From be66d79189ec8a1006ec6ec302bb27b160b3e6ce Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Fri, 2 Feb 2024 18:39:35 +0800
Subject: selftest/bpf: Test the read of vsyscall page under x86-64

Under x86-64, when using bpf_probe_read_kernel{_str}() or
bpf_probe_read{_str}() to read vsyscall page, the read may trigger oops,
so add one test case to ensure that the problem is fixed. Beside those
four bpf helpers mentioned above, testing the read of vsyscall page by
using bpf_probe_read_user{_str} and bpf_copy_from_user{_task}() as well.

The test case passes the address of vsyscall page to these six helpers
and checks whether the returned values are expected:

1) For bpf_probe_read_kernel{_str}()/bpf_probe_read{_str}(), the
   expected return value is -ERANGE as shown below:

bpf_probe_read_kernel_common
  copy_from_kernel_nofault
    // false, return -ERANGE
    copy_from_kernel_nofault_allowed

2) For bpf_probe_read_user{_str}(), the expected return value is -EFAULT
   as show below:

bpf_probe_read_user_common
  copy_from_user_nofault
    // false, return -EFAULT
    __access_ok

3) For bpf_copy_from_user(), the expected return value is -EFAULT:

// return -EFAULT
bpf_copy_from_user
  copy_from_user
    _copy_from_user
      // return false
      access_ok

4) For bpf_copy_from_user_task(), the expected return value is -EFAULT:

// return -EFAULT
bpf_copy_from_user_task
  access_process_vm
    // return 0
    vma_lookup()
    // return 0
    expand_stack()

The occurrence of oops depends on the availability of CPU SMAP [1]
feature and there are three possible configurations of vsyscall page in
the boot cmd-line: vsyscall={xonly|none|emulate}, so there are a total
of six possible combinations. Under all these combinations, the test
case runs successfully.

[1]: https://en.wikipedia.org/wiki/Supervisor_Mode_Access_Prevention

Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20240202103935.3154011-4-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/read_vsyscall.c       | 57 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/read_vsyscall.c  | 45 +++++++++++++++++
 2 files changed, 102 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
 create mode 100644 tools/testing/selftests/bpf/progs/read_vsyscall.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
new file mode 100644
index 000000000000..3405923fe4e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "test_progs.h"
+#include "read_vsyscall.skel.h"
+
+#if defined(__x86_64__)
+/* For VSYSCALL_ADDR */
+#include <asm/vsyscall.h>
+#else
+/* To prevent build failure on non-x86 arch */
+#define VSYSCALL_ADDR 0UL
+#endif
+
+struct read_ret_desc {
+	const char *name;
+	int ret;
+} all_read[] = {
+	{ .name = "probe_read_kernel", .ret = -ERANGE },
+	{ .name = "probe_read_kernel_str", .ret = -ERANGE },
+	{ .name = "probe_read", .ret = -ERANGE },
+	{ .name = "probe_read_str", .ret = -ERANGE },
+	{ .name = "probe_read_user", .ret = -EFAULT },
+	{ .name = "probe_read_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user", .ret = -EFAULT },
+	{ .name = "copy_from_user_task", .ret = -EFAULT },
+};
+
+void test_read_vsyscall(void)
+{
+	struct read_vsyscall *skel;
+	unsigned int i;
+	int err;
+
+#if !defined(__x86_64__)
+	test__skip();
+	return;
+#endif
+	skel = read_vsyscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+	err = read_vsyscall__attach(skel);
+	if (!ASSERT_EQ(err, 0, "read_vsyscall attach"))
+		goto out;
+
+	/* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE,
+	 * but it doesn't affect the returned error codes.
+	 */
+	skel->bss->user_ptr = (void *)VSYSCALL_ADDR;
+	usleep(1);
+
+	for (i = 0; i < ARRAY_SIZE(all_read); i++)
+		ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name);
+out:
+	read_vsyscall__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
new file mode 100644
index 000000000000..986f96687ae1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+int target_pid = 0;
+void *user_ptr = 0;
+int read_ret[8];
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int do_probe_read(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr);
+	read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr);
+	read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr);
+	read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr);
+	read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr);
+	read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int do_copy_from_user(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr);
+	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
+					      bpf_get_current_task_btf(), 0);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 52f671db18823089a02f07efc04efdb2272ddc17 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 15 Feb 2024 06:33:45 -0800
Subject: net/sched: act_mirred: use the backlog for mirred ingress

The test Davide added in commit ca22da2fbd69 ("act_mirred: use the backlog
for nested calls to mirred ingress") hangs our testing VMs every 10 or so
runs, with the familiar tcp_v4_rcv -> tcp_v4_rcv deadlock reported by
lockdep.

The problem as previously described by Davide (see Link) is that
if we reverse flow of traffic with the redirect (egress -> ingress)
we may reach the same socket which generated the packet. And we may
still be holding its socket lock. The common solution to such deadlocks
is to put the packet in the Rx backlog, rather than run the Rx path
inline. Do that for all egress -> ingress reversals, not just once
we started to nest mirred calls.

In the past there was a concern that the backlog indirection will
lead to loss of error reporting / less accurate stats. But the current
workaround does not seem to address the issue.

Fixes: 53592b364001 ("net/sched: act_mirred: Implement ingress actions")
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Suggested-by: Davide Caratti <dcaratti@redhat.com>
Link: https://lore.kernel.org/netdev/33dc43f587ec1388ba456b4915c75f02a8aae226.1663945716.git.dcaratti@redhat.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/tc_actions.sh | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index b0f5e55d2d0b..589629636502 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -235,9 +235,6 @@ mirred_egress_to_ingress_tcp_test()
 	check_err $? "didn't mirred redirect ICMP"
 	tc_check_packets "dev $h1 ingress" 102 10
 	check_err $? "didn't drop mirred ICMP"
-	local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits)
-	test ${overlimits} = 10
-	check_err $? "wrong overlimits, expected 10 got ${overlimits}"
 
 	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
 	tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower
-- 
cgit v1.2.3


From d2a2547565a9f1ad7989f7e21f97cbf065a9390d Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:34 +0100
Subject: selftests: mptcp: pm nl: also list skipped tests

If the feature is not supported by older kernels, and instead of just
ignoring some tests, we should mark them as skipped, so we can still
track them.

Fixes: d85555ac11f9 ("selftests: mptcp: pm_netlink: format subtests results in TAP")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/pm_netlink.sh | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 8f4ff123a7eb..79e83a2c95de 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -194,6 +194,12 @@ subflow 10.0.1.1" "          (nofullmesh)"
 	ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh
 	check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
 subflow,backup,fullmesh 10.0.1.1" "          (backup,fullmesh)"
+else
+	for st in fullmesh nofullmesh backup,fullmesh; do
+		st="          (${st})"
+		printf "%-50s%s\n" "${st}" "[SKIP]"
+		mptcp_lib_result_skip "${st}"
+	done
 fi
 
 mptcp_lib_result_print_all_tap
-- 
cgit v1.2.3


From 662f084f3396d8a804d56cb53ac05c9e39902a7b Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:35 +0100
Subject: selftests: mptcp: pm nl: avoid error msg on older kernels

Since the 'Fixes' commit mentioned below, and if the kernel being tested
doesn't support the 'fullmesh' flag, this error will be printed:

  netlink error -22 (Invalid argument)
  ./pm_nl_ctl: bailing out due to netlink error[s]

But that can be normal if the kernel doesn't support the feature, no
need to print this worrying error message while everything else looks
OK. So we can mute stderr. Failures will still be detected if any.

Fixes: 1dc88d241f92 ("selftests: mptcp: pm_nl_ctl: always look for errors")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/pm_netlink.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 79e83a2c95de..71899a3ffa7a 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -183,7 +183,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
 subflow 10.0.1.1" "          (nobackup)"
 
 # fullmesh support has been added later
-ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh
+ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh 2>/dev/null
 if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" ||
    mptcp_lib_expect_all_features; then
 	check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
-- 
cgit v1.2.3


From 694bd45980a61045eb5ec07799e3b94c76db830e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:36 +0100
Subject: selftests: mptcp: diag: fix bash warnings on older kernels

Since the 'Fixes' commit mentioned below, the command that is executed
in __chk_nr() helper can return nothing if the feature is not supported.
This is the case when the MPTCP CURRESTAB counter is not supported.

To avoid this warning ...

  ./diag.sh: line 65: [: !=: unary operator expected

... we just need to surround '$nr' with double quotes, to support an
empty string when the feature is not supported.

Fixes: 81ab772819da ("selftests: mptcp: diag: check CURRESTAB counters")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/diag.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 04fcb8a077c9..e0615c6ffb8d 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -62,8 +62,8 @@ __chk_nr()
 	nr=$(eval $command)
 
 	printf "%-50s" "$msg"
-	if [ $nr != $expected ]; then
-		if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then
+	if [ "$nr" != "$expected" ]; then
+		if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then
 			echo "[ skip ] Feature probably not supported"
 			mptcp_lib_result_skip "${msg}"
 		else
-- 
cgit v1.2.3


From 4d8e0dde0403b5a86aa83e243f020711a9c3e31f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:37 +0100
Subject: selftests: mptcp: simult flows: fix some subtest names

The selftest was correctly recording all the results, but the 'reverse
direction' part was missing in the name when needed.

It is important to have a unique (sub)test name in TAP, because some CI
environments drop tests with duplicated name.

Fixes: 675d99338e7a ("selftests: mptcp: simult flows: format subtests results in TAP")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 0cc964e6f2c1..8f9ddb3ad4fe 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -250,7 +250,8 @@ run_test()
 		[ $bail -eq 0 ] || exit $ret
 	fi
 
-	printf "%-60s" "$msg - reverse direction"
+	msg+=" - reverse direction"
+	printf "%-60s" "${msg}"
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-- 
cgit v1.2.3


From 2ef0d804c090658960c008446523863fd7e3541e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:38 +0100
Subject: selftests: mptcp: userspace_pm: unique subtest names

It is important to have a unique (sub)test name in TAP, because some CI
environments drop tests with duplicated names.

Some subtests from the userspace_pm selftest had the same names. That's
because different subflows are created (and deleted) between the same
pair of IP addresses.

Simply adding the destination port in the name is then enough to have
different names, because the destination port is always different.

Note that adding such info takes a bit more space, so we need to
increase a bit the width to print the name, simply to keep all the
'[ OK ]' aligned as before.

Fixes: f589234e1af0 ("selftests: mptcp: userspace_pm: format subtests results in TAP")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/userspace_pm.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 6167837f48e1..1b94a75604fe 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -75,7 +75,7 @@ print_test()
 {
 	test_name="${1}"
 
-	_printf "%-63s" "${test_name}"
+	_printf "%-68s" "${test_name}"
 }
 
 print_results()
@@ -542,7 +542,7 @@ verify_subflow_events()
 	local remid
 	local info
 
-	info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})"
+	info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})"
 
 	if [ "$e_type" = "$SUB_ESTABLISHED" ]
 	then
-- 
cgit v1.2.3


From 645c1dc965ef6b5554e5e69737bb179c7a0f872f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:39 +0100
Subject: selftests: mptcp: diag: unique 'in use' subtest names

It is important to have a unique (sub)test name in TAP, because some CI
environments drop tests with duplicated name.

Some 'in use' subtests from the diag selftest had the same names, e.g.:

    chk 0 msk in use after flush

Now the previous value is taken, to have different names, e.g.:

    chk 2->0 msk in use after flush

While at it, avoid repeating the full message, declare it once in the
helper.

Fixes: ce9902573652 ("selftests: mptcp: diag: format subtests results in TAP")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/diag.sh | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index e0615c6ffb8d..266656a16229 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -166,9 +166,13 @@ chk_msk_listen()
 chk_msk_inuse()
 {
 	local expected=$1
-	local msg="$2"
+	local msg="....chk ${2:-${expected}} msk in use"
 	local listen_nr
 
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
+
 	listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN)
 	expected=$((expected + listen_nr))
 
@@ -179,7 +183,7 @@ chk_msk_inuse()
 		sleep 0.1
 	done
 
-	__chk_nr get_msk_inuse $expected "$msg" 0
+	__chk_nr get_msk_inuse $expected "${msg}" 0
 }
 
 # $1: cestab nr
@@ -227,11 +231,11 @@ wait_connected $ns 10000
 chk_msk_nr 2 "after MPC handshake "
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
-chk_msk_inuse 2 "....chk 2 msk in use"
+chk_msk_inuse 2
 chk_msk_cestab 2
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_inuse 0 "2->0"
 chk_msk_cestab 0
 
 echo "a" | \
@@ -247,11 +251,11 @@ echo "b" | \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10001
 chk_msk_fallback_nr 1 "check fallback"
-chk_msk_inuse 1 "....chk 1 msk in use"
+chk_msk_inuse 1
 chk_msk_cestab 1
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_inuse 0 "1->0"
 chk_msk_cestab 0
 
 NR_CLIENTS=100
@@ -273,11 +277,11 @@ for I in `seq 1 $NR_CLIENTS`; do
 done
 
 wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
-chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use"
+chk_msk_inuse $((NR_CLIENTS*2)) "many"
 chk_msk_cestab $((NR_CLIENTS*2))
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_inuse 0 "many->0"
 chk_msk_cestab 0
 
 mptcp_lib_result_print_all_tap
-- 
cgit v1.2.3


From 4103d8480866fe5abb71ef0ed8af3a3b7b9625bf Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 15 Feb 2024 19:25:40 +0100
Subject: selftests: mptcp: diag: unique 'cestab' subtest names

It is important to have a unique (sub)test name in TAP, because some CI
environments drop tests with duplicated name.

Some 'cestab' subtests from the diag selftest had the same names, e.g.:

    ....chk 0 cestab

Now the previous value is taken, to have different names, e.g.:

    ....chk 2->0 cestab after flush

While at it, the 'after flush' info is added, similar to what is done
with the 'in use' subtests. Also inspired by these 'in use' subtests,
'many' is displayed instead of a large number:

    many msk socket present                           [  ok  ]
    ....chk many msk in use                           [  ok  ]
    ....chk many cestab                               [  ok  ]
    ....chk many->0 msk in use after flush            [  ok  ]
    ....chk many->0 cestab after flush                [  ok  ]

Fixes: 81ab772819da ("selftests: mptcp: diag: check CURRESTAB counters")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/diag.sh | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 266656a16229..0a58ebb8b04c 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -189,10 +189,15 @@ chk_msk_inuse()
 # $1: cestab nr
 chk_msk_cestab()
 {
-	local cestab=$1
+	local expected=$1
+	local msg="....chk ${2:-${expected}} cestab"
+
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
 
 	__chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \
-		 "${cestab}" "....chk ${cestab} cestab" ""
+		 "${expected}" "${msg}" ""
 }
 
 wait_connected()
@@ -236,7 +241,7 @@ chk_msk_cestab 2
 flush_pids
 
 chk_msk_inuse 0 "2->0"
-chk_msk_cestab 0
+chk_msk_cestab 0 "2->0"
 
 echo "a" | \
 	timeout ${timeout_test} \
@@ -256,7 +261,7 @@ chk_msk_cestab 1
 flush_pids
 
 chk_msk_inuse 0 "1->0"
-chk_msk_cestab 0
+chk_msk_cestab 0 "1->0"
 
 NR_CLIENTS=100
 for I in `seq 1 $NR_CLIENTS`; do
@@ -278,11 +283,11 @@ done
 
 wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
 chk_msk_inuse $((NR_CLIENTS*2)) "many"
-chk_msk_cestab $((NR_CLIENTS*2))
+chk_msk_cestab $((NR_CLIENTS*2)) "many"
 flush_pids
 
 chk_msk_inuse 0 "many->0"
-chk_msk_cestab 0
+chk_msk_cestab 0 "many->0"
 
 mptcp_lib_result_print_all_tap
 exit $ret
-- 
cgit v1.2.3


From cd65c48d66920457129584553f217005d09b1edb Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 15 Feb 2024 10:33:25 +0800
Subject: selftests: bonding: set active slave to primary eth1 specifically

In bond priority testing, we set the primary interface to eth1 and add
eth0,1,2 to bond in serial. This is OK in normal times. But when in
debug kernel, the bridge port that eth0,1,2 connected would start
slowly (enter blocking, forwarding state), which caused the primary
interface down for a while after enslaving and active slave changed.
Here is a test log from Jakub's debug test[1].

 [  400.399070][   T50] br0: port 1(s0) entered disabled state
 [  400.400168][   T50] br0: port 4(s2) entered disabled state
 [  400.941504][ T2791] bond0: (slave eth0): making interface the new active one
 [  400.942603][ T2791] bond0: (slave eth0): Enslaving as an active interface with an up link
 [  400.943633][ T2766] br0: port 1(s0) entered blocking state
 [  400.944119][ T2766] br0: port 1(s0) entered forwarding state
 [  401.128792][ T2792] bond0: (slave eth1): making interface the new active one
 [  401.130771][ T2792] bond0: (slave eth1): Enslaving as an active interface with an up link
 [  401.131643][   T69] br0: port 2(s1) entered blocking state
 [  401.132067][   T69] br0: port 2(s1) entered forwarding state
 [  401.346201][ T2793] bond0: (slave eth2): Enslaving as a backup interface with an up link
 [  401.348414][   T50] br0: port 4(s2) entered blocking state
 [  401.348857][   T50] br0: port 4(s2) entered forwarding state
 [  401.519669][  T250] bond0: (slave eth0): link status definitely down, disabling slave
 [  401.526522][  T250] bond0: (slave eth1): link status definitely down, disabling slave
 [  401.526986][  T250] bond0: (slave eth2): making interface the new active one
 [  401.629470][  T250] bond0: (slave eth0): link status definitely up
 [  401.630089][  T250] bond0: (slave eth1): link status definitely up
 [...]
 # TEST: prio (active-backup ns_ip6_target primary_reselect 1)         [FAIL]
 # Current active slave is eth2 but not eth1

Fix it by setting active slave to primary slave specifically before
testing.

[1] https://netdev-3.bots.linux.dev/vmksft-bonding-dbg/results/464301/1-bond-options-sh/stdout

Fixes: 481b56e0391e ("selftests: bonding: re-format bond option tests")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/bonding/bond_options.sh | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index d508486cc0bd..9a3d3c389dad 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -62,6 +62,8 @@ prio_test()
 
 	# create bond
 	bond_reset "${param}"
+	# set active_slave to primary eth1 specifically
+	ip -n ${s_ns} link set bond0 type bond active_slave eth1
 
 	# check bonding member prio value
 	ip -n ${s_ns} link set eth0 type bond_slave prio 0
-- 
cgit v1.2.3


From 3f00e4a9c96f4488a924aff4e35b77c8eced897e Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 15 Feb 2024 13:12:18 -0800
Subject: selftests/bpf: Test racing between bpf_timer_cancel_and_free and
 bpf_timer_cancel

This selftest is based on a Alexei's test adopted from an internal
user to troubleshoot another bug. During this exercise, a separate
racing bug was discovered between bpf_timer_cancel_and_free
and bpf_timer_cancel. The details can be found in the previous
patch.

This patch is to add a selftest that can trigger the bug.
I can trigger the UAF everytime in my qemu setup with KASAN. The idea
is to have multiple user space threads running in a tight loop to exercise
both bpf_map_update_elem (which calls into bpf_timer_cancel_and_free)
and bpf_timer_cancel.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20240215211218.990808-2-martin.lau@linux.dev
---
 tools/testing/selftests/bpf/prog_tests/timer.c | 35 +++++++++++++++++++++++++-
 tools/testing/selftests/bpf/progs/timer.c      | 34 ++++++++++++++++++++++++-
 2 files changed, 67 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 760ad96b4be0..d66687f1ee6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -4,10 +4,29 @@
 #include "timer.skel.h"
 #include "timer_failure.skel.h"
 
+#define NUM_THR 8
+
+static void *spin_lock_thread(void *arg)
+{
+	int i, err, prog_fd = *(int *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	for (i = 0; i < 10000; i++) {
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (!ASSERT_OK(err, "test_run_opts err") ||
+		    !ASSERT_OK(topts.retval, "test_run_opts retval"))
+			break;
+	}
+
+	pthread_exit(arg);
+}
+
 static int timer(struct timer *timer_skel)
 {
-	int err, prog_fd;
+	int i, err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	pthread_t thread_id[NUM_THR];
+	void *ret;
 
 	err = timer__attach(timer_skel);
 	if (!ASSERT_OK(err, "timer_attach"))
@@ -43,6 +62,20 @@ static int timer(struct timer *timer_skel)
 	/* check that code paths completed */
 	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
+	prog_fd = bpf_program__fd(timer_skel->progs.race);
+	for (i = 0; i < NUM_THR; i++) {
+		err = pthread_create(&thread_id[i], NULL,
+				     &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (i) {
+		err = pthread_join(thread_id[--i], &ret);
+		if (ASSERT_OK(err, "pthread_join"))
+			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
+	}
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index 8b946c8188c6..f615da97df26 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -51,7 +51,8 @@ struct {
 	__uint(max_entries, 1);
 	__type(key, int);
 	__type(value, struct elem);
-} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps");
+} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"),
+	race_array SEC(".maps");
 
 __u64 bss_data;
 __u64 abs_data;
@@ -390,3 +391,34 @@ int BPF_PROG2(test5, int, a)
 
 	return 0;
 }
+
+static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer)
+{
+	bpf_timer_start(timer, 1000000, 0);
+	return 0;
+}
+
+SEC("syscall")
+int race(void *ctx)
+{
+	struct bpf_timer *timer;
+	int err, race_key = 0;
+	struct elem init;
+
+	__builtin_memset(&init, 0, sizeof(struct elem));
+	bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY);
+
+	timer = bpf_map_lookup_elem(&race_array, &race_key);
+	if (!timer)
+		return 1;
+
+	err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
+	if (err && err != -EBUSY)
+		return 1;
+
+	bpf_timer_set_callback(timer, race_timer_callback);
+	bpf_timer_start(timer, 0, 0);
+	bpf_timer_cancel(timer);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 5c138a8a4abe152fcbef1ed40a6a4b5727b2991b Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sat, 17 Feb 2024 19:41:52 +0800
Subject: selftests/bpf: Add negtive test cases for task iter

Incorporate a test case to assess the handling of invalid flags or
task__nullable parameters passed to bpf_iter_task_new(). Prior to the
preceding commit, this scenario could potentially trigger a kernel panic.
However, with the previous commit, this test case is expected to function
correctly.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240217114152.1623-3-laoar.shao@gmail.com
---
 tools/testing/selftests/bpf/prog_tests/iters.c |  1 +
 tools/testing/selftests/bpf/progs/iters_task.c | 12 +++++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index bf84d4a1d9ae..3c440370c1f0 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -193,6 +193,7 @@ static void subtest_task_iters(void)
 	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
 	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
 	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt");
 	pthread_mutex_unlock(&do_nothing_mutex);
 	for (int i = 0; i < thread_num; i++)
 		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c
index c9b4055cd410..e4d53e40ff20 100644
--- a/tools/testing/selftests/bpf/progs/iters_task.c
+++ b/tools/testing/selftests/bpf/progs/iters_task.c
@@ -10,7 +10,7 @@
 char _license[] SEC("license") = "GPL";
 
 pid_t target_pid;
-int procs_cnt, threads_cnt, proc_threads_cnt;
+int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt;
 
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
@@ -26,6 +26,16 @@ int iter_task_for_each_sleep(void *ctx)
 	procs_cnt = threads_cnt = proc_threads_cnt = 0;
 
 	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, ~0U) {
+		/* Below instructions shouldn't be executed for invalid flags */
+		invalid_cnt++;
+	}
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) {
+		/* Below instructions shouldn't be executed for invalid task__nullable */
+		invalid_cnt++;
+	}
+
 	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
 		if (pos->pid == target_pid)
 			procs_cnt++;
-- 
cgit v1.2.3


From 7b2a4c2a623a9f9c5fd9cff499bb9457fa2192ec Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 15 Feb 2024 17:17:32 +0100
Subject: selftests: tls: add test for merging of same-type control messages

Two consecutive control messages of the same type should never be
merged into one large received blob of data.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/018f1633d5471684c65def5fe390de3b15c3d683.1708007371.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 49c84602707f..2714c230a0f9 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1485,6 +1485,32 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+TEST_F(tls, control_msg_nomerge)
+{
+	char *rec1 = "1111";
+	char *rec2 = "2222";
+	int send_len = 5;
+	char buf[15];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec1, send_len, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len);
+	EXPECT_EQ(memcmp(buf, rec2, send_len), 0);
+}
+
 TEST_F(tls, shutdown)
 {
 	char const *test_str = "test_read";
-- 
cgit v1.2.3


From 2bf6172632e1d4a6ec7ee7e734d53a43a145f5c6 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 15 Feb 2024 17:17:33 +0100
Subject: selftests: tls: add test for peeking past a record of a different
 type

If we queue 3 records:
 - record 1, type DATA
 - record 2, some other type
 - record 3, type DATA
the current code can look past the 2nd record and merge the 2 data
records.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/4623550f8617c239581030c13402d3262f2bd14f.1708007371.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 2714c230a0f9..b95c249f81c2 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1511,6 +1511,25 @@ TEST_F(tls, control_msg_nomerge)
 	EXPECT_EQ(memcmp(buf, rec2, send_len), 0);
 }
 
+TEST_F(tls, data_control_data)
+{
+	char *rec1 = "1111";
+	char *rec2 = "2222";
+	char *rec3 = "3333";
+	int send_len = 5;
+	char buf[15];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	EXPECT_EQ(send(self->fd, rec1, send_len, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len);
+	EXPECT_EQ(send(self->fd, rec3, send_len, 0), send_len);
+
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+}
+
 TEST_F(tls, shutdown)
 {
 	char const *test_str = "test_read";
-- 
cgit v1.2.3


From e4fe082c38cd74a8fa384bc7542cf3edf1cb7318 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 20 Feb 2024 08:11:11 -0800
Subject: tools: ynl: make sure we always pass yarg to mnl_cb_run

There is one common error handler in ynl - ynl_cb_error().
It expects priv to be a pointer to struct ynl_parse_arg AKA yarg.
To avoid potential crashes if we encounter a stray NLMSG_ERROR
always pass yarg as priv (or a struct which has it as the first
member).

ynl_cb_null() has a similar problem directly - it expects yarg
but priv passed by the caller is ys.

Found by code inspection.

Fixes: 86878f14d71a ("tools: ynl: user space helpers")
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://lore.kernel.org/r/20240220161112.2735195-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index c82a7f41b31c..9e41c8c0cc99 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -466,6 +466,8 @@ ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version)
 
 int ynl_recv_ack(struct ynl_sock *ys, int ret)
 {
+	struct ynl_parse_arg yarg = { .ys = ys, };
+
 	if (!ret) {
 		yerr(ys, YNL_ERROR_EXPECT_ACK,
 		     "Expecting an ACK but nothing received");
@@ -478,7 +480,7 @@ int ynl_recv_ack(struct ynl_sock *ys, int ret)
 		return ret;
 	}
 	return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid,
-			  ynl_cb_null, ys);
+			  ynl_cb_null, &yarg);
 }
 
 int ynl_cb_null(const struct nlmsghdr *nlh, void *data)
@@ -741,11 +743,14 @@ err_free:
 
 static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data)
 {
-	return ynl_ntf_parse((struct ynl_sock *)data, nlh);
+	struct ynl_parse_arg *yarg = data;
+
+	return ynl_ntf_parse(yarg->ys, nlh);
 }
 
 int ynl_ntf_check(struct ynl_sock *ys)
 {
+	struct ynl_parse_arg yarg = { .ys = ys, };
 	ssize_t len;
 	int err;
 
@@ -767,7 +772,7 @@ int ynl_ntf_check(struct ynl_sock *ys)
 			return len;
 
 		err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid,
-				  ynl_ntf_trampoline, ys,
+				  ynl_ntf_trampoline, &yarg,
 				  ynl_cb_array, NLMSG_MIN_TYPE);
 		if (err < 0)
 			return err;
-- 
cgit v1.2.3


From 5d78b73e851455d525a064f3b042b29fdc0c1a4a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 20 Feb 2024 08:11:12 -0800
Subject: tools: ynl: don't leak mcast_groups on init error

Make sure to free the already-parsed mcast_groups if
we don't get an ack from the kernel when reading family info.
This is part of the ynl_sock_create() error path, so we won't
get a call to ynl_sock_destroy() to free them later.

Fixes: 86878f14d71a ("tools: ynl: user space helpers")
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://lore.kernel.org/r/20240220161112.2735195-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index 9e41c8c0cc99..6e6d474c8366 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -588,7 +588,13 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name)
 		return err;
 	}
 
-	return ynl_recv_ack(ys, err);
+	err = ynl_recv_ack(ys, err);
+	if (err < 0) {
+		free(ys->mcast_groups);
+		return err;
+	}
+
+	return 0;
 }
 
 struct ynl_sock *
-- 
cgit v1.2.3


From 187bbb6968af5400e436c193765c5d845a07364f Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Mon, 19 Feb 2024 14:52:55 +0100
Subject: selftests: ioam: refactoring to align with the fix

ioam6_parser uses a packet socket. After the fix to prevent writing to
cloned skb's, the receiver does not see its IOAM data anymore, which
makes input/forward ioam-selftests to fail. As a workaround,
ioam6_parser now uses an IPv6 raw socket and leverages ancillary data to
get hop-by-hop options. As a consequence, the hook is "after" the IOAM
data insertion by the receiver and all tests are working again.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/ioam6.sh       | 38 ++++++------
 tools/testing/selftests/net/ioam6_parser.c | 95 +++++++++++++++---------------
 2 files changed, 66 insertions(+), 67 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
index fe59ca3e5596..12491850ae98 100755
--- a/tools/testing/selftests/net/ioam6.sh
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -367,14 +367,12 @@ run_test()
   local desc=$2
   local node_src=$3
   local node_dst=$4
-  local ip6_src=$5
-  local ip6_dst=$6
-  local if_dst=$7
-  local trace_type=$8
-  local ioam_ns=$9
-
-  ip netns exec $node_dst ./ioam6_parser $if_dst $name $ip6_src $ip6_dst \
-         $trace_type $ioam_ns &
+  local ip6_dst=$5
+  local trace_type=$6
+  local ioam_ns=$7
+  local type=$8
+
+  ip netns exec $node_dst ./ioam6_parser $name $trace_type $ioam_ns $type &
   local spid=$!
   sleep 0.1
 
@@ -489,7 +487,7 @@ out_undef_ns()
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0x800000 0
+         db01::1 0x800000 0 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -509,7 +507,7 @@ out_no_room()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -543,14 +541,14 @@ out_bits()
       if [ $cmd_res != 0 ]
       then
         npassed=$((npassed+1))
-        log_test_passed "$descr"
+        log_test_passed "$descr ($1 mode)"
       else
         nfailed=$((nfailed+1))
-        log_test_failed "$descr"
+        log_test_failed "$descr ($1 mode)"
       fi
     else
 	run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
     fi
   done
 
@@ -574,7 +572,7 @@ out_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 100 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xfff002 123
+         db01::1 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -604,7 +602,7 @@ in_undef_ns()
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0x800000 0
+         db01::1 0x800000 0 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -624,7 +622,7 @@ in_no_room()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -651,7 +649,7 @@ in_bits()
            dev veth0
 
     run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
   done
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
@@ -679,7 +677,7 @@ in_oflag()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 
@@ -703,7 +701,7 @@ in_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 80 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xfff002 123
+         db01::1 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -731,7 +729,7 @@ fwd_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \
-         db01::2 db02::2 veth0 0xfff002 123
+         db02::2 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down
 }
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
index d9d1d4190126..895e5bb5044b 100644
--- a/tools/testing/selftests/net/ioam6_parser.c
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -8,7 +8,6 @@
 #include <errno.h>
 #include <limits.h>
 #include <linux/const.h>
-#include <linux/if_ether.h>
 #include <linux/ioam6.h>
 #include <linux/ipv6.h>
 #include <stdlib.h>
@@ -512,14 +511,6 @@ static int str2id(const char *tname)
 	return -1;
 }
 
-static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2)
-{
-	return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) |
-		(a1->s6_addr32[1] ^ a2->s6_addr32[1]) |
-		(a1->s6_addr32[2] ^ a2->s6_addr32[2]) |
-		(a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0;
-}
-
 static int get_u32(__u32 *val, const char *arg, int base)
 {
 	unsigned long res;
@@ -603,70 +594,80 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = {
 
 int main(int argc, char **argv)
 {
-	int fd, size, hoplen, tid, ret = 1;
-	struct in6_addr src, dst;
+	int fd, size, hoplen, tid, ret = 1, on = 1;
 	struct ioam6_hdr *opt;
-	struct ipv6hdr *ip6h;
-	__u8 buffer[400], *p;
-	__u16 ioam_ns;
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	struct iovec iov;
+	__u8 buffer[512];
 	__u32 tr_type;
+	__u16 ioam_ns;
+	__u8 *ptr;
 
-	if (argc != 7)
+	if (argc != 5)
 		goto out;
 
-	tid = str2id(argv[2]);
+	tid = str2id(argv[1]);
 	if (tid < 0 || !func[tid])
 		goto out;
 
-	if (inet_pton(AF_INET6, argv[3], &src) != 1 ||
-	    inet_pton(AF_INET6, argv[4], &dst) != 1)
+	if (get_u32(&tr_type, argv[2], 16) ||
+	    get_u16(&ioam_ns, argv[3], 0))
 		goto out;
 
-	if (get_u32(&tr_type, argv[5], 16) ||
-	    get_u16(&ioam_ns, argv[6], 0))
+	fd = socket(PF_INET6, SOCK_RAW,
+		    !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6);
+	if (fd < 0)
 		goto out;
 
-	fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6));
-	if (!fd)
-		goto out;
+	setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS,  &on, sizeof(on));
 
-	if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
-		       argv[1], strlen(argv[1])))
+	iov.iov_len = 1;
+	iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer)));
+	if (!iov.iov_base)
 		goto close;
-
 recv:
-	size = recv(fd, buffer, sizeof(buffer), 0);
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = buffer;
+	msg.msg_controllen = CMSG_SPACE(sizeof(buffer));
+
+	size = recvmsg(fd, &msg, 0);
 	if (size <= 0)
 		goto close;
 
-	ip6h = (struct ipv6hdr *)buffer;
+	for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+		if (cmsg->cmsg_level != IPPROTO_IPV6 ||
+		    cmsg->cmsg_type != IPV6_HOPOPTS ||
+		    cmsg->cmsg_len < sizeof(struct ipv6_hopopt_hdr))
+			continue;
 
-	if (!ipv6_addr_equal(&ip6h->saddr, &src) ||
-	    !ipv6_addr_equal(&ip6h->daddr, &dst))
-		goto recv;
+		ptr = (__u8 *)CMSG_DATA(cmsg);
 
-	if (ip6h->nexthdr != IPPROTO_HOPOPTS)
-		goto close;
+		hoplen = (ptr[1] + 1) << 3;
+		ptr += sizeof(struct ipv6_hopopt_hdr);
 
-	p = buffer + sizeof(*ip6h);
-	hoplen = (p[1] + 1) << 3;
-	p += sizeof(struct ipv6_hopopt_hdr);
+		while (hoplen > 0) {
+			opt = (struct ioam6_hdr *)ptr;
 
-	while (hoplen > 0) {
-		opt = (struct ioam6_hdr *)p;
+			if (opt->opt_type == IPV6_TLV_IOAM &&
+			    opt->type == IOAM6_TYPE_PREALLOC) {
+				ptr += sizeof(*opt);
+				ret = func[tid](tid,
+						(struct ioam6_trace_hdr *)ptr,
+						tr_type, ioam_ns);
+				goto close;
+			}
 
-		if (opt->opt_type == IPV6_TLV_IOAM &&
-		    opt->type == IOAM6_TYPE_PREALLOC) {
-			p += sizeof(*opt);
-			ret = func[tid](tid, (struct ioam6_trace_hdr *)p,
-					   tr_type, ioam_ns);
-			break;
+			ptr += opt->opt_len + 2;
+			hoplen -= opt->opt_len + 2;
 		}
-
-		p += opt->opt_len + 2;
-		hoplen -= opt->opt_len + 2;
 	}
+
+	goto recv;
 close:
+	free(iov.iov_base);
 	close(fd);
 out:
 	return ret;
-- 
cgit v1.2.3