS" +else + count=0 + # Prime NETIFS from the command line, but retain if none given. + if [[ $# -gt 0 ]]; then unset NETIFS declare -A NETIFS + + while [[ $# -gt 0 ]]; do + count=$((count + 1)) + NETIFS[p$count]="$1" + TARGETS[$1]="local:" + shift + done fi - count=$((count + 1)) - NETIFS[p$count]="$1" - shift -done +fi ############################################################################## # Network interfaces configuration @@ -418,10 +547,11 @@ mac_addr_prepare() dev=${NETIFS[p$i]} new_addr=$(printf "00:01:02:03:04:%02x" $i) - MAC_ADDR_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].address') + MAC_ADDR_ORIG["$dev"]=$(run_on "$dev" \ + ip -j link show dev "$dev" | jq -e '.[].address') # Strip quotes MAC_ADDR_ORIG["$dev"]=${MAC_ADDR_ORIG["$dev"]//\"/} - ip link set dev $dev address $new_addr + run_on "$dev" ip link set dev "$dev" address $new_addr done } @@ -431,7 +561,8 @@ mac_addr_restore() for ((i = 1; i <= NUM_NETIFS; ++i)); do dev=${NETIFS[p$i]} - ip link set dev $dev address ${MAC_ADDR_ORIG["$dev"]} + run_on "$dev" \ + ip link set dev "$dev" address ${MAC_ADDR_ORIG["$dev"]} done } @@ -444,7 +575,9 @@ if [[ "$STABLE_MAC_ADDRS" = "yes" ]]; then fi for ((i = 1; i <= NUM_NETIFS; ++i)); do - ip link show dev ${NETIFS[p$i]} &> /dev/null + int="${NETIFS[p$i]}" + + run_on "$int" ip link show dev "$int" &> /dev/null if [[ $? -ne 0 ]]; then echo "SKIP: could not find all required interfaces" exit $ksft_skip @@ -527,7 +660,7 @@ setup_wait_dev_with_timeout() local i for ((i = 1; i <= $max_iterations; ++i)); do - ip link show dev $dev up \ + run_on "$dev" ip link show dev "$dev" up \ | grep 'state UP' &> /dev/null if [[ $? -ne 0 ]]; then sleep 1 @@ -831,8 +964,15 @@ ethtool_std_stats_get() local name=$1; shift local src=$1; shift - ethtool --json -S $dev --groups $grp -- --src $src | \ - jq '.[]."'"$grp"'"."'$name'"' + if [[ "$grp" == "pause" ]]; then + run_on "$dev" ethtool -I --json -a "$dev" --src "$src" | \ + jq --arg name "$name" '.[].statistics[$name]' + return + fi + + run_on "$dev" \ + ethtool --json -S "$dev" --groups "$grp" -- --src "$src" | \ + jq --arg grp "$grp" --arg name "$name" '.[][$grp][$name]' } qdisc_stats_get() @@ -1610,12 +1750,17 @@ tcpdump_start() sleep 1 } -tcpdump_stop() +tcpdump_stop_nosleep() { local if_name=$1 local pid=${cappid[$if_name]} $ns_cmd kill "$pid" && wait "$pid" +} + +tcpdump_stop() +{ + tcpdump_stop_nosleep "$1" sleep 1 } @@ -1630,7 +1775,7 @@ tcpdump_show() { local if_name=$1 - tcpdump -e -n -r ${capfile[$if_name]} 2>&1 + tcpdump -e -nn -r ${capfile[$if_name]} 2>&1 } # return 0 if the packet wasn't seen on host2_if or 1 if it was diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 1f2bf6e81847..15b1a1255a41 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -57,21 +57,21 @@ PTP_1588_L2_PDELAY_REQ=" \ PTP_1588_IPV4_SYNC=" \ 01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ 00 48 0a 9a 40 00 01 11 cb 88 c0 00 02 01 e0 00 \ -01 81 01 3f 01 3f 00 34 a3 c8 00 02 00 2c 00 00 \ +01 81 01 3f 01 3f 00 34 9f 41 00 02 00 2c 00 00 \ 02 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ 63 ff fe cf 17 0e 00 01 00 00 00 00 00 00 00 00 \ 00 00 00 00 00 00" PTP_1588_IPV4_FOLLOW_UP=" 01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ 00 48 0a 9b 40 00 01 11 cb 87 c0 00 02 01 e0 00 \ -01 81 01 40 01 40 00 34 a3 c8 08 02 00 2c 00 00 \ +01 81 01 40 01 40 00 34 eb 8a 08 02 00 2c 00 00 \ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ 63 ff fe cf 17 0e 00 01 00 00 02 00 00 00 66 83 \ c6 0f 1d 9a 61 87" PTP_1588_IPV4_PDELAY_REQ=" \ 01:00:5e:00:00:6b 00:00:de:ad:be:ef 08:00 45 00 \ 00 52 35 a9 40 00 01 11 a1 85 c0 00 02 01 e0 00 \ -00 6b 01 3f 01 3f 00 3e a2 bc 02 02 00 36 00 00 \ +00 6b 01 3f 01 3f 00 3e 9a b9 02 02 00 36 00 00 \ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ 63 ff fe cf 17 0e 00 01 00 01 05 7f 00 00 00 00 \ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00" @@ -79,7 +79,7 @@ PTP_1588_IPV6_SYNC=" \ 33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 06 \ 7c 2f 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ 00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ -00 00 00 00 01 81 01 3f 01 3f 00 36 2e 92 00 02 \ +00 00 00 00 01 81 01 3f 01 3f 00 36 14 76 00 02 \ 00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ 00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ 00 00 00 00 00 00 00 00 00 00 00 00" @@ -87,7 +87,7 @@ PTP_1588_IPV6_FOLLOW_UP=" \ 33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 0a \ 00 bc 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ 00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ -00 00 00 00 01 81 01 40 01 40 00 36 2e 92 08 02 \ +00 00 00 00 01 81 01 40 01 40 00 36 f0 47 08 02 \ 00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ 00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ 00 00 66 83 c6 2a 32 09 bd 74 00 00" @@ -95,11 +95,20 @@ PTP_1588_IPV6_PDELAY_REQ=" \ 33:33:00:00:00:6b 00:00:de:ad:be:ef 86:dd 60 0c \ 5c fd 00 40 11 01 fe 80 00 00 00 00 00 00 3c 37 \ 63 ff fe cf 17 0e ff 02 00 00 00 00 00 00 00 00 \ -00 00 00 00 00 6b 01 3f 01 3f 00 40 b4 54 02 02 \ +00 00 00 00 00 6b 01 3f 01 3f 00 40 89 1f 02 02 \ 00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ 00 00 3e 37 63 ff fe cf 17 0e 00 01 00 01 05 7f \ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ 00 00 00 00 00 00" +LINK_LOCAL_STP_BPDU=" \ +01:80:c2:00:00:00 00:00:de:ad:be:ef 00 26 42 42 03 \ +00 00 00 00 00 80 00 aa bb cc dd ee ff 00 00 00 00 \ +80 00 aa bb cc dd ee ff 80 01 00 00 14 00 02 00 \ +0f 00" +LINK_LOCAL_LLDP=" \ +01:80:c2:00:00:0e 00:00:de:ad:be:ef 88:cc 02 07 04 \ +00 11 22 33 44 55 04 05 05 65 74 68 30 06 02 00 \ +78 00 00" # Disable promisc to ensure we don't receive unknown MAC DA packets export TCPDUMP_EXTRA_FLAGS="-pl" @@ -213,7 +222,15 @@ run_test() mc_route_destroy $rcv_if_name mc_route_destroy $send_if_name + ip maddress add 01:80:c2:00:00:00 dev $rcv_if_name + send_raw $send_if_name "$LINK_LOCAL_STP_BPDU" + ip maddress del 01:80:c2:00:00:00 dev $rcv_if_name + if [ $skip_ptp = false ]; then + ip maddress add 01:80:c2:00:00:0e dev $rcv_if_name + send_raw $send_if_name "$LINK_LOCAL_LLDP" + ip maddress del 01:80:c2:00:00:0e dev $rcv_if_name + ip maddress add 01:1b:19:00:00:00 dev $rcv_if_name send_raw $send_if_name "$PTP_1588_L2_SYNC" send_raw $send_if_name "$PTP_1588_L2_FOLLOW_UP" @@ -304,7 +321,15 @@ run_test() "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ true "$test_name" + check_rcv $rcv_if_name "Link-local STP BPDU" \ + "> 01:80:c2:00:00:00" \ + true "$test_name" + if [ $skip_ptp = false ]; then + check_rcv $rcv_if_name "Link-local LLDP" \ + "> 01:80:c2:00:00:0e" \ + true "$test_name" + check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \ "ethertype PTP (0x88f7).* PTPv2.* msg type *: sync msg" \ true "$test_name" diff --git a/tools/testing/selftests/net/fq_band_pktlimit.sh b/tools/testing/selftests/net/fq_band_pktlimit.sh index 977070ed42b3..223f9efe4090 100755 --- a/tools/testing/selftests/net/fq_band_pktlimit.sh +++ b/tools/testing/selftests/net/fq_band_pktlimit.sh @@ -32,19 +32,19 @@ tc qdisc replace dev dummy0 root handle 1: fq quantum 1514 initial_quantum 1514 DELAY=400000 ./cmsg_sender -6 -p u -d "${DELAY}" -n 20 fdaa::2 8000 -OUT1="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" +OUT1="$(tc -s qdisc show dev dummy0 | grep '^ Sent')" ./cmsg_sender -6 -p u -d "${DELAY}" -n 20 fdaa::2 8000 -OUT2="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" +OUT2="$(tc -s qdisc show dev dummy0 | grep '^ Sent')" ./cmsg_sender -6 -p u -d "${DELAY}" -n 20 -P 7 fdaa::2 8000 -OUT3="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" +OUT3="$(tc -s qdisc show dev dummy0 | grep '^ Sent')" # Initial stats will report zero sent, as all packets are still # queued in FQ. Sleep for at least the delay period and see that # twenty are now sent. sleep 0.6 -OUT4="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" +OUT4="$(tc -s qdisc show dev dummy0 | grep '^ Sent')" # Log the output after the test echo "${OUT1}" @@ -53,7 +53,7 @@ echo "${OUT3}" echo "${OUT4}" # Test the output for expected values -echo "${OUT1}" | grep -q '0\ pkt\ (dropped\ 10' || die "unexpected drop count at 1" -echo "${OUT2}" | grep -q '0\ pkt\ (dropped\ 30' || die "unexpected drop count at 2" -echo "${OUT3}" | grep -q '0\ pkt\ (dropped\ 40' || die "unexpected drop count at 3" -echo "${OUT4}" | grep -q '20\ pkt\ (dropped\ 40' || die "unexpected accept count at 4" +echo "${OUT1}" | grep -q '0 pkt (dropped 10' || die "unexpected drop count at 1" +echo "${OUT2}" | grep -q '0 pkt (dropped 30' || die "unexpected drop count at 2" +echo "${OUT3}" | grep -q '0 pkt (dropped 40' || die "unexpected drop count at 3" +echo "${OUT4}" | grep -q '20 pkt (dropped 40' || die "unexpected accept count at 4" diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh index 123439545013..8c3647de9b4c 100755 --- a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh @@ -77,9 +77,13 @@ esac # Start of state changes: install cleanup handler +old_io_uring_disabled=0 cleanup() { ip netns del "${NS2}" ip netns del "${NS1}" + if [ "$old_io_uring_disabled" -ne 0 ]; then + sysctl -w -q kernel.io_uring_disabled="$old_io_uring_disabled" 2>/dev/null || true + fi } trap cleanup EXIT @@ -122,5 +126,10 @@ do_test() { wait } +old_io_uring_disabled=$(sysctl -n kernel.io_uring_disabled 2>/dev/null || echo "0") +if [ "$old_io_uring_disabled" -ne 0 ]; then + sysctl -w -q kernel.io_uring_disabled=0 +fi + do_test "${EXTRA_ARGS}" echo ok diff --git a/tools/testing/selftests/net/ip6_tunnel.sh b/tools/testing/selftests/net/ip6_tunnel.sh new file mode 100755 index 000000000000..fe081a521819 --- /dev/null +++ b/tools/testing/selftests/net/ip6_tunnel.sh @@ -0,0 +1,44 @@ +#!/bin/bash +# Test that IPv4-over-IPv6 tunneling works. + +source lib.sh +set -e + +setup_prepare() { + ip link add transport1 type veth peer name transport2 + + setup_ns ns1 + ip link set transport1 netns $ns1 + ip -n $ns1 address add 2001:db8::1/64 dev transport1 nodad + ip -n $ns1 address add 2001:db8::3/64 dev transport1 nodad + ip -n $ns1 link set transport1 up + ip -n $ns1 link add link transport1 name tunnel4 type ip6tnl mode ipip6 local 2001:db8::1 remote 2001:db8::2 + ip -n $ns1 address add 172.0.0.1/32 peer 172.0.0.2/32 dev tunnel4 + ip -n $ns1 link set tunnel4 up + ip -n $ns1 link add link transport1 name tunnel6 type ip6tnl mode ip6ip6 local 2001:db8::3 remote 2001:db8::4 + ip -n $ns1 address add 2001:db8:6::1/64 dev tunnel6 + ip -n $ns1 link set tunnel6 up + + setup_ns ns2 + ip link set transport2 netns $ns2 + ip -n $ns2 address add 2001:db8::2/64 dev transport2 nodad + ip -n $ns2 address add 2001:db8::4/64 dev transport2 nodad + ip -n $ns2 link set transport2 up + ip -n $ns2 link add link transport2 name tunnel4 type ip6tnl mode ipip6 local 2001:db8::2 remote 2001:db8::1 + ip -n $ns2 address add 172.0.0.2/32 peer 172.0.0.1/32 dev tunnel4 + ip -n $ns2 link set tunnel4 up + ip -n $ns2 link add link transport2 name tunnel6 type ip6tnl mode ip6ip6 local 2001:db8::4 remote 2001:db8::3 + ip -n $ns2 address add 2001:db8:6::2/64 dev tunnel6 + ip -n $ns2 link set tunnel6 up +} + +cleanup() { + cleanup_all_ns + # in case the namespaces haven't been set up yet + ip link delete transport1 &>/dev/null || true +} + +trap cleanup EXIT +setup_prepare +ip netns exec $ns1 ping -q -W1 -c1 172.0.0.2 >/dev/null +ip netns exec $ns1 ping -q -W1 -c1 2001:db8:6::2 >/dev/null diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index f4afef51b930..89c32c354c00 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -62,8 +62,6 @@ #define VETH_FMT "ktst-%d" #define VETH_LEN 12 -#define XFRM_ALGO_NR_KEYS 29 - static int nsfd_parent = -1; static int nsfd_childa = -1; static int nsfd_childb = -1; @@ -96,7 +94,6 @@ struct xfrm_key_entry xfrm_key_entries[] = { {"cbc(cast5)", 128}, {"cbc(serpent)", 128}, {"hmac(sha1)", 160}, - {"hmac(rmd160)", 160}, {"cbc(des3_ede)", 192}, {"hmac(sha256)", 256}, {"cbc(aes)", 256}, @@ -813,7 +810,7 @@ static int xfrm_fill_key(char *name, char *buf, { int i; - for (i = 0; i < XFRM_ALGO_NR_KEYS; i++) { + for (i = 0; i < ARRAY_SIZE(xfrm_key_entries); i++) { if (strncmp(name, xfrm_key_entries[i].algo_name, ALGO_LEN) == 0) *key_len = xfrm_key_entries[i].key_len; } @@ -2061,8 +2058,7 @@ static int write_desc(int proto, int test_desc_fd, int proto_list[] = { IPPROTO_AH, IPPROTO_COMP, IPPROTO_ESP }; char *ah_list[] = { "digest_null", "hmac(md5)", "hmac(sha1)", "hmac(sha256)", - "hmac(sha384)", "hmac(sha512)", "hmac(rmd160)", - "xcbc(aes)", "cmac(aes)" + "hmac(sha384)", "hmac(sha512)", "xcbc(aes)", "cmac(aes)" }; char *comp_list[] = { "deflate", diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index b40694573f4c..b3827b43782b 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -224,6 +224,19 @@ setup_ns() NS_LIST+=("${ns_list[@]}") } +in_all_ns() +{ + local ret=0 + local ns_list=("${NS_LIST[@]}") + + for ns in "${ns_list[@]}"; do + ip netns exec "${ns}" "$@" + (( ret = ret || $? )) + done + + return "${ret}" +} + # Create netdevsim with given id and net namespace. create_netdevsim() { local id="$1" @@ -514,7 +527,8 @@ mac_get() { local if_name=$1 - ip -j link show dev $if_name | jq -r '.[]["address"]' + run_on "$if_name" \ + ip -j link show dev "$if_name" | jq -r '.[]["address"]' } kill_process() @@ -670,3 +684,8 @@ cmd_jq() # return success only in case of non-empty output [ ! -z "$output" ] } + +run_on() +{ + shift; "$@" +} diff --git a/tools/testing/selftests/net/lib/.gitignore b/tools/testing/selftests/net/lib/.gitignore index bbc97d6bf556..6cd2b762af5d 100644 --- a/tools/testing/selftests/net/lib/.gitignore +++ b/tools/testing/selftests/net/lib/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only csum +gro xdp_helper diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index 5339f56329e1..ff83603397d0 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -14,6 +14,7 @@ TEST_FILES := \ TEST_GEN_FILES := \ $(patsubst %.c,%.o,$(wildcard *.bpf.c)) \ csum \ + gro \ xdp_helper \ # end of TEST_GEN_FILES diff --git a/tools/testing/selftests/net/lib/gro.c b/tools/testing/selftests/net/lib/gro.c new file mode 100644 index 000000000000..11b16ae5f0e8 --- /dev/null +++ b/tools/testing/selftests/net/lib/gro.c @@ -0,0 +1,1837 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This testsuite provides conformance testing for GRO coalescing. + * + * Test cases: + * + * data_*: + * Data packets of the same size and same header setup with correct + * sequence numbers coalesce. The one exception being the last data + * packet coalesced: it can be smaller than the rest and coalesced + * as long as it is in the same flow. + * - data_same: same size packets coalesce + * - data_lrg_sml: large then small coalesces + * - data_lrg_1byte: large then 1 byte coalesces (Ethernet padding) + * - data_sml_lrg: small then large doesn't coalesce + * - data_burst: two bursts of two, separated by 100ms + * + * ack: + * Pure ACK does not coalesce. + * + * flags_*: + * No packets with PSH, SYN, URG, RST, CWR set will be coalesced. + * - flags_psh, flags_syn, flags_rst, flags_urg, flags_cwr + * + * tcp_*: + * Packets with incorrect checksum, non-consecutive seqno and + * different TCP header options shouldn't coalesce. Nit: given that + * some extension headers have paddings, such as timestamp, headers + * that are padded differently would not be coalesced. + * - tcp_csum: incorrect checksum + * - tcp_seq: non-consecutive sequence numbers + * - tcp_ts: different timestamps + * - tcp_opt: different TCP options + * + * ip_*: + * Packets with different (ECN, TTL, TOS) header, IP options or + * IP fragments shouldn't coalesce. + * - ip_ecn, ip_tos: shared between IPv4/IPv6 + * - ip_csum: IPv4 only, bad IP header checksum + * - ip_ttl, ip_opt, ip_frag4: IPv4 only + * - ip_id_df*: IPv4 IP ID field coalescing tests + * - ip_frag6, ip_v6ext_*: IPv6 only + * + * large_*: + * Packets larger than GRO_MAX_SIZE packets shouldn't coalesce. + * - large_max: exceeding max size + * - large_rem: remainder handling + * + * single, capacity: + * Boring cases used to test coalescing machinery itself and stats + * more than protocol behavior. + * + * MSS is defined as 4096 - header because if it is too small + * (i.e. 1500 MTU - header), it will result in many packets, + * increasing the "large" test case's flakiness. This is because + * due to time sensitivity in the coalescing window, the receiver + * may not coalesce all of the packets. + * + * Note the timing issue applies to all of the test cases, so some + * flakiness is to be expected. + * + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <linux/filter.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <linux/net_tstamp.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdarg.h> +#include <string.h> +#include <time.h> +#include <unistd.h> + +#include "kselftest.h" +#include "ksft.h" + +#define DPORT 8000 +#define SPORT 1500 +#define PAYLOAD_LEN 100 +#define NUM_PACKETS 4 +#define START_SEQ 100 +#define START_ACK 100 +#define ETH_P_NONE 0 +#define ASSUMED_MTU 4096 +#define MAX_MSS (ASSUMED_MTU - sizeof(struct iphdr) - sizeof(struct tcphdr)) +#define MAX_HDR_LEN \ + (ETH_HLEN + sizeof(struct ipv6hdr) * 2 + sizeof(struct tcphdr)) +#define MAX_LARGE_PKT_CNT ((IP_MAXPACKET - (MAX_HDR_LEN - ETH_HLEN)) / \ + (ASSUMED_MTU - (MAX_HDR_LEN - ETH_HLEN))) +#define MIN_EXTHDR_SIZE 8 +#define EXT_PAYLOAD_1 "\x00\x00\x00\x00\x00\x00" +#define EXT_PAYLOAD_2 "\x11\x11\x11\x11\x11\x11" + +#define ipv6_optlen(p) (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */ +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) + +enum flush_id_case { + FLUSH_ID_DF1_INC, + FLUSH_ID_DF1_FIXED, + FLUSH_ID_DF0_INC, + FLUSH_ID_DF0_FIXED, + FLUSH_ID_DF1_INC_FIXED, + FLUSH_ID_DF1_FIXED_INC, +}; + +static const char *addr6_src = "fdaa::2"; +static const char *addr6_dst = "fdaa::1"; +static const char *addr4_src = "192.168.1.200"; +static const char *addr4_dst = "192.168.1.100"; +static int proto = -1; +static uint8_t src_mac[ETH_ALEN], dst_mac[ETH_ALEN]; +static char *testname = "data"; +static char *ifname = "eth0"; +static char *smac = "aa:00:00:00:00:02"; +static char *dmac = "aa:00:00:00:00:01"; +static bool verbose; +static bool tx_socket = true; +static int tcp_offset = -1; +static int total_hdr_len = -1; +static int ethhdr_proto = -1; +static bool ipip; +static bool ip6ip6; +static uint64_t txtime_ns; +static int num_flows = 4; +static bool order_check; + +#define CAPACITY_PAYLOAD_LEN 200 + +#define TXTIME_DELAY_MS 5 + +/* Max TCP payload that GRO will coalesce. The outer header overhead + * varies by encapsulation, reducing the effective max payload. + */ +static int max_payload(void) +{ + return IP_MAXPACKET - (total_hdr_len - ETH_HLEN); +} + +static int calc_mss(void) +{ + return ASSUMED_MTU - (total_hdr_len - ETH_HLEN); +} + +static int num_large_pkt(void) +{ + return max_payload() / calc_mss(); +} + +static void vlog(const char *fmt, ...) +{ + va_list args; + + if (verbose) { + va_start(args, fmt); + vfprintf(stderr, fmt, args); + va_end(args); + } +} + +static void setup_sock_filter(int fd) +{ + const int dport_off = tcp_offset + offsetof(struct tcphdr, dest); + const int ethproto_off = offsetof(struct ethhdr, h_proto); + int optlen = 0; + int ipproto_off, opt_ipproto_off; + + if (proto == PF_INET) + ipproto_off = tcp_offset - sizeof(struct iphdr) + + offsetof(struct iphdr, protocol); + else + ipproto_off = tcp_offset - sizeof(struct ipv6hdr) + + offsetof(struct ipv6hdr, nexthdr); + + /* Overridden later if exthdrs are used: */ + opt_ipproto_off = ipproto_off; + + if (strcmp(testname, "ip_opt") == 0) { + optlen = sizeof(struct ip_timestamp); + } else if (strcmp(testname, "ip_frag6") == 0 || + strcmp(testname, "ip_v6ext_same") == 0 || + strcmp(testname, "ip_v6ext_diff") == 0) { + BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE); + BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE); + BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE); + + /* same size for HBH and Fragment extension header types */ + optlen = MIN_EXTHDR_SIZE; + opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr) + + offsetof(struct ip6_ext, ip6e_nxt); + } + + /* this filter validates the following: + * - packet is IPv4/IPv6 according to the running test. + * - packet is TCP. Also handles the case of one extension header and then TCP. + * - checks the packet tcp dport equals to DPORT. Also handles the case of one + * extension header and then TCP. + */ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, ethproto_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 9), + BPF_STMT(BPF_LD + BPF_B + BPF_ABS, ipproto_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 2, 0), + BPF_STMT(BPF_LD + BPF_B + BPF_ABS, opt_ipproto_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 0, 5), + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, dport_off), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 2, 0), + BPF_STMT(BPF_LD + BPF_H + BPF_ABS, dport_off + optlen), + BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 0, 1), + BPF_STMT(BPF_RET + BPF_K, 0xFFFFFFFF), + BPF_STMT(BPF_RET + BPF_K, 0), + }; + + struct sock_fprog bpf = { + .len = ARRAY_SIZE(filter), + .filter = filter, + }; + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf)) < 0) + error(1, errno, "error setting filter"); +} + +static uint32_t checksum_nofold(void *data, size_t len, uint32_t sum) +{ + uint16_t *words = data; + int i; + + for (i = 0; i < len / 2; i++) + sum += words[i]; + if (len & 1) + sum += ((char *)data)[len - 1]; + return sum; +} + +static uint16_t checksum_fold(void *data, size_t len, uint32_t sum) +{ + sum = checksum_nofold(data, len, sum); + while (sum > 0xFFFF) + sum = (sum & 0xFFFF) + (sum >> 16); + return ~sum; +} + +static uint16_t tcp_checksum(void *buf, int payload_len) +{ + struct pseudo_header6 { + struct in6_addr saddr; + struct in6_addr daddr; + uint16_t protocol; + uint16_t payload_len; + } ph6; + struct pseudo_header4 { + struct in_addr saddr; + struct in_addr daddr; + uint16_t protocol; + uint16_t payload_len; + } ph4; + uint32_t sum = 0; + + if (proto == PF_INET6) { + if (inet_pton(AF_INET6, addr6_src, &ph6.saddr) != 1) + error(1, errno, "inet_pton6 source ip pseudo"); + if (inet_pton(AF_INET6, addr6_dst, &ph6.daddr) != 1) + error(1, errno, "inet_pton6 dest ip pseudo"); + ph6.protocol = htons(IPPROTO_TCP); + ph6.payload_len = htons(sizeof(struct tcphdr) + payload_len); + + sum = checksum_nofold(&ph6, sizeof(ph6), 0); + } else if (proto == PF_INET) { + if (inet_pton(AF_INET, addr4_src, &ph4.saddr) != 1) + error(1, errno, "inet_pton source ip pseudo"); + if (inet_pton(AF_INET, addr4_dst, &ph4.daddr) != 1) + error(1, errno, "inet_pton dest ip pseudo"); + ph4.protocol = htons(IPPROTO_TCP); + ph4.payload_len = htons(sizeof(struct tcphdr) + payload_len); + + sum = checksum_nofold(&ph4, sizeof(ph4), 0); + } + + return checksum_fold(buf, sizeof(struct tcphdr) + payload_len, sum); +} + +static void read_MAC(uint8_t *mac_addr, char *mac) +{ + if (sscanf(mac, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", + &mac_addr[0], &mac_addr[1], &mac_addr[2], + &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) + error(1, 0, "sscanf"); +} + +static void fill_datalinklayer(void *buf) +{ + struct ethhdr *eth = buf; + + memcpy(eth->h_dest, dst_mac, ETH_ALEN); + memcpy(eth->h_source, src_mac, ETH_ALEN); + eth->h_proto = ethhdr_proto; +} + +static void fill_networklayer(void *buf, int payload_len, int protocol) +{ + struct ipv6hdr *ip6h = buf; + struct iphdr *iph = buf; + + if (proto == PF_INET6) { + memset(ip6h, 0, sizeof(*ip6h)); + + ip6h->version = 6; + ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len); + ip6h->nexthdr = protocol; + ip6h->hop_limit = 8; + if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1) + error(1, errno, "inet_pton source ip6"); + if (inet_pton(AF_INET6, addr6_dst, &ip6h->daddr) != 1) + error(1, errno, "inet_pton dest ip6"); + } else if (proto == PF_INET) { + memset(iph, 0, sizeof(*iph)); + + iph->version = 4; + iph->ihl = 5; + iph->ttl = 8; + iph->protocol = protocol; + iph->tot_len = htons(sizeof(struct tcphdr) + + payload_len + sizeof(struct iphdr)); + iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */ + if (inet_pton(AF_INET, addr4_src, &iph->saddr) != 1) + error(1, errno, "inet_pton source ip"); + if (inet_pton(AF_INET, addr4_dst, &iph->daddr) != 1) + error(1, errno, "inet_pton dest ip"); + iph->check = checksum_fold(buf, sizeof(struct iphdr), 0); + } +} + +static void fill_transportlayer(void *buf, int seq_offset, int ack_offset, + int payload_len, int fin) +{ + struct tcphdr *tcph = buf; + + memset(tcph, 0, sizeof(*tcph)); + + tcph->source = htons(SPORT); + tcph->dest = htons(DPORT); + tcph->seq = ntohl(START_SEQ + seq_offset); + tcph->ack_seq = ntohl(START_ACK + ack_offset); + tcph->ack = 1; + tcph->fin = fin; + tcph->doff = 5; + tcph->window = htons(TCP_MAXWIN); + tcph->urg_ptr = 0; + tcph->check = tcp_checksum(tcph, payload_len); +} + +static void write_packet(int fd, char *buf, int len, struct sockaddr_ll *daddr) +{ + char control[CMSG_SPACE(sizeof(uint64_t))]; + struct msghdr msg = {}; + struct iovec iov = {}; + struct cmsghdr *cm; + int ret = -1; + + iov.iov_base = buf; + iov.iov_len = len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_name = daddr; + msg.msg_namelen = sizeof(*daddr); + + if (txtime_ns) { + memset(control, 0, sizeof(control)); + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + cm = CMSG_FIRSTHDR(&msg); + cm->cmsg_level = SOL_SOCKET; + cm->cmsg_type = SCM_TXTIME; + cm->cmsg_len = CMSG_LEN(sizeof(uint64_t)); + memcpy(CMSG_DATA(cm), &txtime_ns, sizeof(txtime_ns)); + } + + ret = sendmsg(fd, &msg, 0); + if (ret == -1) + error(1, errno, "sendmsg failure"); + if (ret != len) + error(1, 0, "sendmsg wrong length: %d vs %d", ret, len); +} + +static void create_packet(void *buf, int seq_offset, int ack_offset, + int payload_len, int fin) +{ + int ip_hdr_len = (proto == PF_INET) ? + sizeof(struct iphdr) : sizeof(struct ipv6hdr); + int inner_ip_off = tcp_offset - ip_hdr_len; + + memset(buf, 0, total_hdr_len); + memset(buf + total_hdr_len, 'a', payload_len); + + fill_transportlayer(buf + tcp_offset, seq_offset, ack_offset, + payload_len, fin); + + fill_networklayer(buf + inner_ip_off, payload_len, IPPROTO_TCP); + if (inner_ip_off > ETH_HLEN) { + int encap_proto = (proto == PF_INET) ? + IPPROTO_IPIP : IPPROTO_IPV6; + + fill_networklayer(buf + ETH_HLEN, + payload_len + ip_hdr_len, encap_proto); + } + + fill_datalinklayer(buf); +} + +static void create_capacity_packet(void *buf, int flow_id, int pkt_idx, int psh) +{ + int seq_offset = pkt_idx * CAPACITY_PAYLOAD_LEN; + struct tcphdr *tcph; + + create_packet(buf, seq_offset, 0, CAPACITY_PAYLOAD_LEN, 0); + + /* Customize for this flow id */ + memset(buf + total_hdr_len, 'a' + flow_id, CAPACITY_PAYLOAD_LEN); + + tcph = buf + tcp_offset; + tcph->source = htons(SPORT + flow_id); + tcph->psh = psh; + tcph->check = 0; + tcph->check = tcp_checksum(tcph, CAPACITY_PAYLOAD_LEN); +} + +/* Send a capacity test, 2 packets per flow, all first packets then all second: + * A1 B1 C1 D1 ... A2 B2 C2 D2 ... + */ +static void send_capacity(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + CAPACITY_PAYLOAD_LEN]; + int pkt_size = total_hdr_len + CAPACITY_PAYLOAD_LEN; + int i; + + /* Send first packet of each flow (no PSH) */ + for (i = 0; i < num_flows; i++) { + create_capacity_packet(buf, i, 0, 0); + write_packet(fd, buf, pkt_size, daddr); + } + + /* Send second packet of each flow (with PSH to flush) */ + for (i = 0; i < num_flows; i++) { + create_capacity_packet(buf, i, 1, 1); + write_packet(fd, buf, pkt_size, daddr); + } +} + +#ifndef TH_CWR +#define TH_CWR 0x80 +#endif +static void set_flags(struct tcphdr *tcph, int payload_len, int psh, int syn, + int rst, int urg, int cwr) +{ + tcph->psh = psh; + tcph->syn = syn; + tcph->rst = rst; + tcph->urg = urg; + if (cwr) + tcph->th_flags |= TH_CWR; + else + tcph->th_flags &= ~TH_CWR; + tcph->check = 0; + tcph->check = tcp_checksum(tcph, payload_len); +} + +/* send extra flags of the (NUM_PACKETS / 2) and (NUM_PACKETS / 2 - 1) + * pkts, not first and not last pkt + */ +static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, + int rst, int urg, int cwr) +{ + static char flag_buf[2][MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + int payload_len, pkt_size, i; + struct tcphdr *tcph; + int flag[2]; + + payload_len = PAYLOAD_LEN * (psh || cwr); + pkt_size = total_hdr_len + payload_len; + flag[0] = NUM_PACKETS / 2; + flag[1] = NUM_PACKETS / 2 - 1; + + /* Create and configure packets with flags + */ + for (i = 0; i < 2; i++) { + if (flag[i] > 0) { + create_packet(flag_buf[i], flag[i] * payload_len, 0, + payload_len, 0); + tcph = (struct tcphdr *)(flag_buf[i] + tcp_offset); + set_flags(tcph, payload_len, psh, syn, rst, urg, cwr); + } + } + + for (i = 0; i < NUM_PACKETS + 1; i++) { + if (i == flag[0]) { + write_packet(fd, flag_buf[0], pkt_size, daddr); + continue; + } else if (i == flag[1] && cwr) { + write_packet(fd, flag_buf[1], pkt_size, daddr); + continue; + } + create_packet(buf, i * PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, total_hdr_len + PAYLOAD_LEN, daddr); + } +} + +/* Test for data of same length, smaller than previous + * and of different lengths + */ +static void send_data_pkts(int fd, struct sockaddr_ll *daddr, + int payload_len1, int payload_len2) +{ + static char buf[ETH_HLEN + IP_MAXPACKET]; + + create_packet(buf, 0, 0, payload_len1, 0); + write_packet(fd, buf, total_hdr_len + payload_len1, daddr); + create_packet(buf, payload_len1, 0, payload_len2, 0); + write_packet(fd, buf, total_hdr_len + payload_len2, daddr); +} + +/* If incoming segments make tracked segment length exceed + * legal IP datagram length, do not coalesce + */ +static void send_large(int fd, struct sockaddr_ll *daddr, int remainder) +{ + static char pkts[MAX_LARGE_PKT_CNT][MAX_HDR_LEN + MAX_MSS]; + static char new_seg[MAX_HDR_LEN + MAX_MSS]; + static char last[MAX_HDR_LEN + MAX_MSS]; + const int num_pkt = num_large_pkt(); + const int mss = calc_mss(); + int i; + + for (i = 0; i < num_pkt; i++) + create_packet(pkts[i], i * mss, 0, mss, 0); + create_packet(last, num_pkt * mss, 0, remainder, 0); + create_packet(new_seg, (num_pkt + 1) * mss, 0, remainder, 0); + + for (i = 0; i < num_pkt; i++) + write_packet(fd, pkts[i], total_hdr_len + mss, daddr); + write_packet(fd, last, total_hdr_len + remainder, daddr); + write_packet(fd, new_seg, total_hdr_len + remainder, daddr); +} + +/* Pure acks and dup acks don't coalesce */ +static void send_ack(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN]; + + create_packet(buf, 0, 0, 0, 0); + write_packet(fd, buf, total_hdr_len, daddr); + write_packet(fd, buf, total_hdr_len, daddr); + create_packet(buf, 0, 1, 0, 0); + write_packet(fd, buf, total_hdr_len, daddr); +} + +static void recompute_packet(char *buf, char *no_ext, int extlen) +{ + struct tcphdr *tcphdr = (struct tcphdr *)(buf + tcp_offset); + int off; + + memmove(buf, no_ext, total_hdr_len); + memmove(buf + total_hdr_len + extlen, + no_ext + total_hdr_len, PAYLOAD_LEN); + + tcphdr->doff = tcphdr->doff + (extlen / 4); + tcphdr->check = 0; + tcphdr->check = tcp_checksum(tcphdr, PAYLOAD_LEN + extlen); + if (proto == PF_INET) { + for (off = ETH_HLEN; off < tcp_offset; + off += sizeof(struct iphdr)) { + struct iphdr *iph = (struct iphdr *)(buf + off); + + iph->tot_len = htons(ntohs(iph->tot_len) + extlen); + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + } + } else { + for (off = ETH_HLEN; off < tcp_offset; + off += sizeof(struct ipv6hdr)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buf + off); + + ip6h->payload_len = + htons(ntohs(ip6h->payload_len) + extlen); + } + } +} + +static void tcp_write_options(char *buf, int kind, int ts) +{ + struct tcp_option_ts { + uint8_t kind; + uint8_t len; + uint32_t tsval; + uint32_t tsecr; + } *opt_ts = (void *)buf; + struct tcp_option_window { + uint8_t kind; + uint8_t len; + uint8_t shift; + } *opt_window = (void *)buf; + + switch (kind) { + case TCPOPT_NOP: + buf[0] = TCPOPT_NOP; + break; + case TCPOPT_WINDOW: + memset(opt_window, 0, sizeof(struct tcp_option_window)); + opt_window->kind = TCPOPT_WINDOW; + opt_window->len = TCPOLEN_WINDOW; + opt_window->shift = 0; + break; + case TCPOPT_TIMESTAMP: + memset(opt_ts, 0, sizeof(struct tcp_option_ts)); + opt_ts->kind = TCPOPT_TIMESTAMP; + opt_ts->len = TCPOLEN_TIMESTAMP; + opt_ts->tsval = ts; + opt_ts->tsecr = 0; + break; + default: + error(1, 0, "unimplemented TCP option"); + break; + } +} + +/* TCP with options is always a permutation of {TS, NOP, NOP}. + * Implement different orders to verify coalescing stops. + */ +static void add_standard_tcp_options(char *buf, char *no_ext, int ts, int order) +{ + switch (order) { + case 0: + tcp_write_options(buf + total_hdr_len, TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + 1, TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + 2 /* two NOP opts */, + TCPOPT_TIMESTAMP, ts); + break; + case 1: + tcp_write_options(buf + total_hdr_len, TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + 1, + TCPOPT_TIMESTAMP, ts); + tcp_write_options(buf + total_hdr_len + 1 + TCPOLEN_TIMESTAMP, + TCPOPT_NOP, 0); + break; + case 2: + tcp_write_options(buf + total_hdr_len, TCPOPT_TIMESTAMP, ts); + tcp_write_options(buf + total_hdr_len + TCPOLEN_TIMESTAMP + 1, + TCPOPT_NOP, 0); + tcp_write_options(buf + total_hdr_len + TCPOLEN_TIMESTAMP + 2, + TCPOPT_NOP, 0); + break; + default: + error(1, 0, "unknown order"); + break; + } + recompute_packet(buf, no_ext, TCPOLEN_TSTAMP_APPA); +} + +/* Packets with invalid checksum don't coalesce. */ +static void send_changed_checksum(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct tcphdr *tcph = (struct tcphdr *)(buf + tcp_offset); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + tcph->check = tcph->check - 1; + write_packet(fd, buf, pkt_size, daddr); +} + +/* Packets with incorrect IPv4 header checksum don't coalesce. */ +static void send_changed_ip_checksum(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + iph->check = iph->check - 1; + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); +} + + /* Packets with non-consecutive sequence number don't coalesce.*/ +static void send_changed_seq(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct tcphdr *tcph = (struct tcphdr *)(buf + tcp_offset); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + tcph->seq = ntohl(htonl(tcph->seq) + 1); + tcph->check = 0; + tcph->check = tcp_checksum(tcph, PAYLOAD_LEN); + write_packet(fd, buf, pkt_size, daddr); +} + + /* Packet with different timestamp option or different timestamps + * don't coalesce. + */ +static void send_changed_ts(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char extpkt[sizeof(buf) + TCPOLEN_TSTAMP_APPA]; + int pkt_size = total_hdr_len + PAYLOAD_LEN + TCPOLEN_TSTAMP_APPA; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 0, 0); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 0, 0); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 100, 0); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 3, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 100, 1); + write_packet(fd, extpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 4, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt, buf, 100, 2); + write_packet(fd, extpkt, pkt_size, daddr); +} + +/* Packet with different tcp options don't coalesce. */ +static void send_diff_opt(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char extpkt1[sizeof(buf) + TCPOLEN_TSTAMP_APPA]; + static char extpkt2[sizeof(buf) + TCPOLEN_MAXSEG]; + int extpkt1_size = total_hdr_len + PAYLOAD_LEN + TCPOLEN_TSTAMP_APPA; + int extpkt2_size = total_hdr_len + PAYLOAD_LEN + TCPOLEN_MAXSEG; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt1, buf, 0, 0); + write_packet(fd, extpkt1, extpkt1_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + add_standard_tcp_options(extpkt1, buf, 0, 0); + write_packet(fd, extpkt1, extpkt1_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + tcp_write_options(extpkt2 + MAX_HDR_LEN, TCPOPT_NOP, 0); + tcp_write_options(extpkt2 + MAX_HDR_LEN + 1, TCPOPT_WINDOW, 0); + recompute_packet(extpkt2, buf, TCPOLEN_WINDOW + 1); + write_packet(fd, extpkt2, extpkt2_size, daddr); +} + +static void add_ipv4_ts_option(void *buf, void *optpkt) +{ + struct ip_timestamp *ts = (struct ip_timestamp *)(optpkt + tcp_offset); + int optlen = sizeof(struct ip_timestamp); + struct iphdr *iph; + + if (optlen % 4) + error(1, 0, "ipv4 timestamp length is not a multiple of 4B"); + + ts->ipt_code = IPOPT_TS; + ts->ipt_len = optlen; + ts->ipt_ptr = 5; + ts->ipt_flg = IPOPT_TS_TSONLY; + + memcpy(optpkt, buf, tcp_offset); + memcpy(optpkt + tcp_offset + optlen, buf + tcp_offset, + sizeof(struct tcphdr) + PAYLOAD_LEN); + + iph = (struct iphdr *)(optpkt + ETH_HLEN); + iph->ihl = 5 + (optlen / 4); + iph->tot_len = htons(ntohs(iph->tot_len) + optlen); + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr) + optlen, 0); +} + +static void add_ipv6_exthdr(void *buf, void *optpkt, __u8 exthdr_type, char *ext_payload) +{ + struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(optpkt + tcp_offset); + struct ipv6hdr *iph = (struct ipv6hdr *)(optpkt + ETH_HLEN); + char *exthdr_payload_start = (char *)(exthdr + 1); + + exthdr->hdrlen = 0; + exthdr->nexthdr = IPPROTO_TCP; + + memcpy(exthdr_payload_start, ext_payload, MIN_EXTHDR_SIZE - sizeof(*exthdr)); + + memcpy(optpkt, buf, tcp_offset); + memcpy(optpkt + tcp_offset + MIN_EXTHDR_SIZE, buf + tcp_offset, + sizeof(struct tcphdr) + PAYLOAD_LEN); + + iph->nexthdr = exthdr_type; + iph->payload_len = htons(ntohs(iph->payload_len) + MIN_EXTHDR_SIZE); +} + +static void fix_ip4_checksum(struct iphdr *iph) +{ + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); +} + +static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, + enum flush_id_case tcase) +{ + static char buf1[MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf2[MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf3[MAX_HDR_LEN + PAYLOAD_LEN]; + bool send_three = false; + struct iphdr *iph1; + struct iphdr *iph2; + struct iphdr *iph3; + + iph1 = (struct iphdr *)(buf1 + ETH_HLEN); + iph2 = (struct iphdr *)(buf2 + ETH_HLEN); + iph3 = (struct iphdr *)(buf3 + ETH_HLEN); + + create_packet(buf1, 0, 0, PAYLOAD_LEN, 0); + create_packet(buf2, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + create_packet(buf3, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + + switch (tcase) { + case FLUSH_ID_DF1_INC: /* DF=1, Incrementing - should coalesce */ + iph1->frag_off |= htons(IP_DF); + iph1->id = htons(8); + + iph2->frag_off |= htons(IP_DF); + iph2->id = htons(9); + break; + + case FLUSH_ID_DF1_FIXED: /* DF=1, Fixed - should coalesce */ + iph1->frag_off |= htons(IP_DF); + iph1->id = htons(8); + + iph2->frag_off |= htons(IP_DF); + iph2->id = htons(8); + break; + + case FLUSH_ID_DF0_INC: /* DF=0, Incrementing - should coalesce */ + iph1->frag_off &= ~htons(IP_DF); + iph1->id = htons(8); + + iph2->frag_off &= ~htons(IP_DF); + iph2->id = htons(9); + break; + + case FLUSH_ID_DF0_FIXED: /* DF=0, Fixed - should coalesce */ + iph1->frag_off &= ~htons(IP_DF); + iph1->id = htons(8); + + iph2->frag_off &= ~htons(IP_DF); + iph2->id = htons(8); + break; + + case FLUSH_ID_DF1_INC_FIXED: /* DF=1, two packets incrementing, and + * one fixed - should coalesce only the + * first two packets + */ + iph1->frag_off |= htons(IP_DF); + iph1->id = htons(8); + + iph2->frag_off |= htons(IP_DF); + iph2->id = htons(9); + + iph3->frag_off |= htons(IP_DF); + iph3->id = htons(9); + send_three = true; + break; + + case FLUSH_ID_DF1_FIXED_INC: /* DF=1, two packets fixed, and one + * incrementing - should coalesce only + * the first two packets + */ + iph1->frag_off |= htons(IP_DF); + iph1->id = htons(8); + + iph2->frag_off |= htons(IP_DF); + iph2->id = htons(8); + + iph3->frag_off |= htons(IP_DF); + iph3->id = htons(9); + send_three = true; + break; + } + + fix_ip4_checksum(iph1); + fix_ip4_checksum(iph2); + write_packet(fd, buf1, total_hdr_len + PAYLOAD_LEN, daddr); + write_packet(fd, buf2, total_hdr_len + PAYLOAD_LEN, daddr); + + if (send_three) { + fix_ip4_checksum(iph3); + write_packet(fd, buf3, total_hdr_len + PAYLOAD_LEN, daddr); + } +} + +static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char exthdr_pck[sizeof(buf) + MIN_EXTHDR_SIZE]; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data1); + write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr); + + create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0); + add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data2); + write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr); +} + +/* IPv4 options shouldn't coalesce */ +static void send_ip_options(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char optpkt[sizeof(buf) + sizeof(struct ip_timestamp)]; + int optlen = sizeof(struct ip_timestamp); + int pkt_size = total_hdr_len + PAYLOAD_LEN + optlen; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, total_hdr_len + PAYLOAD_LEN, daddr); + + create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0); + add_ipv4_ts_option(buf, optpkt); + write_packet(fd, optpkt, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, total_hdr_len + PAYLOAD_LEN, daddr); +} + +/* IPv4 fragments shouldn't coalesce */ +static void send_fragment4(int fd, struct sockaddr_ll *daddr) +{ + static char buf[IP_MAXPACKET]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + int pkt_size = total_hdr_len + PAYLOAD_LEN; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + /* Once fragmented, packet would retain the total_len. + * Tcp header is prepared as if rest of data is in follow-up frags, + * but follow up frags aren't actually sent. + */ + memset(buf + total_hdr_len, 'a', PAYLOAD_LEN * 2); + fill_transportlayer(buf + tcp_offset, PAYLOAD_LEN, 0, PAYLOAD_LEN * 2, 0); + fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN, IPPROTO_TCP); + fill_datalinklayer(buf); + + iph->frag_off = htons(0x6000); // DF = 1, MF = 1 + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + write_packet(fd, buf, pkt_size, daddr); +} + +/* IPv4 packets with different ttl don't coalesce.*/ +static void send_changed_ttl(int fd, struct sockaddr_ll *daddr) +{ + int pkt_size = total_hdr_len + PAYLOAD_LEN; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + iph->ttl = 7; + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + write_packet(fd, buf, pkt_size, daddr); +} + +/* Packets with different tos don't coalesce.*/ +static void send_changed_tos(int fd, struct sockaddr_ll *daddr) +{ + int pkt_size = total_hdr_len + PAYLOAD_LEN; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buf + ETH_HLEN); + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + if (proto == PF_INET) { + iph->tos = 1; + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + } else if (proto == PF_INET6) { + ip6h->priority = 0xf; + } + write_packet(fd, buf, pkt_size, daddr); +} + +/* Packets with different ECN don't coalesce.*/ +static void send_changed_ECN(int fd, struct sockaddr_ll *daddr) +{ + int pkt_size = total_hdr_len + PAYLOAD_LEN; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + struct iphdr *iph = (struct iphdr *)(buf + ETH_HLEN); + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, pkt_size, daddr); + + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + if (proto == PF_INET) { + buf[ETH_HLEN + 1] ^= 0x2; // ECN set to 10 + iph->check = 0; + iph->check = checksum_fold(iph, sizeof(struct iphdr), 0); + } else { + buf[ETH_HLEN + 1] ^= 0x20; // ECN set to 10 + } + write_packet(fd, buf, pkt_size, daddr); +} + +/* IPv6 fragments and packets with extensions don't coalesce.*/ +static void send_fragment6(int fd, struct sockaddr_ll *daddr) +{ + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + static char extpkt[MAX_HDR_LEN + PAYLOAD_LEN + + sizeof(struct ip6_frag)]; + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buf + ETH_HLEN); + struct ip6_frag *frag = (void *)(extpkt + tcp_offset); + int extlen = sizeof(struct ip6_frag); + int bufpkt_len = total_hdr_len + PAYLOAD_LEN; + int extpkt_len = bufpkt_len + extlen; + int i; + + for (i = 0; i < 2; i++) { + create_packet(buf, PAYLOAD_LEN * i, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, bufpkt_len, daddr); + } + sleep(1); + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + memset(extpkt, 0, extpkt_len); + + ip6h->nexthdr = IPPROTO_FRAGMENT; + ip6h->payload_len = htons(ntohs(ip6h->payload_len) + extlen); + frag->ip6f_nxt = IPPROTO_TCP; + + memcpy(extpkt, buf, tcp_offset); + memcpy(extpkt + tcp_offset + extlen, buf + tcp_offset, + sizeof(struct tcphdr) + PAYLOAD_LEN); + write_packet(fd, extpkt, extpkt_len, daddr); + + create_packet(buf, PAYLOAD_LEN * 3, 0, PAYLOAD_LEN, 0); + write_packet(fd, buf, bufpkt_len, daddr); +} + +static void bind_packetsocket(int fd) +{ + struct sockaddr_ll daddr = {}; + + daddr.sll_family = AF_PACKET; + daddr.sll_protocol = ethhdr_proto; + daddr.sll_ifindex = if_nametoindex(ifname); + if (daddr.sll_ifindex == 0) + error(1, errno, "if_nametoindex"); + + if (bind(fd, (void *)&daddr, sizeof(daddr)) < 0) + error(1, errno, "could not bind socket"); +} + +static void set_timeout(int fd) +{ + struct timeval timeout; + + timeout.tv_sec = 3; + timeout.tv_usec = 0; + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (char *)&timeout, + sizeof(timeout)) < 0) + error(1, errno, "cannot set timeout, setsockopt failed"); +} + +static void set_rcvbuf(int fd) +{ + int bufsize = 1 * 1024 * 1024; /* 1 MB */ + + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &bufsize, sizeof(bufsize))) + error(1, errno, "cannot set rcvbuf size, setsockopt failed"); +} + +static void recv_error(int fd, int rcv_errno) +{ + struct tpacket_stats stats; + socklen_t len; + + len = sizeof(stats); + if (getsockopt(fd, SOL_PACKET, PACKET_STATISTICS, &stats, &len)) + error(1, errno, "can't get stats"); + + fprintf(stderr, "Socket stats: packets=%u, drops=%u\n", + stats.tp_packets, stats.tp_drops); + error(1, rcv_errno, "could not receive"); +} + +static void check_recv_pkts(int fd, int *correct_payload, + int correct_num_pkts) +{ + static char buffer[IP_MAXPACKET + ETH_HLEN + 1]; + struct iphdr *iph = (struct iphdr *)(buffer + ETH_HLEN); + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + ETH_HLEN); + struct tcphdr *tcph; + bool bad_packet = false; + int tcp_ext_len = 0; + int ip_ext_len = 0; + int pkt_size = -1; + int data_len = 0; + int num_pkt = 0; + int i; + + vlog("Expected {"); + for (i = 0; i < correct_num_pkts; i++) + vlog("%d ", correct_payload[i]); + vlog("}, Total %d packets\nReceived {", correct_num_pkts); + + while (1) { + ip_ext_len = 0; + pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0); + if (pkt_size < 0) + recv_error(fd, errno); + + if (iph->version == 4) + ip_ext_len = (iph->ihl - 5) * 4; + else if (ip6h->version == 6 && !ip6ip6 && + ip6h->nexthdr != IPPROTO_TCP) + ip_ext_len = MIN_EXTHDR_SIZE; + + tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len); + + if (tcph->fin) + break; + + tcp_ext_len = (tcph->doff - 5) * 4; + data_len = pkt_size - total_hdr_len - tcp_ext_len - ip_ext_len; + /* Min ethernet frame payload is 46(ETH_ZLEN - ETH_HLEN) by RFC 802.3. + * Ipv4/tcp packets without at least 6 bytes of data will be padded. + * Packet sockets are protocol agnostic, and will not trim the padding. + */ + if (pkt_size == ETH_ZLEN && iph->version == 4) { + data_len = ntohs(iph->tot_len) + - sizeof(struct tcphdr) - sizeof(struct iphdr); + } + vlog("%d ", data_len); + if (data_len != correct_payload[num_pkt]) { + vlog("[!=%d]", correct_payload[num_pkt]); + bad_packet = true; + } + num_pkt++; + } + vlog("}, Total %d packets.\n", num_pkt); + if (num_pkt != correct_num_pkts) + error(1, 0, "incorrect number of packets"); + if (bad_packet) + error(1, 0, "incorrect packet geometry"); + + printf("Test succeeded\n\n"); +} + +static void check_capacity_pkts(int fd) +{ + static char buffer[IP_MAXPACKET + ETH_HLEN + 1]; + struct iphdr *iph = (struct iphdr *)(buffer + ETH_HLEN); + struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + ETH_HLEN); + int num_pkt = 0, num_coal = 0, pkt_idx; + const char *fail_reason = NULL; + int flow_order[num_flows * 2]; + int coalesced[num_flows]; + struct tcphdr *tcph; + int ip_ext_len = 0; + int total_data = 0; + int pkt_size = -1; + int data_len = 0; + int flow_id; + int sport; + + memset(coalesced, 0, sizeof(coalesced)); + memset(flow_order, -1, sizeof(flow_order)); + + while (1) { + ip_ext_len = 0; + pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0); + if (pkt_size < 0) + recv_error(fd, errno); + + if (iph->version == 4) + ip_ext_len = (iph->ihl - 5) * 4; + else if (ip6h->version == 6 && !ip6ip6 && + ip6h->nexthdr != IPPROTO_TCP) + ip_ext_len = MIN_EXTHDR_SIZE; + + tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len); + + if (tcph->fin) + break; + + sport = ntohs(tcph->source); + flow_id = sport - SPORT; + + if (flow_id < 0 || flow_id >= num_flows) { + vlog("Invalid flow_id %d from sport %d\n", + flow_id, sport); + fail_reason = fail_reason ?: "invalid packet"; + continue; + } + + /* Calculate payload length */ + if (pkt_size == ETH_ZLEN && iph->version == 4) { + data_len = ntohs(iph->tot_len) + - sizeof(struct tcphdr) - sizeof(struct iphdr); + } else { + data_len = pkt_size - total_hdr_len - ip_ext_len; + } + + if (num_pkt < num_flows * 2) { + flow_order[num_pkt] = flow_id; + } else if (num_pkt == num_flows * 2) { + vlog("More packets than expected (%d)\n", + num_flows * 2); + fail_reason = fail_reason ?: "too many packets"; + } + coalesced[flow_id] = data_len; + + if (data_len == CAPACITY_PAYLOAD_LEN * 2) { + num_coal++; + } else { + vlog("Pkt %d: flow %d, sport %d, len %d (expected %d)\n", + num_pkt, flow_id, sport, data_len, + CAPACITY_PAYLOAD_LEN * 2); + fail_reason = fail_reason ?: "not coalesced"; + } + + num_pkt++; + total_data += data_len; + } + + /* Check flow ordering. We expect to see all non-coalesced first segs + * then interleaved coalesced and non-coalesced second frames. + */ + pkt_idx = 0; + for (flow_id = 0; order_check && flow_id < num_flows; flow_id++) { + bool coaled = coalesced[flow_id] > CAPACITY_PAYLOAD_LEN; + + if (coaled) + continue; + + if (flow_order[pkt_idx] != flow_id) { + vlog("Flow order mismatch (non-coalesced) at position %d: expected flow %d, got flow %d\n", + pkt_idx, flow_id, flow_order[pkt_idx]); + fail_reason = fail_reason ?: "bad packet order (1)"; + } + pkt_idx++; + } + for (flow_id = 0; order_check && flow_id < num_flows; flow_id++) { + bool coaled = coalesced[flow_id] > CAPACITY_PAYLOAD_LEN; + + if (flow_order[pkt_idx] != flow_id) { + vlog("Flow order mismatch at position %d: expected flow %d, got flow %d, coalesced: %d\n", + pkt_idx, flow_id, flow_order[pkt_idx], coaled); + fail_reason = fail_reason ?: "bad packet order (2)"; + } + pkt_idx++; + } + + if (!fail_reason) { + vlog("All %d flows coalesced correctly\n", num_flows); + printf("Test succeeded\n\n"); + } else { + printf("FAILED\n"); + } + + /* Always print stats for external validation */ + printf("STATS: received=%d wire=%d coalesced=%d\n", + num_pkt, num_pkt + num_coal, num_coal); + + if (fail_reason) + error(1, 0, "capacity test failed %s", fail_reason); +} + +static void gro_sender(void) +{ + int bufsize = 4 * 1024 * 1024; /* 4 MB */ + const int fin_delay_us = 100 * 1000; + static char fin_pkt[MAX_HDR_LEN]; + struct sockaddr_ll daddr = {}; + int txfd = -1; + + txfd = socket(PF_PACKET, SOCK_RAW, IPPROTO_RAW); + if (txfd < 0) + error(1, errno, "socket creation"); + + if (setsockopt(txfd, SOL_SOCKET, SO_SNDBUF, &bufsize, sizeof(bufsize))) + error(1, errno, "cannot set sndbuf size, setsockopt failed"); + + /* Enable SO_TXTIME unless test case generates more than one flow + * SO_TXTIME could result in qdisc layer sorting the packets at sender. + */ + if (strcmp(testname, "single") && strcmp(testname, "capacity")) { + struct sock_txtime so_txtime = { .clockid = CLOCK_MONOTONIC, }; + struct timespec ts; + + if (setsockopt(txfd, SOL_SOCKET, SO_TXTIME, + &so_txtime, sizeof(so_txtime))) + error(1, errno, "setsockopt SO_TXTIME"); + + if (clock_gettime(CLOCK_MONOTONIC, &ts)) + error(1, errno, "clock_gettime"); + + txtime_ns = ts.tv_sec * 1000000000ULL + ts.tv_nsec; + txtime_ns += TXTIME_DELAY_MS * 1000000ULL; + } + + memset(&daddr, 0, sizeof(daddr)); + daddr.sll_ifindex = if_nametoindex(ifname); + if (daddr.sll_ifindex == 0) + error(1, errno, "if_nametoindex"); + daddr.sll_family = AF_PACKET; + memcpy(daddr.sll_addr, dst_mac, ETH_ALEN); + daddr.sll_halen = ETH_ALEN; + create_packet(fin_pkt, PAYLOAD_LEN * 2, 0, 0, 1); + + /* data sub-tests */ + if (strcmp(testname, "data_same") == 0) { + send_data_pkts(txfd, &daddr, PAYLOAD_LEN, PAYLOAD_LEN); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "data_lrg_sml") == 0) { + send_data_pkts(txfd, &daddr, PAYLOAD_LEN, PAYLOAD_LEN / 2); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "data_lrg_1byte") == 0) { + send_data_pkts(txfd, &daddr, PAYLOAD_LEN, 1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "data_sml_lrg") == 0) { + send_data_pkts(txfd, &daddr, PAYLOAD_LEN / 2, PAYLOAD_LEN); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "data_burst") == 0) { + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(txfd, buf, total_hdr_len + PAYLOAD_LEN, &daddr); + create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); + write_packet(txfd, buf, total_hdr_len + PAYLOAD_LEN, &daddr); + + usleep(100 * 1000); /* 100ms */ + create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); + write_packet(txfd, buf, total_hdr_len + PAYLOAD_LEN, &daddr); + create_packet(buf, PAYLOAD_LEN * 3, 0, PAYLOAD_LEN, 0); + write_packet(txfd, buf, total_hdr_len + PAYLOAD_LEN, &daddr); + + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* ack test */ + } else if (strcmp(testname, "ack") == 0) { + send_ack(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* flags sub-tests */ + } else if (strcmp(testname, "flags_psh") == 0) { + send_flags(txfd, &daddr, 1, 0, 0, 0, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_syn") == 0) { + send_flags(txfd, &daddr, 0, 1, 0, 0, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_rst") == 0) { + send_flags(txfd, &daddr, 0, 0, 1, 0, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_urg") == 0) { + send_flags(txfd, &daddr, 0, 0, 0, 1, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_cwr") == 0) { + send_flags(txfd, &daddr, 0, 0, 0, 0, 1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* tcp sub-tests */ + } else if (strcmp(testname, "tcp_csum") == 0) { + send_changed_checksum(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "tcp_seq") == 0) { + send_changed_seq(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "tcp_ts") == 0) { + send_changed_ts(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "tcp_opt") == 0) { + send_diff_opt(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* ip sub-tests - shared between IPv4 and IPv6 */ + } else if (strcmp(testname, "ip_ecn") == 0) { + send_changed_ECN(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_tos") == 0) { + send_changed_tos(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* ip sub-tests - IPv4 only */ + } else if (strcmp(testname, "ip_csum") == 0) { + send_changed_ip_checksum(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_ttl") == 0) { + send_changed_ttl(txfd, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_opt") == 0) { + send_ip_options(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_frag4") == 0) { + send_fragment4(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_inc") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_INC); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_fixed") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_FIXED); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df0_inc") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF0_INC); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df0_fixed") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF0_FIXED); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_inc_fixed") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_INC_FIXED); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_id_df1_fixed_inc") == 0) { + send_flush_id_case(txfd, &daddr, FLUSH_ID_DF1_FIXED_INC); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* ip sub-tests - IPv6 only */ + } else if (strcmp(testname, "ip_frag6") == 0) { + send_fragment6(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_v6ext_same") == 0) { + send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "ip_v6ext_diff") == 0) { + send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* large sub-tests */ + } else if (strcmp(testname, "large_max") == 0) { + int remainder = max_payload() % calc_mss(); + + send_large(txfd, &daddr, remainder); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "large_rem") == 0) { + int remainder = max_payload() % calc_mss(); + + send_large(txfd, &daddr, remainder + 1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + /* machinery sub-tests */ + } else if (strcmp(testname, "single") == 0) { + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + + create_packet(buf, 0, 0, PAYLOAD_LEN, 0); + write_packet(txfd, buf, total_hdr_len + PAYLOAD_LEN, &daddr); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "capacity") == 0) { + send_capacity(txfd, &daddr); + usleep(fin_delay_us); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + } else { + error(1, 0, "Unknown testcase: %s", testname); + } + + if (close(txfd)) + error(1, errno, "socket close"); +} + +static void gro_receiver(void) +{ + static int correct_payload[NUM_PACKETS]; + int rxfd = -1; + + rxfd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_NONE)); + if (rxfd < 0) + error(1, 0, "socket creation"); + setup_sock_filter(rxfd); + set_timeout(rxfd); + set_rcvbuf(rxfd); + bind_packetsocket(rxfd); + + ksft_ready(); + + memset(correct_payload, 0, sizeof(correct_payload)); + + /* data sub-tests */ + if (strcmp(testname, "data_same") == 0) { + printf("pure data packet of same size: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "data_lrg_sml") == 0) { + printf("large data packets followed by a smaller one: "); + correct_payload[0] = PAYLOAD_LEN * 1.5; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "data_lrg_1byte") == 0) { + printf("large data packet followed by a 1 byte one: "); + correct_payload[0] = PAYLOAD_LEN + 1; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "data_sml_lrg") == 0) { + printf("small data packets followed by a larger one: "); + correct_payload[0] = PAYLOAD_LEN / 2; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "data_burst") == 0) { + printf("two bursts of two data packets: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 2); + + /* ack test */ + } else if (strcmp(testname, "ack") == 0) { + printf("duplicate ack and pure ack: "); + check_recv_pkts(rxfd, correct_payload, 3); + + /* flags sub-tests */ + } else if (strcmp(testname, "flags_psh") == 0) { + correct_payload[0] = PAYLOAD_LEN * 3; + correct_payload[1] = PAYLOAD_LEN * 2; + printf("psh flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "flags_syn") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = 0; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("syn flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "flags_rst") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = 0; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("rst flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "flags_urg") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = 0; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("urg flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "flags_cwr") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN * 2; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("cwr flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); + + /* tcp sub-tests */ + } else if (strcmp(testname, "tcp_csum") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("changed checksum does not coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "tcp_seq") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("Wrong Seq number doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "tcp_ts") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + correct_payload[3] = PAYLOAD_LEN; + printf("Different timestamp doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 4); + } else if (strcmp(testname, "tcp_opt") == 0) { + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + printf("Different options doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + /* ip sub-tests - shared between IPv4 and IPv6 */ + } else if (strcmp(testname, "ip_ecn") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("different ECN doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_tos") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("different tos doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + + /* ip sub-tests - IPv4 only */ + } else if (strcmp(testname, "ip_csum") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + printf("bad ip checksum doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "ip_ttl") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("different ttl doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_opt") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + printf("ip options doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "ip_frag4") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + printf("fragmented ip4 doesn't coalesce: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_id_df1_inc") == 0) { + printf("DF=1, Incrementing - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df1_fixed") == 0) { + printf("DF=1, Fixed - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df0_inc") == 0) { + printf("DF=0, Incrementing - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df0_fixed") == 0) { + printf("DF=0, Fixed - should coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_id_df1_inc_fixed") == 0) { + printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "ip_id_df1_fixed_inc") == 0) { + printf("DF=1, 2 Fixed and one incrementing - should coalesce only first 2 packets: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + + /* ip sub-tests - IPv6 only */ + } else if (strcmp(testname, "ip_frag6") == 0) { + /* GRO doesn't check for ipv6 hop limit when flushing. + * Hence no corresponding test to the ipv4 case. + */ + printf("fragmented ip6 doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "ip_v6ext_same") == 0) { + printf("ipv6 with ext header does coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "ip_v6ext_diff") == 0) { + printf("ipv6 with ext header with different payloads doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 2); + + /* large sub-tests */ + } else if (strcmp(testname, "large_max") == 0) { + int remainder = max_payload() % calc_mss(); + + correct_payload[0] = max_payload(); + correct_payload[1] = remainder; + printf("Shouldn't coalesce if exceed IP max pkt size: "); + check_recv_pkts(rxfd, correct_payload, 2); + } else if (strcmp(testname, "large_rem") == 0) { + int remainder = max_payload() % calc_mss(); + + /* last segment sent individually, doesn't start new segment */ + correct_payload[0] = max_payload() - remainder; + correct_payload[1] = remainder + 1; + correct_payload[2] = remainder + 1; + printf("last segment sent individually: "); + check_recv_pkts(rxfd, correct_payload, 3); + + /* machinery sub-tests */ + } else if (strcmp(testname, "single") == 0) { + printf("single data packet: "); + correct_payload[0] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 1); + } else if (strcmp(testname, "capacity") == 0) { + check_capacity_pkts(rxfd); + + } else { + error(1, 0, "Test case error: unknown testname %s", testname); + } + + if (close(rxfd)) + error(1, 0, "socket close"); +} + +static void parse_args(int argc, char **argv) +{ + static const struct option opts[] = { + { "daddr", required_argument, NULL, 'd' }, + { "dmac", required_argument, NULL, 'D' }, + { "iface", required_argument, NULL, 'i' }, + { "ipv4", no_argument, NULL, '4' }, + { "ipv6", no_argument, NULL, '6' }, + { "ipip", no_argument, NULL, 'e' }, + { "ip6ip6", no_argument, NULL, 'E' }, + { "num-flows", required_argument, NULL, 'n' }, + { "rx", no_argument, NULL, 'r' }, + { "saddr", required_argument, NULL, 's' }, + { "smac", required_argument, NULL, 'S' }, + { "test", required_argument, NULL, 't' }, + { "order-check", no_argument, NULL, 'o' }, + { "verbose", no_argument, NULL, 'v' }, + { 0, 0, 0, 0 } + }; + int c; + + while ((c = getopt_long(argc, argv, "46d:D:eEi:n:rs:S:t:ov", opts, NULL)) != -1) { + switch (c) { + case '4': + proto = PF_INET; + ethhdr_proto = htons(ETH_P_IP); + break; + case '6': + proto = PF_INET6; + ethhdr_proto = htons(ETH_P_IPV6); + break; + case 'e': + ipip = true; + proto = PF_INET; + ethhdr_proto = htons(ETH_P_IP); + break; + case 'E': + ip6ip6 = true; + proto = PF_INET6; + ethhdr_proto = htons(ETH_P_IPV6); + break; + case 'd': + addr4_dst = addr6_dst = optarg; + break; + case 'D': + dmac = optarg; + break; + case 'i': + ifname = optarg; + break; + case 'n': + num_flows = atoi(optarg); + break; + case 'r': + tx_socket = false; + break; + case 's': + addr4_src = addr6_src = optarg; + break; + case 'S': + smac = optarg; + break; + case 't': + testname = optarg; + break; + case 'o': + order_check = true; + break; + case 'v': + verbose = true; + break; + default: + error(1, 0, "%s invalid option %c\n", __func__, c); + break; + } + } +} + +int main(int argc, char **argv) +{ + parse_args(argc, argv); + + if (ipip) { + tcp_offset = ETH_HLEN + sizeof(struct iphdr) * 2; + total_hdr_len = tcp_offset + sizeof(struct tcphdr); + } else if (ip6ip6) { + tcp_offset = ETH_HLEN + sizeof(struct ipv6hdr) * 2; + total_hdr_len = tcp_offset + sizeof(struct tcphdr); + } else if (proto == PF_INET) { + tcp_offset = ETH_HLEN + sizeof(struct iphdr); + total_hdr_len = tcp_offset + sizeof(struct tcphdr); + } else if (proto == PF_INET6) { + tcp_offset = ETH_HLEN + sizeof(struct ipv6hdr); + total_hdr_len = tcp_offset + sizeof(struct tcphdr); + } else { + error(1, 0, "Protocol family is not ipv4 or ipv6"); + } + + read_MAC(src_mac, smac); + read_MAC(dst_mac, dmac); + + if (tx_socket) { + gro_sender(); + } else { + /* Only the receiver exit status determines test success. */ + gro_receiver(); + fprintf(stderr, "Gro::%s test passed.\n", testname); + } + + return 0; +} diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index f528b67639de..7c81d86a7e97 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -13,9 +13,12 @@ from .ksft import KsftFailEx, KsftSkipEx, KsftXfailEx, ksft_pr, ksft_eq, \ from .netns import NetNS, NetNSEnter from .nsim import NetdevSim, NetdevSimDev from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \ - bpftool, ip, ethtool, bpftrace, rand_port, wait_port_listen, wait_file, tool -from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily -from .ynl import NetshaperFamily, DevlinkFamily, PSPFamily + bpftool, ip, ethtool, bpftrace, rand_port, rand_ports, wait_port_listen, \ + wait_file, tool +from .bpf import bpf_map_set, bpf_map_dump, bpf_prog_map_ids +from .ynl import NlError, NlctrlFamily, YnlFamily, \ + EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily +from .ynl import NetshaperFamily, DevlinkFamily, PSPFamily, Netlink __all__ = ["KSRC", "KsftFailEx", "KsftSkipEx", "KsftXfailEx", "ksft_pr", "ksft_eq", @@ -25,9 +28,10 @@ __all__ = ["KSRC", "ksft_run", "ksft_exit", "ksft_variants", "KsftNamedVariant", "NetNS", "NetNSEnter", "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer", - "bpftool", "ip", "ethtool", "bpftrace", "rand_port", + "bpftool", "ip", "ethtool", "bpftrace", "rand_port", "rand_ports", "wait_port_listen", "wait_file", "tool", + "bpf_map_set", "bpf_map_dump", "bpf_prog_map_ids", "NetdevSim", "NetdevSimDev", "NetshaperFamily", "DevlinkFamily", "PSPFamily", "NlError", "YnlFamily", "EthtoolFamily", "NetdevFamily", "RtnlFamily", - "RtnlAddrFamily"] + "NlctrlFamily", "RtnlAddrFamily", "Netlink"] diff --git a/tools/testing/selftests/net/lib/py/bpf.py b/tools/testing/selftests/net/lib/py/bpf.py new file mode 100644 index 000000000000..beb6bf2896a8 --- /dev/null +++ b/tools/testing/selftests/net/lib/py/bpf.py @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: GPL-2.0 + +""" +BPF helper utilities for kernel selftests. + +Provides common operations for interacting with BPF maps and programs +via bpftool, used by XDP and other BPF-based test files. +""" + +from .utils import bpftool + +def _format_hex_bytes(value): + """ + Helper function that converts an integer into a formatted hexadecimal byte string. + + Args: + value: An integer representing the number to be converted. + + Returns: + A string representing hexadecimal equivalent of value, with bytes separated by spaces. + """ + hex_str = value.to_bytes(4, byteorder='little', signed=True) + return ' '.join(f'{byte:02x}' for byte in hex_str) + + +def bpf_map_set(map_name, key, value): + """ + Updates an XDP map with a given key-value pair using bpftool. + + Args: + map_name: The name of the XDP map to update. + key: The key to update in the map, formatted as a hexadecimal string. + value: The value to associate with the key, formatted as a hexadecimal string. + """ + key_formatted = _format_hex_bytes(key) + value_formatted = _format_hex_bytes(value) + bpftool( + f"map update name {map_name} key hex {key_formatted} value hex {value_formatted}" + ) + +def bpf_map_dump(map_id): + """Dump all entries of a BPF array map. + + Args: + map_id: Numeric map ID (as returned by bpftool prog show). + + Returns: + A dict mapping formatted key (int) to formatted value (int). + """ + raw = bpftool(f"map dump id {map_id}", json=True) + return {e["formatted"]["key"]: e["formatted"]["value"] for e in raw} + + +def bpf_prog_map_ids(prog_id): + """Get the map name-to-ID mapping for a loaded BPF program. + + Args: + prog_id: Numeric program ID. + + Returns: + A dict mapping map name (str) to map ID (int). + """ + map_ids = bpftool(f"prog show id {prog_id}", json=True)["map_ids"] + maps = {} + for mid in map_ids: + name = bpftool(f"map show id {mid}", json=True)["name"] + maps[name] = mid + return maps diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 6cdfb8afccb5..81287c2daff0 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -1,7 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 +import fnmatch import functools +import getopt import inspect +import os import signal import sys import time @@ -31,6 +34,45 @@ class KsftTerminate(KeyboardInterrupt): pass +class _KsftArgs: + def __init__(self): + self.list_tests = False + self.filters = [] + + try: + opts, _ = getopt.getopt(sys.argv[1:], 'hlt:T:') + except getopt.GetoptError as e: + print(e, file=sys.stderr) + sys.exit(1) + + for opt, val in opts: + if opt == '-h': + print(f"Usage: {sys.argv[0]} [-h|-l] [-t|-T name]\n" + f"\t-h print help\n" + f"\t-l list tests (filtered, if filters were specified)\n" + f"\t-t name include test\n" + f"\t-T name exclude test", + file=sys.stderr) + sys.exit(0) + elif opt == '-l': + self.list_tests = True + elif opt == '-t': + self.filters.append((True, val)) + elif opt == '-T': + self.filters.append((False, val)) + + +@functools.lru_cache() +def _ksft_supports_color(): + if os.environ.get("NO_COLOR") is not None: + return False + if not hasattr(sys.stdout, "isatty") or not sys.stdout.isatty(): + return False + if os.environ.get("TERM") == "dumb": + return False + return True + + def ksft_pr(*objs, **kwargs): """ Print logs to stdout. @@ -165,6 +207,14 @@ def ktap_result(ok, cnt=1, case_name="", comment=""): res += "." + case_name if comment: res += " # " + comment + if _ksft_supports_color(): + if comment.startswith(("SKIP", "XFAIL")): + color = "\033[33m" + elif ok: + color = "\033[32m" + else: + color = "\033[31m" + res = color + res + "\033[0m" print(res, flush=True) @@ -278,8 +328,26 @@ def _ksft_intr(signum, frame): ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...") -def _ksft_generate_test_cases(cases, globs, case_pfx, args): - """Generate a flat list of (func, args, name) tuples""" +def _ksft_name_matches(name, pattern): + if '*' in pattern or '?' in pattern or '[' in pattern: + return fnmatch.fnmatchcase(name, pattern) + return name == pattern + + +def _ksft_test_enabled(name, filters): + has_positive = False + for include, pattern in filters: + has_positive |= include + if _ksft_name_matches(name, pattern): + return include + return not has_positive + + +def _ksft_generate_test_cases(cases, globs, case_pfx, args, cli_args): + """Generate a filtered list of (func, args, name) tuples. + + If -l is given, prints matching test names and exits. + """ cases = cases or [] test_cases = [] @@ -309,11 +377,22 @@ def _ksft_generate_test_cases(cases, globs, case_pfx, args): else: test_cases.append((func, args, func.__name__)) + if cli_args.filters: + test_cases = [tc for tc in test_cases + if _ksft_test_enabled(tc[2], cli_args.filters)] + + if cli_args.list_tests: + for _, _, name in test_cases: + print(name) + sys.exit(0) + return test_cases def ksft_run(cases=None, globs=None, case_pfx=None, args=()): - test_cases = _ksft_generate_test_cases(cases, globs, case_pfx, args) + cli_args = _KsftArgs() + test_cases = _ksft_generate_test_cases(cases, globs, case_pfx, args, + cli_args) global term_cnt term_cnt = 0 @@ -321,10 +400,13 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} + global KSFT_RESULT + if KSFT_RESULT is not None: + raise RuntimeError("ksft_run() can't be called multiple times.") + print("TAP version 13", flush=True) print("1.." + str(len(test_cases)), flush=True) - global KSFT_RESULT cnt = 0 stop = False for func, args, name in test_cases: diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 85884f3e827b..6c44a3d2bbf7 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -9,9 +9,17 @@ import subprocess import time +class CmdInitFailure(Exception): + """ Command failed to start. Only raised by bkg(). """ + def __init__(self, msg, cmd_obj): + super().__init__(msg + "\n" + repr(cmd_obj)) + self.cmd = cmd_obj + + class CmdExitFailure(Exception): + """ Command failed (returned non-zero exit code). """ def __init__(self, msg, cmd_obj): - super().__init__(msg) + super().__init__(msg + "\n" + repr(cmd_obj)) self.cmd = cmd_obj @@ -76,30 +84,37 @@ class cmd: msg = fd_read_timeout(rfd, ksft_wait) os.close(rfd) if not msg: - raise Exception("Did not receive ready message") + terminate = self.proc.poll() is None + self._process_terminate(terminate=terminate, timeout=1) + raise CmdInitFailure("Did not receive ready message", self) if not background: self.process(terminate=False, fail=fail, timeout=timeout) - def process(self, terminate=True, fail=None, timeout=5): - if fail is None: - fail = not terminate - - if self.ksft_term_fd: - os.write(self.ksft_term_fd, b"1") + def _process_terminate(self, terminate, timeout): if terminate: self.proc.terminate() - stdout, stderr = self.proc.communicate(timeout) + stdout, stderr = self.proc.communicate(timeout=timeout) self.stdout = stdout.decode("utf-8") self.stderr = stderr.decode("utf-8") self.proc.stdout.close() self.proc.stderr.close() self.ret = self.proc.returncode + return stdout, stderr + + def process(self, terminate=True, fail=None, timeout=5): + if fail is None: + fail = not terminate + + if self.ksft_term_fd: + os.write(self.ksft_term_fd, b"1") + + stdout, stderr = self._process_terminate(terminate=terminate, + timeout=timeout) if self.proc.returncode != 0 and fail: if len(stderr) > 0 and stderr[-1] == "\n": stderr = stderr[:-1] - raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % - (self.proc.args, stdout, stderr), self) + raise CmdExitFailure("Command failed", self) def __repr__(self): def str_fmt(name, s): @@ -159,8 +174,11 @@ class bkg(cmd): return self def __exit__(self, ex_type, ex_value, ex_tb): - # Force termination on exception - terminate = self.terminate or (self._exit_wait and ex_type is not None) + terminate = self.terminate + # Force termination on exception, but only if bkg() didn't already exit + # since forcing termination silences failures with fail=None + if self.proc.poll() is None: + terminate = terminate or (self._exit_wait and ex_type is not None) return self.process(terminate=terminate, fail=self.check_fail) @@ -240,8 +258,9 @@ def bpftrace(expr, json=None, ns=None, host=None, timeout=None): cmd_arr += ['-f', 'json', '-q'] if timeout: expr += ' interval:s:' + str(timeout) + ' { exit(); }' + timeout += 20 cmd_arr += ['-e', expr] - cmd_obj = cmd(cmd_arr, ns=ns, host=host, shell=False) + cmd_obj = cmd(cmd_arr, ns=ns, host=host, shell=False, timeout=timeout) if json: # bpftrace prints objects as lines ret = {} @@ -263,9 +282,27 @@ def rand_port(stype=socket.SOCK_STREAM): """ Get a random unprivileged port. """ - with socket.socket(socket.AF_INET6, stype) as s: - s.bind(("", 0)) - return s.getsockname()[1] + return rand_ports(1, stype)[0] + + +def rand_ports(count, stype=socket.SOCK_STREAM): + """ + Get a unique set of random unprivileged ports. + """ + sockets = [] + ports = [] + + try: + for _ in range(count): + s = socket.socket(socket.AF_INET6, stype) + sockets.append(s) + s.bind(("", 0)) + ports.append(s.getsockname()[1]) + finally: + for s in sockets: + s.close() + + return ports def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5): diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index 32c223e93b2c..2e567062aa6c 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -13,20 +13,27 @@ try: SPEC_PATH = KSFT_DIR / "net/lib/specs" sys.path.append(tools_full_path.as_posix()) - from net.lib.ynl.pyynl.lib import YnlFamily, NlError + from net.lib.ynl.pyynl.lib import YnlFamily, NlError, NlPolicy, Netlink else: # Running in tree tools_full_path = KSRC / "tools" SPEC_PATH = KSRC / "Documentation/netlink/specs" sys.path.append(tools_full_path.as_posix()) - from net.ynl.pyynl.lib import YnlFamily, NlError + from net.ynl.pyynl.lib import YnlFamily, NlError, NlPolicy, Netlink except ModuleNotFoundError as e: ksft_pr("Failed importing `ynl` library from kernel sources") ksft_pr(str(e)) ktap_result(True, comment="SKIP") sys.exit(4) +__all__ = [ + "NlError", "NlPolicy", "Netlink", "YnlFamily", "SPEC_PATH", + "EthtoolFamily", "RtnlFamily", "RtnlAddrFamily", + "NetdevFamily", "NetshaperFamily", "NlctrlFamily", "DevlinkFamily", + "PSPFamily", +] + # # Wrapper classes, loading the right specs # Set schema='' to avoid jsonschema validation, it's slow @@ -57,6 +64,13 @@ class NetshaperFamily(YnlFamily): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), schema='', recv_size=recv_size) + +class NlctrlFamily(YnlFamily): + def __init__(self, recv_size=0): + super().__init__((SPEC_PATH / Path('nlctrl.yaml')).as_posix(), + schema='', recv_size=recv_size) + + class DevlinkFamily(YnlFamily): def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(), diff --git a/tools/testing/selftests/net/lib/xdp_metadata.bpf.c b/tools/testing/selftests/net/lib/xdp_metadata.bpf.c new file mode 100644 index 000000000000..f71f59215239 --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_metadata.bpf.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +enum { + XDP_PORT = 1, + XDP_PROTO = 4, +} xdp_map_setup_keys; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __s32); +} map_xdp_setup SEC(".maps"); + +/* RSS hash results: key 0 = hash, key 1 = hash type, + * key 2 = packet count, key 3 = error count. + */ +enum { + RSS_KEY_HASH = 0, + RSS_KEY_TYPE = 1, + RSS_KEY_PKT_CNT = 2, + RSS_KEY_ERR_CNT = 3, +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 4); +} map_rss SEC(".maps"); + +/* Mirror of enum xdp_rss_hash_type from include/net/xdp.h. + * Needed because the enum is not part of UAPI headers. + */ +enum xdp_rss_hash_type { + XDP_RSS_L3_IPV4 = 1U << 0, + XDP_RSS_L3_IPV6 = 1U << 1, + XDP_RSS_L3_DYNHDR = 1U << 2, + XDP_RSS_L4 = 1U << 3, + XDP_RSS_L4_TCP = 1U << 4, + XDP_RSS_L4_UDP = 1U << 5, + XDP_RSS_L4_SCTP = 1U << 6, + XDP_RSS_L4_IPSEC = 1U << 7, + XDP_RSS_L4_ICMP = 1U << 8, +}; + +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; + +static __always_inline __u16 get_dest_port(void *l4, void *data_end, + __u8 protocol) +{ + if (protocol == IPPROTO_UDP) { + struct udphdr *udp = l4; + + if ((void *)(udp + 1) > data_end) + return 0; + return udp->dest; + } else if (protocol == IPPROTO_TCP) { + struct tcphdr *tcp = l4; + + if ((void *)(tcp + 1) > data_end) + return 0; + return tcp->dest; + } + + return 0; +} + +SEC("xdp") +int xdp_rss_hash(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + enum xdp_rss_hash_type rss_type = 0; + struct ethhdr *eth = data; + __u8 l4_proto = 0; + __u32 hash = 0; + __u32 key, val; + void *l4 = NULL; + __u32 *cnt; + int ret; + + if ((void *)(eth + 1) > data_end) + return XDP_PASS; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (void *)(eth + 1); + + if ((void *)(iph + 1) > data_end) + return XDP_PASS; + l4_proto = iph->protocol; + l4 = (void *)(iph + 1); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (void *)(eth + 1); + + if ((void *)(ip6h + 1) > data_end) + return XDP_PASS; + l4_proto = ip6h->nexthdr; + l4 = (void *)(ip6h + 1); + } + + if (!l4) + return XDP_PASS; + + /* Filter on the configured protocol (map_xdp_setup key XDP_PROTO). + * When set, only process packets matching the requested L4 protocol. + */ + key = XDP_PROTO; + __s32 *proto_cfg = bpf_map_lookup_elem(&map_xdp_setup, &key); + + if (proto_cfg && *proto_cfg != 0 && l4_proto != (__u8)*proto_cfg) + return XDP_PASS; + + /* Filter on the configured port (map_xdp_setup key XDP_PORT). + * Only applies to protocols with ports (UDP, TCP). + */ + key = XDP_PORT; + __s32 *port_cfg = bpf_map_lookup_elem(&map_xdp_setup, &key); + + if (port_cfg && *port_cfg != 0) { + __u16 dest = get_dest_port(l4, data_end, l4_proto); + + if (!dest || bpf_ntohs(dest) != (__u16)*port_cfg) + return XDP_PASS; + } + + ret = bpf_xdp_metadata_rx_hash(ctx, &hash, &rss_type); + if (ret < 0) { + key = RSS_KEY_ERR_CNT; + cnt = bpf_map_lookup_elem(&map_rss, &key); + if (cnt) + __sync_fetch_and_add(cnt, 1); + return XDP_PASS; + } + + key = RSS_KEY_HASH; + bpf_map_update_elem(&map_rss, &key, &hash, BPF_ANY); + + key = RSS_KEY_TYPE; + val = (__u32)rss_type; + bpf_map_update_elem(&map_rss, &key, &val, BPF_ANY); + + key = RSS_KEY_PKT_CNT; + cnt = bpf_map_lookup_elem(&map_rss, &key); + if (cnt) + __sync_fetch_and_add(cnt, 1); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/macvlan_mcast_shared_mac.sh b/tools/testing/selftests/net/macvlan_mcast_shared_mac.sh new file mode 100755 index 000000000000..ff5b89347247 --- /dev/null +++ b/tools/testing/selftests/net/macvlan_mcast_shared_mac.sh @@ -0,0 +1,93 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test multicast delivery to macvlan bridge ports when the source MAC +# matches the macvlan's own MAC address (e.g., VRRP virtual MAC shared +# across multiple hosts). +# +# Topology: +# +# NS_SRC NS_BRIDGE +# veth_src (SHARED_MAC) <-----> veth_dst +# | +# +-- macvlan0 (bridge mode, SHARED_MAC) +# +# A multicast packet sent from NS_SRC with source MAC equal to +# macvlan0's MAC must still be delivered to macvlan0. + +source lib.sh + +SHARED_MAC="00:00:5e:00:01:01" +MCAST_ADDR="239.0.0.1" + +setup() { + setup_ns NS_SRC NS_BRIDGE + + ip -net "${NS_BRIDGE}" link add veth_dst type veth \ + peer name veth_src netns "${NS_SRC}" + + ip -net "${NS_SRC}" link set veth_src address "${SHARED_MAC}" + ip -net "${NS_SRC}" link set veth_src up + ip -net "${NS_SRC}" addr add 192.168.1.1/24 dev veth_src + + ip -net "${NS_BRIDGE}" link set veth_dst up + + ip -net "${NS_BRIDGE}" link add macvlan0 link veth_dst \ + type macvlan mode bridge + ip -net "${NS_BRIDGE}" link set macvlan0 address "${SHARED_MAC}" + ip -net "${NS_BRIDGE}" link set macvlan0 up + ip -net "${NS_BRIDGE}" addr add 192.168.1.2/24 dev macvlan0 + + # Accept all multicast so the mc_filter passes for any group. + ip -net "${NS_BRIDGE}" link set macvlan0 allmulticast on +} + +cleanup() { + rm -f "${CAPFILE}" "${CAPOUT}" + cleanup_ns "${NS_SRC}" "${NS_BRIDGE}" +} + +test_macvlan_mcast_shared_mac() { + CAPFILE=$(mktemp) + CAPOUT=$(mktemp) + + echo "Testing multicast delivery to macvlan with shared source MAC" + + # Listen for one ICMP packet on macvlan0. + timeout 5s ip netns exec "${NS_BRIDGE}" \ + tcpdump -i macvlan0 -c 1 -w "${CAPFILE}" icmp &> "${CAPOUT}" & + local pid=$! + if ! slowwait 1 grep -qs "listening" "${CAPOUT}"; then + echo "[FAIL] tcpdump did not start listening" + return "${ksft_fail}" + fi + + # Send multicast ping from NS_SRC; source MAC equals macvlan0's MAC. + ip netns exec "${NS_SRC}" \ + ping -W 0.1 -c 3 -I veth_src "${MCAST_ADDR}" &> /dev/null + + wait "${pid}" + + local count + count=$(tcpdump -r "${CAPFILE}" 2>/dev/null | wc -l) + if [[ "${count}" -ge 1 ]]; then + echo "[ OK ]" + return "${ksft_pass}" + else + echo "[FAIL] expected at least 1 ICMP packet on macvlan0," \ + "got ${count}" + return "${ksft_fail}" + fi +} + +if [ ! -x "$(command -v tcpdump)" ]; then + echo "SKIP: Could not run test without tcpdump tool" + exit "${ksft_skip}" +fi + +trap cleanup EXIT + +setup +test_macvlan_mcast_shared_mac + +exit $? diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index a3144d7298a5..beec41f6662a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -4343,13 +4343,13 @@ endpoint_tests() chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 [ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1 - pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal + pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal wait_mpj 4 chk_subflow_nr "after re-add ID 0" 3 chk_mptcp_info subflows 3 subflows 3 chk_mptcp_info add_addr_signal 3 add_addr_accepted 2 - pm_nl_del_endpoint $ns1 99 10.0.1.1 + pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after re-delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 diff --git a/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh b/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh index d16de13fe5a7..1dc7b0450145 100755 --- a/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh +++ b/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh @@ -190,13 +190,13 @@ table inet filter { } EOF - timeout "$timeout" ip netns exec "$nsrouter" socat -u "$socat_ipproto" udp-listen:12345,fork,ip-transparent,reuseport udp:"$ns1_ip_port",ip-transparent,reuseport,bind="$ns2_ip_port" 2>/dev/null & + timeout "$timeout" ip netns exec "$nsrouter" socat -u "$socat_ipproto" udp-listen:12345,fork,ip-transparent,reuseport,shut-none udp:"$ns1_ip_port",ip-transparent,reuseport,bind="$ns2_ip_port",shut-none 2>/dev/null & local tproxy_pid=$! - timeout "$timeout" ip netns exec "$ns2" socat "$socat_ipproto" udp-listen:8080,fork SYSTEM:"echo PONG_NS2" 2>/dev/null & + timeout "$timeout" ip netns exec "$ns2" socat "$socat_ipproto" udp-listen:8080,fork,shut-none SYSTEM:"echo PONG_NS2" 2>/dev/null & local server2_pid=$! - timeout "$timeout" ip netns exec "$ns3" socat "$socat_ipproto" udp-listen:8080,fork SYSTEM:"echo PONG_NS3" 2>/dev/null & + timeout "$timeout" ip netns exec "$ns3" socat "$socat_ipproto" udp-listen:8080,fork,shut-none SYSTEM:"echo PONG_NS3" 2>/dev/null & local server3_pid=$! busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter" 12345 "-u" @@ -205,7 +205,7 @@ EOF local result # request from ns1 to ns2 (forwarded traffic) - result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",sourceport=18888) + result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",sourceport=18888,shut-none) if [ "$result" == "$expect_ns1_ns2" ] ;then echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns2" else @@ -214,7 +214,7 @@ EOF fi # request from ns1 to ns3 (forwarded traffic) - result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port") + result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port",shut-none) if [ "$result" = "$expect_ns1_ns3" ] ;then echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns3" else @@ -223,7 +223,7 @@ EOF fi # request from nsrouter to ns2 (localy originated traffic) - result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port") + result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",shut-none) if [ "$result" == "$expect_nsrouter_ns2" ] ;then echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns2" else @@ -232,7 +232,7 @@ EOF fi # request from nsrouter to ns3 (localy originated traffic) - result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port") + result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port",shut-none) if [ "$result" = "$expect_nsrouter_ns3" ] ;then echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns3" else diff --git a/tools/testing/selftests/net/nk_qlease.py b/tools/testing/selftests/net/nk_qlease.py new file mode 100755 index 000000000000..a84a73ff4eda --- /dev/null +++ b/tools/testing/selftests/net/nk_qlease.py @@ -0,0 +1,2109 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import errno +import time +from lib.py import ( + ksft_run, + ksft_exit, + ksft_eq, + ksft_ne, + ksft_in, + ksft_not_in, + ksft_raises, +) +from lib.py import ( + NetNS, + NetNSEnter, + EthtoolFamily, + NetdevFamily, + RtnlFamily, + NetdevSimDev, +) +from lib.py import ( + NlError, + Netlink, + cmd, + defer, + ip, +) + + +def wait_until(cond, timeout=2.0, interval=0.05): + deadline = time.monotonic() + timeout + while not cond(): + if time.monotonic() >= deadline: + return + time.sleep(interval) + + +def create_netkit(rxqueues, mode="l2"): + all_links = ip("-d link show", json=True) + old_idxs = { + link["ifindex"] + for link in all_links + if link.get("linkinfo", {}).get("info_kind") == "netkit" + } + + rtnl = RtnlFamily() + rtnl.newlink( + { + "linkinfo": { + "kind": "netkit", + "data": { + "mode": mode, + "policy": "forward", + "peer-policy": "forward", + }, + }, + "num-rx-queues": rxqueues, + }, + flags=[Netlink.NLM_F_CREATE, Netlink.NLM_F_EXCL], + ) + + all_links = ip("-d link show", json=True) + nk_links = [ + link + for link in all_links + if link.get("linkinfo", {}).get("info_kind") == "netkit" + and link["ifindex"] not in old_idxs + ] + nk_links.sort(key=lambda x: x["ifindex"]) + return ( + nk_links[1]["ifname"], + nk_links[1]["ifindex"], + nk_links[0]["ifname"], + nk_links[0]["ifindex"], + ) + + +def create_netkit_single(rxqueues): + rtnl = RtnlFamily() + rtnl.newlink( + { + "linkinfo": { + "kind": "netkit", + "data": { + "mode": "l2", + "pairing": "single", + }, + }, + "num-rx-queues": rxqueues, + }, + flags=[Netlink.NLM_F_CREATE, Netlink.NLM_F_EXCL], + ) + + all_links = ip("-d link show", json=True) + nk_links = [ + link + for link in all_links + if link.get("linkinfo", {}).get("info_kind") == "netkit" + and "UP" not in link.get("flags", []) + ] + return nk_links[0]["ifname"], nk_links[0]["ifindex"] + + +def test_remove_phys(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + nk_queue_id = result["id"] + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["ifindex"], nk_guest_idx) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + nsimdev.remove() + wait_until(lambda: cmd(f"ip link show dev {nk_host}", fail=False).ret != 0) + ret = cmd(f"ip link show dev {nk_host}", fail=False) + ksft_ne(ret.ret, 0) + + +def test_double_lease(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=3) + defer(cmd, f"ip link del dev {nk_host}") + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EBUSY) + + +def test_virtual_lessor(netns) -> None: + nk_host_a, _, nk_guest_a, nk_guest_a_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_a}") + ip(f"link set dev {nk_host_a} up") + ip(f"link set dev {nk_guest_a} up") + + nk_host_b, _, nk_guest_b, nk_guest_b_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_b}") + + ip(f"link set dev {nk_guest_b} netns {netns.name}") + ip(f"link set dev {nk_host_b} up") + ip(f"link set dev {nk_guest_b} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_b_idx, + "type": "rx", + "lease": { + "ifindex": nk_guest_a_idx, + "queue": {"id": 0, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_phys_lessee(_netns) -> None: + nsimdev_a = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev_a.remove) + nsim_a = nsimdev_a.nsims[0] + ip(f"link set dev {nsim_a.ifname} up") + + nsimdev_b = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev_b.remove) + nsim_b = nsimdev_b.nsims[0] + ip(f"link set dev {nsim_b.ifname} up") + + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nsim_a.ifindex, + "type": "rx", + "lease": { + "ifindex": nsim_b.ifindex, + "queue": {"id": 0, "type": "rx"}, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_different_lessors(netns) -> None: + nsimdev_a = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev_a.remove) + nsim_a = nsimdev_a.nsims[0] + ip(f"link set dev {nsim_a.ifname} up") + + nsimdev_b = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev_b.remove) + nsim_b = nsimdev_b.nsims[0] + ip(f"link set dev {nsim_b.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=3) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim_a.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim_b.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EOPNOTSUPP) + + +def test_queue_out_of_range(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.ERANGE) + + +def test_resize_leased(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + ethnl = EthtoolFamily() + with ksft_raises(NlError) as e: + ethnl.channels_set({"header": {"dev-index": nsim.ifindex}, "combined-count": 1}) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_self_lease(_netns) -> None: + nk_host, _, _, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nk_guest_idx, + "queue": {"id": 0, "type": "rx"}, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_veth_queue_create(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + ip("link add veth0 type veth peer name veth1") + defer(cmd, "ip link del dev veth0", fail=False) + + all_links = ip("-d link show", json=True) + veth_peer = [ + link + for link in all_links + if link.get("ifname") == "veth1" + ] + veth_peer_idx = veth_peer[0]["ifindex"] + + ip(f"link set dev veth1 netns {netns.name}") + ip("link set dev veth0 up") + ip("link set dev veth1 up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": veth_peer_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_create_tx_type(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "tx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_create_primary(_netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, nk_host_idx, _, _ = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_host} up") + + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_host_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EOPNOTSUPP) + + +def test_create_limit(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=1) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_link_flap_phys(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}") + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + nk_queue_id = result["id"] + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + # Link flap the physical device + ip(f"link set dev {nsim.ifname} down") + ip(f"link set dev {nsim.ifname} up") + + # Verify lease survives the flap + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + +def test_queue_get_virtual(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}") + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + nk_queue_id = result["id"] + + # queue-get on virtual device's leased queue should not show lease + # info (lease info is only shown from the physical device's side) + queue_info = netdevnl.queue_get( + {"ifindex": nk_guest_idx, "id": nk_queue_id, "type": "rx"} + ) + ksft_eq(queue_info["id"], nk_queue_id) + ksft_eq(queue_info["ifindex"], nk_guest_idx) + ksft_not_in("lease", queue_info) + + # Default queue (not leased) also has no lease info + queue_info = netdevnl.queue_get( + {"ifindex": nk_guest_idx, "id": 0, "type": "rx"} + ) + ksft_not_in("lease", queue_info) + + +def test_remove_virt_first(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], result["id"]) + + # Delete netkit (virtual device removed first, physical stays) + cmd(f"ip link del dev {nk_host}") + + # Verify lease is cleaned up on physical device + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_not_in("lease", queue_info) + + +def test_multiple_leases(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=3) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=4) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + r1 = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + r2 = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + ksft_eq(r1["id"], 1) + ksft_eq(r2["id"], 2) + + # Verify both leases visible on physical device + netdevnl = NetdevFamily() + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_in("lease", q1) + ksft_in("lease", q2) + ksft_eq(q1["lease"]["ifindex"], nk_guest_idx) + ksft_eq(q2["lease"]["ifindex"], nk_guest_idx) + ksft_eq(q1["lease"]["queue"]["id"], r1["id"]) + ksft_eq(q2["lease"]["queue"]["id"], r2["id"]) + + +def test_lease_queue_tx_type(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "tx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_invalid_netns(netns) -> None: + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": 1, + "queue": {"id": 0, "type": "rx"}, + "netns-id": 999, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.ENONET) + + +def test_invalid_phys_ifindex(netns) -> None: + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": 99999, + "queue": {"id": 0, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.ENODEV) + + +def test_multi_netkit_remove_phys(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=3) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + # Create two netkit pairs, each leasing a different physical queue + nk_host_a, _, nk_guest_a, nk_guest_a_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_a}", fail=False) + + nk_host_b, _, nk_guest_b, nk_guest_b_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_b}", fail=False) + + ip(f"link set dev {nk_guest_a} netns {netns.name}") + ip(f"link set dev {nk_host_a} up") + ip(f"link set dev {nk_guest_a} up", ns=netns) + + ip(f"link set dev {nk_guest_b} netns {netns.name}") + ip(f"link set dev {nk_host_b} up") + ip(f"link set dev {nk_guest_b} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_guest_a_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + netdevnl.queue_create( + { + "ifindex": nk_guest_b_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + # Removing the physical device should take down both netkit pairs + nsimdev.remove() + wait_until(lambda: cmd(f"ip link show dev {nk_host_a}", fail=False).ret != 0 + and cmd(f"ip link show dev {nk_host_b}", fail=False).ret != 0) + ret = cmd(f"ip link show dev {nk_host_a}", fail=False) + ksft_ne(ret.ret, 0) + ret = cmd(f"ip link show dev {nk_host_b}", fail=False) + ksft_ne(ret.ret, 0) + + +def test_single_remove_phys(_netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_name, nk_idx = create_netkit_single(rxqueues=2) + defer(cmd, f"ip link del dev {nk_name}", fail=False) + + ip(f"link set dev {nk_name} up") + + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + + # Removing the physical device should take down the single netkit device + nsimdev.remove() + wait_until(lambda: cmd(f"ip link show dev {nk_name}", fail=False).ret != 0) + ret = cmd(f"ip link show dev {nk_name}", fail=False) + ksft_ne(ret.ret, 0) + + +def test_link_flap_virt(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}") + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + nk_queue_id = result["id"] + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + # Link flap the virtual (netkit) device + ip(f"link set dev {nk_guest} down", ns=netns) + ip(f"link set dev {nk_guest} up", ns=netns) + + # Verify lease survives the virtual device flap + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + +def test_phys_queue_no_lease(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}") + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + # Physical queue 0 (not leased) should have no lease info + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 0, "type": "rx"} + ) + ksft_not_in("lease", queue_info) + + # Physical queue 1 (leased) should have lease info + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + + +def test_same_ns_lease(_netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_name, nk_idx = create_netkit_single(rxqueues=2) + defer(cmd, f"ip link del dev {nk_name}", fail=False) + + ip(f"link set dev {nk_name} up") + + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + ksft_eq(result["id"], 1) + + # Same namespace: lease info should NOT have netns-id + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["ifindex"], nk_idx) + ksft_eq(queue_info["lease"]["queue"]["id"], result["id"]) + ksft_not_in("netns-id", queue_info["lease"]) + + +def test_resize_after_unlease(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + # Resize should fail while lease is active + ethnl = EthtoolFamily() + with ksft_raises(NlError) as e: + ethnl.channels_set({"header": {"dev-index": nsim.ifindex}, "combined-count": 1}) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + # Delete netkit, clearing the lease + cmd(f"ip link del dev {nk_host}") + + # Resize should now succeed + ethnl.channels_set({"header": {"dev-index": nsim.ifindex}, "combined-count": 1}) + + +def test_lease_queue_zero(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 0, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 0, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], result["id"]) + + +def test_release_and_reuse(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + src_queue = 1 + + # First lease + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + + # Delete netkit, freeing the lease + cmd(f"ip link del dev {nk_host}") + + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_not_in("lease", queue_info) + + # Re-create netkit and lease the same physical queue again + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)): + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], result["id"]) + + +def test_two_netkits_same_queue(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host_a, _, nk_guest_a, nk_guest_a_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_a}", fail=False) + + nk_host_b, _, nk_guest_b, nk_guest_b_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_b}", fail=False) + + ip(f"link set dev {nk_guest_a} netns {netns.name}") + ip(f"link set dev {nk_host_a} up") + ip(f"link set dev {nk_guest_a} up", ns=netns) + + ip(f"link set dev {nk_guest_b} netns {netns.name}") + ip(f"link set dev {nk_host_b} up") + ip(f"link set dev {nk_guest_b} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_a_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + with ksft_raises(NlError) as e: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_b_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EBUSY) + + +def test_l3_mode_lease(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2, mode="l3") + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + result = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["ifindex"], nk_guest_idx) + ksft_eq(queue_info["lease"]["queue"]["id"], result["id"]) + + +def test_single_double_lease(_netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_name, nk_idx = create_netkit_single(rxqueues=3) + defer(cmd, f"ip link del dev {nk_name}", fail=False) + + ip(f"link set dev {nk_name} up") + + netdevnl = NetdevFamily() + result = netdevnl.queue_create( + { + "ifindex": nk_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + ksft_eq(result["id"], 1) + + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EBUSY) + + +def test_single_different_lessors(_netns) -> None: + nsimdev_a = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev_a.remove) + nsim_a = nsimdev_a.nsims[0] + ip(f"link set dev {nsim_a.ifname} up") + + nsimdev_b = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev_b.remove) + nsim_b = nsimdev_b.nsims[0] + ip(f"link set dev {nsim_b.ifname} up") + + nk_name, nk_idx = create_netkit_single(rxqueues=3) + defer(cmd, f"ip link del dev {nk_name}", fail=False) + + ip(f"link set dev {nk_name} up") + + netdevnl = NetdevFamily() + netdevnl.queue_create( + { + "ifindex": nk_idx, + "type": "rx", + "lease": { + "ifindex": nsim_a.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + + with ksft_raises(NlError) as e: + netdevnl.queue_create( + { + "ifindex": nk_idx, + "type": "rx", + "lease": { + "ifindex": nsim_b.ifindex, + "queue": {"id": 1, "type": "rx"}, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EOPNOTSUPP) + + +def test_cross_ns_netns_id(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_in("netns-id", queue_info["lease"]) + + +def test_delete_guest_netns(_netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + test_ns = NetNS() + ip("netns set init 0", ns=test_ns) + ip("link set lo up", ns=test_ns) + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {test_ns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=test_ns) + + src_queue = 1 + with NetNSEnter(str(test_ns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + + del test_ns + wait_until(lambda: "lease" not in netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"})) + + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_not_in("lease", queue_info) + + ret = cmd(f"ip link show dev {nk_host}", fail=False) + ksft_ne(ret.ret, 0) + + +def test_move_guest_netns(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + result = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + nk_queue_id = result["id"] + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + new_ns = NetNS() + defer(new_ns.__del__) + ip(f"link set dev {nk_guest} netns {new_ns.name}", ns=netns) + + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + +def test_resize_phys_no_reduction(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + ethnl = EthtoolFamily() + ethnl.channels_set( + {"header": {"dev-index": nsim.ifindex}, "combined-count": 2} + ) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + + +def test_delete_one_netkit_of_two(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=3) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host_a, _, nk_guest_a, nk_guest_a_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_a}", fail=False) + + nk_host_b, _, nk_guest_b, nk_guest_b_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_b}", fail=False) + + ip(f"link set dev {nk_guest_a} netns {netns.name}") + ip(f"link set dev {nk_host_a} up") + ip(f"link set dev {nk_guest_a} up", ns=netns) + + ip(f"link set dev {nk_guest_b} netns {netns.name}") + ip(f"link set dev {nk_host_b} up") + ip(f"link set dev {nk_guest_b} up", ns=netns) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_a_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_b_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + netdevnl = NetdevFamily() + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_in("lease", q1) + ksft_in("lease", q2) + + cmd(f"ip link del dev {nk_host_a}") + + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_not_in("lease", q1) + ksft_in("lease", q2) + + +def test_bind_rx_leased_phys_queue(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + netdevnl = NetdevFamily() + with ksft_raises(NlError) as e: + netdevnl.bind_rx( + { + "ifindex": nsim.ifindex, + "fd": 0, + "queues": [ + {"id": 0, "type": "rx"}, + {"id": 1, "type": "rx"}, + ], + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EOPNOTSUPP) + + +def test_resize_phys_shrink_past_leased(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=4) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + ethnl = EthtoolFamily() + + # Shrink past the leased queue — only queue 3 removed, queue 1 untouched + ethnl.channels_set( + {"header": {"dev-index": nsim.ifindex}, "combined-count": 3} + ) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + + # Shrink further — queue 2 removed, queue 1 still untouched + ethnl.channels_set( + {"header": {"dev-index": nsim.ifindex}, "combined-count": 2} + ) + + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + + # Shrink into the leased queue — queue 1 is busy, must fail + with ksft_raises(NlError) as e: + ethnl.channels_set( + {"header": {"dev-index": nsim.ifindex}, "combined-count": 1} + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + +def test_resize_virt_not_supported(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, nk_host_idx, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + # Channel resize on the netkit host must fail — not supported + ethnl = EthtoolFamily() + with ksft_raises(NlError) as e: + ethnl.channels_set( + {"header": {"dev-index": nk_host_idx}, "combined-count": 1} + ) + ksft_eq(e.exception.nl_msg.error, -errno.EOPNOTSUPP) + + # Lease must be intact + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + + +def test_lease_devices_down(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + + # Create lease while both physical and virtual devices are down + src_queue = 1 + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + result = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + # Bring devices up before queue_get: netdevsim only instantiates NAPIs in + # ndo_open, and netdev-genl queue_get returns -ENOENT without a NAPI. + ip(f"link set dev {nsim.ifname} up") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], result["id"]) + + +def test_lease_capacity_exhaustion(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=4) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + # rxqueues=3 means num_rx_queues=3, real_num_rx_queues starts at 1. + # Can create 2 leased queues (real goes 1->2->3) but not a 3rd (3->4 > 3). + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=3) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + r1 = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(r1["id"], 1) + + r2 = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(r2["id"], 2) + + # Third lease fails — netkit queue capacity exhausted + with ksft_raises(NlError) as e: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 3, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + + # Verify the two successful leases are intact + netdevnl = NetdevFamily() + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_in("lease", q1) + ksft_in("lease", q2) + + +def test_resize_phys_up(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=3) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + # Shrink nsim first so we have room to grow + ethnl = EthtoolFamily() + ethnl.channels_set( + {"header": {"dev-index": nsim.ifindex}, "combined-count": 2} + ) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + # Grow channels — should succeed since leased queue is not removed + ethnl.channels_set( + {"header": {"dev-index": nsim.ifindex}, "combined-count": 3} + ) + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", queue_info) + + # New queue 2 should exist without a lease + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_not_in("lease", queue_info) + + +def test_multi_ns_lease(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=3) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + ns_b = NetNS() + defer(ns_b.__del__) + ip("netns set init 0", ns=ns_b) + ip("link set lo up", ns=ns_b) + + # First netkit pair, guest in netns + nk_host_a, _, nk_guest_a, nk_guest_a_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_a}", fail=False) + ip(f"link set dev {nk_guest_a} netns {netns.name}") + ip(f"link set dev {nk_host_a} up") + ip(f"link set dev {nk_guest_a} up", ns=netns) + + # Second netkit pair, guest in ns_b + nk_host_b, _, nk_guest_b, nk_guest_b_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_b}", fail=False) + ip(f"link set dev {nk_guest_b} netns {ns_b.name}") + ip(f"link set dev {nk_host_b} up") + ip(f"link set dev {nk_guest_b} up", ns=ns_b) + + # Lease from netns + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + result = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_a_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + # Lease from ns_b (different namespace, same physical device) + with NetNSEnter(str(ns_b)), NetdevFamily() as netdevnl_ns: + result = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_b_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + ksft_eq(result["id"], 1) + + # Verify both leases from the physical side + netdevnl = NetdevFamily() + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_in("lease", q1) + ksft_in("lease", q2) + ksft_eq(q1["lease"]["ifindex"], nk_guest_a_idx) + ksft_eq(q2["lease"]["ifindex"], nk_guest_b_idx) + + +def test_multi_ns_delete_one(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=3) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + ns_b = NetNS() + ip("netns set init 0", ns=ns_b) + ip("link set lo up", ns=ns_b) + + # First netkit pair, guest in netns (ns_a) + nk_host_a, _, nk_guest_a, nk_guest_a_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_a}", fail=False) + ip(f"link set dev {nk_guest_a} netns {netns.name}") + ip(f"link set dev {nk_host_a} up") + ip(f"link set dev {nk_guest_a} up", ns=netns) + + # Second netkit pair, guest in ns_b + nk_host_b, _, nk_guest_b, nk_guest_b_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host_b}", fail=False) + + ip(f"link set dev {nk_guest_b} netns {ns_b.name}") + ip(f"link set dev {nk_host_b} up") + ip(f"link set dev {nk_guest_b} up", ns=ns_b) + + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_a_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 1, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + with NetNSEnter(str(ns_b)), NetdevFamily() as netdevnl_ns: + netdevnl_ns.queue_create( + { + "ifindex": nk_guest_b_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": 2, "type": "rx"}, + "netns-id": 0, + }, + } + ) + + netdevnl = NetdevFamily() + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_in("lease", q1) + ksft_in("lease", q2) + + # Delete ns_b — destroys nk_guest_b, triggers unlease of queue 2 + del ns_b + wait_until(lambda: "lease" not in netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"})) + + # ns_a's lease on queue 1 must survive + q1 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 1, "type": "rx"} + ) + ksft_in("lease", q1) + ksft_eq(q1["lease"]["ifindex"], nk_guest_a_idx) + + # ns_b's lease on queue 2 must be gone + q2 = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": 2, "type": "rx"} + ) + ksft_not_in("lease", q2) + + # nk_host_b should be gone too (phys removal cascades to netkit pair) + ret = cmd(f"ip link show dev {nk_host_b}", fail=False) + ksft_ne(ret.ret, 0) + + +def test_move_phys_netns(netns) -> None: + nsimdev = NetdevSimDev(port_count=1, queue_count=2) + defer(nsimdev.remove) + nsim = nsimdev.nsims[0] + ip(f"link set dev {nsim.ifname} up") + + nk_host, _, nk_guest, nk_guest_idx = create_netkit(rxqueues=2) + defer(cmd, f"ip link del dev {nk_host}", fail=False) + + ip(f"link set dev {nk_guest} netns {netns.name}") + ip(f"link set dev {nk_host} up") + ip(f"link set dev {nk_guest} up", ns=netns) + + src_queue = 1 + with NetNSEnter(str(netns)), NetdevFamily() as netdevnl_ns: + nk_queue_id = netdevnl_ns.queue_create( + { + "ifindex": nk_guest_idx, + "type": "rx", + "lease": { + "ifindex": nsim.ifindex, + "queue": {"id": src_queue, "type": "rx"}, + "netns-id": 0, + }, + } + )["id"] + + netdevnl = NetdevFamily() + queue_info = netdevnl.queue_get( + {"ifindex": nsim.ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + + # Move the physical device to a new namespace. Move it back to init_net + # on cleanup before the other defers fire (new_ns deletion, nsimdev.remove) + # so nsim lives in a stable namespace when they run. + new_ns = NetNS() + defer(new_ns.__del__) + ip(f"link set dev {nsim.ifname} netns {new_ns.name}") + defer(ip, f"link set dev {nsim.ifname} netns init", ns=new_ns) + + # Physical device is now in new_ns — find its ifindex there + all_links = ip("-d link show", json=True, ns=new_ns) + nsim_in_new = [lnk for lnk in all_links if lnk.get("ifname") == nsim.ifname] + new_ifindex = nsim_in_new[0]["ifindex"] + + # Moving a device across netns brings it admin-down; bring it back up so + # netdevsim re-creates the NAPI (netdev-genl queue_get needs it). + ip(f"link set dev {nsim.ifname} up", ns=new_ns) + + # Verify lease survived the namespace move + with NetNSEnter(str(new_ns)), NetdevFamily() as netdevnl_ns: + queue_info = netdevnl_ns.queue_get( + {"ifindex": new_ifindex, "id": src_queue, "type": "rx"} + ) + ksft_in("lease", queue_info) + ksft_eq(queue_info["lease"]["queue"]["id"], nk_queue_id) + + +def main() -> None: + netns = NetNS() + cmd("ip netns attach init 1") + ip("netns set init 0", ns=netns) + ip("link set lo up", ns=netns) + + ksft_run( + [ + test_remove_phys, + test_double_lease, + test_virtual_lessor, + test_phys_lessee, + test_different_lessors, + test_queue_out_of_range, + test_resize_leased, + test_self_lease, + test_create_tx_type, + test_create_primary, + test_create_limit, + test_link_flap_phys, + test_queue_get_virtual, + test_remove_virt_first, + test_multiple_leases, + test_lease_queue_tx_type, + test_invalid_netns, + test_invalid_phys_ifindex, + test_multi_netkit_remove_phys, + test_single_remove_phys, + test_link_flap_virt, + test_phys_queue_no_lease, + test_same_ns_lease, + test_resize_after_unlease, + test_lease_queue_zero, + test_release_and_reuse, + test_veth_queue_create, + test_two_netkits_same_queue, + test_l3_mode_lease, + test_single_double_lease, + test_single_different_lessors, + test_cross_ns_netns_id, + test_delete_guest_netns, + test_move_guest_netns, + test_resize_phys_no_reduction, + test_delete_one_netkit_of_two, + test_bind_rx_leased_phys_queue, + test_resize_phys_shrink_past_leased, + test_resize_virt_not_supported, + test_lease_devices_down, + test_lease_capacity_exhaustion, + test_resize_phys_up, + test_multi_ns_lease, + test_multi_ns_delete_one, + test_move_phys_netns, + ], + args=(netns,), + ) + + cmd("ip netns del init", fail=False) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index 5c66421ab8aa..eff55c64a012 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -1,11 +1,15 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -import time +""" +Tests for the netdev netlink family. +""" + +import errno from os import system -from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_eq, ksft_ge, ksft_ne, ksft_busy_wait -from lib.py import NetdevFamily, NetdevSimDev, ip +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_eq, ksft_ge, ksft_ne, ksft_raises, ksft_busy_wait +from lib.py import NetdevFamily, NetdevSimDev, NlError, ip def empty_check(nf) -> None: @@ -19,6 +23,15 @@ def lo_check(nf) -> None: ksft_eq(len(lo_info['xdp-rx-metadata-features']), 0) +def dev_dump_reject_attr(nf) -> None: + """Test that dev-get dump rejects attributes (no dump request policy).""" + with ksft_raises(NlError) as cm: + nf.dev_get({'ifindex': 1}, dump=True) + ksft_eq(cm.exception.nl_msg.error, -errno.EINVAL) + ksft_eq(cm.exception.nl_msg.extack['msg'], 'Unknown attribute type') + ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex') + + def napi_list_check(nf) -> None: with NetdevSimDev(queue_count=100) as nsimdev: nsim = nsimdev.nsims[0] @@ -243,9 +256,16 @@ def page_pool_check(nf) -> None: def main() -> None: + """ Ksft boiler plate main """ nf = NetdevFamily() - ksft_run([empty_check, lo_check, page_pool_check, napi_list_check, - dev_set_threaded, napi_set_threaded, nsim_rxq_reset_down], + ksft_run([empty_check, + lo_check, + dev_dump_reject_attr, + napi_list_check, + napi_set_threaded, + dev_set_threaded, + nsim_rxq_reset_down, + page_pool_check], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/nl_nlctrl.py b/tools/testing/selftests/net/nl_nlctrl.py new file mode 100755 index 000000000000..fe1f66dc9435 --- /dev/null +++ b/tools/testing/selftests/net/nl_nlctrl.py @@ -0,0 +1,131 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Tests for the nlctrl genetlink family (family info and policy dumps). +""" + +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_eq, ksft_ge, ksft_true, ksft_in, ksft_not_in +from lib.py import NetdevFamily, EthtoolFamily, NlctrlFamily + + +def getfamily_do(ctrl) -> None: + """Query a single family by name and validate its ops.""" + fam = ctrl.getfamily({'family-name': 'netdev'}) + ksft_eq(fam['family-name'], 'netdev') + ksft_true(fam['family-id'] > 0) + + # The format of ops is quite odd, [{$idx: {"id"...}}, {$idx: {"id"...}}] + # Discard the indices and re-key by command id. + ops_by_id = {v['id']: v for op in fam['ops'] for v in op.values()} + ksft_eq(len(ops_by_id), len(fam['ops'])) + + # All ops should have a policy (either do or dump has one) + for op in ops_by_id.values(): + ksft_in('cmd-cap-haspol', op['flags'], + comment=f"op {op['id']} missing haspol") + + # dev-get (id 1) should support both do and dump + ksft_in('cmd-cap-do', ops_by_id[1]['flags']) + ksft_in('cmd-cap-dump', ops_by_id[1]['flags']) + + # qstats-get (id 12) is dump-only + ksft_not_in('cmd-cap-do', ops_by_id[12]['flags']) + ksft_in('cmd-cap-dump', ops_by_id[12]['flags']) + + # napi-set (id 14) is do-only and requires admin + ksft_in('cmd-cap-do', ops_by_id[14]['flags']) + ksft_not_in('cmd-cap-dump', ops_by_id[14]['flags']) + ksft_in('admin-perm', ops_by_id[14]['flags']) + + # Notification-only commands (dev-add/del/change-ntf etc.) must + # not appear in the ops list since they have no do/dump handlers. + for ntf_id in [2, 3, 4, 6, 7, 8]: + ksft_not_in(ntf_id, ops_by_id, + comment=f"ntf-only cmd {ntf_id} should not be in ops") + + +def getfamily_dump(ctrl) -> None: + """Dump all families and verify expected entries.""" + families = ctrl.getfamily({}, dump=True) + ksft_ge(len(families), 2) + + names = [f['family-name'] for f in families] + ksft_in('nlctrl', names, comment="nlctrl not found in family dump") + ksft_in('netdev', names, comment="netdev not found in family dump") + + +def getpolicy_dump(_ctrl) -> None: + """Dump policies for ops using get_policy() and validate results. + + Test with netdev (split ops) where do and dump can have different + policies, and with ethtool (full ops) where they always share one. + """ + # -- netdev (split ops) -- + ndev = NetdevFamily() + + # dev-get: do has a real policy with ifindex, dump has no policy + # (only the reject-all policy with maxattr=0) + pol = ndev.get_policy('dev-get', 'do') + ksft_in('ifindex', pol, comment="dev-get do policy should have ifindex") + ksft_eq(pol['ifindex'].type, 'u32') + + pol_dump = ndev.get_policy('dev-get', 'dump') + ksft_eq(len(pol_dump), 0, comment="dev-get should not accept any attrs") + + # napi-get: both do and dump have real policies + pol_do = ndev.get_policy('napi-get', 'do') + ksft_ge(len(pol_do), 1) + + pol_dump = ndev.get_policy('napi-get', 'dump') + ksft_ge(len(pol_dump), 1) + + # -- ethtool (full ops) -- + et = EthtoolFamily() + + # strset-get (has both do and dump, full ops share policy) + pol_do = et.get_policy('strset-get', 'do') + ksft_ge(len(pol_do), 1, comment="strset-get should have a do policy") + + pol_dump = et.get_policy('strset-get', 'dump') + ksft_ge(len(pol_dump), 1, comment="strset-get should have a dump policy") + + # Same policy means same attribute names + ksft_eq(set(pol_do.keys()), set(pol_dump.keys())) + + # linkinfo-set is do-only (SET command), no dump + pol_do = et.get_policy('linkinfo-set', 'do') + ksft_ge(len(pol_do), 1, comment="linkinfo-set should have a do policy") + + pol_dump = et.get_policy('linkinfo-set', 'dump') + ksft_eq(pol_dump, None, + comment="linkinfo-set should not have a dump policy") + + +def getpolicy_by_op(_ctrl) -> None: + """Query policy for specific ops, check attr names are resolved.""" + ndev = NetdevFamily() + + # dev-get do policy should have named attributes from the spec + pol = ndev.get_policy('dev-get', 'do') + ksft_ge(len(pol), 1) + # All attr names should be resolved (no 'attr-N' fallbacks) + for name in pol: + ksft_true(not name.startswith('attr-'), + comment=f"unresolved attr name: {name}") + + +def main() -> None: + """ Ksft boiler plate main """ + ctrl = NlctrlFamily() + ksft_run([getfamily_do, + getfamily_dump, + getpolicy_dump, + getpolicy_by_op], + args=(ctrl, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index b521e0dea506..848f61fdcee0 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -2583,7 +2583,7 @@ def main(argv): prverscheck = pyroute2.__version__.split(".") if int(prverscheck[0]) == 0 and int(prverscheck[1]) < 6: print("Need to upgrade the python pyroute2 package to >= 0.6.") - sys.exit(0) + sys.exit(1) parser = argparse.ArgumentParser() parser.add_argument( diff --git a/tools/testing/selftests/net/ovpn/Makefile b/tools/testing/selftests/net/ovpn/Makefile index dbe0388c8512..169f0464ac3a 100644 --- a/tools/testing/selftests/net/ovpn/Makefile +++ b/tools/testing/selftests/net/ovpn/Makefile @@ -2,22 +2,35 @@ # Copyright (C) 2020-2025 OpenVPN, Inc. # CFLAGS = -pedantic -Wextra -Wall -Wl,--no-as-needed -g -O0 -ggdb $(KHDR_INCLUDES) +CFLAGS += $(shell pkg-config --cflags mbedcrypto-3 mbedtls-3 2>/dev/null) + VAR_CFLAGS = $(shell pkg-config --cflags libnl-3.0 libnl-genl-3.0 2>/dev/null) ifeq ($(VAR_CFLAGS),) VAR_CFLAGS = -I/usr/include/libnl3 endif CFLAGS += $(VAR_CFLAGS) +MTLS_LDLIBS= $(shell pkg-config --libs mbedcrypto-3 mbedtls-3 2>/dev/null) +ifeq ($(MTLS_LDLIBS),) +MTLS_LDLIBS = -lmbedtls -lmbedcrypto +endif +LDLIBS += $(MTLS_LDLIBS) -LDLIBS = -lmbedtls -lmbedcrypto -VAR_LDLIBS = $(shell pkg-config --libs libnl-3.0 libnl-genl-3.0 2>/dev/null) -ifeq ($(VAR_LDLIBS),) -VAR_LDLIBS = -lnl-genl-3 -lnl-3 +NL_LDLIBS = $(shell pkg-config --libs libnl-3.0 libnl-genl-3.0 2>/dev/null) +ifeq ($(NL_LDLIBS),) +NL_LDLIBS = -lnl-genl-3 -lnl-3 endif -LDLIBS += $(VAR_LDLIBS) +LDLIBS += $(NL_LDLIBS) -TEST_FILES = common.sh +TEST_FILES = \ + common.sh \ + data64.key \ + json \ + tcp_peers.txt \ + udp_peers.txt \ + ../../../../net/ynl/pyynl/cli.py \ +# end of TEST_FILES TEST_PROGS := \ test-chachapoly.sh \ @@ -25,6 +38,10 @@ TEST_PROGS := \ test-close-socket.sh \ test-float.sh \ test-large-mtu.sh \ + test-mark.sh \ + test-symmetric-id-float.sh \ + test-symmetric-id-tcp.sh \ + test-symmetric-id.sh \ test-tcp.sh \ test.sh \ # end of TEST_PROGS diff --git a/tools/testing/selftests/net/ovpn/common.sh b/tools/testing/selftests/net/ovpn/common.sh index 88869c675d03..4c08f756e63a 100644 --- a/tools/testing/selftests/net/ovpn/common.sh +++ b/tools/testing/selftests/net/ovpn/common.sh @@ -7,12 +7,21 @@ UDP_PEERS_FILE=${UDP_PEERS_FILE:-udp_peers.txt} TCP_PEERS_FILE=${TCP_PEERS_FILE:-tcp_peers.txt} OVPN_CLI=${OVPN_CLI:-./ovpn-cli} +YNL_CLI=${YNL_CLI:-../../../../net/ynl/pyynl/cli.py} ALG=${ALG:-aes} PROTO=${PROTO:-UDP} FLOAT=${FLOAT:-0} +SYMMETRIC_ID=${SYMMETRIC_ID:-0} +export ID_OFFSET=$(( 9 * (SYMMETRIC_ID == 0) )) + +JQ_FILTER='map(select(.msg.peer | has("remote-ipv6") | not)) | + map(del(.msg.ifindex)) | sort_by(.msg.peer.id)[]' LAN_IP="11.11.11.11" +declare -A tmp_jsons=() +declare -A listener_pids=() + create_ns() { ip netns add peer${1} } @@ -48,27 +57,67 @@ setup_ns() { ip -n peer${1} link set tun${1} up } +build_capture_filter() { + # match the first four bytes of the openvpn data payload + if [ "${PROTO}" == "UDP" ]; then + # For UDP, libpcap transport indexing only works for IPv4, so + # use an explicit IPv4 or IPv6 expression based on the peer + # address. The IPv6 branch assumes there are no extension + # headers in the outer packet. + if [[ "${2}" == *:* ]]; then + printf "ip6 and ip6[6] = 17 and ip6[48:4] = %s" "${1}" + else + printf "ip and udp[8:4] = %s" "${1}" + fi + else + # openvpn over TCP prepends a 2-byte packet length ahead of the + # DATA_V2 opcode, so skip it before matching the payload header + printf "ip and tcp[(((tcp[12] & 0xf0) >> 2) + 2):4] = %s" "${1}" + fi +} + +setup_listener() { + file=$(mktemp) + PYTHONUNBUFFERED=1 ip netns exec peer${p} ${YNL_CLI} --family ovpn \ + --subscribe peers --output-json --duration 40 > ${file} & + listener_pids[$1]=$! + tmp_jsons[$1]="${file}" +} + add_peer() { + labels=("ASYMM" "SYMM") + M_ID=${labels[SYMMETRIC_ID]} + if [ "${PROTO}" == "UDP" ]; then if [ ${1} -eq 0 ]; then - ip netns exec peer0 ${OVPN_CLI} new_multi_peer tun0 1 ${UDP_PEERS_FILE} + ip netns exec peer0 ${OVPN_CLI} new_multi_peer tun0 1 \ + ${M_ID} ${UDP_PEERS_FILE} for p in $(seq 1 ${NUM_PEERS}); do ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 ${ALG} 0 \ data64.key done else - RADDR=$(awk "NR == ${1} {print \$2}" ${UDP_PEERS_FILE}) - RPORT=$(awk "NR == ${1} {print \$3}" ${UDP_PEERS_FILE}) - LPORT=$(awk "NR == ${1} {print \$5}" ${UDP_PEERS_FILE}) - ip netns exec peer${1} ${OVPN_CLI} new_peer tun${1} ${1} ${LPORT} \ - ${RADDR} ${RPORT} - ip netns exec peer${1} ${OVPN_CLI} new_key tun${1} ${1} 1 0 ${ALG} 1 \ - data64.key + if [ "${SYMMETRIC_ID}" -eq 1 ]; then + PEER_ID=${1} + TX_ID="none" + else + PEER_ID=$(awk "NR == ${1} {print \$2}" \ + ${UDP_PEERS_FILE}) + TX_ID=${1} + fi + RADDR=$(awk "NR == ${1} {print \$3}" ${UDP_PEERS_FILE}) + RPORT=$(awk "NR == ${1} {print \$4}" ${UDP_PEERS_FILE}) + LPORT=$(awk "NR == ${1} {print \$6}" ${UDP_PEERS_FILE}) + ip netns exec peer${1} ${OVPN_CLI} new_peer tun${1} \ + ${PEER_ID} ${TX_ID} ${LPORT} ${RADDR} ${RPORT} + ip netns exec peer${1} ${OVPN_CLI} new_key tun${1} \ + ${PEER_ID} 1 0 ${ALG} 1 data64.key fi else if [ ${1} -eq 0 ]; then - (ip netns exec peer0 ${OVPN_CLI} listen tun0 1 ${TCP_PEERS_FILE} && { + (ip netns exec peer0 ${OVPN_CLI} listen tun0 1 ${M_ID} \ + ${TCP_PEERS_FILE} && { for p in $(seq 1 ${NUM_PEERS}); do ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 \ ${ALG} 0 data64.key @@ -76,9 +125,37 @@ add_peer() { }) & sleep 5 else - ip netns exec peer${1} ${OVPN_CLI} connect tun${1} ${1} 10.10.${1}.1 1 \ - data64.key + if [ "${SYMMETRIC_ID}" -eq 1 ]; then + PEER_ID=${1} + TX_ID="none" + else + PEER_ID=$(awk "NR == ${1} {print \$2}" \ + ${TCP_PEERS_FILE}) + TX_ID=${1} + fi + ip netns exec peer${1} ${OVPN_CLI} connect tun${1} \ + ${PEER_ID} ${TX_ID} 10.10.${1}.1 1 data64.key + fi + fi +} + +compare_ntfs() { + if [ ${#tmp_jsons[@]} -gt 0 ]; then + suffix="" + [ "${SYMMETRIC_ID}" -eq 1 ] && suffix="${suffix}-symm" + [ "$FLOAT" == 1 ] && suffix="${suffix}-float" + expected="json/peer${1}${suffix}.json" + received="${tmp_jsons[$1]}" + + kill -TERM ${listener_pids[$1]} || true + wait ${listener_pids[$1]} || true + printf "Checking notifications for peer ${1}... " + if diff <(jq -s "${JQ_FILTER}" ${expected}) \ + <(jq -s "${JQ_FILTER}" ${received}); then + echo "OK" fi + + rm -f ${received} || true fi } @@ -104,5 +181,3 @@ if [ "${PROTO}" == "UDP" ]; then else NUM_PEERS=${NUM_PEERS:-$(wc -l ${TCP_PEERS_FILE} | awk '{print $1}')} fi - - diff --git a/tools/testing/selftests/net/ovpn/data64.key b/tools/testing/selftests/net/ovpn/data64.key index a99e88c4e290..d04febcdf5a2 100644 --- a/tools/testing/selftests/net/ovpn/data64.key +++ b/tools/testing/selftests/net/ovpn/data64.key @@ -1,5 +1 @@ -jRqMACN7d7/aFQNT8S7jkrBD8uwrgHbG5OQZP2eu4R1Y7tfpS2bf5RHv06Vi163CGoaIiTX99R3B -ia9ycAH8Wz1+9PWv51dnBLur9jbShlgZ2QHLtUc4a/gfT7zZwULXuuxdLnvR21DDeMBaTbkgbai9 -uvAa7ne1liIgGFzbv+Bas4HDVrygxIxuAnP5Qgc3648IJkZ0QEXPF+O9f0n5+QIvGCxkAUVx+5K6 -KIs+SoeWXnAopELmoGSjUpFtJbagXK82HfdqpuUxT2Tnuef0/14SzVE/vNleBNu2ZbyrSAaah8tE -BofkPJUBFY+YQcfZNM5Dgrw3i+Bpmpq/gpdg5w== +jRqMACN7d7/aFQNT8S7jkrBD8uwrgHbG5OQZP2eu4R1Y7tfpS2bf5RHv06Vi163CGoaIiTX99R3Bia9ycAH8Wz1+9PWv51dnBLur9jbShlgZ2QHLtUc4a/gfT7zZwULXuuxdLnvR21DDeMBaTbkgbai9uvAa7ne1liIgGFzbv+Bas4HDVrygxIxuAnP5Qgc3648IJkZ0QEXPF+O9f0n5+QIvGCxkAUVx+5K6KIs+SoeWXnAopELmoGSjUpFtJbagXK82HfdqpuUxT2Tnuef0/14SzVE/vNleBNu2ZbyrSAaah8tEBofkPJUBFY+YQcfZNM5Dgrw3i+Bpmpq/gpdg5w== diff --git a/tools/testing/selftests/net/ovpn/json/peer0-float.json b/tools/testing/selftests/net/ovpn/json/peer0-float.json new file mode 100644 index 000000000000..682fa58ad4ea --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer0-float.json @@ -0,0 +1,9 @@ +{"name": "peer-float-ntf", "msg": {"ifindex": 0, "peer": {"id": 1, "remote-ipv4": "10.10.1.3", "remote-port": 1}}} +{"name": "peer-float-ntf", "msg": {"ifindex": 0, "peer": {"id": 2, "remote-ipv4": "10.10.2.3", "remote-port": 1}}} +{"name": "peer-float-ntf", "msg": {"ifindex": 0, "peer": {"id": 3, "remote-ipv4": "10.10.3.3", "remote-port": 1}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 1}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 2}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 3}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 4}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 5}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 6}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer0-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer0-symm-float.json new file mode 120000 index 000000000000..e31a5bd59863 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer0-symm-float.json @@ -0,0 +1 @@ +peer0-float.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer0-symm.json b/tools/testing/selftests/net/ovpn/json/peer0-symm.json new file mode 120000 index 000000000000..57a163048eed --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer0-symm.json @@ -0,0 +1 @@ +peer0.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer0.json b/tools/testing/selftests/net/ovpn/json/peer0.json new file mode 100644 index 000000000000..7c46a33d5ecd --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer0.json @@ -0,0 +1,6 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 1}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 2}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 3}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 4}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 5}}} +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 6}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer1-float.json b/tools/testing/selftests/net/ovpn/json/peer1-float.json new file mode 120000 index 000000000000..d28c328d1452 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer1-float.json @@ -0,0 +1 @@ +peer1.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer1-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer1-symm-float.json new file mode 120000 index 000000000000..b3615dcc523d --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer1-symm-float.json @@ -0,0 +1 @@ +peer1-symm.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer1-symm.json b/tools/testing/selftests/net/ovpn/json/peer1-symm.json new file mode 100644 index 000000000000..5da4ea9d51fb --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer1-symm.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 1}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer1.json b/tools/testing/selftests/net/ovpn/json/peer1.json new file mode 100644 index 000000000000..1009d26dc14a --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer1.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 10}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer2-float.json b/tools/testing/selftests/net/ovpn/json/peer2-float.json new file mode 120000 index 000000000000..b9f09980aaa0 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer2-float.json @@ -0,0 +1 @@ +peer2.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer2-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer2-symm-float.json new file mode 120000 index 000000000000..28a895cb5170 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer2-symm-float.json @@ -0,0 +1 @@ +peer2-symm.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer2-symm.json b/tools/testing/selftests/net/ovpn/json/peer2-symm.json new file mode 100644 index 000000000000..8f6db4f8c2ac --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer2-symm.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 2}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer2.json b/tools/testing/selftests/net/ovpn/json/peer2.json new file mode 100644 index 000000000000..44e9fad2b622 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer2.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "userspace", "id": 11}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer3-float.json b/tools/testing/selftests/net/ovpn/json/peer3-float.json new file mode 120000 index 000000000000..2700b55bcf2e --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer3-float.json @@ -0,0 +1 @@ +peer3.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer3-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer3-symm-float.json new file mode 120000 index 000000000000..ee8b9719c2fd --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer3-symm-float.json @@ -0,0 +1 @@ +peer3-symm.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer3-symm.json b/tools/testing/selftests/net/ovpn/json/peer3-symm.json new file mode 100644 index 000000000000..bdabd6fa2e64 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer3-symm.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 3}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer3.json b/tools/testing/selftests/net/ovpn/json/peer3.json new file mode 100644 index 000000000000..d4be8ba130ae --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer3.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 12}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer4-float.json b/tools/testing/selftests/net/ovpn/json/peer4-float.json new file mode 120000 index 000000000000..460f6c14cd60 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer4-float.json @@ -0,0 +1 @@ +peer4.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer4-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer4-symm-float.json new file mode 120000 index 000000000000..7d34ff7305da --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer4-symm-float.json @@ -0,0 +1 @@ +peer4-symm.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer4-symm.json b/tools/testing/selftests/net/ovpn/json/peer4-symm.json new file mode 100644 index 000000000000..c3734bb9251b --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer4-symm.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 4}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer4.json b/tools/testing/selftests/net/ovpn/json/peer4.json new file mode 100644 index 000000000000..67d27e2d48ac --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer4.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 13}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer5-float.json b/tools/testing/selftests/net/ovpn/json/peer5-float.json new file mode 120000 index 000000000000..0f725c50ce19 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer5-float.json @@ -0,0 +1 @@ +peer5.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer5-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer5-symm-float.json new file mode 120000 index 000000000000..afc0f5f9f13b --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer5-symm-float.json @@ -0,0 +1 @@ +peer5-symm.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer5-symm.json b/tools/testing/selftests/net/ovpn/json/peer5-symm.json new file mode 100644 index 000000000000..46c4a348299d --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer5-symm.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 5}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer5.json b/tools/testing/selftests/net/ovpn/json/peer5.json new file mode 100644 index 000000000000..ecd9bd0b2f37 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer5.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 14}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer6-float.json b/tools/testing/selftests/net/ovpn/json/peer6-float.json new file mode 120000 index 000000000000..4d9ded3e0a84 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer6-float.json @@ -0,0 +1 @@ +peer6.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer6-symm-float.json b/tools/testing/selftests/net/ovpn/json/peer6-symm-float.json new file mode 120000 index 000000000000..e39203204d8c --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer6-symm-float.json @@ -0,0 +1 @@ +peer6-symm.json
\ No newline at end of file diff --git a/tools/testing/selftests/net/ovpn/json/peer6-symm.json b/tools/testing/selftests/net/ovpn/json/peer6-symm.json new file mode 100644 index 000000000000..aa30f2cff625 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer6-symm.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 6}}} diff --git a/tools/testing/selftests/net/ovpn/json/peer6.json b/tools/testing/selftests/net/ovpn/json/peer6.json new file mode 100644 index 000000000000..7fded29c5804 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/json/peer6.json @@ -0,0 +1 @@ +{"name": "peer-del-ntf", "msg": {"ifindex": 0, "peer": {"del-reason": "expired", "id": 15}}} diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c index 0f3babf19fd0..d40953375c86 100644 --- a/tools/testing/selftests/net/ovpn/ovpn-cli.c +++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c @@ -6,6 +6,7 @@ * Author: Antonio Quartulli <antonio@openvpn.net> */ +#include <stdint.h> #include <stdio.h> #include <inttypes.h> #include <stdbool.h> @@ -103,7 +104,7 @@ struct ovpn_ctx { sa_family_t sa_family; - unsigned long peer_id; + unsigned long peer_id, tx_id; unsigned long lport; union { @@ -133,6 +134,9 @@ struct ovpn_ctx { enum ovpn_key_slot key_slot; int key_id; + uint32_t mark; + bool asymm_id; + const char *peers_file; }; @@ -521,6 +525,15 @@ static int ovpn_socket(struct ovpn_ctx *ctx, sa_family_t family, int proto) return ret; } + if (ctx->mark != 0) { + ret = setsockopt(s, SOL_SOCKET, SO_MARK, (void *)&ctx->mark, + sizeof(ctx->mark)); + if (ret < 0) { + perror("setsockopt for SO_MARK"); + return ret; + } + } + if (family == AF_INET6) { opt = 0; if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, &opt, @@ -649,6 +662,8 @@ static int ovpn_new_peer(struct ovpn_ctx *ovpn, bool is_tcp) attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER); NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id); + if (ovpn->asymm_id) + NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_TX_ID, ovpn->tx_id); NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_SOCKET, ovpn->socket); if (!is_tcp) { @@ -767,6 +782,10 @@ static int ovpn_handle_peer(struct nl_msg *msg, void (*arg)__always_unused) fprintf(stderr, "* Peer %u\n", nla_get_u32(pattrs[OVPN_A_PEER_ID])); + if (pattrs[OVPN_A_PEER_TX_ID]) + fprintf(stderr, "\tTX peer ID %u\n", + nla_get_u32(pattrs[OVPN_A_PEER_TX_ID])); + if (pattrs[OVPN_A_PEER_SOCKET_NETNSID]) fprintf(stderr, "\tsocket NetNS ID: %d\n", nla_get_s32(pattrs[OVPN_A_PEER_SOCKET_NETNSID])); @@ -1516,6 +1535,9 @@ static int ovpn_handle_msg(struct nl_msg *msg, void *arg) case OVPN_CMD_PEER_DEL_NTF: fprintf(stdout, "received CMD_PEER_DEL_NTF\n"); break; + case OVPN_CMD_PEER_FLOAT_NTF: + fprintf(stdout, "received CMD_PEER_FLOAT_NTF\n"); + break; case OVPN_CMD_KEY_SWAP_NTF: fprintf(stdout, "received CMD_KEY_SWAP_NTF\n"); break; @@ -1654,41 +1676,58 @@ static void usage(const char *cmd) fprintf(stderr, "\tiface: ovpn interface name\n"); fprintf(stderr, - "* listen <iface> <lport> <peers_file> [ipv6]: listen for incoming peer TCP connections\n"); + "* listen <iface> <lport> <id_type> <peers_file> [ipv6]: listen for incoming peer TCP connections\n"); fprintf(stderr, "\tiface: ovpn interface name\n"); fprintf(stderr, "\tlport: TCP port to listen to\n"); + fprintf(stderr, "\tid_type:\n"); + fprintf(stderr, + "\t\t- SYMM for ignoring the TX peer ID from the peers_file\n"); + fprintf(stderr, + "\t\t- ASYMM for using the TX peer ID from the peers_file\n"); fprintf(stderr, "\tpeers_file: file containing one peer per line: Line format:\n"); - fprintf(stderr, "\t\t<peer_id> <vpnaddr>\n"); + fprintf(stderr, "\t\t<peer_id> <tx_id> <vpnaddr>\n"); fprintf(stderr, "\tipv6: whether the socket should listen to the IPv6 wildcard address\n"); fprintf(stderr, - "* connect <iface> <peer_id> <raddr> <rport> [key_file]: start connecting peer of TCP-based VPN session\n"); + "* connect <iface> <peer_id> <tx_id> <raddr> <rport> [key_file]: start connecting peer of TCP-based VPN session\n"); fprintf(stderr, "\tiface: ovpn interface name\n"); - fprintf(stderr, "\tpeer_id: peer ID of the connecting peer\n"); + fprintf(stderr, + "\tpeer_id: peer ID found in data packets received from this peer\n"); + fprintf(stderr, + "\ttx_id: peer ID to be used when sending to this peer, 'none' for symmetric peer ID\n"); fprintf(stderr, "\traddr: peer IP address to connect to\n"); fprintf(stderr, "\trport: peer TCP port to connect to\n"); fprintf(stderr, "\tkey_file: file containing the symmetric key for encryption\n"); fprintf(stderr, - "* new_peer <iface> <peer_id> <lport> <raddr> <rport> [vpnaddr]: add new peer\n"); + "* new_peer <iface> <peer_id> <tx_id> <lport> <raddr> <rport> [vpnaddr]: add new peer\n"); fprintf(stderr, "\tiface: ovpn interface name\n"); - fprintf(stderr, "\tlport: local UDP port to bind to\n"); fprintf(stderr, - "\tpeer_id: peer ID to be used in data packets to/from this peer\n"); + "\tpeer_id: peer ID found in data packets received from this peer\n"); + fprintf(stderr, + "\ttx_id: peer ID to be used when sending to this peer, 'none' for symmetric peer ID\n"); + fprintf(stderr, "\tlport: local UDP port to bind to\n"); fprintf(stderr, "\traddr: peer IP address\n"); fprintf(stderr, "\trport: peer UDP port\n"); fprintf(stderr, "\tvpnaddr: peer VPN IP\n"); fprintf(stderr, - "* new_multi_peer <iface> <lport> <peers_file>: add multiple peers as listed in the file\n"); + "* new_multi_peer <iface> <lport> <id_type> <peers_file> [mark]: add multiple peers as listed in the file\n"); fprintf(stderr, "\tiface: ovpn interface name\n"); fprintf(stderr, "\tlport: local UDP port to bind to\n"); + fprintf(stderr, "\tid_type:\n"); + fprintf(stderr, + "\t\t- SYMM for ignoring the TX peer ID from the peers_file\n"); + fprintf(stderr, + "\t\t- ASYMM for using the TX peer ID from the peers_file\n"); fprintf(stderr, "\tpeers_file: text file containing one peer per line. Line format:\n"); - fprintf(stderr, "\t\t<peer_id> <raddr> <rport> <vpnaddr>\n"); + fprintf(stderr, + "\t\t<peer_id> <tx_id> <raddr> <rport> <laddr> <lport> <vpnaddr>\n"); + fprintf(stderr, "\tmark: socket FW mark value\n"); fprintf(stderr, "* set_peer <iface> <peer_id> <keepalive_interval> <keepalive_timeout>: set peer attributes\n"); @@ -1801,15 +1840,23 @@ out: } static int ovpn_parse_new_peer(struct ovpn_ctx *ovpn, const char *peer_id, - const char *raddr, const char *rport, - const char *vpnip) + const char *tx_id, const char *raddr, + const char *rport, const char *vpnip) { ovpn->peer_id = strtoul(peer_id, NULL, 10); if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) { - fprintf(stderr, "peer ID value out of range\n"); + fprintf(stderr, "rx peer ID value out of range\n"); return -1; } + if (ovpn->asymm_id) { + ovpn->tx_id = strtoul(tx_id, NULL, 10); + if (errno == ERANGE || ovpn->tx_id > PEER_ID_UNDEF) { + fprintf(stderr, "tx peer ID value out of range\n"); + return -1; + } + } + return ovpn_parse_remote(ovpn, raddr, rport, vpnip); } @@ -1936,8 +1983,8 @@ static void ovpn_waitbg(void) static int ovpn_run_cmd(struct ovpn_ctx *ovpn) { - char peer_id[10], vpnip[INET6_ADDRSTRLEN], laddr[128], lport[10]; - char raddr[128], rport[10]; + char peer_id[10], tx_id[10], vpnip[INET6_ADDRSTRLEN], laddr[128]; + char lport[10], raddr[128], rport[10]; int n, ret; FILE *fp; @@ -1964,7 +2011,8 @@ static int ovpn_run_cmd(struct ovpn_ctx *ovpn) int num_peers = 0; - while ((n = fscanf(fp, "%s %s\n", peer_id, vpnip)) == 2) { + while ((n = fscanf(fp, "%s %s %s\n", peer_id, tx_id, + vpnip)) == 3) { struct ovpn_ctx peer_ctx = { 0 }; if (num_peers == MAX_PEERS) { @@ -1974,6 +2022,7 @@ static int ovpn_run_cmd(struct ovpn_ctx *ovpn) peer_ctx.ifindex = ovpn->ifindex; peer_ctx.sa_family = ovpn->sa_family; + peer_ctx.asymm_id = ovpn->asymm_id; peer_ctx.socket = ovpn_accept(ovpn); if (peer_ctx.socket < 0) { @@ -1984,8 +2033,8 @@ static int ovpn_run_cmd(struct ovpn_ctx *ovpn) /* store peer sockets to test TCP I/O */ ovpn->cli_sockets[num_peers] = peer_ctx.socket; - ret = ovpn_parse_new_peer(&peer_ctx, peer_id, NULL, - NULL, vpnip); + ret = ovpn_parse_new_peer(&peer_ctx, peer_id, tx_id, + NULL, NULL, vpnip); if (ret < 0) { fprintf(stderr, "error while parsing line\n"); return -1; @@ -2053,16 +2102,17 @@ static int ovpn_run_cmd(struct ovpn_ctx *ovpn) return -1; } - while ((n = fscanf(fp, "%s %s %s %s %s %s\n", peer_id, laddr, - lport, raddr, rport, vpnip)) == 6) { + while ((n = fscanf(fp, "%s %s %s %s %s %s %s\n", peer_id, tx_id, + laddr, lport, raddr, rport, vpnip)) == 7) { struct ovpn_ctx peer_ctx = { 0 }; peer_ctx.ifindex = ovpn->ifindex; peer_ctx.socket = ovpn->socket; peer_ctx.sa_family = AF_UNSPEC; + peer_ctx.asymm_id = ovpn->asymm_id; - ret = ovpn_parse_new_peer(&peer_ctx, peer_id, raddr, - rport, vpnip); + ret = ovpn_parse_new_peer(&peer_ctx, peer_id, tx_id, + raddr, rport, vpnip); if (ret < 0) { fprintf(stderr, "error while parsing line\n"); return -1; @@ -2158,7 +2208,7 @@ static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[]) case CMD_DEL_IFACE: break; case CMD_LISTEN: - if (argc < 5) + if (argc < 6) return -EINVAL; ovpn->lport = strtoul(argv[3], NULL, 10); @@ -2167,55 +2217,67 @@ static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[]) return -1; } - ovpn->peers_file = argv[4]; + if (strcmp(argv[4], "SYMM") == 0) { + ovpn->asymm_id = false; + } else if (strcmp(argv[4], "ASYMM") == 0) { + ovpn->asymm_id = true; + } else { + fprintf(stderr, "Cannot parse id type: %s\n", argv[4]); + return -1; + } + + ovpn->peers_file = argv[5]; ovpn->sa_family = AF_INET; - if (argc > 5 && !strcmp(argv[5], "ipv6")) + if (argc > 6 && !strcmp(argv[6], "ipv6")) ovpn->sa_family = AF_INET6; break; case CMD_CONNECT: - if (argc < 6) + if (argc < 7) return -EINVAL; ovpn->sa_family = AF_INET; + ovpn->asymm_id = strcmp(argv[4], "none"); ret = ovpn_parse_new_peer(ovpn, argv[3], argv[4], argv[5], - NULL); + argv[6], NULL); if (ret < 0) { fprintf(stderr, "Cannot parse remote peer data\n"); return -1; } - if (argc > 6) { + if (argc > 7) { ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY; ovpn->key_id = 0; ovpn->cipher = OVPN_CIPHER_ALG_AES_GCM; ovpn->key_dir = KEY_DIR_OUT; - ret = ovpn_parse_key(argv[6], ovpn); + ret = ovpn_parse_key(argv[7], ovpn); if (ret) return -1; } break; case CMD_NEW_PEER: - if (argc < 7) + if (argc < 8) return -EINVAL; - ovpn->lport = strtoul(argv[4], NULL, 10); + ovpn->asymm_id = strcmp(argv[4], "none"); + + ovpn->lport = strtoul(argv[5], NULL, 10); if (errno == ERANGE || ovpn->lport > 65535) { fprintf(stderr, "lport value out of range\n"); return -1; } - const char *vpnip = (argc > 7) ? argv[7] : NULL; + const char *vpnip = (argc > 8) ? argv[8] : NULL; - ret = ovpn_parse_new_peer(ovpn, argv[3], argv[5], argv[6], - vpnip); + ret = ovpn_parse_new_peer(ovpn, argv[3], argv[4], argv[6], + argv[7], vpnip); if (ret < 0) return -1; break; case CMD_NEW_MULTI_PEER: - if (argc < 5) + if (argc < 6) return -EINVAL; ovpn->lport = strtoul(argv[3], NULL, 10); @@ -2224,7 +2286,25 @@ static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[]) return -1; } - ovpn->peers_file = argv[4]; + if (!strcmp(argv[4], "SYMM")) { + ovpn->asymm_id = false; + } else if (!strcmp(argv[4], "ASYMM")) { + ovpn->asymm_id = true; + } else { + fprintf(stderr, "Cannot parse id type: %s\n", argv[4]); + return -1; + } + + ovpn->peers_file = argv[5]; + + ovpn->mark = 0; + if (argc > 6) { + ovpn->mark = strtoul(argv[6], NULL, 10); + if (errno == ERANGE || ovpn->mark > UINT32_MAX) { + fprintf(stderr, "mark value out of range\n"); + return -1; + } + } break; case CMD_SET_PEER: if (argc < 6) diff --git a/tools/testing/selftests/net/ovpn/tcp_peers.txt b/tools/testing/selftests/net/ovpn/tcp_peers.txt index d753eebe8716..3cb67b560705 100644 --- a/tools/testing/selftests/net/ovpn/tcp_peers.txt +++ b/tools/testing/selftests/net/ovpn/tcp_peers.txt @@ -1,5 +1,6 @@ -1 5.5.5.2 -2 5.5.5.3 -3 5.5.5.4 -4 5.5.5.5 -5 5.5.5.6 +1 10 5.5.5.2 +2 11 5.5.5.3 +3 12 5.5.5.4 +4 13 5.5.5.5 +5 14 5.5.5.6 +6 15 5.5.5.7 diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh index 5e48a8b67928..0d09df14fe8e 100755 --- a/tools/testing/selftests/net/ovpn/test-close-socket.sh +++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh @@ -27,7 +27,7 @@ done for p in $(seq 1 ${NUM_PEERS}); do ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120 - ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120 + ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} $((${p}+9)) 60 120 done sleep 1 diff --git a/tools/testing/selftests/net/ovpn/test-mark.sh b/tools/testing/selftests/net/ovpn/test-mark.sh new file mode 100755 index 000000000000..8534428ed3eb --- /dev/null +++ b/tools/testing/selftests/net/ovpn/test-mark.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2020-2025 OpenVPN, Inc. +# +# Author: Ralf Lici <ralf@mandelbit.com> +# Antonio Quartulli <antonio@openvpn.net> + +#set -x +set -e + +MARK=1056 + +source ./common.sh + +cleanup + +modprobe -q ovpn || true + +for p in $(seq 0 "${NUM_PEERS}"); do + create_ns "${p}" +done + +for p in $(seq 0 3); do + setup_ns "${p}" 5.5.5.$((p + 1))/24 +done + +# add peer0 with mark +ip netns exec peer0 "${OVPN_CLI}" new_multi_peer tun0 1 ASYMM \ + "${UDP_PEERS_FILE}" \ + ${MARK} +for p in $(seq 1 3); do + ip netns exec peer0 "${OVPN_CLI}" new_key tun0 "${p}" 1 0 "${ALG}" 0 \ + data64.key +done + +for p in $(seq 1 3); do + add_peer "${p}" +done + +for p in $(seq 1 3); do + ip netns exec peer0 "${OVPN_CLI}" set_peer tun0 "${p}" 60 120 + ip netns exec peer"${p}" "${OVPN_CLI}" set_peer tun"${p}" \ + $((p + 9)) 60 120 +done + +sleep 1 + +for p in $(seq 1 3); do + ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((p + 1)) +done + +echo "Adding an nftables drop rule based on mark value ${MARK}" +ip netns exec peer0 nft flush ruleset +ip netns exec peer0 nft 'add table inet filter' +ip netns exec peer0 nft 'add chain inet filter output { + type filter hook output priority 0; + policy accept; +}' +ip netns exec peer0 nft add rule inet filter output \ + meta mark == ${MARK} \ + counter drop + +DROP_COUNTER=$(ip netns exec peer0 nft list chain inet filter output \ + | sed -n 's/.*packets \([0-9]*\).*/\1/p') +sleep 1 + +# ping should fail +for p in $(seq 1 3); do + PING_OUTPUT=$(ip netns exec peer0 ping \ + -qfc 500 -w 1 5.5.5.$((p + 1)) 2>&1) && exit 1 + echo "${PING_OUTPUT}" + LOST_PACKETS=$(echo "$PING_OUTPUT" \ + | awk '/packets transmitted/ { print $1 }') + # increment the drop counter by the amount of lost packets + DROP_COUNTER=$((DROP_COUNTER + LOST_PACKETS)) +done + +# check if the final nft counter matches our counter +TOTAL_COUNT=$(ip netns exec peer0 nft list chain inet filter output \ + | sed -n 's/.*packets \([0-9]*\).*/\1/p') +if [ "${DROP_COUNTER}" -ne "${TOTAL_COUNT}" ]; then + echo "Expected ${TOTAL_COUNT} drops, got ${DROP_COUNTER}" + exit 1 +fi + +echo "Removing the drop rule" +ip netns exec peer0 nft flush ruleset +sleep 1 + +for p in $(seq 1 3); do + ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((p + 1)) +done + +cleanup + +modprobe -r ovpn || true diff --git a/tools/testing/selftests/net/ovpn/test-symmetric-id-float.sh b/tools/testing/selftests/net/ovpn/test-symmetric-id-float.sh new file mode 100755 index 000000000000..b3711a81b463 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/test-symmetric-id-float.sh @@ -0,0 +1,11 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2025 OpenVPN, Inc. +# +# Author: Ralf Lici <ralf@mandelbit.com> +# Antonio Quartulli <antonio@openvpn.net> + +SYMMETRIC_ID="1" +FLOAT="1" + +source test.sh diff --git a/tools/testing/selftests/net/ovpn/test-symmetric-id-tcp.sh b/tools/testing/selftests/net/ovpn/test-symmetric-id-tcp.sh new file mode 100755 index 000000000000..188cafb67b2f --- /dev/null +++ b/tools/testing/selftests/net/ovpn/test-symmetric-id-tcp.sh @@ -0,0 +1,11 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2025 OpenVPN, Inc. +# +# Author: Ralf Lici <ralf@mandelbit.com> +# Antonio Quartulli <antonio@openvpn.net> + +PROTO="TCP" +SYMMETRIC_ID=1 + +source test.sh diff --git a/tools/testing/selftests/net/ovpn/test-symmetric-id.sh b/tools/testing/selftests/net/ovpn/test-symmetric-id.sh new file mode 100755 index 000000000000..35b119c72e4f --- /dev/null +++ b/tools/testing/selftests/net/ovpn/test-symmetric-id.sh @@ -0,0 +1,10 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2025 OpenVPN, Inc. +# +# Author: Ralf Lici <ralf@mandelbit.com> +# Antonio Quartulli <antonio@openvpn.net> + +SYMMETRIC_ID="1" + +source test.sh diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh index e8acdc303307..b60e94a4094e 100755 --- a/tools/testing/selftests/net/ovpn/test.sh +++ b/tools/testing/selftests/net/ovpn/test.sh @@ -18,6 +18,10 @@ for p in $(seq 0 ${NUM_PEERS}); do done for p in $(seq 0 ${NUM_PEERS}); do + setup_listener ${p} +done + +for p in $(seq 0 ${NUM_PEERS}); do setup_ns ${p} 5.5.5.$((${p} + 1))/24 ${MTU} done @@ -27,14 +31,45 @@ done for p in $(seq 1 ${NUM_PEERS}); do ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120 - ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120 + ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} \ + $((${p}+ID_OFFSET)) 60 120 done sleep 1 +TCPDUMP_TIMEOUT="1.5s" for p in $(seq 1 ${NUM_PEERS}); do + # The first part of the data packet header consists of: + # - TCP only: 2 bytes for the packet length + # - 5 bits for opcode ("9" for DATA_V2) + # - 3 bits for key-id ("0" at this point) + # - 12 bytes for peer-id: + # - with asymmetric ID: "${p}" one way and "${p} + 9" the other way + # - with symmetric ID: "${p}" both ways + HEADER1=$(printf "0x4800000%x" ${p}) + HEADER2=$(printf "0x4800000%x" $((${p} + ID_OFFSET))) + RADDR="" + if [ "${PROTO}" == "UDP" ]; then + RADDR=$(awk "NR == ${p} {print \$3}" ${UDP_PEERS_FILE}) + fi + + timeout ${TCPDUMP_TIMEOUT} ip netns exec peer${p} \ + tcpdump --immediate-mode -p -ni veth${p} -c 1 \ + "$(build_capture_filter "${HEADER1}" "${RADDR}")" \ + >/dev/null 2>&1 & + TCPDUMP_PID1=$! + timeout ${TCPDUMP_TIMEOUT} ip netns exec peer${p} \ + tcpdump --immediate-mode -p -ni veth${p} -c 1 \ + "$(build_capture_filter "${HEADER2}" "${RADDR}")" \ + >/dev/null 2>&1 & + TCPDUMP_PID2=$! + + sleep 0.3 ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1)) ip netns exec peer0 ping -qfc 500 -s 3000 -w 3 5.5.5.$((${p} + 1)) + + wait ${TCPDUMP_PID1} + wait ${TCPDUMP_PID2} done # ping LAN behind client 1 @@ -57,9 +92,12 @@ ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1 echo "Adding secondary key and then swap:" for p in $(seq 1 ${NUM_PEERS}); do - ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 2 1 ${ALG} 0 data64.key - ip netns exec peer${p} ${OVPN_CLI} new_key tun${p} ${p} 2 1 ${ALG} 1 data64.key - ip netns exec peer${p} ${OVPN_CLI} swap_keys tun${p} ${p} + ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 2 1 ${ALG} 0 \ + data64.key + ip netns exec peer${p} ${OVPN_CLI} new_key tun${p} \ + $((${p} + ID_OFFSET)) 2 1 ${ALG} 1 data64.key + ip netns exec peer${p} ${OVPN_CLI} swap_keys tun${p} \ + $((${p} + ID_OFFSET)) done sleep 1 @@ -71,17 +109,19 @@ ip netns exec peer1 ${OVPN_CLI} get_peer tun1 echo "Querying peer 1:" ip netns exec peer0 ${OVPN_CLI} get_peer tun0 1 -echo "Querying non-existent peer 10:" -ip netns exec peer0 ${OVPN_CLI} get_peer tun0 10 || true +echo "Querying non-existent peer 20:" +ip netns exec peer0 ${OVPN_CLI} get_peer tun0 20 || true echo "Deleting peer 1:" ip netns exec peer0 ${OVPN_CLI} del_peer tun0 1 -ip netns exec peer1 ${OVPN_CLI} del_peer tun1 1 +ip netns exec peer1 ${OVPN_CLI} del_peer tun1 $((1 + ID_OFFSET)) echo "Querying keys:" for p in $(seq 2 ${NUM_PEERS}); do - ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 1 - ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 2 + ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} \ + $((${p} + ID_OFFSET)) 1 + ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} \ + $((${p} + ID_OFFSET)) 2 done echo "Deleting peer while sending traffic:" @@ -90,28 +130,36 @@ sleep 2 ip netns exec peer0 ${OVPN_CLI} del_peer tun0 2 # following command fails in TCP mode # (both ends get conn reset when one peer disconnects) -ip netns exec peer2 ${OVPN_CLI} del_peer tun2 2 || true +ip netns exec peer2 ${OVPN_CLI} del_peer tun2 $((2 + ID_OFFSET)) || true echo "Deleting keys:" for p in $(seq 3 ${NUM_PEERS}); do - ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 1 - ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 2 + ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} \ + $((${p} + ID_OFFSET)) 1 + ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} \ + $((${p} + ID_OFFSET)) 2 done echo "Setting timeout to 3s MP:" for p in $(seq 3 ${NUM_PEERS}); do ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 3 3 || true - ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 0 0 + ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} \ + $((${p} + ID_OFFSET)) 0 0 done # wait for peers to timeout sleep 5 echo "Setting timeout to 3s P2P:" for p in $(seq 3 ${NUM_PEERS}); do - ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 3 3 + ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} \ + $((${p} + ID_OFFSET)) 3 3 done sleep 5 +for p in $(seq 0 ${NUM_PEERS}); do + compare_ntfs ${p} +done + cleanup modprobe -r ovpn || true diff --git a/tools/testing/selftests/net/ovpn/udp_peers.txt b/tools/testing/selftests/net/ovpn/udp_peers.txt index e9773ddf875c..93de6465353c 100644 --- a/tools/testing/selftests/net/ovpn/udp_peers.txt +++ b/tools/testing/selftests/net/ovpn/udp_peers.txt @@ -1,6 +1,6 @@ -1 10.10.1.1 1 10.10.1.2 1 5.5.5.2 -2 10.10.2.1 1 10.10.2.2 1 5.5.5.3 -3 10.10.3.1 1 10.10.3.2 1 5.5.5.4 -4 fd00:0:0:4::1 1 fd00:0:0:4::2 1 5.5.5.5 -5 fd00:0:0:5::1 1 fd00:0:0:5::2 1 5.5.5.6 -6 fd00:0:0:6::1 1 fd00:0:0:6::2 1 5.5.5.7 +1 10 10.10.1.1 1 10.10.1.2 1 5.5.5.2 +2 11 10.10.2.1 1 10.10.2.2 1 5.5.5.3 +3 12 10.10.3.1 1 10.10.3.2 1 5.5.5.4 +4 13 fd00:0:0:4::1 1 fd00:0:0:4::2 1 5.5.5.5 +5 14 fd00:0:0:5::1 1 fd00:0:0:5::2 1 5.5.5.6 +6 15 fd00:0:0:6::1 1 fd00:0:0:6::2 1 5.5.5.7 diff --git a/tools/testing/selftests/net/packetdrill/tcp_disorder_fin_in_FIN_WAIT.pkt b/tools/testing/selftests/net/packetdrill/tcp_disorder_fin_in_FIN_WAIT.pkt new file mode 100644 index 000000000000..336cbf7815c8 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_disorder_fin_in_FIN_WAIT.pkt @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Check fix in 795a7dfbc3d9 ("net: tcp: accept old ack during closing") + +// Set up config. +`./defaults.sh` + +// Initialize a server socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7> + * > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 shutdown(4, SHUT_WR) = 0 + * > F. 1:1(0) ack 1 + +// We expect to receive one ACK. +// But what happens if a FIN was already in transmt and received out-of-order ? + + +0 < . 2:2(0) ack 2 win 257 + +// This FIN packet was sent before the prior ACK (see ack 1). + +0 < F. 1:1(0) ack 1 win 257 + +// Even if the FIN is received out-of-order, we should ACK it. + + * > . 2:2(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt index 6c0f32c40f19..12882be10f2e 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -36,7 +36,7 @@ +0 read(4, ..., 100000) = 4000 -// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd +// If queue is empty, accept a packet even if its end_seq is above rcv_mwnd_seq +0 < P. 4001:54001(50000) ack 1 win 257 * > . 1:1(0) ack 54001 win 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_neg_window.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_neg_window.pkt new file mode 100644 index 000000000000..b9ab264b2a11 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_neg_window.pkt @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test maximum advertised window limit when rcv_nxt advances past +// rcv_mwnd_seq. The "usable window" must be properly clamped to zero +// rather than becoming negative. + +--mss=1000 + +`./defaults.sh` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + +// A too big packet is accepted if the receive queue is empty. It +// does not trigger an immediate ACK. + +0 < P. 1:20001(20000) ack 1 win 257 + +0 %{ assert tcpi_bytes_received == 20000, tcpi_bytes_received; }% + +// Send a RST immediately so that there is no rcv_wup/rcv_mwnd_seq update yet + +0 < R. 20001:20001(0) ack 1 win 257 + +// Verify that the RST was accepted. Indirectly this also verifies that no +// immediate ACK was sent for the data packet above. + +0 < . 20001:20001(0) ack 1 win 257 + +0 > R 1:1(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_allowed.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_allowed.pkt new file mode 100644 index 000000000000..6af0e0eb183a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_allowed.pkt @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_shrink_window=1 +sysctl -q net.ipv4.tcp_rmem="4096 32768 $((32*1024*1024))"` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 10> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:10001(10000) ack 1 win 257 + * > . 1:1(0) ack 10001 win 15 + + +0 < P. 10001:11024(1023) ack 1 win 257 + * > . 1:1(0) ack 11024 win 13 + +// Max window seq advertised 10001 + 15*1024 = 25361, last advertised: 11024 + 13*1024 = 24336 + +// Segment beyond the max window is dropped + +0 < P. 11024:25362(14338) ack 1 win 257 + * > . 1:1(0) ack 11024 win 13 + +// Segment using the max window is accepted + +0 < P. 11024:25361(14337) ack 1 win 257 + * > . 1:1(0) ack 25361 win 0 + +// Check LINUX_MIB_BEYOND_WINDOW has been incremented once + +0 `nstat | grep TcpExtBeyondWindow | grep -q " 1 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_nomem.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_nomem.pkt new file mode 100644 index 000000000000..a80eb55dc69a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_wnd_shrink_nomem.pkt @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +// When tcp_receive_window() < tcp_max_receive_window(), tcp_sequence() accepts +// packets that would be dropped under normal conditions (i.e. tcp_receive_window() +// equal to tcp_max_receive_window()). +// Test that such packets are handled as expected for RWIN == 0 and for RWIN > 0. + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [1000000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 4> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + +// Put 1040000 bytes into the receive buffer + +0 < P. 1:65001(65000) ack 1 win 257 + * > . 1:1(0) ack 65001 + +0 < P. 65001:130001(65000) ack 1 win 257 + * > . 1:1(0) ack 130001 + +0 < P. 130001:195001(65000) ack 1 win 257 + * > . 1:1(0) ack 195001 + +0 < P. 195001:260001(65000) ack 1 win 257 + * > . 1:1(0) ack 260001 + +0 < P. 260001:325001(65000) ack 1 win 257 + * > . 1:1(0) ack 325001 + +0 < P. 325001:390001(65000) ack 1 win 257 + * > . 1:1(0) ack 390001 + +0 < P. 390001:455001(65000) ack 1 win 257 + * > . 1:1(0) ack 455001 + +0 < P. 455001:520001(65000) ack 1 win 257 + * > . 1:1(0) ack 520001 + +0 < P. 520001:585001(65000) ack 1 win 257 + * > . 1:1(0) ack 585001 + +0 < P. 585001:650001(65000) ack 1 win 257 + * > . 1:1(0) ack 650001 + +0 < P. 650001:715001(65000) ack 1 win 257 + * > . 1:1(0) ack 715001 + +0 < P. 715001:780001(65000) ack 1 win 257 + * > . 1:1(0) ack 780001 + +0 < P. 780001:845001(65000) ack 1 win 257 + * > . 1:1(0) ack 845001 + +0 < P. 845001:910001(65000) ack 1 win 257 + * > . 1:1(0) ack 910001 + +0 < P. 910001:975001(65000) ack 1 win 257 + * > . 1:1(0) ack 975001 + +0 < P. 975001:1040001(65000) ack 1 win 257 + * > . 1:1(0) ack 1040001 + +// Trigger an extreme memory squeeze by shrinking SO_RCVBUF + +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [16000], 4) = 0 + + +0 < P. 1040001:1105001(65000) ack 1 win 257 + * > . 1:1(0) ack 1040001 win 0 +// Check LINUX_MIB_TCPRCVQDROP has been incremented + +0 `nstat -s | grep TcpExtTCPRcvQDrop| grep -q " 1 "` + +// RWIN == 0: rcv_wup = 1040001, rcv_wnd = 0, rcv_mwnd_seq > 1105001 (significantly larger, typically ~1970000) + +// Accept pure ack with seq in max adv. window + +0 write(4, ..., 1000) = 1000 + +0 > P. 1:1001(1000) ack 1040001 win 0 + +0 < . 1105001:1105001(0) ack 1001 win 257 + +// In order segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_ZEROWINDOW) + +0 < P. 1040001:1041001(1000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 +// Ooo partial segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_ZEROWINDOW) + +0 < P. 1039001:1041001(2000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 <nop,nop,sack 1039001:1040001> +// Check LINUX_MIB_TCPZEROWINDOWDROP has been incremented twice + +0 `nstat -s | grep TcpExtTCPZeroWindowDrop| grep -q " 2 "` + +// Ooo segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_OVERWINDOW) + +0 < P. 1105001:1106001(1000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 +// Ooo segment, beyond max adv. window -> drop (SKB_DROP_REASON_TCP_INVALID_SEQUENCE) + +0 < P. 2000001:2001001(1000) ack 1001 win 257 + +0 > . 1001:1001(0) ack 1040001 win 0 +// Check LINUX_MIB_BEYOND_WINDOW has been incremented twice + +0 `nstat -s | grep TcpExtBeyondWindow | grep -q " 2 "` + +// Read all data + +0 read(4, ..., 2000000) = 1040000 + * > . 1001:1001(0) ack 1040001 + +// RWIN > 0: rcv_wup = 1040001, 0 < rcv_wnd < 32000, rcv_mwnd_seq > 1105001 (significantly larger, typically ~1970000) + +// Accept pure ack with seq in max adv. window, beyond adv. window + +0 write(4, ..., 1000) = 1000 + +0 > P. 1001:2001(1000) ack 1040001 + +0 < . 1105001:1105001(0) ack 2001 win 257 + +// In order segment, in max adv. window, in adv. window -> accept +// Note: This also ensures that we cannot hit the empty queue exception in tcp_sequence() in the following tests + +0 < P. 1040001:1041001(1000) ack 2001 win 257 + * > . 2001:2001(0) ack 1041001 + +// Ooo partial segment, in adv. window -> accept + +0 < P. 1040001:1042001(2000) ack 2001 win 257 + +0 > . 2001:2001(0) ack 1042001 <nop,nop,sack 1040001:1041001> + +// Ooo segment, in max adv. window, beyond adv. window -> drop (SKB_DROP_REASON_TCP_OVERWINDOW) + +0 < P. 1105001:1106001(1000) ack 2001 win 257 + +0 > . 2001:2001(0) ack 1042001 +// Ooo segment, beyond max adv. window, beyond adv. window -> drop (SKB_DROP_REASON_TCP_INVALID_SEQUENCE) + +0 < P. 2000001:2001001(1000) ack 2001 win 257 + +0 > . 2001:2001(0) ack 1042001 +// Check LINUX_MIB_BEYOND_WINDOW has been incremented twice + +0 `nstat -s | grep TcpExtBeyondWindow | grep -q " 4 "` + +// We are allowed to go beyond the window and buffer with one packet + +0 < P. 1042001:1062001(20000) ack 2001 win 257 + * > . 2001:2001(0) ack 1062001 + +0 < P. 1062001:1082001(20000) ack 2001 win 257 + * > . 2001:2001(0) ack 1082001 win 0 + +// But not more: In order segment, in max adv. window -> drop (SKB_DROP_REASON_TCP_ZEROWINDOW) + +0 < P. 1082001:1083001(1000) ack 2001 win 257 + * > . 2001:2001(0) ack 1082001 +// Check LINUX_MIB_TCPZEROWINDOWDROP has been incremented again + +0 `nstat -s | grep TcpExtTCPZeroWindowDrop| grep -q " 3 "` diff --git a/tools/testing/selftests/net/ppp/Makefile b/tools/testing/selftests/net/ppp/Makefile new file mode 100644 index 000000000000..b39b0abadde6 --- /dev/null +++ b/tools/testing/selftests/net/ppp/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +TEST_PROGS := \ + ppp_async.sh \ + pppoe.sh \ +# end of TEST_PROGS + +TEST_FILES := \ + ppp_common.sh \ + pppoe-server-options \ +# end of TEST_FILES + +include ../../lib.mk diff --git a/tools/testing/selftests/net/ppp/config b/tools/testing/selftests/net/ppp/config new file mode 100644 index 000000000000..b45d25c5b970 --- /dev/null +++ b/tools/testing/selftests/net/ppp/config @@ -0,0 +1,9 @@ +CONFIG_IPV6=y +CONFIG_PACKET=y +CONFIG_PPP=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPPOE=m +CONFIG_PPPOE_HASH_BITS_4=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/net/ppp/ppp_async.sh b/tools/testing/selftests/net/ppp/ppp_async.sh new file mode 100755 index 000000000000..10f54c8dd0bc --- /dev/null +++ b/tools/testing/selftests/net/ppp/ppp_async.sh @@ -0,0 +1,43 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source ppp_common.sh + +# Temporary files for PTY symlinks +TTY_DIR=$(mktemp -d /tmp/ppp.XXXXXX) +TTY_SERVER="$TTY_DIR"/server +TTY_CLIENT="$TTY_DIR"/client + +# shellcheck disable=SC2329 +cleanup() { + cleanup_all_ns + [ -n "$SOCAT_PID" ] && kill_process "$SOCAT_PID" + rm -fr "$TTY_DIR" +} + +trap cleanup EXIT + +ppp_common_init +modprobe -q ppp_async + +# Create the virtual serial device +socat -d PTY,link="$TTY_SERVER",rawer PTY,link="$TTY_CLIENT",rawer & +SOCAT_PID=$! + +# Wait for symlinks to be created +slowwait 5 [ -L "$TTY_SERVER" ] + +# Start the PPP Server +ip netns exec "$NS_SERVER" pppd "$TTY_SERVER" 115200 \ + "$IP_SERVER":"$IP_CLIENT" \ + local noauth nodefaultroute debug + +# Start the PPP Client +ip netns exec "$NS_CLIENT" pppd "$TTY_CLIENT" 115200 \ + local noauth updetach nodefaultroute debug + +ppp_test_connectivity + +log_test "PPP async" + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/ppp/ppp_common.sh b/tools/testing/selftests/net/ppp/ppp_common.sh new file mode 100644 index 000000000000..40bbec317039 --- /dev/null +++ b/tools/testing/selftests/net/ppp/ppp_common.sh @@ -0,0 +1,45 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2153 + +source ../lib.sh + +IP_SERVER="192.168.200.1" +IP_CLIENT="192.168.200.2" + +ppp_common_init() { + # Package requirements + require_command socat + require_command pppd + require_command iperf3 + + # Check for root privileges + if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit "$ksft_skip" + fi + + # Namespaces + setup_ns NS_SERVER NS_CLIENT +} + +ppp_check_addr() { + dev=$1 + addr=$2 + ns=$3 + ip -netns "$ns" -4 addr show dev "$dev" 2>/dev/null | grep -q "$addr" + return $? +} + +ppp_test_connectivity() { + slowwait 10 ppp_check_addr "ppp0" "$IP_CLIENT" "$NS_CLIENT" + + ip netns exec "$NS_CLIENT" ping -c 3 "$IP_SERVER" + check_err $? + + ip netns exec "$NS_SERVER" iperf3 -s -1 -D + wait_local_port_listen "$NS_SERVER" 5201 tcp + + ip netns exec "$NS_CLIENT" iperf3 -c "$IP_SERVER" -Z -t 2 + check_err $? +} diff --git a/tools/testing/selftests/net/ppp/pppoe-server-options b/tools/testing/selftests/net/ppp/pppoe-server-options new file mode 100644 index 000000000000..66c8c9d319e9 --- /dev/null +++ b/tools/testing/selftests/net/ppp/pppoe-server-options @@ -0,0 +1,2 @@ +noauth +noipdefault diff --git a/tools/testing/selftests/net/ppp/pppoe.sh b/tools/testing/selftests/net/ppp/pppoe.sh new file mode 100755 index 000000000000..f67b51df7490 --- /dev/null +++ b/tools/testing/selftests/net/ppp/pppoe.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source ppp_common.sh + +VETH_SERVER="veth-server" +VETH_CLIENT="veth-client" +PPPOE_LOG=$(mktemp /tmp/pppoe.XXXXXX) + +# shellcheck disable=SC2329 +cleanup() { + cleanup_all_ns + [ -n "$SOCAT_PID" ] && kill_process "$SOCAT_PID" + rm -f "$PPPOE_LOG" +} + +trap cleanup EXIT + +require_command pppoe-server +ppp_common_init +modprobe -q pppoe + +# Try to locate pppoe.so plugin +PPPOE_PLUGIN=$(find /usr/{lib,lib64,lib32}/pppd/ -name pppoe.so -type f -print -quit) +if [ -z "$PPPOE_PLUGIN" ]; then + log_test_skip "PPPoE: pppoe.so plugin not found" + exit "$EXIT_STATUS" +fi + +# Create the veth pair +ip link add "$VETH_SERVER" type veth peer name "$VETH_CLIENT" +ip link set "$VETH_SERVER" netns "$NS_SERVER" +ip link set "$VETH_CLIENT" netns "$NS_CLIENT" +ip -netns "$NS_SERVER" link set "$VETH_SERVER" up +ip -netns "$NS_CLIENT" link set "$VETH_CLIENT" up + +# Start socat as syslog listener +socat -v -u UNIX-RECV:/dev/log OPEN:/dev/null > "$PPPOE_LOG" 2>&1 & +SOCAT_PID=$! + +# Start the PPP Server. Note that versions before 4.0 ignore -g option and +# instead use a hardcoded plugin path, so they may fail to find the plugin. +ip netns exec "$NS_SERVER" pppoe-server -I "$VETH_SERVER" \ + -L "$IP_SERVER" -R "$IP_CLIENT" -N 1 -q "$(command -v pppd)" \ + -k -O "$(pwd)/pppoe-server-options" -g "$PPPOE_PLUGIN" + +# Start the PPP Client +ip netns exec "$NS_CLIENT" pppd \ + local debug updetach noipdefault noauth nodefaultroute \ + plugin "$PPPOE_PLUGIN" nic-"$VETH_CLIENT" + +ppp_test_connectivity + +log_test "PPPoE" + +# Dump syslog messages if the test failed +if [ "$RET" -ne 0 ]; then + while read -r _sign _date _time len _from _to + do len=${len##*=} + read -n "$len" -r LINE + echo "$LINE" + done < "$PPPOE_LOG" +fi + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile index 762845cc973c..fe363be8e358 100644 --- a/tools/testing/selftests/net/rds/Makefile +++ b/tools/testing/selftests/net/rds/Makefile @@ -7,6 +7,7 @@ TEST_PROGS := run.sh TEST_FILES := \ include.sh \ + settings \ test.py \ # end of TEST_FILES diff --git a/tools/testing/selftests/net/rds/README.txt b/tools/testing/selftests/net/rds/README.txt index cbde2951ab13..c6fe003d503b 100644 --- a/tools/testing/selftests/net/rds/README.txt +++ b/tools/testing/selftests/net/rds/README.txt @@ -31,8 +31,11 @@ EXAMPLE: # Alternatly create a gcov disabled .config tools/testing/selftests/net/rds/config.sh + # Config paths may also be specified with the -c flag + tools/testing/selftests/net/rds/config.sh -c .config.local + # build the kernel - vng --build --config tools/testing/selftests/net/config + vng --build --config .config # launch the tests in a VM vng -v --rwdir ./ --run . --user root --cpus 4 -- \ diff --git a/tools/testing/selftests/net/rds/config b/tools/testing/selftests/net/rds/config new file mode 100644 index 000000000000..97db7ecb892a --- /dev/null +++ b/tools/testing/selftests/net/rds/config @@ -0,0 +1,5 @@ +CONFIG_NET_NS=y +CONFIG_NET_SCH_NETEM=y +CONFIG_RDS=y +CONFIG_RDS_TCP=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/net/rds/config.sh b/tools/testing/selftests/net/rds/config.sh index 791c8dbe1095..29a79314dd60 100755 --- a/tools/testing/selftests/net/rds/config.sh +++ b/tools/testing/selftests/net/rds/config.sh @@ -6,15 +6,20 @@ set -u set -x unset KBUILD_OUTPUT +CONF_FILE="" +FLAGS=() GENERATE_GCOV_REPORT=0 -while getopts "g" opt; do +while getopts "gc:" opt; do case ${opt} in g) GENERATE_GCOV_REPORT=1 ;; + c) + CONF_FILE=$OPTARG + ;; :) - echo "USAGE: config.sh [-g]" + echo "USAGE: config.sh [-g] [-c config]" exit 1 ;; ?) @@ -24,30 +29,32 @@ while getopts "g" opt; do esac done -CONF_FILE="tools/testing/selftests/net/config" +if [[ "$CONF_FILE" != "" ]]; then + FLAGS=(--file "$CONF_FILE") +fi # no modules -scripts/config --file "$CONF_FILE" --disable CONFIG_MODULES +scripts/config "${FLAGS[@]}" --disable CONFIG_MODULES # enable RDS -scripts/config --file "$CONF_FILE" --enable CONFIG_RDS -scripts/config --file "$CONF_FILE" --enable CONFIG_RDS_TCP +scripts/config "${FLAGS[@]}" --enable CONFIG_RDS +scripts/config "${FLAGS[@]}" --enable CONFIG_RDS_TCP if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then # instrument RDS and only RDS - scripts/config --file "$CONF_FILE" --enable CONFIG_GCOV_KERNEL - scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL - scripts/config --file "$CONF_FILE" --enable GCOV_PROFILE_RDS + scripts/config "${FLAGS[@]}" --enable CONFIG_GCOV_KERNEL + scripts/config "${FLAGS[@]}" --disable GCOV_PROFILE_ALL + scripts/config "${FLAGS[@]}" --enable GCOV_PROFILE_RDS else - scripts/config --file "$CONF_FILE" --disable CONFIG_GCOV_KERNEL - scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL - scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_RDS + scripts/config "${FLAGS[@]}" --disable CONFIG_GCOV_KERNEL + scripts/config "${FLAGS[@]}" --disable GCOV_PROFILE_ALL + scripts/config "${FLAGS[@]}" --disable GCOV_PROFILE_RDS fi # need network namespaces to run tests with veth network interfaces -scripts/config --file "$CONF_FILE" --enable CONFIG_NET_NS -scripts/config --file "$CONF_FILE" --enable CONFIG_VETH +scripts/config "${FLAGS[@]}" --enable CONFIG_NET_NS +scripts/config "${FLAGS[@]}" --enable CONFIG_VETH # simulate packet loss -scripts/config --file "$CONF_FILE" --enable CONFIG_NET_SCH_NETEM +scripts/config "${FLAGS[@]}" --enable CONFIG_NET_SCH_NETEM diff --git a/tools/testing/selftests/net/rds/run.sh b/tools/testing/selftests/net/rds/run.sh index 8aee244f582a..897d17d1b8db 100755 --- a/tools/testing/selftests/net/rds/run.sh +++ b/tools/testing/selftests/net/rds/run.sh @@ -19,6 +19,9 @@ if test -f "$build_include"; then build_dir="$mk_build_dir" fi +# Source settings for timeout value (also used by ksft runner) +source "$current_dir"/settings + # This test requires kernel source and the *.gcda data therein # Locate the top level of the kernel source, and the net/rds # subfolder with the appropriate *.gcno object files @@ -194,8 +197,8 @@ set +e echo running RDS tests... echo Traces will be logged to "$TRACE_FILE" rm -f "$TRACE_FILE" -strace -T -tt -o "$TRACE_FILE" python3 "$(dirname "$0")/test.py" --timeout 400 -d "$LOG_DIR" \ - -l "$PLOSS" -c "$PCORRUPT" -u "$PDUP" +strace -T -tt -o "$TRACE_FILE" python3 "$(dirname "$0")/test.py" \ + --timeout "$timeout" -d "$LOG_DIR" -l "$PLOSS" -c "$PCORRUPT" -u "$PDUP" test_rc=$? dmesg > "${LOG_DIR}/dmesg.out" diff --git a/tools/testing/selftests/net/rds/settings b/tools/testing/selftests/net/rds/settings new file mode 100644 index 000000000000..d2009a64589c --- /dev/null +++ b/tools/testing/selftests/net/rds/settings @@ -0,0 +1 @@ +timeout=400 diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py index 4a7178d11193..93e23e8b256c 100755 --- a/tools/testing/selftests/net/rds/test.py +++ b/tools/testing/selftests/net/rds/test.py @@ -11,9 +11,8 @@ import signal import socket import subprocess import sys -import atexit -from pwd import getpwuid -from os import stat +import tempfile +import shutil # Allow utils module to be imported from different directory this_dir = os.path.dirname(os.path.realpath(__file__)) @@ -23,45 +22,54 @@ from lib.py.utils import ip libc = ctypes.cdll.LoadLibrary('libc.so.6') setns = libc.setns -net0 = 'net0' -net1 = 'net1' +NET0 = 'net0' +NET1 = 'net1' -veth0 = 'veth0' -veth1 = 'veth1' +VETH0 = 'veth0' +VETH1 = 'veth1' # Helper function for creating a socket inside a network namespace. # We need this because otherwise RDS will detect that the two TCP # sockets are on the same interface and use the loop transport instead # of the TCP transport. -def netns_socket(netns, *args): +def netns_socket(netns, *sock_args): + """ + Creates sockets inside of network namespace + + :param netns: the name of the network namespace + :param sock_args: socket family and type + """ u0, u1 = socket.socketpair(socket.AF_UNIX, socket.SOCK_SEQPACKET) child = os.fork() if child == 0: # change network namespace - with open(f'/var/run/netns/{netns}') as f: + with open(f'/var/run/netns/{netns}', encoding='utf-8') as f: try: - ret = setns(f.fileno(), 0) + setns(f.fileno(), 0) except IOError as e: print(e.errno) print(e) # create socket in target namespace - s = socket.socket(*args) + sock = socket.socket(*sock_args) # send resulting socket to parent - socket.send_fds(u0, [], [s.fileno()]) + socket.send_fds(u0, [], [sock.fileno()]) sys.exit(0) # receive socket from child - _, s, _, _ = socket.recv_fds(u1, 0, 1) + _, fds, _, _ = socket.recv_fds(u1, 0, 1) os.waitpid(child, 0) u0.close() u1.close() - return socket.fromfd(s[0], *args) + return socket.fromfd(fds[0], *sock_args) -def signal_handler(sig, frame): +def signal_handler(_sig, _frame): + """ + Test timed out signal handler + """ print('Test timed out') sys.exit(1) @@ -81,13 +89,13 @@ parser.add_argument('-u', '--duplicate', help="Simulate tcp packet duplication", type=int, default=0) args = parser.parse_args() logdir=args.logdir -packet_loss=str(args.loss)+'%' -packet_corruption=str(args.corruption)+'%' -packet_duplicate=str(args.duplicate)+'%' +PACKET_LOSS=str(args.loss)+'%' +PACKET_CORRUPTION=str(args.corruption)+'%' +PACKET_DUPLICATE=str(args.duplicate)+'%' -ip(f"netns add {net0}") -ip(f"netns add {net1}") -ip(f"link add type veth") +ip(f"netns add {NET0}") +ip(f"netns add {NET1}") +ip("link add type veth") addrs = [ # we technically don't need different port numbers, but this will @@ -99,38 +107,38 @@ addrs = [ # move interfaces to separate namespaces so they can no longer be # bound directly; this prevents rds from switching over from the tcp # transport to the loop transport. -ip(f"link set {veth0} netns {net0} up") -ip(f"link set {veth1} netns {net1} up") +ip(f"link set {VETH0} netns {NET0} up") +ip(f"link set {VETH1} netns {NET1} up") # add addresses -ip(f"-n {net0} addr add {addrs[0][0]}/32 dev {veth0}") -ip(f"-n {net1} addr add {addrs[1][0]}/32 dev {veth1}") +ip(f"-n {NET0} addr add {addrs[0][0]}/32 dev {VETH0}") +ip(f"-n {NET1} addr add {addrs[1][0]}/32 dev {VETH1}") # add routes -ip(f"-n {net0} route add {addrs[1][0]}/32 dev {veth0}") -ip(f"-n {net1} route add {addrs[0][0]}/32 dev {veth1}") +ip(f"-n {NET0} route add {addrs[1][0]}/32 dev {VETH0}") +ip(f"-n {NET1} route add {addrs[0][0]}/32 dev {VETH1}") # sanity check that our two interfaces/addresses are correctly set up # and communicating by doing a single ping -ip(f"netns exec {net0} ping -c 1 {addrs[1][0]}") +ip(f"netns exec {NET0} ping -c 1 {addrs[1][0]}") # Start a packet capture on each network -for net in [net0, net1]: - tcpdump_pid = os.fork() - if tcpdump_pid == 0: - pcap = logdir+'/'+net+'.pcap' - subprocess.check_call(['touch', pcap]) - user = getpwuid(stat(pcap).st_uid).pw_name - ip(f"netns exec {net} /usr/sbin/tcpdump -Z {user} -i any -w {pcap}") - sys.exit(0) +tcpdump_procs = [] +for net in [NET0, NET1]: + pcap = logdir+'/'+net+'.pcap' + fd, pcap_tmp = tempfile.mkstemp(suffix=".pcap", prefix=f"{net}-", dir="/tmp") + p = subprocess.Popen( + ['ip', 'netns', 'exec', net, + '/usr/sbin/tcpdump', '-i', 'any', '-w', pcap_tmp]) + tcpdump_procs.append((p, pcap_tmp, pcap, fd)) # simulate packet loss, duplication and corruption -for net, iface in [(net0, veth0), (net1, veth1)]: +for net, iface in [(NET0, VETH0), (NET1, VETH1)]: ip(f"netns exec {net} /usr/sbin/tc qdisc add dev {iface} root netem \ - corrupt {packet_corruption} loss {packet_loss} duplicate \ - {packet_duplicate}") + corrupt {PACKET_CORRUPTION} loss {PACKET_LOSS} duplicate \ + {PACKET_DUPLICATE}") # add a timeout if args.timeout > 0: @@ -138,8 +146,8 @@ if args.timeout > 0: signal.signal(signal.SIGALRM, signal_handler) sockets = [ - netns_socket(net0, socket.AF_RDS, socket.SOCK_SEQPACKET), - netns_socket(net1, socket.AF_RDS, socket.SOCK_SEQPACKET), + netns_socket(NET0, socket.AF_RDS, socket.SOCK_SEQPACKET), + netns_socket(NET1, socket.AF_RDS, socket.SOCK_SEQPACKET), ] for s, addr in zip(sockets, addrs): @@ -150,9 +158,7 @@ fileno_to_socket = { s.fileno(): s for s in sockets } -addr_to_socket = { - addr: s for addr, s in zip(addrs, sockets) -} +addr_to_socket = dict(zip(addrs, sockets)) socket_to_addr = { s: addr for addr, s in zip(addrs, sockets) @@ -166,14 +172,14 @@ ep = select.epoll() for s in sockets: ep.register(s, select.EPOLLRDNORM) -n = 50000 +NUM_PACKETS = 50000 nr_send = 0 nr_recv = 0 -while nr_send < n: +while nr_send < NUM_PACKETS: # Send as much as we can without blocking print("sending...", nr_send, nr_recv) - while nr_send < n: + while nr_send < NUM_PACKETS: send_data = hashlib.sha256( f'packet {nr_send}'.encode('utf-8')).hexdigest().encode('utf-8') @@ -212,7 +218,7 @@ while nr_send < n: break # exercise net/rds/tcp.c:rds_tcp_sysctl_reset() - for net in [net0, net1]: + for net in [NET0, NET1]: ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_rcvbuf=10000") ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_sndbuf=10000") @@ -242,7 +248,11 @@ for s in sockets: print(f"getsockopt(): {nr_success}/{nr_error}") print("Stopping network packet captures") -subprocess.check_call(['killall', '-q', 'tcpdump']) +for p, pcap_tmp, pcap, fd in tcpdump_procs: + p.terminate() + p.wait() + os.close(fd) + shutil.move(pcap_tmp, pcap) # We're done sending and receiving stuff, now let's check if what # we received is what we sent. diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c index b6634d6da3d6..12e48b97b862 100644 --- a/tools/testing/selftests/net/reuseport_bpf.c +++ b/tools/testing/selftests/net/reuseport_bpf.c @@ -23,6 +23,7 @@ #include <sys/socket.h> #include <sys/resource.h> #include <unistd.h> +#include <sched.h> #include "kselftest.h" @@ -455,8 +456,18 @@ static __attribute__((destructor)) void main_dtor(void) setrlimit(RLIMIT_MEMLOCK, &rlim_old); } +static void setup_netns(void) +{ + if (unshare(CLONE_NEWNET)) + error(1, errno, "failed to unshare netns"); + if (system("ip link set lo up")) + error(1, 0, "failed to bring up lo interface in netns"); +} + int main(void) { + setup_netns(); + fprintf(stderr, "---- IPv4 UDP ----\n"); /* NOTE: UDP socket lookups traverse a different code path when there * are > 10 sockets in a group. Run the bpf test through both paths. diff --git a/tools/testing/selftests/net/reuseport_bpf_cpu.c b/tools/testing/selftests/net/reuseport_bpf_cpu.c index 2d646174729f..ddfe92f6597a 100644 --- a/tools/testing/selftests/net/reuseport_bpf_cpu.c +++ b/tools/testing/selftests/net/reuseport_bpf_cpu.c @@ -228,10 +228,20 @@ static void test(int *rcv_fd, int len, int family, int proto) close(rcv_fd[cpu]); } +static void setup_netns(void) +{ + if (unshare(CLONE_NEWNET)) + error(1, errno, "failed to unshare netns"); + if (system("ip link set lo up")) + error(1, 0, "failed to bring up lo interface in netns"); +} + int main(void) { int *rcv_fd, cpus; + setup_netns(); + cpus = sysconf(_SC_NPROCESSORS_ONLN); if (cpus <= 0) error(1, errno, "failed counting cpus"); diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c index 2ffd957ffb15..8ec52fc5ef41 100644 --- a/tools/testing/selftests/net/reuseport_bpf_numa.c +++ b/tools/testing/selftests/net/reuseport_bpf_numa.c @@ -230,10 +230,20 @@ static void test(int *rcv_fd, int len, int family, int proto) close(rcv_fd[node]); } +static void setup_netns(void) +{ + if (unshare(CLONE_NEWNET)) + error(1, errno, "failed to unshare netns"); + if (system("ip link set lo up")) + error(1, 0, "failed to bring up lo interface in netns"); +} + int main(void) { int *rcv_fd, nodes; + setup_netns(); + if (numa_available() < 0) ksft_exit_skip("no numa api support\n"); diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c index fb7a59ed759e..0eaf739d0c85 100644 --- a/tools/testing/selftests/net/reuseport_dualstack.c +++ b/tools/testing/selftests/net/reuseport_dualstack.c @@ -25,6 +25,7 @@ #include <sys/types.h> #include <sys/socket.h> #include <unistd.h> +#include <sched.h> static const int PORT = 8888; @@ -156,10 +157,20 @@ static void test(int *rcv_fds, int count, int proto) close(epfd); } +static void setup_netns(void) +{ + if (unshare(CLONE_NEWNET)) + error(1, errno, "failed to unshare netns"); + if (system("ip link set lo up")) + error(1, 0, "failed to bring up lo interface in netns"); +} + int main(void) { int rcv_fds[32], i; + setup_netns(); + fprintf(stderr, "---- UDP IPv4 created before IPv6 ----\n"); build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 5); build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[5]), 5); diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh index 6a68c7eff1dc..cd7d061e21f8 100755 --- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh @@ -193,6 +193,8 @@ ret=${ksft_skip} nsuccess=0 nfail=0 +HAS_TUNSRC=false + log_test() { local rc="$1" @@ -345,6 +347,17 @@ setup_rt_networking() ip -netns "${nsname}" addr \ add "${net_prefix}::${rt}/64" dev "${devname}" nodad + # A dedicated ::dead:<rt> address (with preferred_lft 0, i.e., + # deprecated) is added when there is support for tunsrc. Because + # it is deprecated, the kernel should never auto-select it as + # source with current config. Only an explicit tunsrc can place + # it in the outer header. + if $HAS_TUNSRC; then + ip -netns "${nsname}" addr \ + add "${net_prefix}::dead:${rt}/64" \ + dev "${devname}" nodad preferred_lft 0 + fi + ip -netns "${nsname}" link set "${devname}" up done @@ -420,6 +433,7 @@ setup_rt_local_sids() # to the destination host) # $5 - encap mode (full or red) # $6 - traffic type (IPv6 or IPv4) +# $7 - force tunsrc (true or false) __setup_rt_policy() { local dst="$1" @@ -428,10 +442,46 @@ __setup_rt_policy() local dec_rt="$4" local mode="$5" local traffic="$6" + local with_tunsrc="$7" local nsname local policy='' + local tunsrc='' local n + # Verify the per-route tunnel source address ("tunsrc") feature. + # If it is not supported, fallback on encap config without tunsrc. + if $with_tunsrc && $HAS_TUNSRC; then + local net_prefix + local drule + local nxt + + eval nsname=\${$(get_rtname "${dec_rt}")} + + # Next SRv6 hop: first End router if any, or the decap router + [ -z "${end_rts}" ] && nxt="${dec_rt}" || nxt="${end_rts%% *}" + + # Use the right prefix for tunsrc depending on the next SRv6 hop + net_prefix="$(get_network_prefix "${encap_rt}" "${nxt}")" + tunsrc="tunsrc ${net_prefix}::dead:${encap_rt}" + + # To verify that the outer source address matches the one + # configured with tunsrc, the decap router discards packets + # with any other source address. + ip netns exec "${nsname}" ip6tables -t raw -I PREROUTING 1 \ + -s "${net_prefix}::dead:${encap_rt}" \ + -d "${VPN_LOCATOR_SERVICE}:${dec_rt}::${DT46_FUNC}" \ + -j ACCEPT + + drule="PREROUTING \ + -d ${VPN_LOCATOR_SERVICE}:${dec_rt}::${DT46_FUNC} \ + -j DROP" + + if ! ip netns exec "${nsname}" \ + ip6tables -t raw -C ${drule} &>/dev/null; then + ip netns exec "${nsname}" ip6tables -t raw -A ${drule} + fi + fi + eval nsname=\${$(get_rtname "${encap_rt}")} for n in ${end_rts}; do @@ -444,7 +494,7 @@ __setup_rt_policy() if [ "${traffic}" -eq 6 ]; then ip -netns "${nsname}" -6 route \ add "${IPv6_HS_NETWORK}::${dst}" vrf "${VRF_DEVNAME}" \ - encap seg6 mode "${mode}" segs "${policy}" \ + encap seg6 mode "${mode}" ${tunsrc} segs "${policy}" \ dev "${VRF_DEVNAME}" ip -netns "${nsname}" -6 neigh \ @@ -455,7 +505,7 @@ __setup_rt_policy() # received, otherwise the proxy arp does not work. ip -netns "${nsname}" -4 route \ add "${IPv4_HS_NETWORK}.${dst}" vrf "${VRF_DEVNAME}" \ - encap seg6 mode "${mode}" segs "${policy}" \ + encap seg6 mode "${mode}" ${tunsrc} segs "${policy}" \ dev "${VRF_DEVNAME}" fi } @@ -463,13 +513,13 @@ __setup_rt_policy() # see __setup_rt_policy setup_rt_policy_ipv6() { - __setup_rt_policy "$1" "$2" "$3" "$4" "$5" 6 + __setup_rt_policy "$1" "$2" "$3" "$4" "$5" 6 "$6" } #see __setup_rt_policy setup_rt_policy_ipv4() { - __setup_rt_policy "$1" "$2" "$3" "$4" "$5" 4 + __setup_rt_policy "$1" "$2" "$3" "$4" "$5" 4 "$6" } setup_hs() @@ -567,41 +617,41 @@ setup() # the network path between hs-1 and hs-2 traverses several routers # depending on the direction of traffic. # - # Direction hs-1 -> hs-2 (H.Encaps.Red) + # Direction hs-1 -> hs-2 (H.Encaps.Red + tunsrc) # - rt-3,rt-4 (SRv6 End behaviors) # - rt-2 (SRv6 End.DT46 behavior) # # Direction hs-2 -> hs-1 (H.Encaps.Red) # - rt-1 (SRv6 End.DT46 behavior) - setup_rt_policy_ipv6 2 1 "3 4" 2 encap.red - setup_rt_policy_ipv6 1 2 "" 1 encap.red + setup_rt_policy_ipv6 2 1 "3 4" 2 encap.red true + setup_rt_policy_ipv6 1 2 "" 1 encap.red false # create an IPv4 VPN between hosts hs-1 and hs-2 # the network path between hs-1 and hs-2 traverses several routers # depending on the direction of traffic. # - # Direction hs-1 -> hs-2 (H.Encaps.Red) + # Direction hs-1 -> hs-2 (H.Encaps.Red + tunsrc) # - rt-2 (SRv6 End.DT46 behavior) # # Direction hs-2 -> hs-1 (H.Encaps.Red) # - rt-4,rt-3 (SRv6 End behaviors) # - rt-1 (SRv6 End.DT46 behavior) - setup_rt_policy_ipv4 2 1 "" 2 encap.red - setup_rt_policy_ipv4 1 2 "4 3" 1 encap.red + setup_rt_policy_ipv4 2 1 "" 2 encap.red true + setup_rt_policy_ipv4 1 2 "4 3" 1 encap.red false # create an IPv6 VPN between hosts hs-3 and hs-4 # the network path between hs-3 and hs-4 traverses several routers # depending on the direction of traffic. # - # Direction hs-3 -> hs-4 (H.Encaps.Red) + # Direction hs-3 -> hs-4 (H.Encaps.Red + tunsrc) # - rt-2 (SRv6 End Behavior) # - rt-4 (SRv6 End.DT46 behavior) # # Direction hs-4 -> hs-3 (H.Encaps.Red) # - rt-1 (SRv6 End behavior) # - rt-3 (SRv6 End.DT46 behavior) - setup_rt_policy_ipv6 4 3 "2" 4 encap.red - setup_rt_policy_ipv6 3 4 "1" 3 encap.red + setup_rt_policy_ipv6 4 3 "2" 4 encap.red true + setup_rt_policy_ipv6 3 4 "1" 3 encap.red false # testing environment was set up successfully SETUP_ERR=0 @@ -809,6 +859,38 @@ test_vrf_or_ksft_skip() fi } +# Before enabling tunsrc tests, make sure tunsrc and ip6tables are supported. +check_tunsrc_support() +{ + setup_ns tunsrc_ns + + ip -netns "${tunsrc_ns}" link add veth0 type veth \ + peer name veth1 netns "${tunsrc_ns}" + + ip -netns "${tunsrc_ns}" link set veth0 up + + if ! ip -netns "${tunsrc_ns}" -6 route add fc00::dead:beef/128 \ + encap seg6 mode encap.red tunsrc fc00::1 segs fc00::2 \ + dev veth0 &>/dev/null; then + cleanup_ns "${tunsrc_ns}" + return + fi + + if ! ip -netns "${tunsrc_ns}" -6 route show | grep -q "tunsrc"; then + cleanup_ns "${tunsrc_ns}" + return + fi + + if ! ip netns exec "${tunsrc_ns}" ip6tables -t raw -A PREROUTING \ + -d fc00::dead:beef -j DROP &>/dev/null; then + cleanup_ns "${tunsrc_ns}" + return + fi + + cleanup_ns "${tunsrc_ns}" + HAS_TUNSRC=true +} + if [ "$(id -u)" -ne 0 ]; then echo "SKIP: Need root privileges" exit "${ksft_skip}" @@ -826,6 +908,7 @@ test_vrf_or_ksft_skip set -e trap cleanup EXIT +check_tunsrc_support setup set +e diff --git a/tools/testing/selftests/net/xfrm_state.sh b/tools/testing/selftests/net/xfrm_state.sh new file mode 100755 index 000000000000..f6c54a6496d7 --- /dev/null +++ b/tools/testing/selftests/net/xfrm_state.sh @@ -0,0 +1,613 @@ +#!/bin/bash -e +# SPDX-License-Identifier: GPL-2.0 +# +# xfrm/IPsec tests. +# Currently implemented: +# - ICMP error source address verification (IETF RFC 4301 section 6) +# - ICMP MTU exceeded handling over IPsec tunnels. +# +# Addresses and topology: +# IPv4 prefix 10.1.c.d IPv6 prefix fc00:c::d/64 where c is the segment number +# and d is the interface identifier. +# IPv6 uses the same c:d as IPv4, and start with IPv6 prefix instead ipv4 prefix +# +# Network topology default: ns_set_v4 or ns_set_v6 +# 1.1 1.2 2.1 2.2 3.1 3.2 4.1 4.2 5.1 5.2 6.1 6.2 +# eth0 eth1 eth0 eth1 eth0 eth1 eth0 eth1 eth0 eth1 eth0 eth1 +# a -------- r1 -------- s1 -------- r2 -------- s2 -------- r3 -------- b +# a, b = Alice and Bob hosts without IPsec. +# r1, r2, r3 routers, without IPsec +# s1, s2, IPsec gateways/routers that setup tunnel(s). + +# Network topology x: IPsec gateway that generates ICMP response - ns_set_v4x or ns_set_v6x +# 1.1 1.2 2.1 2.2 3.1 3.2 4.1 4.2 5.1 5.2 +# eth0 eth1 eth0 eth1 eth0 eth1 eth0 eth1 eth0 eth1 +# a -------- r1 -------- s1 -------- r2 -------- s2 -------- b + +. lib.sh + +EXIT_ON_TEST_FAIL=no +PAUSE=no +VERBOSE=${VERBOSE:-0} +DEBUG=0 + +# Name Description +tests=" + unreachable_ipv4 IPv4 unreachable from router r3 + unreachable_ipv6 IPv6 unreachable from router r3 + unreachable_gw_ipv4 IPv4 unreachable from IPsec gateway s2 + unreachable_gw_ipv6 IPv6 unreachable from IPsec gateway s2 + mtu_ipv4_s2 IPv4 MTU exceeded from IPsec gateway s2 + mtu_ipv6_s2 IPv6 MTU exceeded from IPsec gateway s2 + mtu_ipv4_r2 IPv4 MTU exceeded from ESP router r2 + mtu_ipv6_r2 IPv6 MTU exceeded from ESP router r2 + mtu_ipv4_r3 IPv4 MTU exceeded from router r3 + mtu_ipv6_r3 IPv6 MTU exceeded from router r3" + +prefix4="10.1" +prefix6="fc00" + +run_cmd_err() { + cmd="$*" + + if [ "$VERBOSE" -gt 0 ]; then + printf " COMMAND: %s\n" "$cmd" + fi + + out="$($cmd 2>&1)" && rc=0 || rc=$? + if [ "$VERBOSE" -gt 1 ] && [ -n "$out" ]; then + echo " $out" + echo + fi + return 0 +} + +run_cmd() { + run_cmd_err "$@" || exit 1 +} + +run_test() { + # If errexit is set, unset it for sub-shell and restore after test + errexit=0 + if [[ $- =~ "e" ]]; then + errexit=1 + set +e + fi + + ( + unset IFS + + # shellcheck disable=SC2030 # fail is read by trap/cleanup within this subshell + fail="yes" + + # Since cleanup() relies on variables modified by this sub shell, + # it has to run in this context. + trap 'log_test_error $?; cleanup' EXIT INT TERM + + if [ "$VERBOSE" -gt 0 ]; then + printf "\n#############################################################\n\n" + fi + + ret=0 + case "${name}" in + # can't use eval and test names shell check will complain about unused code + unreachable_ipv4) test_unreachable_ipv4 ;; + unreachable_ipv6) test_unreachable_ipv6 ;; + unreachable_gw_ipv4) test_unreachable_gw_ipv4 ;; + unreachable_gw_ipv6) test_unreachable_gw_ipv6 ;; + mtu_ipv4_s2) test_mtu_ipv4_s2 ;; + mtu_ipv6_s2) test_mtu_ipv6_s2 ;; + mtu_ipv4_r2) test_mtu_ipv4_r2 ;; + mtu_ipv6_r2) test_mtu_ipv6_r2 ;; + mtu_ipv4_r3) test_mtu_ipv4_r3 ;; + mtu_ipv6_r3) test_mtu_ipv6_r3 ;; + esac + ret=$? + + if [ $ret -eq 0 ]; then + fail="no" + + if [ "$VERBOSE" -gt 1 ]; then + show_icmp_filter + fi + + printf "TEST: %-60s [ PASS ]\n" "${desc}" + elif [ $ret -eq "$ksft_skip" ]; then + fail="no" + printf "TEST: %-60s [SKIP]\n" "${desc}" + fi + + return $ret + ) + ret=$? + + [ $errexit -eq 1 ] && set -e + + case $ret in + 0) + all_skipped=false + [ "$exitcode" -eq "$ksft_skip" ] && exitcode=0 + ;; + "$ksft_skip") + [ $all_skipped = true ] && exitcode=$ksft_skip + ;; + *) + all_skipped=false + exitcode=1 + ;; + esac + + return 0 # don't trigger errexit (-e); actual status in exitcode +} + +setup_namespaces() { + local namespaces="" + + NS_A="" + NS_B="" + NS_R1="" + NS_R2="" + NS_R3="" + NS_S1="" + NS_S2="" + + for ns in ${ns_set}; do + namespaces="$namespaces NS_${ns^^}" + done + + # shellcheck disable=SC2086 # setup_ns expects unquoted list + setup_ns $namespaces + + ns_active= #ordered list of namespaces for this test. + + [ -n "${NS_A}" ] && ns_a=(ip netns exec "${NS_A}") && ns_active="${ns_active} $NS_A" + [ -n "${NS_R1}" ] && ns_active="${ns_active} $NS_R1" + [ -n "${NS_S1}" ] && ns_s1=(ip netns exec "${NS_S1}") && ns_active="${ns_active} $NS_S1" + [ -n "${NS_R2}" ] && ns_r2=(ip netns exec "${NS_R2}") && ns_active="${ns_active} $NS_R2" + [ -n "${NS_S2}" ] && ns_s2=(ip netns exec "${NS_S2}") && ns_active="${ns_active} $NS_S2" + [ -n "${NS_R3}" ] && ns_r3=(ip netns exec "${NS_R3}") && ns_active="${ns_active} $NS_R3" + [ -n "${NS_B}" ] && ns_active="${ns_active} $NS_B" +} + +addr_add() { + local -a ns_cmd=(ip netns exec "$1") + local addr="$2" + local dev="$3" + + run_cmd "${ns_cmd[@]}" ip addr add "${addr}" dev "${dev}" + run_cmd "${ns_cmd[@]}" ip link set up "${dev}" +} + +veth_add() { + local ns=$2 + local pns=$1 + local -a ns_cmd=(ip netns exec "${pns}") + local ln="eth0" + local rn="eth1" + + run_cmd "${ns_cmd[@]}" ip link add "${ln}" type veth peer name "${rn}" netns "${ns}" +} + +show_icmp_filter() { + run_cmd "${ns_r2[@]}" nft list ruleset + echo "$out" +} + +setup_icmp_filter() { + run_cmd "${ns_r2[@]}" nft add table inet filter + run_cmd "${ns_r2[@]}" nft add chain inet filter FORWARD \ + '{ type filter hook forward priority filter; policy drop ; }' + run_cmd "${ns_r2[@]}" nft add rule inet filter FORWARD counter ip protocol esp \ + counter log accept + run_cmd "${ns_r2[@]}" nft add rule inet filter FORWARD counter ip protocol \ + icmp counter log drop + + if [ "$VERBOSE" -gt 0 ]; then + run_cmd "${ns_r2[@]}" nft list ruleset + echo "$out" + fi +} + +setup_icmpv6_filter() { + run_cmd "${ns_r2[@]}" nft add table inet filter + run_cmd "${ns_r2[@]}" nft add chain inet filter FORWARD \ + '{ type filter hook forward priority filter; policy drop ; }' + run_cmd "${ns_r2[@]}" nft add rule inet filter FORWARD ip6 nexthdr \ + ipv6-icmp icmpv6 type echo-request counter log drop + run_cmd "${ns_r2[@]}" nft add rule inet filter FORWARD ip6 nexthdr esp \ + counter log accept + run_cmd "${ns_r2[@]}" nft add rule inet filter FORWARD ip6 nexthdr \ + ipv6-icmp icmpv6 type \ + '{nd-neighbor-solicit,nd-neighbor-advert,nd-router-solicit,nd-router-advert}' \ + counter log drop + if [ "$VERBOSE" -gt 0 ]; then + run_cmd "${ns_r2[@]}" nft list ruleset + echo "$out" + fi +} + +set_xfrm_params() { + s1_src=${src} + s1_dst=${dst} + s1_src_net=${src_net} + s1_dst_net=${dst_net} +} + +setup_ns_set_v4() { + ns_set="a r1 s1 r2 s2 r3 b" # Network topology default + imax=$(echo "$ns_set" | wc -w) # number of namespaces in this topology + + src="10.1.3.1" + dst="10.1.4.2" + src_net="10.1.1.0/24" + dst_net="10.1.6.0/24" + + prefix=${prefix4} + prefix_len=24 + s="." + S="." + + set_xfrm_params +} + +setup_ns_set_v4x() { + ns_set="a r1 s1 r2 s2 b" # Network topology: x + imax=$(echo "$ns_set" | wc -w) # number of namespaces in this topology + prefix=${prefix4} + s="." + S="." + src="10.1.3.1" + dst="10.1.4.2" + src_net="10.1.1.0/24" + dst_net="10.1.5.0/24" + prefix_len=24 + + set_xfrm_params +} + +setup_ns_set_v6() { + ns_set="a r1 s1 r2 s2 r3 b" # Network topology default + imax=$(echo "$ns_set" | wc -w) # number of namespaces in this topology + prefix=${prefix6} + s=":" + S="::" + src="fc00:3::1" + dst="fc00:4::2" + src_net="fc00:1::0/64" + dst_net="fc00:6::0/64" + prefix_len=64 + + set_xfrm_params +} + +setup_ns_set_v6x() { + ns_set="a r1 s1 r2 s2 b" # Network topology: x + imax=$(echo "$ns_set" | wc -w) + prefix=${prefix6} + s=":" + S="::" + src="fc00:3::1" + dst="fc00:4::2" + src_net="fc00:1::0/64" + dst_net="fc00:5::0/64" + prefix_len=64 + + set_xfrm_params +} + +setup_network() { + # Create veths and add addresses + local -a ns_cmd + i=1 + p="" + for ns in ${ns_active}; do + ns_cmd=(ip netns exec "${ns}") + + if [ "${i}" -ne 1 ]; then + # Create veth between previous and current namespace + veth_add "${p}" "${ns}" + # Add addresses: previous gets .1 on eth0, current gets .2 on eth1 + addr_add "${p}" "${prefix}${s}$((i-1))${S}1/${prefix_len}" eth0 + addr_add "${ns}" "${prefix}${s}$((i-1))${S}2/${prefix_len}" eth1 + fi + + # Enable forwarding + run_cmd "${ns_cmd[@]}" sysctl -q net/ipv4/ip_forward=1 + run_cmd "${ns_cmd[@]}" sysctl -q net/ipv6/conf/all/forwarding=1 + run_cmd "${ns_cmd[@]}" sysctl -q net/ipv6/conf/default/accept_dad=0 + + p=${ns} + i=$((i + 1)) + done + + # Add routes (needs all addresses to exist first) + i=1 + for ns in ${ns_active}; do + ns_cmd=(ip netns exec "${ns}") + + # Forward routes to networks beyond this node + if [ "${i}" -ne "${imax}" ]; then + nhf="${prefix}${s}${i}${S}2" # nexthop forward + for j in $(seq $((i + 1)) "${imax}"); do + run_cmd "${ns_cmd[@]}" ip route replace \ + "${prefix}${s}${j}${S}0/${prefix_len}" via "${nhf}" + done + fi + + # Reverse routes to networks before this node + if [ "${i}" -gt 1 ]; then + nhr="${prefix}${s}$((i-1))${S}1" # nexthop reverse + for j in $(seq 1 $((i - 2))); do + run_cmd "${ns_cmd[@]}" ip route replace \ + "${prefix}${s}${j}${S}0/${prefix_len}" via "${nhr}" + done + fi + + i=$((i + 1)) + done +} + +setup_xfrm_mode() { + local MODE=${1:-tunnel} + if [ "${MODE}" != "tunnel" ] && [ "${MODE}" != "beet" ]; then + echo "xfrm mode ${MODE} not supported" + log_test_error + return 1 + fi + + run_cmd "${ns_s1[@]}" ip xfrm policy add src "${s1_src_net}" dst "${s1_dst_net}" dir out \ + tmpl src "${s1_src}" dst "${s1_dst}" proto esp reqid 1 mode "${MODE}" + + # no "input" policies. we are only doing forwarding so far + + run_cmd "${ns_s1[@]}" ip xfrm policy add src "${s1_dst_net}" dst "${s1_src_net}" dir fwd \ + flag icmp tmpl src "${s1_dst}" dst "${s1_src}" proto esp reqid 2 mode "${MODE}" + + run_cmd "${ns_s1[@]}" ip xfrm state add src "${s1_src}" dst "${s1_dst}" proto esp spi 1 \ + reqid 1 mode "${MODE}" aead 'rfc4106(gcm(aes))' \ + 0x1111111111111111111111111111111111111111 96 \ + sel src "${s1_src_net}" dst "${s1_dst_net}" dir out + + run_cmd "${ns_s1[@]}" ip xfrm state add src "${s1_dst}" dst "${s1_src}" proto esp spi 2 \ + reqid 2 flag icmp replay-window 8 mode "${MODE}" aead 'rfc4106(gcm(aes))' \ + 0x2222222222222222222222222222222222222222 96 \ + sel src "${s1_dst_net}" dst "${s1_src_net}" dir in + + run_cmd "${ns_s2[@]}" ip xfrm policy add src "${s1_dst_net}" dst "${s1_src_net}" dir out \ + flag icmp tmpl src "${s1_dst}" dst "${s1_src}" proto esp reqid 2 mode "${MODE}" + + run_cmd "${ns_s2[@]}" ip xfrm policy add src "${s1_src_net}" dst "${s1_dst_net}" dir fwd \ + tmpl src "${s1_src}" dst "${s1_dst}" proto esp reqid 1 mode "${MODE}" + + run_cmd "${ns_s2[@]}" ip xfrm state add src "${s1_dst}" dst "${s1_src}" proto esp spi 2 \ + reqid 2 mode "${MODE}" aead 'rfc4106(gcm(aes))' \ + 0x2222222222222222222222222222222222222222 96 \ + sel src "${s1_dst_net}" dst "${s1_src_net}" dir out + + run_cmd "${ns_s2[@]}" ip xfrm state add src "${s1_src}" dst "${s1_dst}" proto esp spi 1 \ + reqid 1 flag icmp replay-window 8 mode "${MODE}" aead 'rfc4106(gcm(aes))' \ + 0x1111111111111111111111111111111111111111 96 \ + sel src "${s1_src_net}" dst "${s1_dst_net}" dir in +} + +setup_xfrm() { + setup_xfrm_mode tunnel +} + +setup() { + [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return "$ksft_skip" + + for arg; do + case "${arg}" in + ns_set_v4) setup_ns_set_v4 ;; + ns_set_v4x) setup_ns_set_v4x ;; + ns_set_v6) setup_ns_set_v6 ;; + ns_set_v6x) setup_ns_set_v6x ;; + namespaces) setup_namespaces ;; + network) setup_network ;; + xfrm) setup_xfrm ;; + icmp_filter) setup_icmp_filter ;; + icmpv6_filter) setup_icmpv6_filter ;; + *) echo " ${arg} not supported"; return 1 ;; + esac || return 1 + done +} + +# shellcheck disable=SC2317 # called via trap +pause() { + echo + echo "Pausing. Hit enter to continue" + read -r _ +} + +# shellcheck disable=SC2317 # called via trap +log_test_error() { + # shellcheck disable=SC2031 # fail is set in subshell, read via trap + if [ "${fail}" = "yes" ] && [ -n "${desc}" ]; then + if [ "$VERBOSE" -gt 0 ]; then + show_icmp_filter + fi + printf "TEST: %-60s [ FAIL ] %s\n" "${desc}" "${name}" + [ -n "${cmd}" ] && printf '%s\n\n' "${cmd}" + [ -n "${out}" ] && printf '%s\n\n' "${out}" + fi +} + +# shellcheck disable=SC2317 # called via trap +cleanup() { + # shellcheck disable=SC2031 # fail is set in subshell, read via trap + [[ "$PAUSE" = "always" || ( "$PAUSE" = "fail" && "$fail" = "yes" ) ]] && pause + cleanup_all_ns + # shellcheck disable=SC2031 # fail is set in subshell, read via trap + [ "${EXIT_ON_TEST_FAIL}" = "yes" ] && [ "${fail}" = "yes" ] && exit 1 +} + +test_unreachable_ipv6() { + setup ns_set_v6 namespaces network xfrm icmpv6_filter || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:6::2 + run_cmd_err "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:6::3 + rc=0 + echo -e "$out" | grep -q -E 'From fc00:5::2 icmp_seq.* Destination' || rc=1 + return "${rc}" +} + +test_unreachable_gw_ipv6() { + setup ns_set_v6x namespaces network xfrm icmpv6_filter || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:5::2 + run_cmd_err "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:5::3 + rc=0 + echo -e "$out" | grep -q -E 'From fc00:4::2 icmp_seq.* Destination' || rc=1 + return "${rc}" +} + +test_unreachable_ipv4() { + setup ns_set_v4 namespaces network icmp_filter xfrm || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.6.2 + run_cmd_err "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.6.3 + rc=0 + echo -e "$out" | grep -q -E 'From 10.1.5.2 icmp_seq.* Destination' || rc=1 + return "${rc}" +} + +test_unreachable_gw_ipv4() { + setup ns_set_v4x namespaces network icmp_filter xfrm || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.5.2 + run_cmd_err "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.5.3 + rc=0 + echo -e "$out" | grep -q -E 'From 10.1.4.2 icmp_seq.* Destination' || rc=1 + return "${rc}" +} + +test_mtu_ipv4_r2() { + setup ns_set_v4 namespaces network icmp_filter xfrm || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.6.2 + run_cmd "${ns_r2[@]}" ip route replace 10.1.3.0/24 dev eth1 src 10.1.3.2 mtu 1300 + run_cmd "${ns_r2[@]}" ip route replace 10.1.4.0/24 dev eth0 src 10.1.4.1 mtu 1300 + # shellcheck disable=SC1010 # -M do: do = dont-fragment, not shell keyword + run_cmd "${ns_a[@]}" ping -M do -s 1300 -W 5 -w 4 -c 1 10.1.6.2 || true + rc=0 + echo -e "$out" | grep -q -E "From 10.1.2.2 icmp_seq=.* Frag needed and DF set" || rc=1 + return "${rc}" +} + +test_mtu_ipv6_r2() { + setup ns_set_v6 namespaces network xfrm icmpv6_filter || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:6::2 + run_cmd "${ns_r2[@]}" ip -6 route replace fc00:3::/64 \ + dev eth1 metric 256 src fc00:3::2 mtu 1300 + run_cmd "${ns_r2[@]}" ip -6 route replace fc00:4::/64 \ + dev eth0 metric 256 src fc00:4::1 mtu 1300 + # shellcheck disable=SC1010 # -M do: do = dont-fragment, not shell keyword + run_cmd "${ns_a[@]}" ping -M do -s 1300 -W 5 -w 4 -c 1 fc00:6::2 || true + rc=0 + echo -e "$out" | grep -q -E "From fc00:2::2 icmp_seq=.* Packet too big: mtu=1230" || rc=1 + return "${rc}" +} + +test_mtu_ipv4_r3() { + setup ns_set_v4 namespaces network icmp_filter xfrm || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.6.2 + run_cmd "${ns_r3[@]}" ip route replace 10.1.6.0/24 dev eth0 mtu 1300 + # shellcheck disable=SC1010 # -M do: do = dont-fragment, not shell keyword + run_cmd "${ns_a[@]}" ping -M do -s 1350 -W 5 -w 4 -c 1 10.1.6.2 || true + rc=0 + echo -e "$out" | grep -q -E "From 10.1.5.2 .* Frag needed and DF set \(mtu = 1300\)" || rc=1 + return "${rc}" +} + +test_mtu_ipv4_s2() { + setup ns_set_v4x namespaces network icmp_filter xfrm || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 10.1.5.2 + run_cmd "${ns_s2[@]}" ip route replace 10.1.5.0/24 dev eth0 src 10.1.5.1 mtu 1300 + # shellcheck disable=SC1010 # -M do: do = dont-fragment, not shell keyword + run_cmd "${ns_a[@]}" ping -M do -s 1350 -W 5 -w 4 -c 1 10.1.5.2 || true + rc=0 + echo -e "$out" | grep -q -E "From 10.1.4.2.*Frag needed and DF set \(mtu = 1300\)" || rc=1 + return "${rc}" +} + +test_mtu_ipv6_s2() { + setup ns_set_v6x namespaces network xfrm icmpv6_filter || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:5::2 + run_cmd "${ns_s2[@]}" ip -6 route replace fc00:5::/64 dev eth0 metric 256 mtu 1300 + # shellcheck disable=SC1010 # -M do: do = dont-fragment, not shell keyword + run_cmd "${ns_a[@]}" ping -M do -s 1350 -W 5 -w 4 -c 1 fc00:5::2 || true + rc=0 + echo -e "$out" | grep -q -E "From fc00:4::2.*Packet too big: mtu=1300" || rc=1 + return "${rc}" +} + +test_mtu_ipv6_r3() { + setup ns_set_v6 namespaces network xfrm icmpv6_filter || return "$ksft_skip" + run_cmd "${ns_a[@]}" ping -W 5 -w 4 -c 1 fc00:6::2 + run_cmd "${ns_r3[@]}" ip -6 route replace fc00:6::/64 dev eth1 metric 256 mtu 1300 + # shellcheck disable=SC1010 # -M do: do = dont-fragment, not shell keyword + run_cmd "${ns_a[@]}" ping -M do -s 1300 -W 5 -w 4 -c 1 fc00:6::2 || true + rc=0 + echo -e "$out" | grep -q -E "From fc00:5::2 icmp_seq=.* Packet too big: mtu=1300" || rc=1 + return "${rc}" +} + +################################################################################ +# +usage() { + echo + echo "$0 [OPTIONS] [TEST]..." + echo "If no TEST argument is given, all tests will be run." + echo + echo -e "\t-p Pause on fail. Namespaces are kept for diagnostics" + echo -e "\t-P Pause after the test. Namespaces are kept for diagnostics" + echo -e "\t-v Verbose output. Show commands; -vv Show output and nft rules also" + echo "Available tests${tests}" + exit 1 +} + +################################################################################ +# +exitcode=0 +all_skipped=true +out= +cmd= + +while getopts :epPv o; do + case $o in + e) EXIT_ON_TEST_FAIL=yes ;; + P) PAUSE=always ;; + p) PAUSE=fail ;; + v) VERBOSE=$((VERBOSE + 1)) ;; + *) usage ;; + esac +done +shift $((OPTIND - 1)) + +IFS=$'\t\n' + +for arg; do + # Check first that all requested tests are available before running any + command -v "test_${arg}" >/dev/null || { + echo "=== Test ${arg} not found" + usage + } +done + +name="" +desc="" +fail="no" + +for t in ${tests}; do + [ "${name}" = "" ] && name="${t}" && continue + [ "${desc}" = "" ] && desc="${t}" + + run_this=1 + for arg; do + [ "${arg}" = "${name}" ] && run_this=1 && break + run_this=0 + done + if [ $run_this -eq 1 ]; then + run_test + fi + name="" + desc="" +done + +exit ${exitcode} |