From 83752e12896a72b24845c94f000e4c51b2bc5b50 Mon Sep 17 00:00:00 2001
From: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Date: Thu, 26 Sep 2024 19:30:22 +0200
Subject: selftests/bpf: Add mptcp subflow example

Move Nicolas' patch into bpf selftests directory. This example adds a
different mark (SO_MARK) on each subflow, and changes the TCP CC only on
the first subflow.

From the userspace, an application can do a setsockopt() on an MPTCP
socket, and typically the same value will be propagated to all subflows
(paths). If someone wants to have different values per subflow, the
recommended way is to use BPF. So it is good to add such example here,
and make sure there is no regressions.

This example shows how it is possible to:

    Identify the parent msk of an MPTCP subflow.
    Put different sockopt for each subflow of a same MPTCP connection.

Here especially, two different behaviours are implemented:

    A socket mark (SOL_SOCKET SO_MARK) is put on each subflow of a same
    MPTCP connection. The order of creation of the current subflow defines
    its mark. The TCP CC algorithm of the very first subflow of an MPTCP
    connection is set to "reno".

This is just to show it is possible to identify an MPTCP connection, and
set socket options, from different SOL levels, per subflow. "reno" has
been picked because it is built-in and usually not set as default one.
It is easy to verify with 'ss' that these modifications have been
applied correctly. That's what the next patch is going to do.

Nicolas' code comes from:

    commit 4d120186e4d6 ("bpf:examples: update mptcp_set_mark_kern.c")

from the MPTCP repo https://github.com/multipath-tcp/mptcp_net-next (the
"scripts" branch), and it has been adapted by Geliang.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/76
Co-developed-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-1-d26029e15cdd@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/progs/mptcp_subflow.c | 59 +++++++++++++++++++++++
 1 file changed, 59 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_subflow.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
new file mode 100644
index 000000000000..2e28f4a215b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Tessares SA. */
+/* Copyright (c) 2024, Kylin Software */
+
+/* vmlinux.h, bpf_helpers.h and other 'define' */
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+char cc[TCP_CA_NAME_MAX] = "reno";
+
+/* Associate a subflow counter to each token */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, 100);
+} mptcp_sf SEC(".maps");
+
+SEC("sockops")
+int mptcp_subflow(struct bpf_sock_ops *skops)
+{
+	__u32 init = 1, key, mark, *cnt;
+	struct mptcp_sock *msk;
+	struct bpf_sock *sk;
+	int err;
+
+	if (skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return 1;
+
+	sk = skops->sk;
+	if (!sk)
+		return 1;
+
+	msk = bpf_skc_to_mptcp_sock(sk);
+	if (!msk)
+		return 1;
+
+	key = msk->token;
+	cnt = bpf_map_lookup_elem(&mptcp_sf, &key);
+	if (cnt) {
+		/* A new subflow is added to an existing MPTCP connection */
+		__sync_fetch_and_add(cnt, 1);
+		mark = *cnt;
+	} else {
+		/* A new MPTCP connection is just initiated and this is its primary subflow */
+		bpf_map_update_elem(&mptcp_sf, &key, &init, BPF_ANY);
+		mark = init;
+	}
+
+	/* Set the mark of the subflow's socket based on appearance order */
+	err = bpf_setsockopt(skops, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (err < 0)
+		return 1;
+	if (mark == 2)
+		err = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, cc, TCP_CA_NAME_MAX);
+
+	return 1;
+}
-- 
cgit v1.2.3


From cd19b885106e0a24c28ef72fccc4c020782e6e7e Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 26 Sep 2024 19:30:23 +0200
Subject: selftests/bpf: Add getsockopt to inspect mptcp subflow

This patch adds a "cgroup/getsockopt" way to inspect the subflows of an
MPTCP socket, and verify the modifications done by the same BPF program
in the previous commit: a different mark per subflow, and a different
TCP CC set on the second one. This new hook will be used by the next
commit to verify the socket options set on each subflow.

This extra "cgroup/getsockopt" prog walks the msk->conn_list and use
bpf_core_cast to cast a pointer for readonly. It allows to inspect all
the fields of a structure.

Note that on the kernel side, the MPTCP socket stores a list of subflows
under 'msk->conn_list'. They can be iterated using the generic 'list'
helpers. They have been imported here, with a small difference:
list_for_each_entry() uses 'can_loop' to limit the number of iterations,
and ease its use. Because only data need to be read here, it is enough
to use this technique. It is planned to use bpf_iter, when BPF programs
will be used to modify data from the different subflows.
mptcp_subflow_tcp_sock() and mptcp_for_each_stubflow() helpers have also
be imported.

Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-2-d26029e15cdd@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 MAINTAINERS                                       |  2 +-
 tools/testing/selftests/bpf/progs/mptcp_bpf.h     | 42 ++++++++++++++
 tools/testing/selftests/bpf/progs/mptcp_subflow.c | 69 +++++++++++++++++++++++
 3 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf.h

(limited to 'tools/testing')

diff --git a/MAINTAINERS b/MAINTAINERS
index e71d066dc919..f02b7485b215 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16281,7 +16281,7 @@ F:	include/net/mptcp.h
 F:	include/trace/events/mptcp.h
 F:	include/uapi/linux/mptcp*.h
 F:	net/mptcp/
-F:	tools/testing/selftests/bpf/*/*mptcp*.c
+F:	tools/testing/selftests/bpf/*/*mptcp*.[ch]
 F:	tools/testing/selftests/net/mptcp/
 
 NETWORKING [TCP]
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
new file mode 100644
index 000000000000..3b188ccdcc40
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __MPTCP_BPF_H__
+#define __MPTCP_BPF_H__
+
+#include "bpf_experimental.h"
+
+/* list helpers from include/linux/list.h */
+static inline int list_is_head(const struct list_head *list,
+			       const struct list_head *head)
+{
+	return list == head;
+}
+
+#define list_entry(ptr, type, member)					\
+	container_of(ptr, type, member)
+
+#define list_first_entry(ptr, type, member)				\
+	list_entry((ptr)->next, type, member)
+
+#define list_next_entry(pos, member)					\
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+#define list_entry_is_head(pos, head, member)				\
+	list_is_head(&pos->member, (head))
+
+/* small difference: 'can_loop' has been added in the conditions */
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_first_entry(head, typeof(*pos), member);	\
+	     !list_entry_is_head(pos, head, member) && can_loop;	\
+	     pos = list_next_entry(pos, member))
+
+/* mptcp helpers from protocol.h */
+#define mptcp_for_each_subflow(__msk, __subflow)			\
+	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
+
+static __always_inline struct sock *
+mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
+{
+	return subflow->tcp_sock;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
index 2e28f4a215b5..70302477e326 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
@@ -4,10 +4,12 @@
 
 /* vmlinux.h, bpf_helpers.h and other 'define' */
 #include "bpf_tracing_net.h"
+#include "mptcp_bpf.h"
 
 char _license[] SEC("license") = "GPL";
 
 char cc[TCP_CA_NAME_MAX] = "reno";
+int pid;
 
 /* Associate a subflow counter to each token */
 struct {
@@ -57,3 +59,70 @@ int mptcp_subflow(struct bpf_sock_ops *skops)
 
 	return 1;
 }
+
+static int _check_getsockopt_subflow_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+	int i = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+
+		if (ssk->sk_mark != ++i) {
+			ctx->retval = -2;
+			break;
+		}
+	}
+
+	return 1;
+}
+
+static int _check_getsockopt_subflow_cc(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct inet_connection_sock *icsk;
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+		icsk = bpf_core_cast(ssk, struct inet_connection_sock);
+
+		if (ssk->sk_mark == 2 &&
+		    __builtin_memcmp(icsk->icsk_ca_ops->name, cc, TCP_CA_NAME_MAX)) {
+			ctx->retval = -2;
+			break;
+		}
+	}
+
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int _getsockopt_subflow(struct bpf_sockopt *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	struct mptcp_sock *msk;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	if (!sk || sk->protocol != IPPROTO_MPTCP ||
+	    (!(ctx->level == SOL_SOCKET && ctx->optname == SO_MARK) &&
+	     !(ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION)))
+		return 1;
+
+	msk = bpf_core_cast(sk, struct mptcp_sock);
+	if (msk->pm.subflows != 1) {
+		ctx->retval = -1;
+		return 1;
+	}
+
+	if (ctx->optname == SO_MARK)
+		return _check_getsockopt_subflow_mark(msk, ctx);
+	return _check_getsockopt_subflow_cc(msk, ctx);
+}
-- 
cgit v1.2.3


From 9b85f11efa02f3dc78c60961c0b9cff166516464 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 26 Sep 2024 19:30:24 +0200
Subject: selftests/bpf: Add mptcp subflow subtest

This patch adds a subtest named test_subflow in test_mptcp to load and
verify the newly added MPTCP subflow BPF program. To goal is to make
sure it is possible to set different socket options per subflows, while
the userspace socket interface only lets the application to set the same
socket options for the whole MPTCP connection and its multiple subflows.

To check that, a client and a server are started in a dedicated netns,
with veth interfaces to simulate multiple paths. They will exchange data
to allow the creation of an additional subflow.

When the different subflows are being created, the new MPTCP subflow BPF
program will set some socket options: marks and TCP CC. The validation
is done by the same program, when the userspace checks the value of the
modified socket options. On the userspace side, it will see that the
default values are still being used on the MPTCP connection, while the
BPF program will see different options set per subflow of the same MPTCP
connection.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/76
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240926-upstream-bpf-next-20240506-mptcp-subflow-test-v7-3-d26029e15cdd@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 121 +++++++++++++++++++++++++
 1 file changed, 121 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index d2ca32fa3b21..be3cad2aff77 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -5,12 +5,17 @@
 #include <linux/const.h>
 #include <netinet/in.h>
 #include <test_progs.h>
+#include <unistd.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
 #include "mptcpify.skel.h"
+#include "mptcp_subflow.skel.h"
 
 #define NS_TEST "mptcp_ns"
+#define ADDR_1	"10.0.1.1"
+#define ADDR_2	"10.0.1.2"
+#define PORT_1	10001
 
 #ifndef IPPROTO_MPTCP
 #define IPPROTO_MPTCP 262
@@ -335,10 +340,126 @@ fail:
 	close(cgroup_fd);
 }
 
+static int endpoint_init(char *flags)
+{
+	SYS(fail, "ip -net %s link add veth1 type veth peer name veth2", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/24 dev veth1", NS_TEST, ADDR_1);
+	SYS(fail, "ip -net %s link set dev veth1 up", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/24 dev veth2", NS_TEST, ADDR_2);
+	SYS(fail, "ip -net %s link set dev veth2 up", NS_TEST);
+	if (SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", NS_TEST, ADDR_2, flags)) {
+		printf("'ip mptcp' not supported, skip this test.\n");
+		test__skip();
+		goto fail;
+	}
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void wait_for_new_subflows(int fd)
+{
+	socklen_t len;
+	u8 subflows;
+	int err, i;
+
+	len = sizeof(subflows);
+	/* Wait max 5 sec for new subflows to be created */
+	for (i = 0; i < 50; i++) {
+		err = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &subflows, &len);
+		if (!err && subflows > 0)
+			break;
+
+		usleep(100000); /* 0.1s */
+	}
+}
+
+static void run_subflow(void)
+{
+	int server_fd, client_fd, err;
+	char new[TCP_CA_NAME_MAX];
+	char cc[TCP_CA_NAME_MAX];
+	unsigned int mark;
+	socklen_t len;
+
+	server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0);
+	if (!ASSERT_OK_FD(server_fd, "start_mptcp_server"))
+		return;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_fd"))
+		goto close_server;
+
+	send_byte(client_fd);
+	wait_for_new_subflows(client_fd);
+
+	len = sizeof(mark);
+	err = getsockopt(client_fd, SOL_SOCKET, SO_MARK, &mark, &len);
+	if (ASSERT_OK(err, "getsockopt(client_fd, SO_MARK)"))
+		ASSERT_EQ(mark, 0, "mark");
+
+	len = sizeof(new);
+	err = getsockopt(client_fd, SOL_TCP, TCP_CONGESTION, new, &len);
+	if (ASSERT_OK(err, "getsockopt(client_fd, TCP_CONGESTION)")) {
+		get_msk_ca_name(cc);
+		ASSERT_STREQ(new, cc, "cc");
+	}
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+}
+
+static void test_subflow(void)
+{
+	struct mptcp_subflow *skel;
+	struct nstoken *nstoken;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcp_subflow");
+	if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_subflow"))
+		return;
+
+	skel = mptcp_subflow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_subflow"))
+		goto close_cgroup;
+
+	skel->bss->pid = getpid();
+
+	skel->links.mptcp_subflow =
+		bpf_program__attach_cgroup(skel->progs.mptcp_subflow, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.mptcp_subflow, "attach mptcp_subflow"))
+		goto skel_destroy;
+
+	skel->links._getsockopt_subflow =
+		bpf_program__attach_cgroup(skel->progs._getsockopt_subflow, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow"))
+		goto skel_destroy;
+
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow"))
+		goto skel_destroy;
+
+	if (endpoint_init("subflow") < 0)
+		goto close_netns;
+
+	run_subflow();
+
+close_netns:
+	cleanup_netns(nstoken);
+skel_destroy:
+	mptcp_subflow__destroy(skel);
+close_cgroup:
+	close(cgroup_fd);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
 	if (test__start_subtest("mptcpify"))
 		test_mptcpify();
+	if (test__start_subtest("subflow"))
+		test_subflow();
 }
-- 
cgit v1.2.3


From 7c2f1c2690a5965fa0913c7b8c1b833dccddbb39 Mon Sep 17 00:00:00 2001
From: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Date: Fri, 27 Sep 2024 12:00:50 +0800
Subject: selftests/net: Add missing va_end.

There is no va_end after va_copy, just add it.

Signed-off-by: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240927040050.7851-1-zhangjiao2@cmss.chinamobile.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/tcp_ao/lib/aolib.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index db44e77428dd..5db2f65cddc4 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -46,6 +46,7 @@ static inline char *test_snprintf(const char *fmt, va_list vargs)
 
 	va_copy(tmp, vargs);
 	n = vsnprintf(ret, size, fmt, tmp);
+	va_end(tmp);
 	if (n < 0)
 		return NULL;
 
-- 
cgit v1.2.3


From be4e3235445725546f25f09ace04a4237c72e071 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 30 Sep 2024 17:12:50 +0200
Subject: selftests: mlxsw: rtnetlink: Use devlink_reload() API

The test runs "devlink reload" explicitly. Instead, it is better to use
devlink_reload() which waits for udev events to be processed. Do not sleep
after reload, as devlink_reload() blocks until all the netdevs are renamed.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/844509e3057b65277a7181a23c95b71ec95e8a56.1727706741.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 893a693ad805..45a569618424 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -186,10 +186,7 @@ bridge_vlan_flags_test()
 
 	# If we did not handle references correctly, then this should produce a
 	# trace
-	devlink dev reload "$DEVLINK_DEV"
-
-	# Allow netdevices to be re-created following the reload
-	sleep 20
+	devlink_reload
 
 	log_test "bridge vlan flags"
 }
@@ -923,12 +920,9 @@ devlink_reload_test()
 	# devlink reload can be performed without errors
 	RET=0
 
-	devlink dev reload "$DEVLINK_DEV"
-	check_err $? "devlink reload failed"
+	devlink_reload
 
 	log_test "devlink reload - last test"
-
-	sleep 20
 }
 
 trap cleanup EXIT
-- 
cgit v1.2.3


From d772cc25ccf772f4cbb81270970cbe1356c23d3e Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 30 Sep 2024 12:29:34 -0400
Subject: selftests: net: csum: Clean up recv_verify_packet_ipv6

Rename ip_len to payload_len since the length in this case refers only
to the payload, and not the entire IP packet like for IPv4. While we're
at it, just use the variable directly when calling
recv_verify_packet_udp/tcp.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240930162935.980712-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib/csum.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/lib/csum.c b/tools/testing/selftests/net/lib/csum.c
index e0a34e5e8dd5..27437590eeb5 100644
--- a/tools/testing/selftests/net/lib/csum.c
+++ b/tools/testing/selftests/net/lib/csum.c
@@ -675,22 +675,20 @@ static int recv_verify_packet_ipv6(void *nh, int len)
 {
 	struct ipv6hdr *ip6h = nh;
 	uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto;
-	uint16_t ip_len;
+	uint16_t payload_len;
 
 	if (len < sizeof(*ip6h) || ip6h->nexthdr != proto)
 		return -1;
 
-	ip_len = ntohs(ip6h->payload_len);
-	if (ip_len > len - sizeof(*ip6h))
+	payload_len = ntohs(ip6h->payload_len);
+	if (payload_len > len - sizeof(*ip6h))
 		return -1;
 
-	len = ip_len;
 	iph_addr_p = &ip6h->saddr;
-
 	if (proto == IPPROTO_TCP)
-		return recv_verify_packet_tcp(ip6h + 1, len);
+		return recv_verify_packet_tcp(ip6h + 1, payload_len);
 	else
-		return recv_verify_packet_udp(ip6h + 1, len);
+		return recv_verify_packet_udp(ip6h + 1, payload_len);
 }
 
 /* return whether auxdata includes TP_STATUS_CSUM_VALID */
-- 
cgit v1.2.3


From a89568e9be75845bdbba496f40e8cd0ea29c7af1 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Tue, 1 Oct 2024 05:57:16 -0700
Subject: selftests: txtimestamp: add SCM_TS_OPT_ID test

Extend txtimestamp test to run with fixed tskey using
SCM_TS_OPT_ID control message for all types of sockets.

Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://patch.msgid.link/20241001125716.2832769-4-vadfed@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/include/uapi/asm-generic/socket.h    |  2 ++
 tools/testing/selftests/net/txtimestamp.c  | 44 +++++++++++++++++++++++-------
 tools/testing/selftests/net/txtimestamp.sh | 12 ++++----
 3 files changed, 43 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index 54d9c8bf7c55..281df9139d2b 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -124,6 +124,8 @@
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SCM_TS_OPT_ID		78
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c
index d626f22f9550..dae91eb97d69 100644
--- a/tools/testing/selftests/net/txtimestamp.c
+++ b/tools/testing/selftests/net/txtimestamp.c
@@ -77,6 +77,8 @@ static bool cfg_epollet;
 static bool cfg_do_listen;
 static uint16_t dest_port = 9000;
 static bool cfg_print_nsec;
+static uint32_t ts_opt_id;
+static bool cfg_use_cmsg_opt_id;
 
 static struct sockaddr_in daddr;
 static struct sockaddr_in6 daddr6;
@@ -136,12 +138,13 @@ static void validate_key(int tskey, int tstype)
 	/* compare key for each subsequent request
 	 * must only test for one type, the first one requested
 	 */
-	if (saved_tskey == -1)
+	if (saved_tskey == -1 || cfg_use_cmsg_opt_id)
 		saved_tskey_type = tstype;
 	else if (saved_tskey_type != tstype)
 		return;
 
 	stepsize = cfg_proto == SOCK_STREAM ? cfg_payload_len : 1;
+	stepsize = cfg_use_cmsg_opt_id ? 0 : stepsize;
 	if (tskey != saved_tskey + stepsize) {
 		fprintf(stderr, "ERROR: key %d, expected %d\n",
 				tskey, saved_tskey + stepsize);
@@ -484,7 +487,7 @@ static void fill_header_udp(void *p, bool is_ipv4)
 
 static void do_test(int family, unsigned int report_opt)
 {
-	char control[CMSG_SPACE(sizeof(uint32_t))];
+	char control[2 * CMSG_SPACE(sizeof(uint32_t))];
 	struct sockaddr_ll laddr;
 	unsigned int sock_opt;
 	struct cmsghdr *cmsg;
@@ -624,18 +627,32 @@ static void do_test(int family, unsigned int report_opt)
 		msg.msg_iov = &iov;
 		msg.msg_iovlen = 1;
 
-		if (cfg_use_cmsg) {
+		if (cfg_use_cmsg || cfg_use_cmsg_opt_id) {
 			memset(control, 0, sizeof(control));
 
 			msg.msg_control = control;
-			msg.msg_controllen = sizeof(control);
+			msg.msg_controllen = cfg_use_cmsg * CMSG_SPACE(sizeof(uint32_t));
+			msg.msg_controllen += cfg_use_cmsg_opt_id * CMSG_SPACE(sizeof(uint32_t));
 
-			cmsg = CMSG_FIRSTHDR(&msg);
-			cmsg->cmsg_level = SOL_SOCKET;
-			cmsg->cmsg_type = SO_TIMESTAMPING;
-			cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t));
+			cmsg = NULL;
+			if (cfg_use_cmsg) {
+				cmsg = CMSG_FIRSTHDR(&msg);
+				cmsg->cmsg_level = SOL_SOCKET;
+				cmsg->cmsg_type = SO_TIMESTAMPING;
+				cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t));
+
+				*((uint32_t *)CMSG_DATA(cmsg)) = report_opt;
+			}
+			if (cfg_use_cmsg_opt_id) {
+				cmsg = cmsg ? CMSG_NXTHDR(&msg, cmsg) : CMSG_FIRSTHDR(&msg);
+				cmsg->cmsg_level = SOL_SOCKET;
+				cmsg->cmsg_type = SCM_TS_OPT_ID;
+				cmsg->cmsg_len = CMSG_LEN(sizeof(uint32_t));
+
+				*((uint32_t *)CMSG_DATA(cmsg)) = ts_opt_id;
+				saved_tskey = ts_opt_id;
+			}
 
-			*((uint32_t *) CMSG_DATA(cmsg)) = report_opt;
 		}
 
 		val = sendmsg(fd, &msg, 0);
@@ -685,6 +702,7 @@ static void __attribute__((noreturn)) usage(const char *filepath)
 			"  -L    listen on hostname and port\n"
 			"  -n:   set no-payload option\n"
 			"  -N:   print timestamps and durations in nsec (instead of usec)\n"
+			"  -o N: use SCM_TS_OPT_ID control message to provide N as tskey\n"
 			"  -p N: connect to port N\n"
 			"  -P:   use PF_PACKET\n"
 			"  -r:   use raw\n"
@@ -705,7 +723,7 @@ static void parse_opt(int argc, char **argv)
 	int c;
 
 	while ((c = getopt(argc, argv,
-				"46bc:CeEFhIl:LnNp:PrRS:t:uv:V:x")) != -1) {
+				"46bc:CeEFhIl:LnNo:p:PrRS:t:uv:V:x")) != -1) {
 		switch (c) {
 		case '4':
 			do_ipv6 = 0;
@@ -746,6 +764,10 @@ static void parse_opt(int argc, char **argv)
 		case 'N':
 			cfg_print_nsec = true;
 			break;
+		case 'o':
+			ts_opt_id = strtoul(optarg, NULL, 10);
+			cfg_use_cmsg_opt_id = true;
+			break;
 		case 'p':
 			dest_port = strtoul(optarg, NULL, 10);
 			break;
@@ -803,6 +825,8 @@ static void parse_opt(int argc, char **argv)
 		error(1, 0, "cannot ask for pktinfo over pf_packet");
 	if (cfg_busy_poll && cfg_use_epoll)
 		error(1, 0, "pass epoll or busy_poll, not both");
+	if (cfg_proto == SOCK_STREAM && cfg_use_cmsg_opt_id)
+		error(1, 0, "TCP sockets don't support SCM_TS_OPT_ID");
 
 	if (optind != argc - 1)
 		error(1, 0, "missing required hostname argument");
diff --git a/tools/testing/selftests/net/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh
index 25baca4b148e..fe4649bb8786 100755
--- a/tools/testing/selftests/net/txtimestamp.sh
+++ b/tools/testing/selftests/net/txtimestamp.sh
@@ -37,11 +37,13 @@ run_test_v4v6() {
 run_test_tcpudpraw() {
 	local -r args=$@
 
-	run_test_v4v6 ${args}		# tcp
-	run_test_v4v6 ${args} -u	# udp
-	run_test_v4v6 ${args} -r	# raw
-	run_test_v4v6 ${args} -R	# raw (IPPROTO_RAW)
-	run_test_v4v6 ${args} -P	# pf_packet
+	run_test_v4v6 ${args}		  # tcp
+	run_test_v4v6 ${args} -u	  # udp
+	run_test_v4v6 ${args} -u -o 42	  # udp with fixed tskey
+	run_test_v4v6 ${args} -r	  # raw
+	run_test_v4v6 ${args} -r -o 42	  # raw
+	run_test_v4v6 ${args} -R	  # raw (IPPROTO_RAW)
+	run_test_v4v6 ${args} -P	  # pf_packet
 }
 
 run_test_all() {
-- 
cgit v1.2.3


From 897408d5e2248b8f139d57fe8f8bab651f80e6e6 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Wed, 2 Oct 2024 18:27:30 +0200
Subject: selftests: net: remove ioam tests

This patch entirely removes the ioam selftests to prepare for the next
patch in this series, which re-adds the new ioam selftests for better
readability.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20241002162731.19847-2-justin.iurman@uliege.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile       |   2 -
 tools/testing/selftests/net/config         |   1 -
 tools/testing/selftests/net/ioam6.sh       | 771 -----------------------------
 tools/testing/selftests/net/ioam6_parser.c | 674 -------------------------
 4 files changed, 1448 deletions(-)
 delete mode 100755 tools/testing/selftests/net/ioam6.sh
 delete mode 100644 tools/testing/selftests/net/ioam6_parser.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 649f1fe0dc46..ef40d099aa1c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -28,7 +28,6 @@ TEST_PROGS += unicast_extensions.sh
 TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS += udpgro_frglist.sh
 TEST_PROGS += veth.sh
-TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
 TEST_PROGS += cmsg_so_mark.sh
@@ -67,7 +66,6 @@ TEST_GEN_FILES += fin_ack_lat
 TEST_GEN_FILES += reuseaddr_ports_exhausted
 TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
 TEST_GEN_FILES += ipsec
-TEST_GEN_FILES += ioam6_parser
 TEST_GEN_FILES += gro
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_poll
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5b9baf708950..3f0b02835e78 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -95,7 +95,6 @@ CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_ACT_TUNNEL_KEY=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_BAREUDP=m
-CONFIG_IPV6_IOAM6_LWTUNNEL=y
 CONFIG_CRYPTO_SM4_GENERIC=y
 CONFIG_AMT=m
 CONFIG_TUN=y
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
deleted file mode 100755
index 12491850ae98..000000000000
--- a/tools/testing/selftests/net/ioam6.sh
+++ /dev/null
@@ -1,771 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0+
-#
-# Author: Justin Iurman <justin.iurman@uliege.be>
-#
-# This script evaluates the IOAM insertion for IPv6 by checking the IOAM data
-# consistency directly inside packets on the receiver side. Tests are divided
-# into three categories: OUTPUT (evaluates the IOAM processing by the sender),
-# INPUT (evaluates the IOAM processing by a receiver) and GLOBAL (evaluates
-# wider use cases that do not fall into the other two categories). Both OUTPUT
-# and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL
-# tests use the entire three-node topology (alpha, beta, gamma). Each test is
-# documented inside its own handler in the code below.
-#
-# An IOAM domain is configured from Alpha to Gamma but not on the reverse path.
-# When either Beta or Gamma is the destination (depending on the test category),
-# Alpha adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop.
-#
-#
-#            +-------------------+            +-------------------+
-#            |                   |            |                   |
-#            |    Alpha netns    |            |    Gamma netns    |
-#            |                   |            |                   |
-#            |  +-------------+  |            |  +-------------+  |
-#            |  |    veth0    |  |            |  |    veth0    |  |
-#            |  |  db01::2/64 |  |            |  |  db02::2/64 |  |
-#            |  +-------------+  |            |  +-------------+  |
-#            |         .         |            |         .         |
-#            +-------------------+            +-------------------+
-#                      .                                .
-#                      .                                .
-#                      .                                .
-#            +----------------------------------------------------+
-#            |         .                                .         |
-#            |  +-------------+                  +-------------+  |
-#            |  |    veth0    |                  |    veth1    |  |
-#            |  |  db01::1/64 | ................ |  db02::1/64 |  |
-#            |  +-------------+                  +-------------+  |
-#            |                                                    |
-#            |                      Beta netns                    |
-#            |                                                    |
-#            +----------------------------------------------------+
-#
-#
-#
-#        =============================================================
-#        |                Alpha - IOAM configuration                 |
-#        +===========================================================+
-#        | Node ID             | 1                                   |
-#        +-----------------------------------------------------------+
-#        | Node Wide ID        | 11111111                            |
-#        +-----------------------------------------------------------+
-#        | Ingress ID          | 0xffff (default value)              |
-#        +-----------------------------------------------------------+
-#        | Ingress Wide ID     | 0xffffffff (default value)          |
-#        +-----------------------------------------------------------+
-#        | Egress ID           | 101                                 |
-#        +-----------------------------------------------------------+
-#        | Egress Wide ID      | 101101                              |
-#        +-----------------------------------------------------------+
-#        | Namespace Data      | 0xdeadbee0                          |
-#        +-----------------------------------------------------------+
-#        | Namespace Wide Data | 0xcafec0caf00dc0de                  |
-#        +-----------------------------------------------------------+
-#        | Schema ID           | 777                                 |
-#        +-----------------------------------------------------------+
-#        | Schema Data         | something that will be 4n-aligned   |
-#        +-----------------------------------------------------------+
-#
-#
-#        =============================================================
-#        |                 Beta - IOAM configuration                 |
-#        +===========================================================+
-#        | Node ID             | 2                                   |
-#        +-----------------------------------------------------------+
-#        | Node Wide ID        | 22222222                            |
-#        +-----------------------------------------------------------+
-#        | Ingress ID          | 201                                 |
-#        +-----------------------------------------------------------+
-#        | Ingress Wide ID     | 201201                              |
-#        +-----------------------------------------------------------+
-#        | Egress ID           | 202                                 |
-#        +-----------------------------------------------------------+
-#        | Egress Wide ID      | 202202                              |
-#        +-----------------------------------------------------------+
-#        | Namespace Data      | 0xdeadbee1                          |
-#        +-----------------------------------------------------------+
-#        | Namespace Wide Data | 0xcafec0caf11dc0de                  |
-#        +-----------------------------------------------------------+
-#        | Schema ID           | 666                                 |
-#        +-----------------------------------------------------------+
-#        | Schema Data         | Hello there -Obi                    |
-#        +-----------------------------------------------------------+
-#
-#
-#        =============================================================
-#        |                Gamma - IOAM configuration                 |
-#        +===========================================================+
-#        | Node ID             | 3                                   |
-#        +-----------------------------------------------------------+
-#        | Node Wide ID        | 33333333                            |
-#        +-----------------------------------------------------------+
-#        | Ingress ID          | 301                                 |
-#        +-----------------------------------------------------------+
-#        | Ingress Wide ID     | 301301                              |
-#        +-----------------------------------------------------------+
-#        | Egress ID           | 0xffff (default value)              |
-#        +-----------------------------------------------------------+
-#        | Egress Wide ID      | 0xffffffff (default value)          |
-#        +-----------------------------------------------------------+
-#        | Namespace Data      | 0xdeadbee2                          |
-#        +-----------------------------------------------------------+
-#        | Namespace Wide Data | 0xcafec0caf22dc0de                  |
-#        +-----------------------------------------------------------+
-#        | Schema ID           | 0xffffff (= None)                   |
-#        +-----------------------------------------------------------+
-#        | Schema Data         |                                     |
-#        +-----------------------------------------------------------+
-
-source lib.sh
-
-################################################################################
-#                                                                              #
-# WARNING: Be careful if you modify the block below - it MUST be kept          #
-#          synchronized with configurations inside ioam6_parser.c and always   #
-#          reflect the same.                                                   #
-#                                                                              #
-################################################################################
-
-ALPHA=(
-	1					# ID
-	11111111				# Wide ID
-	0xffff					# Ingress ID
-	0xffffffff				# Ingress Wide ID
-	101					# Egress ID
-	101101					# Egress Wide ID
-	0xdeadbee0				# Namespace Data
-	0xcafec0caf00dc0de			# Namespace Wide Data
-	777					# Schema ID (0xffffff = None)
-	"something that will be 4n-aligned"	# Schema Data
-)
-
-BETA=(
-	2
-	22222222
-	201
-	201201
-	202
-	202202
-	0xdeadbee1
-	0xcafec0caf11dc0de
-	666
-	"Hello there -Obi"
-)
-
-GAMMA=(
-	3
-	33333333
-	301
-	301301
-	0xffff
-	0xffffffff
-	0xdeadbee2
-	0xcafec0caf22dc0de
-	0xffffff
-	""
-)
-
-TESTS_OUTPUT="
-	out_undef_ns
-	out_no_room
-	out_bits
-	out_full_supp_trace
-"
-
-TESTS_INPUT="
-	in_undef_ns
-	in_no_room
-	in_oflag
-	in_bits
-	in_full_supp_trace
-"
-
-TESTS_GLOBAL="
-	fwd_full_supp_trace
-"
-
-
-################################################################################
-#                                                                              #
-#                                   LIBRARY                                    #
-#                                                                              #
-################################################################################
-
-check_kernel_compatibility()
-{
-  setup_ns ioam_tmp_node
-  ip link add name veth0 netns $ioam_tmp_node type veth \
-         peer name veth1 netns $ioam_tmp_node
-
-  ip -netns $ioam_tmp_node link set veth0 up
-  ip -netns $ioam_tmp_node link set veth1 up
-
-  ip -netns $ioam_tmp_node ioam namespace add 0
-  ns_ad=$?
-
-  ip -netns $ioam_tmp_node ioam namespace show | grep -q "namespace 0"
-  ns_sh=$?
-
-  if [[ $ns_ad != 0 || $ns_sh != 0 ]]
-  then
-    echo "SKIP: kernel version probably too old, missing ioam support"
-    ip link del veth0 2>/dev/null || true
-    cleanup_ns $ioam_tmp_node || true
-    exit $ksft_skip
-  fi
-
-  ip -netns $ioam_tmp_node route add db02::/64 encap ioam6 mode inline \
-         trace prealloc type 0x800000 ns 0 size 4 dev veth0
-  tr_ad=$?
-
-  ip -netns $ioam_tmp_node -6 route | grep -q "encap ioam6"
-  tr_sh=$?
-
-  if [[ $tr_ad != 0 || $tr_sh != 0 ]]
-  then
-    echo "SKIP: cannot attach an ioam trace to a route, did you compile" \
-         "without CONFIG_IPV6_IOAM6_LWTUNNEL?"
-    ip link del veth0 2>/dev/null || true
-    cleanup_ns $ioam_tmp_node || true
-    exit $ksft_skip
-  fi
-
-  ip link del veth0 2>/dev/null || true
-  cleanup_ns $ioam_tmp_node || true
-
-  lsmod | grep -q "ip6_tunnel"
-  ip6tnl_loaded=$?
-
-  if [ $ip6tnl_loaded = 0 ]
-  then
-    encap_tests=0
-  else
-    modprobe ip6_tunnel &>/dev/null
-    lsmod | grep -q "ip6_tunnel"
-    encap_tests=$?
-
-    if [ $encap_tests != 0 ]
-    then
-      ip a | grep -q "ip6tnl0"
-      encap_tests=$?
-
-      if [ $encap_tests != 0 ]
-      then
-        echo "Note: ip6_tunnel not found neither as a module nor inside the" \
-             "kernel, tests that require it (encap mode) will be omitted"
-      fi
-    fi
-  fi
-}
-
-cleanup()
-{
-  ip link del ioam-veth-alpha 2>/dev/null || true
-  ip link del ioam-veth-gamma 2>/dev/null || true
-
-  cleanup_ns $ioam_node_alpha $ioam_node_beta $ioam_node_gamma || true
-
-  if [ $ip6tnl_loaded != 0 ]
-  then
-    modprobe -r ip6_tunnel 2>/dev/null || true
-  fi
-}
-
-setup()
-{
-  setup_ns ioam_node_alpha ioam_node_beta ioam_node_gamma
-
-  ip link add name ioam-veth-alpha netns $ioam_node_alpha type veth \
-         peer name ioam-veth-betaL netns $ioam_node_beta
-  ip link add name ioam-veth-betaR netns $ioam_node_beta type veth \
-         peer name ioam-veth-gamma netns $ioam_node_gamma
-
-  ip -netns $ioam_node_alpha link set ioam-veth-alpha name veth0
-  ip -netns $ioam_node_beta link set ioam-veth-betaL name veth0
-  ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1
-  ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0
-
-  ip -netns $ioam_node_alpha addr add db01::2/64 dev veth0
-  ip -netns $ioam_node_alpha link set veth0 up
-  ip -netns $ioam_node_alpha link set lo up
-  ip -netns $ioam_node_alpha route add db02::/64 via db01::1 dev veth0
-  ip -netns $ioam_node_alpha route del db01::/64
-  ip -netns $ioam_node_alpha route add db01::/64 dev veth0
-
-  ip -netns $ioam_node_beta addr add db01::1/64 dev veth0
-  ip -netns $ioam_node_beta addr add db02::1/64 dev veth1
-  ip -netns $ioam_node_beta link set veth0 up
-  ip -netns $ioam_node_beta link set veth1 up
-  ip -netns $ioam_node_beta link set lo up
-
-  ip -netns $ioam_node_gamma addr add db02::2/64 dev veth0
-  ip -netns $ioam_node_gamma link set veth0 up
-  ip -netns $ioam_node_gamma link set lo up
-  ip -netns $ioam_node_gamma route add db01::/64 via db02::1 dev veth0
-
-  # - IOAM config -
-  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]}
-  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]}
-  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]}
-  ip netns exec $ioam_node_alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]}
-  ip -netns $ioam_node_alpha ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]}
-  ip -netns $ioam_node_alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}"
-  ip -netns $ioam_node_alpha ioam namespace set 123 schema ${ALPHA[8]}
-
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.all.forwarding=1
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]}
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]}
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]}
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]}
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]}
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]}
-  ip -netns $ioam_node_beta ioam namespace add 123 data ${BETA[6]} wide ${BETA[7]}
-  ip -netns $ioam_node_beta ioam schema add ${BETA[8]} "${BETA[9]}"
-  ip -netns $ioam_node_beta ioam namespace set 123 schema ${BETA[8]}
-
-  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]}
-  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]}
-  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
-  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]}
-  ip netns exec $ioam_node_gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]}
-  ip -netns $ioam_node_gamma ioam namespace add 123 data ${GAMMA[6]} wide ${GAMMA[7]}
-
-  sleep 1
-
-  ip netns exec $ioam_node_alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
-  if [ $? != 0 ]
-  then
-    echo "Setup FAILED"
-    cleanup &>/dev/null
-    exit 0
-  fi
-}
-
-log_test_passed()
-{
-  local desc=$1
-  printf "TEST: %-60s  [ OK ]\n" "${desc}"
-}
-
-log_test_failed()
-{
-  local desc=$1
-  printf "TEST: %-60s  [FAIL]\n" "${desc}"
-}
-
-log_results()
-{
-  echo "- Tests passed: ${npassed}"
-  echo "- Tests failed: ${nfailed}"
-}
-
-run_test()
-{
-  local name=$1
-  local desc=$2
-  local node_src=$3
-  local node_dst=$4
-  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
-
-  ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null
-  if [ $? != 0 ]
-  then
-    nfailed=$((nfailed+1))
-    log_test_failed "${desc}"
-    kill -2 $spid &>/dev/null
-  else
-    wait $spid
-    if [ $? = 0 ]
-    then
-      npassed=$((npassed+1))
-      log_test_passed "${desc}"
-    else
-      nfailed=$((nfailed+1))
-      log_test_failed "${desc}"
-    fi
-  fi
-}
-
-run()
-{
-  echo
-  printf "%0.s-" {1..74}
-  echo
-  echo "OUTPUT tests"
-  printf "%0.s-" {1..74}
-  echo
-
-  # set OUTPUT settings
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0
-
-  for t in $TESTS_OUTPUT
-  do
-    $t "inline"
-    [ $encap_tests = 0 ] && $t "encap"
-  done
-
-  # clean OUTPUT settings
-  ip netns exec $ioam_node_beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
-  ip -netns $ioam_node_alpha route change db01::/64 dev veth0
-
-
-  echo
-  printf "%0.s-" {1..74}
-  echo
-  echo "INPUT tests"
-  printf "%0.s-" {1..74}
-  echo
-
-  # set INPUT settings
-  ip -netns $ioam_node_alpha ioam namespace del 123
-
-  for t in $TESTS_INPUT
-  do
-    $t "inline"
-    [ $encap_tests = 0 ] && $t "encap"
-  done
-
-  # clean INPUT settings
-  ip -netns $ioam_node_alpha ioam namespace add 123 \
-         data ${ALPHA[6]} wide ${ALPHA[7]}
-  ip -netns $ioam_node_alpha ioam namespace set 123 schema ${ALPHA[8]}
-  ip -netns $ioam_node_alpha route change db01::/64 dev veth0
-
-  echo
-  printf "%0.s-" {1..74}
-  echo
-  echo "GLOBAL tests"
-  printf "%0.s-" {1..74}
-  echo
-
-  for t in $TESTS_GLOBAL
-  do
-    $t "inline"
-    [ $encap_tests = 0 ] && $t "encap"
-  done
-
-  echo
-  log_results
-}
-
-bit2type=(
-  0x800000 0x400000 0x200000 0x100000 0x080000 0x040000 0x020000 0x010000
-  0x008000 0x004000 0x002000 0x001000 0x000800 0x000400 0x000200 0x000100
-  0x000080 0x000040 0x000020 0x000010 0x000008 0x000004 0x000002
-)
-bit2size=( 4 4 4 4 4 4 4 4 8 8 8 4 4 4 4 4 4 4 4 4 4 4 4 )
-
-
-################################################################################
-#                                                                              #
-#                              OUTPUT tests                                    #
-#                                                                              #
-#   Two nodes (sender/receiver), IOAM disabled on ingress for the receiver.    #
-################################################################################
-
-out_undef_ns()
-{
-  ##############################################################################
-  # Make sure that the encap node won't fill the trace if the chosen IOAM      #
-  # namespace is not configured locally.                                       #
-  ##############################################################################
-  local desc="Unknown IOAM namespace"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0x800000 ns 0 size 4 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0x800000 0 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-}
-
-out_no_room()
-{
-  ##############################################################################
-  # Make sure that the encap node won't fill the trace and will set the        #
-  # Overflow flag since there is no room enough for its data.                  #
-  ##############################################################################
-  local desc="Missing trace room"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0xc00000 ns 123 size 4 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0xc00000 123 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-}
-
-out_bits()
-{
-  ##############################################################################
-  # Make sure that, for each trace type bit, the encap node will either:       #
-  #  (i)  fill the trace with its data when it is a supported bit              #
-  #  (ii) not fill the trace with its data when it is an unsupported bit       #
-  ##############################################################################
-  local desc="Trace type with bit <n> only"
-
-  local tmp=${bit2size[22]}
-  bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) ))
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  for i in {0..22}
-  do
-    ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-           trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \
-           dev veth0 &>/dev/null
-
-    local cmd_res=$?
-    local descr="${desc/<n>/$i}"
-
-    if [[ $i -ge 12 && $i -le 21 ]]
-    then
-      if [ $cmd_res != 0 ]
-      then
-        npassed=$((npassed+1))
-        log_test_passed "$descr ($1 mode)"
-      else
-        nfailed=$((nfailed+1))
-        log_test_failed "$descr ($1 mode)"
-      fi
-    else
-	run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
-    fi
-  done
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-
-  bit2size[22]=$tmp
-}
-
-out_full_supp_trace()
-{
-  ##############################################################################
-  # Make sure that the encap node will correctly fill a full trace. Be careful,#
-  # "full trace" here does NOT mean all bits (only supported ones).            #
-  ##############################################################################
-  local desc="Full supported trace"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0xfff002 ns 123 size 100 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0xfff002 123 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-}
-
-
-################################################################################
-#                                                                              #
-#                               INPUT tests                                    #
-#                                                                              #
-#     Two nodes (sender/receiver), the sender MUST NOT fill the trace upon     #
-#     insertion -> the IOAM namespace configured on the sender is removed      #
-#     and is used in the inserted trace to force the sender not to fill it.    #
-################################################################################
-
-in_undef_ns()
-{
-  ##############################################################################
-  # Make sure that the receiving node won't fill the trace if the related IOAM #
-  # namespace is not configured locally.                                       #
-  ##############################################################################
-  local desc="Unknown IOAM namespace"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0x800000 ns 0 size 4 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0x800000 0 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-}
-
-in_no_room()
-{
-  ##############################################################################
-  # Make sure that the receiving node won't fill the trace and will set the    #
-  # Overflow flag if there is no room enough for its data.                     #
-  ##############################################################################
-  local desc="Missing trace room"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0xc00000 ns 123 size 4 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0xc00000 123 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-}
-
-in_bits()
-{
-  ##############################################################################
-  # Make sure that, for each trace type bit, the receiving node will either:   #
-  #  (i)  fill the trace with its data when it is a supported bit              #
-  #  (ii) not fill the trace with its data when it is an unsupported bit       #
-  ##############################################################################
-  local desc="Trace type with bit <n> only"
-
-  local tmp=${bit2size[22]}
-  bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) ))
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  for i in {0..11} {22..22}
-  do
-    ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-           trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \
-           dev veth0
-
-    run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
-  done
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-
-  bit2size[22]=$tmp
-}
-
-in_oflag()
-{
-  ##############################################################################
-  # Make sure that the receiving node won't fill the trace since the Overflow  #
-  # flag is set.                                                               #
-  ##############################################################################
-  local desc="Overflow flag is set"
-
-  # Exception:
-  #   Here, we need the sender to set the Overflow flag. For that, we will add
-  #   back the IOAM namespace that was previously configured on the sender.
-  ip -netns $ioam_node_alpha ioam namespace add 123
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0xc00000 ns 123 size 4 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0xc00000 123 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-
-  # And we clean the exception for this test to get things back to normal for
-  # other INPUT tests
-  ip -netns $ioam_node_alpha ioam namespace del 123
-}
-
-in_full_supp_trace()
-{
-  ##############################################################################
-  # Make sure that the receiving node will correctly fill a full trace. Be     #
-  # careful, "full trace" here does NOT mean all bits (only supported ones).   #
-  ##############################################################################
-  local desc="Full supported trace"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db01::/64 encap ioam6 mode $mode \
-         trace prealloc type 0xfff002 ns 123 size 80 dev veth0
-
-  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::1 0xfff002 123 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
-}
-
-
-################################################################################
-#                                                                              #
-#                              GLOBAL tests                                    #
-#                                                                              #
-#   Three nodes (sender/router/receiver), IOAM fully enabled on every node.    #
-################################################################################
-
-fwd_full_supp_trace()
-{
-  ##############################################################################
-  # Make sure that all three nodes correctly filled the full supported trace   #
-  # by checking that the trace data is consistent with the predefined config.  #
-  ##############################################################################
-  local desc="Forward - Full supported trace"
-
-  [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1"
-  [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 up
-
-  ip -netns $ioam_node_alpha route change db02::/64 encap ioam6 mode $mode \
-         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 \
-         db02::2 0xfff002 123 $1
-
-  [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down
-}
-
-
-################################################################################
-#                                                                              #
-#                                     MAIN                                     #
-#                                                                              #
-################################################################################
-
-npassed=0
-nfailed=0
-
-if [ "$(id -u)" -ne 0 ]
-then
-  echo "SKIP: Need root privileges"
-  exit $ksft_skip
-fi
-
-if [ ! -x "$(command -v ip)" ]
-then
-  echo "SKIP: Could not run test without ip tool"
-  exit $ksft_skip
-fi
-
-ip ioam &>/dev/null
-if [ $? = 1 ]
-then
-  echo "SKIP: iproute2 too old, missing ioam command"
-  exit $ksft_skip
-fi
-
-check_kernel_compatibility
-
-cleanup &>/dev/null
-setup
-run
-cleanup &>/dev/null
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
deleted file mode 100644
index 895e5bb5044b..000000000000
--- a/tools/testing/selftests/net/ioam6_parser.c
+++ /dev/null
@@ -1,674 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Author: Justin Iurman (justin.iurman@uliege.be)
- *
- * IOAM tester for IPv6, see ioam6.sh for details on each test case.
- */
-#include <arpa/inet.h>
-#include <errno.h>
-#include <limits.h>
-#include <linux/const.h>
-#include <linux/ioam6.h>
-#include <linux/ipv6.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-
-struct ioam_config {
-	__u32 id;
-	__u64 wide;
-	__u16 ingr_id;
-	__u16 egr_id;
-	__u32 ingr_wide;
-	__u32 egr_wide;
-	__u32 ns_data;
-	__u64 ns_wide;
-	__u32 sc_id;
-	__u8 hlim;
-	char *sc_data;
-};
-
-/*
- * Be careful if you modify structs below - everything MUST be kept synchronized
- * with configurations inside ioam6.sh and always reflect the same.
- */
-
-static struct ioam_config node1 = {
-	.id = 1,
-	.wide = 11111111,
-	.ingr_id = 0xffff, /* default value */
-	.egr_id = 101,
-	.ingr_wide = 0xffffffff, /* default value */
-	.egr_wide = 101101,
-	.ns_data = 0xdeadbee0,
-	.ns_wide = 0xcafec0caf00dc0de,
-	.sc_id = 777,
-	.sc_data = "something that will be 4n-aligned",
-	.hlim = 64,
-};
-
-static struct ioam_config node2 = {
-	.id = 2,
-	.wide = 22222222,
-	.ingr_id = 201,
-	.egr_id = 202,
-	.ingr_wide = 201201,
-	.egr_wide = 202202,
-	.ns_data = 0xdeadbee1,
-	.ns_wide = 0xcafec0caf11dc0de,
-	.sc_id = 666,
-	.sc_data = "Hello there -Obi",
-	.hlim = 63,
-};
-
-static struct ioam_config node3 = {
-	.id = 3,
-	.wide = 33333333,
-	.ingr_id = 301,
-	.egr_id = 0xffff, /* default value */
-	.ingr_wide = 301301,
-	.egr_wide = 0xffffffff, /* default value */
-	.ns_data = 0xdeadbee2,
-	.ns_wide = 0xcafec0caf22dc0de,
-	.sc_id = 0xffffff, /* default value */
-	.sc_data = NULL,
-	.hlim = 62,
-};
-
-enum {
-	/**********
-	 * OUTPUT *
-	 **********/
-	TEST_OUT_UNDEF_NS,
-	TEST_OUT_NO_ROOM,
-	TEST_OUT_BIT0,
-	TEST_OUT_BIT1,
-	TEST_OUT_BIT2,
-	TEST_OUT_BIT3,
-	TEST_OUT_BIT4,
-	TEST_OUT_BIT5,
-	TEST_OUT_BIT6,
-	TEST_OUT_BIT7,
-	TEST_OUT_BIT8,
-	TEST_OUT_BIT9,
-	TEST_OUT_BIT10,
-	TEST_OUT_BIT11,
-	TEST_OUT_BIT22,
-	TEST_OUT_FULL_SUPP_TRACE,
-
-	/*********
-	 * INPUT *
-	 *********/
-	TEST_IN_UNDEF_NS,
-	TEST_IN_NO_ROOM,
-	TEST_IN_OFLAG,
-	TEST_IN_BIT0,
-	TEST_IN_BIT1,
-	TEST_IN_BIT2,
-	TEST_IN_BIT3,
-	TEST_IN_BIT4,
-	TEST_IN_BIT5,
-	TEST_IN_BIT6,
-	TEST_IN_BIT7,
-	TEST_IN_BIT8,
-	TEST_IN_BIT9,
-	TEST_IN_BIT10,
-	TEST_IN_BIT11,
-	TEST_IN_BIT22,
-	TEST_IN_FULL_SUPP_TRACE,
-
-	/**********
-	 * GLOBAL *
-	 **********/
-	TEST_FWD_FULL_SUPP_TRACE,
-
-	__TEST_MAX,
-};
-
-static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h,
-			     __u32 trace_type, __u16 ioam_ns)
-{
-	if (__be16_to_cpu(ioam6h->namespace_id) != ioam_ns ||
-	    __be32_to_cpu(ioam6h->type_be32) != (trace_type << 8))
-		return 1;
-
-	switch (tid) {
-	case TEST_OUT_UNDEF_NS:
-	case TEST_IN_UNDEF_NS:
-		return ioam6h->overflow ||
-		       ioam6h->nodelen != 1 ||
-		       ioam6h->remlen != 1;
-
-	case TEST_OUT_NO_ROOM:
-	case TEST_IN_NO_ROOM:
-	case TEST_IN_OFLAG:
-		return !ioam6h->overflow ||
-		       ioam6h->nodelen != 2 ||
-		       ioam6h->remlen != 1;
-
-	case TEST_OUT_BIT0:
-	case TEST_IN_BIT0:
-	case TEST_OUT_BIT1:
-	case TEST_IN_BIT1:
-	case TEST_OUT_BIT2:
-	case TEST_IN_BIT2:
-	case TEST_OUT_BIT3:
-	case TEST_IN_BIT3:
-	case TEST_OUT_BIT4:
-	case TEST_IN_BIT4:
-	case TEST_OUT_BIT5:
-	case TEST_IN_BIT5:
-	case TEST_OUT_BIT6:
-	case TEST_IN_BIT6:
-	case TEST_OUT_BIT7:
-	case TEST_IN_BIT7:
-	case TEST_OUT_BIT11:
-	case TEST_IN_BIT11:
-		return ioam6h->overflow ||
-		       ioam6h->nodelen != 1 ||
-		       ioam6h->remlen;
-
-	case TEST_OUT_BIT8:
-	case TEST_IN_BIT8:
-	case TEST_OUT_BIT9:
-	case TEST_IN_BIT9:
-	case TEST_OUT_BIT10:
-	case TEST_IN_BIT10:
-		return ioam6h->overflow ||
-		       ioam6h->nodelen != 2 ||
-		       ioam6h->remlen;
-
-	case TEST_OUT_BIT22:
-	case TEST_IN_BIT22:
-		return ioam6h->overflow ||
-		       ioam6h->nodelen ||
-		       ioam6h->remlen;
-
-	case TEST_OUT_FULL_SUPP_TRACE:
-	case TEST_IN_FULL_SUPP_TRACE:
-	case TEST_FWD_FULL_SUPP_TRACE:
-		return ioam6h->overflow ||
-		       ioam6h->nodelen != 15 ||
-		       ioam6h->remlen;
-
-	default:
-		break;
-	}
-
-	return 1;
-}
-
-static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h,
-			    const struct ioam_config cnf)
-{
-	unsigned int len;
-	__u8 aligned;
-	__u64 raw64;
-	__u32 raw32;
-
-	if (ioam6h->type.bit0) {
-		raw32 = __be32_to_cpu(*((__u32 *)*p));
-		if (cnf.hlim != (raw32 >> 24) || cnf.id != (raw32 & 0xffffff))
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit1) {
-		raw32 = __be32_to_cpu(*((__u32 *)*p));
-		if (cnf.ingr_id != (raw32 >> 16) ||
-		    cnf.egr_id != (raw32 & 0xffff))
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit2)
-		*p += sizeof(__u32);
-
-	if (ioam6h->type.bit3)
-		*p += sizeof(__u32);
-
-	if (ioam6h->type.bit4) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit5) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != cnf.ns_data)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit6)
-		*p += sizeof(__u32);
-
-	if (ioam6h->type.bit7) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit8) {
-		raw64 = __be64_to_cpu(*((__u64 *)*p));
-		if (cnf.hlim != (raw64 >> 56) ||
-		    cnf.wide != (raw64 & 0xffffffffffffff))
-			return 1;
-		*p += sizeof(__u64);
-	}
-
-	if (ioam6h->type.bit9) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != cnf.ingr_wide)
-			return 1;
-		*p += sizeof(__u32);
-
-		if (__be32_to_cpu(*((__u32 *)*p)) != cnf.egr_wide)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit10) {
-		if (__be64_to_cpu(*((__u64 *)*p)) != cnf.ns_wide)
-			return 1;
-		*p += sizeof(__u64);
-	}
-
-	if (ioam6h->type.bit11) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit12) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit13) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit14) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit15) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit16) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit17) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit18) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit19) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit20) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit21) {
-		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
-			return 1;
-		*p += sizeof(__u32);
-	}
-
-	if (ioam6h->type.bit22) {
-		len = cnf.sc_data ? strlen(cnf.sc_data) : 0;
-		aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0;
-
-		raw32 = __be32_to_cpu(*((__u32 *)*p));
-		if (aligned != (raw32 >> 24) * 4 ||
-		    cnf.sc_id != (raw32 & 0xffffff))
-			return 1;
-		*p += sizeof(__u32);
-
-		if (cnf.sc_data) {
-			if (strncmp((char *)*p, cnf.sc_data, len))
-				return 1;
-
-			*p += len;
-			aligned -= len;
-
-			while (aligned--) {
-				if (**p != '\0')
-					return 1;
-				*p += sizeof(__u8);
-			}
-		}
-	}
-
-	return 0;
-}
-
-static int check_ioam_header_and_data(int tid, struct ioam6_trace_hdr *ioam6h,
-				      __u32 trace_type, __u16 ioam_ns)
-{
-	__u8 *p;
-
-	if (check_ioam_header(tid, ioam6h, trace_type, ioam_ns))
-		return 1;
-
-	p = ioam6h->data + ioam6h->remlen * 4;
-
-	switch (tid) {
-	case TEST_OUT_BIT0:
-	case TEST_OUT_BIT1:
-	case TEST_OUT_BIT2:
-	case TEST_OUT_BIT3:
-	case TEST_OUT_BIT4:
-	case TEST_OUT_BIT5:
-	case TEST_OUT_BIT6:
-	case TEST_OUT_BIT7:
-	case TEST_OUT_BIT8:
-	case TEST_OUT_BIT9:
-	case TEST_OUT_BIT10:
-	case TEST_OUT_BIT11:
-	case TEST_OUT_BIT22:
-	case TEST_OUT_FULL_SUPP_TRACE:
-		return check_ioam6_data(&p, ioam6h, node1);
-
-	case TEST_IN_BIT0:
-	case TEST_IN_BIT1:
-	case TEST_IN_BIT2:
-	case TEST_IN_BIT3:
-	case TEST_IN_BIT4:
-	case TEST_IN_BIT5:
-	case TEST_IN_BIT6:
-	case TEST_IN_BIT7:
-	case TEST_IN_BIT8:
-	case TEST_IN_BIT9:
-	case TEST_IN_BIT10:
-	case TEST_IN_BIT11:
-	case TEST_IN_BIT22:
-	case TEST_IN_FULL_SUPP_TRACE:
-	{
-		__u32 tmp32 = node2.egr_wide;
-		__u16 tmp16 = node2.egr_id;
-		int res;
-
-		node2.egr_id = 0xffff;
-		node2.egr_wide = 0xffffffff;
-
-		res = check_ioam6_data(&p, ioam6h, node2);
-
-		node2.egr_id = tmp16;
-		node2.egr_wide = tmp32;
-
-		return res;
-	}
-
-	case TEST_FWD_FULL_SUPP_TRACE:
-		if (check_ioam6_data(&p, ioam6h, node3))
-			return 1;
-		if (check_ioam6_data(&p, ioam6h, node2))
-			return 1;
-		return check_ioam6_data(&p, ioam6h, node1);
-
-	default:
-		break;
-	}
-
-	return 1;
-}
-
-static int str2id(const char *tname)
-{
-	if (!strcmp("out_undef_ns", tname))
-		return TEST_OUT_UNDEF_NS;
-	if (!strcmp("out_no_room", tname))
-		return TEST_OUT_NO_ROOM;
-	if (!strcmp("out_bit0", tname))
-		return TEST_OUT_BIT0;
-	if (!strcmp("out_bit1", tname))
-		return TEST_OUT_BIT1;
-	if (!strcmp("out_bit2", tname))
-		return TEST_OUT_BIT2;
-	if (!strcmp("out_bit3", tname))
-		return TEST_OUT_BIT3;
-	if (!strcmp("out_bit4", tname))
-		return TEST_OUT_BIT4;
-	if (!strcmp("out_bit5", tname))
-		return TEST_OUT_BIT5;
-	if (!strcmp("out_bit6", tname))
-		return TEST_OUT_BIT6;
-	if (!strcmp("out_bit7", tname))
-		return TEST_OUT_BIT7;
-	if (!strcmp("out_bit8", tname))
-		return TEST_OUT_BIT8;
-	if (!strcmp("out_bit9", tname))
-		return TEST_OUT_BIT9;
-	if (!strcmp("out_bit10", tname))
-		return TEST_OUT_BIT10;
-	if (!strcmp("out_bit11", tname))
-		return TEST_OUT_BIT11;
-	if (!strcmp("out_bit22", tname))
-		return TEST_OUT_BIT22;
-	if (!strcmp("out_full_supp_trace", tname))
-		return TEST_OUT_FULL_SUPP_TRACE;
-	if (!strcmp("in_undef_ns", tname))
-		return TEST_IN_UNDEF_NS;
-	if (!strcmp("in_no_room", tname))
-		return TEST_IN_NO_ROOM;
-	if (!strcmp("in_oflag", tname))
-		return TEST_IN_OFLAG;
-	if (!strcmp("in_bit0", tname))
-		return TEST_IN_BIT0;
-	if (!strcmp("in_bit1", tname))
-		return TEST_IN_BIT1;
-	if (!strcmp("in_bit2", tname))
-		return TEST_IN_BIT2;
-	if (!strcmp("in_bit3", tname))
-		return TEST_IN_BIT3;
-	if (!strcmp("in_bit4", tname))
-		return TEST_IN_BIT4;
-	if (!strcmp("in_bit5", tname))
-		return TEST_IN_BIT5;
-	if (!strcmp("in_bit6", tname))
-		return TEST_IN_BIT6;
-	if (!strcmp("in_bit7", tname))
-		return TEST_IN_BIT7;
-	if (!strcmp("in_bit8", tname))
-		return TEST_IN_BIT8;
-	if (!strcmp("in_bit9", tname))
-		return TEST_IN_BIT9;
-	if (!strcmp("in_bit10", tname))
-		return TEST_IN_BIT10;
-	if (!strcmp("in_bit11", tname))
-		return TEST_IN_BIT11;
-	if (!strcmp("in_bit22", tname))
-		return TEST_IN_BIT22;
-	if (!strcmp("in_full_supp_trace", tname))
-		return TEST_IN_FULL_SUPP_TRACE;
-	if (!strcmp("fwd_full_supp_trace", tname))
-		return TEST_FWD_FULL_SUPP_TRACE;
-
-	return -1;
-}
-
-static int get_u32(__u32 *val, const char *arg, int base)
-{
-	unsigned long res;
-	char *ptr;
-
-	if (!arg || !*arg)
-		return -1;
-	res = strtoul(arg, &ptr, base);
-
-	if (!ptr || ptr == arg || *ptr)
-		return -1;
-
-	if (res == ULONG_MAX && errno == ERANGE)
-		return -1;
-
-	if (res > 0xFFFFFFFFUL)
-		return -1;
-
-	*val = res;
-	return 0;
-}
-
-static int get_u16(__u16 *val, const char *arg, int base)
-{
-	unsigned long res;
-	char *ptr;
-
-	if (!arg || !*arg)
-		return -1;
-	res = strtoul(arg, &ptr, base);
-
-	if (!ptr || ptr == arg || *ptr)
-		return -1;
-
-	if (res == ULONG_MAX && errno == ERANGE)
-		return -1;
-
-	if (res > 0xFFFFUL)
-		return -1;
-
-	*val = res;
-	return 0;
-}
-
-static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = {
-	[TEST_OUT_UNDEF_NS]		= check_ioam_header,
-	[TEST_OUT_NO_ROOM]		= check_ioam_header,
-	[TEST_OUT_BIT0]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT1]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT2]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT3]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT4]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT5]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT6]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT7]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT8]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT9]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT10]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT11]		= check_ioam_header_and_data,
-	[TEST_OUT_BIT22]		= check_ioam_header_and_data,
-	[TEST_OUT_FULL_SUPP_TRACE]	= check_ioam_header_and_data,
-	[TEST_IN_UNDEF_NS]		= check_ioam_header,
-	[TEST_IN_NO_ROOM]		= check_ioam_header,
-	[TEST_IN_OFLAG]		= check_ioam_header,
-	[TEST_IN_BIT0]			= check_ioam_header_and_data,
-	[TEST_IN_BIT1]			= check_ioam_header_and_data,
-	[TEST_IN_BIT2]			= check_ioam_header_and_data,
-	[TEST_IN_BIT3]			= check_ioam_header_and_data,
-	[TEST_IN_BIT4]			= check_ioam_header_and_data,
-	[TEST_IN_BIT5]			= check_ioam_header_and_data,
-	[TEST_IN_BIT6]			= check_ioam_header_and_data,
-	[TEST_IN_BIT7]			= check_ioam_header_and_data,
-	[TEST_IN_BIT8]			= check_ioam_header_and_data,
-	[TEST_IN_BIT9]			= check_ioam_header_and_data,
-	[TEST_IN_BIT10]		= check_ioam_header_and_data,
-	[TEST_IN_BIT11]		= check_ioam_header_and_data,
-	[TEST_IN_BIT22]		= check_ioam_header_and_data,
-	[TEST_IN_FULL_SUPP_TRACE]	= check_ioam_header_and_data,
-	[TEST_FWD_FULL_SUPP_TRACE]	= check_ioam_header_and_data,
-};
-
-int main(int argc, char **argv)
-{
-	int fd, size, hoplen, tid, ret = 1, on = 1;
-	struct ioam6_hdr *opt;
-	struct cmsghdr *cmsg;
-	struct msghdr msg;
-	struct iovec iov;
-	__u8 buffer[512];
-	__u32 tr_type;
-	__u16 ioam_ns;
-	__u8 *ptr;
-
-	if (argc != 5)
-		goto out;
-
-	tid = str2id(argv[1]);
-	if (tid < 0 || !func[tid])
-		goto out;
-
-	if (get_u32(&tr_type, argv[2], 16) ||
-	    get_u16(&ioam_ns, argv[3], 0))
-		goto out;
-
-	fd = socket(PF_INET6, SOCK_RAW,
-		    !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6);
-	if (fd < 0)
-		goto out;
-
-	setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS,  &on, sizeof(on));
-
-	iov.iov_len = 1;
-	iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer)));
-	if (!iov.iov_base)
-		goto close;
-recv:
-	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;
-
-	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;
-
-		ptr = (__u8 *)CMSG_DATA(cmsg);
-
-		hoplen = (ptr[1] + 1) << 3;
-		ptr += sizeof(struct ipv6_hopopt_hdr);
-
-		while (hoplen > 0) {
-			opt = (struct ioam6_hdr *)ptr;
-
-			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;
-			}
-
-			ptr += 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


From 2d2b5028b4abfb312c3fe964ce724ad8873ac574 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Wed, 2 Oct 2024 18:27:31 +0200
Subject: selftests: net: add new ioam tests

This patch re-adds the (updated) ioam selftests with support for the
tunsrc feature.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20241002162731.19847-3-justin.iurman@uliege.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile       |    2 +
 tools/testing/selftests/net/config         |    1 +
 tools/testing/selftests/net/ioam6.sh       | 1683 ++++++++++++++++++++++++++++
 tools/testing/selftests/net/ioam6_parser.c | 1101 ++++++++++++++++++
 4 files changed, 2787 insertions(+)
 create mode 100755 tools/testing/selftests/net/ioam6.sh
 create mode 100644 tools/testing/selftests/net/ioam6_parser.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ef40d099aa1c..649f1fe0dc46 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -28,6 +28,7 @@ TEST_PROGS += unicast_extensions.sh
 TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS += udpgro_frglist.sh
 TEST_PROGS += veth.sh
+TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
 TEST_PROGS += cmsg_so_mark.sh
@@ -66,6 +67,7 @@ TEST_GEN_FILES += fin_ack_lat
 TEST_GEN_FILES += reuseaddr_ports_exhausted
 TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
 TEST_GEN_FILES += ipsec
+TEST_GEN_FILES += ioam6_parser
 TEST_GEN_FILES += gro
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_poll
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 3f0b02835e78..5b9baf708950 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -95,6 +95,7 @@ CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_ACT_TUNNEL_KEY=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_BAREUDP=m
+CONFIG_IPV6_IOAM6_LWTUNNEL=y
 CONFIG_CRYPTO_SM4_GENERIC=y
 CONFIG_AMT=m
 CONFIG_TUN=y
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
new file mode 100755
index 000000000000..845c26dd01a9
--- /dev/null
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -0,0 +1,1683 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Author: Justin Iurman <justin.iurman@uliege.be>
+#
+# This script evaluates IOAM for IPv6 by checking local IOAM configurations and
+# IOAM data inside packets. There are three categories of tests: LOCAL, OUTPUT,
+# and INPUT. The former (LOCAL) checks all IOAM related configurations locally
+# without sending packets. OUTPUT tests verify the processing of an IOAM
+# encapsulating node, while INPUT tests verify the processing of an IOAM transit
+# node. Both OUTPUT and INPUT tests send packets. Each test is documented inside
+# its own handler.
+#
+# The topology used for OUTPUT and INPUT tests is made of three nodes:
+# - Alpha (the IOAM encapsulating node)
+# - Beta  (the IOAM transit node)
+# - Gamma (the receiver) **
+#
+# An IOAM domain is configured from Alpha to Beta, but not on the reverse path.
+# Alpha adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop.
+#
+# ** Gamma is required because ioam6_parser.c uses a packet socket and we need
+#    to see IOAM data inserted by the very last node (Beta), which would happen
+#    _after_ we get a copy of the packet on Beta. Note that using an
+#    IPv6 raw socket with IPV6_RECVHOPOPTS on Beta would not be enough: we also
+#    need to access the IPv6 header to check some fields (e.g., source and
+#    destination addresses), which is not possible in that case. As a
+#    consequence, we need Gamma as a receiver to run ioam6_parser.c which uses a
+#    packet socket.
+#
+#
+#         +-----------------------+          +-----------------------+
+#         |                       |          |                       |
+#         |      Alpha netns      |          |      Gamma netns      |
+#         |                       |          |                       |
+#         | +-------------------+ |          | +-------------------+ |
+#         | |       veth0       | |          | |       veth0       | |
+#         | | 2001:db8:1::2/64  | |          | | 2001:db8:2::2/64  | |
+#         | +-------------------+ |          | +-------------------+ |
+#         |           .           |          |           .           |
+#         +-----------.-----------+          +-----------.-----------+
+#                     .                                  .
+#                     .                                  .
+#                     .                                  .
+#         +-----------.----------------------------------.-----------+
+#         |           .                                  .           |
+#         | +-------------------+              +-------------------+ |
+#         | |       veth0       |              |       veth1       | |
+#         | | 2001:db8:1::1/64  | ............ | 2001:db8:2::1/64  | |
+#         | +-------------------+              +-------------------+ |
+#         |                                                          |
+#         |                        Beta netns                        |
+#         |                                                          |
+#         +----------------------------------------------------------+
+#
+#
+#
+#         +==========================================================+
+#         |                Alpha - IOAM configuration                |
+#         +=====================+====================================+
+#         | Node ID             | 1                                  |
+#         +---------------------+------------------------------------+
+#         | Node Wide ID        | 11111111                           |
+#         +---------------------+------------------------------------+
+#         | Ingress ID          | 0xffff (default value)             |
+#         +---------------------+------------------------------------+
+#         | Ingress Wide ID     | 0xffffffff (default value)         |
+#         +---------------------+------------------------------------+
+#         | Egress ID           | 101                                |
+#         +---------------------+------------------------------------+
+#         | Egress Wide ID      | 101101                             |
+#         +---------------------+------------------------------------+
+#         | Namespace Data      | 0xdeadbeef                         |
+#         +---------------------+------------------------------------+
+#         | Namespace Wide Data | 0xcafec0caf00dc0de                 |
+#         +---------------------+------------------------------------+
+#         | Schema ID           | 777                                |
+#         +---------------------+------------------------------------+
+#         | Schema Data         | something that will be 4n-aligned  |
+#         +---------------------+------------------------------------+
+#
+#
+#         +==========================================================+
+#         |                 Beta - IOAM configuration                |
+#         +=====================+====================================+
+#         | Node ID             | 2                                  |
+#         +---------------------+------------------------------------+
+#         | Node Wide ID        | 22222222                           |
+#         +---------------------+------------------------------------+
+#         | Ingress ID          | 201                                |
+#         +---------------------+------------------------------------+
+#         | Ingress Wide ID     | 201201                             |
+#         +---------------------+------------------------------------+
+#         | Egress ID           | 202                                |
+#         +---------------------+------------------------------------+
+#         | Egress Wide ID      | 202202                             |
+#         +---------------------+------------------------------------+
+#         | Namespace Data      | 0xffffffff (default value)         |
+#         +---------------------+------------------------------------+
+#         | Namespace Wide Data | 0xffffffffffffffff (default value) |
+#         +---------------------+------------------------------------+
+#         | Schema ID           | 0xffffff (= None)                  |
+#         +---------------------+------------------------------------+
+#         | Schema Data         |                                    |
+#         +---------------------+------------------------------------+
+
+source lib.sh
+
+################################################################################
+#                                                                              #
+# WARNING: Be careful if you modify the block below - it MUST be kept          #
+#          synchronized with configurations inside ioam6_parser.c and always   #
+#          reflect the same.                                                   #
+#                                                                              #
+################################################################################
+
+ALPHA=(
+  1                                    # ID
+  11111111                             # Wide ID
+  0xffff                               # Ingress ID (default value)
+  0xffffffff                           # Ingress Wide ID (default value)
+  101                                  # Egress ID
+  101101                               # Egress Wide ID
+  0xdeadbeef                           # Namespace Data
+  0xcafec0caf00dc0de                   # Namespace Wide Data
+  777                                  # Schema ID
+  "something that will be 4n-aligned"  # Schema Data
+)
+
+BETA=(
+  2                                    # ID
+  22222222                             # Wide ID
+  201                                  # Ingress ID
+  201201                               # Ingress Wide ID
+  202                                  # Egress ID
+  202202                               # Egress Wide ID
+  0xffffffff                           # Namespace Data (empty value)
+  0xffffffffffffffff                   # Namespace Wide Data (empty value)
+  0xffffff                             # Schema ID (empty value)
+  ""                                   # Schema Data (empty value)
+)
+
+TESTS_LOCAL="
+  local_sysctl_ioam_id
+  local_sysctl_ioam_id_wide
+  local_sysctl_ioam_intf_id
+  local_sysctl_ioam_intf_id_wide
+  local_sysctl_ioam_intf_enabled
+  local_ioam_namespace
+  local_ioam_schema
+  local_ioam_schema_namespace
+  local_route_ns
+  local_route_tunsrc
+  local_route_tundst
+  local_route_trace_type
+  local_route_trace_size
+  local_route_trace_type_bits
+  local_route_trace_size_values
+"
+
+TESTS_OUTPUT="
+  output_undef_ns
+  output_no_room
+  output_no_room_oss
+  output_bits
+  output_sizes
+  output_full_supp_trace
+"
+
+TESTS_INPUT="
+  input_undef_ns
+  input_no_room
+  input_no_room_oss
+  input_disabled
+  input_oflag
+  input_bits
+  input_sizes
+  input_full_supp_trace
+"
+
+################################################################################
+#                                                                              #
+#                                   LIBRARY                                    #
+#                                                                              #
+################################################################################
+
+check_kernel_compatibility()
+{
+  setup_ns ioam_tmp_node &>/dev/null
+  local ret=$?
+
+  ip link add name veth0 netns $ioam_tmp_node type veth \
+    peer name veth1 netns $ioam_tmp_node &>/dev/null
+  ret=$((ret + $?))
+
+  ip -netns $ioam_tmp_node link set veth0 up &>/dev/null
+  ret=$((ret + $?))
+
+  ip -netns $ioam_tmp_node link set veth1 up &>/dev/null
+  ret=$((ret + $?))
+
+  if [ $ret != 0 ]
+  then
+    echo "SKIP: Setup failed."
+    cleanup_ns $ioam_tmp_node
+    exit $ksft_skip
+  fi
+
+  ip -netns $ioam_tmp_node route add 2001:db8:2::/64 \
+    encap ioam6 trace prealloc type 0x800000 ns 0 size 4 dev veth0 &>/dev/null
+  ret=$?
+
+  ip -netns $ioam_tmp_node -6 route 2>/dev/null | grep -q "encap ioam6"
+  ret=$((ret + $?))
+
+  if [ $ret != 0 ]
+  then
+    echo "SKIP: Cannot attach an IOAM trace to a route. Was your kernel" \
+         "compiled without CONFIG_IPV6_IOAM6_LWTUNNEL? Are you running an" \
+         "old kernel? Are you using an old version of iproute2?"
+    cleanup_ns $ioam_tmp_node
+    exit $ksft_skip
+  fi
+
+  cleanup_ns $ioam_tmp_node
+
+  lsmod 2>/dev/null | grep -q "ip6_tunnel"
+  ip6tnl_loaded=$?
+
+  if [ $ip6tnl_loaded == 0 ]
+  then
+    encap_tests=0
+  else
+    modprobe ip6_tunnel &>/dev/null
+    lsmod 2>/dev/null | grep -q "ip6_tunnel"
+    encap_tests=$?
+
+    if [ $encap_tests != 0 ]
+    then
+      ip a 2>/dev/null | grep -q "ip6tnl0"
+      encap_tests=$?
+
+      if [ $encap_tests != 0 ]
+      then
+        echo "Note: ip6_tunnel not found neither as a module nor inside the" \
+             "kernel. Any tests that require it will be skipped."
+      fi
+    fi
+  fi
+}
+
+cleanup()
+{
+  cleanup_ns $ioam_node_alpha $ioam_node_beta $ioam_node_gamma
+
+  if [ $ip6tnl_loaded != 0 ]
+  then
+    modprobe -r ip6_tunnel &>/dev/null
+  fi
+}
+
+setup()
+{
+  setup_ns ioam_node_alpha ioam_node_beta ioam_node_gamma &>/dev/null
+
+  ip link add name ioam-veth-alpha netns $ioam_node_alpha type veth \
+    peer name ioam-veth-betaL netns $ioam_node_beta &>/dev/null
+  ip link add name ioam-veth-betaR netns $ioam_node_beta type veth \
+    peer name ioam-veth-gamma netns $ioam_node_gamma &>/dev/null
+
+  ip -netns $ioam_node_alpha link set ioam-veth-alpha name veth0 &>/dev/null
+  ip -netns $ioam_node_beta link set ioam-veth-betaL name veth0 &>/dev/null
+  ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1 &>/dev/null
+  ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0 &>/dev/null
+
+  ip -netns $ioam_node_alpha addr add 2001:db8:1::50/64 dev veth0 &>/dev/null
+  ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null
+  ip -netns $ioam_node_alpha link set veth0 up &>/dev/null
+  ip -netns $ioam_node_alpha link set lo up &>/dev/null
+  ip -netns $ioam_node_alpha route add 2001:db8:2::/64 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  ip -netns $ioam_node_beta addr add 2001:db8:1::1/64 dev veth0 &>/dev/null
+  ip -netns $ioam_node_beta addr add 2001:db8:2::1/64 dev veth1 &>/dev/null
+  ip -netns $ioam_node_beta link set veth0 up &>/dev/null
+  ip -netns $ioam_node_beta link set veth1 up &>/dev/null
+  ip -netns $ioam_node_beta link set lo up &>/dev/null
+
+  ip -netns $ioam_node_gamma addr add 2001:db8:2::2/64 dev veth0 &>/dev/null
+  ip -netns $ioam_node_gamma link set veth0 up &>/dev/null
+  ip -netns $ioam_node_gamma link set lo up &>/dev/null
+  ip -netns $ioam_node_gamma route add 2001:db8:1::/64 \
+    via 2001:db8:2::1 dev veth0 &>/dev/null
+
+  # - Alpha: IOAM config -
+  ip netns exec $ioam_node_alpha \
+    sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]} &>/dev/null
+  ip netns exec $ioam_node_alpha \
+    sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]} &>/dev/null
+  ip netns exec $ioam_node_alpha \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]} &>/dev/null
+  ip netns exec $ioam_node_alpha \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]} &>/dev/null
+  ip -netns $ioam_node_alpha \
+    ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]} &>/dev/null
+  ip -netns $ioam_node_alpha \
+    ioam schema add ${ALPHA[8]} "${ALPHA[9]}" &>/dev/null
+  ip -netns $ioam_node_alpha \
+    ioam namespace set 123 schema ${ALPHA[8]} &>/dev/null
+
+  # - Beta: IOAM config -
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.all.forwarding=1 &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.ioam6_id=${BETA[0]} &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]} &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]} &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]} &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]} &>/dev/null
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]} &>/dev/null
+  ip -netns $ioam_node_beta ioam namespace add 123 &>/dev/null
+
+  sleep 1
+
+  ip netns exec $ioam_node_alpha ping6 -c 5 -W 1 2001:db8:2::2 &>/dev/null
+  if [ $? != 0 ]
+  then
+    echo "SKIP: Setup failed."
+    cleanup
+    exit $ksft_skip
+  fi
+}
+
+log_test_passed()
+{
+  printf " - TEST: %-57s  [ OK ]\n" "$1"
+  npassed=$((npassed+1))
+}
+
+log_test_skipped()
+{
+  printf " - TEST: %-57s  [SKIP]\n" "$1"
+  nskipped=$((nskipped+1))
+}
+
+log_test_failed()
+{
+  printf " - TEST: %-57s  [FAIL]\n" "$1"
+  nfailed=$((nfailed+1))
+}
+
+run_test()
+{
+  local name=$1
+  local desc=$2
+  local ip6_src=$3
+  local trace_type=$4
+  local trace_size=$5
+  local ioam_ns=$6
+  local type=$7
+
+  ip netns exec $ioam_node_gamma \
+    ./ioam6_parser veth0 $name $ip6_src 2001:db8:2::2 \
+                   $trace_type $trace_size $ioam_ns $type &
+  local spid=$!
+  sleep 0.1
+
+  ip netns exec $ioam_node_alpha ping6 -t 64 -c 1 -W 1 2001:db8:2::2 &>/dev/null
+  if [ $? != 0 ]
+  then
+    log_test_failed "${desc}"
+    kill -2 $spid &>/dev/null
+  else
+    wait $spid
+    [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+  fi
+}
+
+run()
+{
+  local test
+
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+  printf "| %-28s LOCAL tests %-29s |"
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+
+  echo
+  echo "Global config"
+  for test in $TESTS_LOCAL
+  do
+    $test
+  done
+
+  echo
+  echo "Inline mode"
+  for test in $TESTS_LOCAL
+  do
+    $test "inline"
+  done
+
+  echo
+  echo "Encap mode"
+  for test in $TESTS_LOCAL
+  do
+    $test "encap"
+  done
+
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+  printf "| %-28s OUTPUT tests %-28s |"
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+
+  # set OUTPUT settings
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0 &>/dev/null
+
+  echo
+  echo "Inline mode"
+  for test in $TESTS_OUTPUT
+  do
+    $test "inline"
+  done
+
+  echo
+  echo "Encap mode"
+  for test in $TESTS_OUTPUT
+  do
+    $test "encap"
+  done
+
+  echo
+  echo "Encap mode (with tunsrc)"
+  for test in $TESTS_OUTPUT
+  do
+    $test "encap" "tunsrc"
+  done
+
+  # clean OUTPUT settings
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 &>/dev/null
+
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+  printf "| %-28s INPUT tests %-29s |"
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+
+  # set INPUT settings
+  ip -netns $ioam_node_alpha ioam namespace del 123 &>/dev/null
+
+  echo
+  echo "Inline mode"
+  for test in $TESTS_INPUT
+  do
+    $test "inline"
+  done
+
+  echo
+  echo "Encap mode"
+  for test in $TESTS_INPUT
+  do
+    $test "encap"
+  done
+
+  # clean INPUT settings
+  ip -netns $ioam_node_alpha \
+    ioam namespace add 123 data ${ALPHA[6]} wide ${ALPHA[7]} &>/dev/null
+  ip -netns $ioam_node_alpha \
+    ioam namespace set 123 schema ${ALPHA[8]} &>/dev/null
+
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+  printf "| %-30s Results %-31s |"
+  echo
+  printf "+"
+  printf "%0.s-" {1..72}
+  printf "+"
+  echo
+
+  echo
+  echo "- Passed:  ${npassed}"
+  echo "- Skipped: ${nskipped}"
+  echo "- Failed:  ${nfailed}"
+  echo
+}
+
+bit2type=(
+  0x800000 0x400000 0x200000 0x100000 0x080000 0x040000 0x020000 0x010000
+  0x008000 0x004000 0x002000 0x001000 0x000800 0x000400 0x000200 0x000100
+  0x000080 0x000040 0x000020 0x000010 0x000008 0x000004 0x000002 0x000001
+)
+bit2size=( 4 4 4 4 4 4 4 4 8 8 8 4 4 4 4 4 4 4 4 4 4 4 4 0 )
+
+
+################################################################################
+#                                                                              #
+#                                 LOCAL tests                                  #
+#                                                                              #
+################################################################################
+
+local_sysctl_ioam_id()
+{
+  ##############################################################################
+  # Make sure the sysctl "net.ipv6.ioam6_id" works as expected.                #
+  ##############################################################################
+  local desc="Sysctl net.ipv6.ioam6_id"
+
+  [ ! -z $1 ] && return
+
+  ip netns exec $ioam_node_alpha \
+    sysctl net.ipv6.ioam6_id 2>/dev/null | grep -wq ${ALPHA[0]}
+
+  [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_sysctl_ioam_id_wide()
+{
+  ##############################################################################
+  # Make sure the sysctl "net.ipv6.ioam6_id_wide" works as expected.           #
+  ##############################################################################
+  local desc="Sysctl net.ipv6.ioam6_id_wide"
+
+  [ ! -z $1 ] && return
+
+  ip netns exec $ioam_node_alpha \
+    sysctl net.ipv6.ioam6_id_wide 2>/dev/null | grep -wq ${ALPHA[1]}
+
+  [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_sysctl_ioam_intf_id()
+{
+  ##############################################################################
+  # Make sure the sysctl "net.ipv6.conf.XX.ioam6_id" works as expected.        #
+  ##############################################################################
+  local desc="Sysctl net.ipv6.conf.XX.ioam6_id"
+
+  [ ! -z $1 ] && return
+
+  ip netns exec $ioam_node_alpha \
+    sysctl net.ipv6.conf.veth0.ioam6_id 2>/dev/null | grep -wq ${ALPHA[4]}
+
+  [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_sysctl_ioam_intf_id_wide()
+{
+  ##############################################################################
+  # Make sure the sysctl "net.ipv6.conf.XX.ioam6_id_wide" works as expected.   #
+  ##############################################################################
+  local desc="Sysctl net.ipv6.conf.XX.ioam6_id_wide"
+
+  [ ! -z $1 ] && return
+
+  ip netns exec $ioam_node_alpha \
+    sysctl net.ipv6.conf.veth0.ioam6_id_wide 2>/dev/null | grep -wq ${ALPHA[5]}
+
+  [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_sysctl_ioam_intf_enabled()
+{
+  ##############################################################################
+  # Make sure the sysctl "net.ipv6.conf.XX.ioam6_enabled" works as expected.   #
+  ##############################################################################
+  local desc="Sysctl net.ipv6.conf.XX.ioam6_enabled"
+
+  [ ! -z $1 ] && return
+
+  ip netns exec $ioam_node_beta \
+    sysctl net.ipv6.conf.veth0.ioam6_enabled 2>/dev/null | grep -wq 1
+
+  [ $? == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_ioam_namespace()
+{
+  ##############################################################################
+  # Make sure the creation of an IOAM Namespace works as expected.             #
+  ##############################################################################
+  local desc="Create an IOAM Namespace"
+
+  [ ! -z $1 ] && return
+
+  ip -netns $ioam_node_alpha \
+    ioam namespace show 2>/dev/null | grep -wq 123
+  local ret=$?
+
+  ip -netns $ioam_node_alpha \
+    ioam namespace show 2>/dev/null | grep -wq ${ALPHA[6]}
+  ret=$((ret + $?))
+
+  ip -netns $ioam_node_alpha \
+    ioam namespace show 2>/dev/null | grep -wq ${ALPHA[7]}
+  ret=$((ret + $?))
+
+  [ $ret == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_ioam_schema()
+{
+  ##############################################################################
+  # Make sure the creation of an IOAM Schema works as expected.                #
+  ##############################################################################
+  local desc="Create an IOAM Schema"
+
+  [ ! -z $1 ] && return
+
+  ip -netns $ioam_node_alpha \
+    ioam schema show 2>/dev/null | grep -wq ${ALPHA[8]}
+  local ret=$?
+
+  local sc_data=$(
+    for i in `seq 0 $((${#ALPHA[9]}-1))`
+    do
+      chr=${ALPHA[9]:i:1}
+      printf "%x " "'${chr}"
+    done
+  )
+
+  ip -netns $ioam_node_alpha \
+    ioam schema show 2>/dev/null | grep -q "$sc_data"
+  ret=$((ret + $?))
+
+  [ $ret == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_ioam_schema_namespace()
+{
+  ##############################################################################
+  # Make sure the binding of a Schema to a Namespace works as expected.        #
+  ##############################################################################
+  local desc="Bind an IOAM Schema to an IOAM Namespace"
+
+  [ ! -z $1 ] && return
+
+  ip -netns $ioam_node_alpha \
+    ioam namespace show 2>/dev/null | grep -wq ${ALPHA[8]}
+  local ret=$?
+
+  ip -netns $ioam_node_alpha \
+    ioam schema show 2>/dev/null | grep -wq 123
+  ret=$((ret + $?))
+
+  [ $ret == 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+}
+
+local_route_ns()
+{
+  ##############################################################################
+  # Make sure the Namespace-ID is always provided, whatever the mode.          #
+  ##############################################################################
+  local desc="Mandatory Namespace-ID"
+  local mode
+
+  [ -z $1 ] && return
+
+  [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret1=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret2=$?
+
+  [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \
+                                 || log_test_passed "${desc}"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+local_route_tunsrc()
+{
+  ##############################################################################
+  # Make sure the Tunnel Source is only (and possibly) used with encap mode.   #
+  ##############################################################################
+  local desc
+  local mode
+  local mode_tunsrc
+
+  [ -z $1 ] && return
+
+  if [ "$1" == "encap" ]
+  then
+    desc="Optional Tunnel Source"
+    mode="$1 tundst 2001:db8:2::2"
+    mode_tunsrc="$1 tunsrc 2001:db8:1::50 tundst 2001:db8:2::2"
+  else
+    desc="Unneeded Tunnel Source"
+    mode="$1"
+    mode_tunsrc="$1 tunsrc 2001:db8:1::50"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret1=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode_tunsrc trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret2=$?
+
+  if [ "$1" == "encap" ]
+  then
+    [[ $ret1 != 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \
+                                   || log_test_passed "${desc}"
+  else
+    [[ $ret1 != 0 || $ret2 == 0 ]] && log_test_failed "${desc}" \
+                                   || log_test_passed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+local_route_tundst()
+{
+  ##############################################################################
+  # Make sure the Tunnel Destination is only (and always) used with encap mode.#
+  ##############################################################################
+  local desc
+
+  [ -z $1 ] && return
+
+  [ "$1" == "encap" ] && desc="Mandatory Tunnel Destination" \
+                     || desc="Unneeded Tunnel Destination"
+
+  local mode="$1"
+  local mode_tundst="$1 tundst 2001:db8:2::2"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret1=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode_tundst trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret2=$?
+
+  if [ "$1" == "encap" ]
+  then
+    [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \
+                                   || log_test_passed "${desc}"
+  else
+    [[ $ret1 != 0 || $ret2 == 0 ]] && log_test_failed "${desc}" \
+                                   || log_test_passed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+local_route_trace_type()
+{
+  ##############################################################################
+  # Make sure the Trace Type is always provided, whatever the mode.            #
+  ##############################################################################
+  local desc="Mandatory Trace Type"
+  local mode
+
+  [ -z $1 ] && return
+
+  [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret1=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret2=$?
+
+  [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \
+                                 || log_test_passed "${desc}"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+local_route_trace_size()
+{
+  ##############################################################################
+  # Make sure the Trace Size is always provided, whatever the mode.            #
+  ##############################################################################
+  local desc="Mandatory Trace Size"
+  local mode
+
+  [ -z $1 ] && return
+
+  [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret1=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size 4 \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  local ret2=$?
+
+  [[ $ret1 == 0 || $ret2 != 0 ]] && log_test_failed "${desc}" \
+                                 || log_test_passed "${desc}"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+local_route_trace_type_bits()
+{
+  ##############################################################################
+  # Make sure only allowed bits (0-11 and 22) are accepted.                    #
+  ##############################################################################
+  local desc="Trace Type bits"
+  local mode
+
+  [ -z $1 ] && return
+
+  [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1"
+
+  local i
+  for i in {0..23}
+  do
+    ip -netns $ioam_node_alpha \
+      route change 2001:db8:2::/64 \
+      encap ioam6 mode $mode trace prealloc type ${bit2type[$i]} ns 0 size 4 \
+      via 2001:db8:1::1 dev veth0 &>/dev/null
+
+    if [[ ($? == 0 && (($i -ge 12 && $i -le 21) || $i == 23)) ||
+          ($? != 0 && (($i -ge 0 && $i -le 11) || $i == 22)) ]]
+    then
+      local err=1
+      break
+    fi
+  done
+
+  [ -z $err ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+local_route_trace_size_values()
+{
+  ##############################################################################
+  # Make sure only allowed sizes (multiples of four in [4,244]) are accepted.  #
+  ##############################################################################
+  local desc="Trace Size values"
+  local mode
+
+  [ -z $1 ] && return
+
+  [ "$1" == "encap" ] && mode="$1 tundst 2001:db8:2::2" || mode="$1"
+
+  # we also try the next multiple of four after the MAX to check it's refused
+  local i
+  for i in {0..248}
+  do
+    ip -netns $ioam_node_alpha \
+      route change 2001:db8:2::/64 \
+      encap ioam6 mode $mode trace prealloc type 0x800000 ns 0 size $i \
+      via 2001:db8:1::1 dev veth0 &>/dev/null
+
+    if [[ ($? == 0 && ($i == 0 || $i == 248 || $(( $i % 4 )) != 0)) ||
+          ($? != 0 && $i != 0 && $i != 248 && $(( $i % 4 )) == 0) ]]
+    then
+      local err=1
+      break
+    fi
+  done
+
+  [ -z $err ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+}
+
+
+################################################################################
+#                                                                              #
+#                                 OUTPUT tests                                 #
+#                                                                              #
+################################################################################
+
+output_undef_ns()
+{
+  ##############################################################################
+  # Make sure an IOAM encapsulating node does NOT fill the trace when the      #
+  # corresponding IOAM Namespace-ID is not configured locally.                 #
+  ##############################################################################
+  local desc="Unknown IOAM Namespace-ID"
+  local ns=0
+  local tr_type=0x800000
+  local tr_size=4
+  local mode="$1"
+  local saddr="2001:db8:1::2"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    if [ "$2" == "tunsrc" ]
+    then
+      saddr="2001:db8:1::50"
+      mode+=" tunsrc 2001:db8:1::50"
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+output_no_room()
+{
+  ##############################################################################
+  # Make sure an IOAM encapsulating node does NOT fill the trace AND sets the  #
+  # Overflow flag when there is not enough room for its data.                  #
+  ##############################################################################
+  local desc="Missing room for data"
+  local ns=123
+  local tr_type=0xc00000
+  local tr_size=4
+  local mode="$1"
+  local saddr="2001:db8:1::2"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    if [ "$2" == "tunsrc" ]
+    then
+      saddr="2001:db8:1::50"
+      mode+=" tunsrc 2001:db8:1::50"
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+output_no_room_oss()
+{
+  ##############################################################################
+  # Make sure an IOAM encapsulating node does NOT fill the trace AND sets the  #
+  # Overflow flag when there is not enough room for the Opaque State Snapshot. #
+  ##############################################################################
+  local desc="Missing room for Opaque State Snapshot"
+  local ns=123
+  local tr_type=0x000002
+  local tr_size=4
+  local mode="$1"
+  local saddr="2001:db8:1::2"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    if [ "$2" == "tunsrc" ]
+    then
+      saddr="2001:db8:1::50"
+      mode+=" tunsrc 2001:db8:1::50"
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+output_bits()
+{
+  ##############################################################################
+  # Make sure an IOAM encapsulating node implements all supported bits by      #
+  # checking it correctly fills the trace with its data.                       #
+  ##############################################################################
+  local desc="Trace Type with supported bit <n> only"
+  local ns=123
+  local mode="$1"
+  local saddr="2001:db8:1::2"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ "$2" == "tunsrc" ]
+    then
+      saddr="2001:db8:1::50"
+      mode+=" tunsrc 2001:db8:1::50"
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  local tmp=${bit2size[22]}
+  bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) ))
+
+  local i
+  for i in {0..11} {22..22}
+  do
+    local descr="${desc/<n>/$i}"
+
+    if [[ "$1" == "encap" && $encap_tests != 0 ]]
+    then
+      log_test_skipped "${descr}"
+      continue
+    fi
+
+    ip -netns $ioam_node_alpha \
+      route change 2001:db8:2::/64 \
+      encap ioam6 mode $mode trace prealloc \
+      type ${bit2type[$i]} ns $ns size ${bit2size[$i]} \
+      via 2001:db8:1::1 dev veth0 &>/dev/null
+
+    if [ $? == 0 ]
+    then
+      run_test "output_bit$i" "${descr}" $saddr \
+        ${bit2type[$i]} ${bit2size[$i]} $ns $1
+    else
+      log_test_failed "${descr}"
+    fi
+  done
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+
+  bit2size[22]=$tmp
+}
+
+output_sizes()
+{
+  ##############################################################################
+  # Make sure an IOAM encapsulating node allocates supported sizes correctly.  #
+  ##############################################################################
+  local desc="Trace Size of <n> bytes"
+  local ns=0
+  local tr_type=0x800000
+  local mode="$1"
+  local saddr="2001:db8:1::2"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ "$2" == "tunsrc" ]
+    then
+      saddr="2001:db8:1::50"
+      mode+=" tunsrc 2001:db8:1::50"
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  local i
+  for i in $(seq 4 4 244)
+  do
+    local descr="${desc/<n>/$i}"
+
+    if [[ "$1" == "encap" && $encap_tests != 0 ]]
+    then
+      log_test_skipped "${descr}"
+      continue
+    fi
+
+    ip -netns $ioam_node_alpha \
+      route change 2001:db8:2::/64 \
+      encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $i \
+      via 2001:db8:1::1 dev veth0 &>/dev/null
+
+    if [ $? == 0 ]
+    then
+      run_test "output_size$i" "${descr}" $saddr $tr_type $i $ns $1
+    else
+      log_test_failed "${descr}"
+    fi
+  done
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+output_full_supp_trace()
+{
+  ##############################################################################
+  # Make sure an IOAM encapsulating node correctly fills a trace when all      #
+  # supported bits are set.                                                    #
+  ##############################################################################
+  local desc="Full supported trace"
+  local ns=123
+  local tr_type=0xfff002
+  local tr_size
+  local mode="$1"
+  local saddr="2001:db8:1::2"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    if [ "$2" == "tunsrc" ]
+    then
+      saddr="2001:db8:1::50"
+      mode+=" tunsrc 2001:db8:1::50"
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  local i
+  tr_size=$(( ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) ))
+  for i in {0..11} {22..22}
+  do
+    tr_size=$((tr_size + bit2size[$i]))
+  done
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" $saddr $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+
+################################################################################
+#                                                                              #
+#                                 INPUT tests                                  #
+#                                                                              #
+################################################################################
+
+input_undef_ns()
+{
+  ##############################################################################
+  # Make sure an IOAM node does NOT fill the trace when the corresponding IOAM #
+  # Namespace-ID is not configured locally.                                    #
+  ##############################################################################
+  local desc="Unknown IOAM Namespace-ID"
+  local ns=0
+  local tr_type=0x800000
+  local tr_size=4
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+input_no_room()
+{
+  ##############################################################################
+  # Make sure an IOAM node does NOT fill the trace AND sets the Overflow flag  #
+  # when there is not enough room for its data.                                #
+  ##############################################################################
+  local desc="Missing room for data"
+  local ns=123
+  local tr_type=0xc00000
+  local tr_size=4
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+input_no_room_oss()
+{
+  ##############################################################################
+  # Make sure an IOAM node does NOT fill the trace AND sets the Overflow flag  #
+  # when there is not enough room for the Opaque State Snapshot.               #
+  ##############################################################################
+  local desc="Missing room for Opaque State Snapshot"
+  local ns=123
+  local tr_type=0x000002
+  local tr_size=4
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+input_disabled()
+{
+  ##############################################################################
+  # Make sure an IOAM node does NOT fill the trace when IOAM is not enabled on #
+  # the corresponding (ingress) interface.                                     #
+  ##############################################################################
+  local desc="IOAM disabled on ingress interface"
+  local ns=123
+  local tr_type=0x800000
+  local tr_size=4
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  # Exception: disable IOAM on ingress interface
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=0 &>/dev/null
+  local ret=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  ret=$((ret + $?))
+
+  if [ $ret == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  # Clean Exception
+  ip netns exec $ioam_node_beta \
+    sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1 &>/dev/null
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+input_oflag()
+{
+  ##############################################################################
+  # Make sure an IOAM node does NOT fill the trace when the Overflow flag is   #
+  # set.                                                                       #
+  ##############################################################################
+  local desc="Overflow flag is set"
+  local ns=123
+  local tr_type=0xc00000
+  local tr_size=4
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  # Exception:
+  #   Here, we need the sender to set the Overflow flag. For that, we will add
+  #   back the IOAM namespace that was previously configured on the sender.
+  ip -netns $ioam_node_alpha ioam namespace add 123 &>/dev/null
+  local ret=$?
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+  ret=$((ret + $?))
+
+  if [ $ret == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  # Clean Exception
+  ip -netns $ioam_node_alpha ioam namespace del 123 &>/dev/null
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+input_bits()
+{
+  ##############################################################################
+  # Make sure an IOAM node implements all supported bits by checking it        #
+  # correctly fills the trace with its data.                                   #
+  ##############################################################################
+  local desc="Trace Type with supported bit <n> only"
+  local ns=123
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  local tmp=${bit2size[22]}
+  bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) ))
+
+  local i
+  for i in {0..11} {22..22}
+  do
+    local descr="${desc/<n>/$i}"
+
+    if [[ "$1" == "encap" && $encap_tests != 0 ]]
+    then
+      log_test_skipped "${descr}"
+      continue
+    fi
+
+    ip -netns $ioam_node_alpha \
+      route change 2001:db8:2::/64 \
+      encap ioam6 mode $mode trace prealloc \
+      type ${bit2type[$i]} ns $ns size ${bit2size[$i]} \
+      via 2001:db8:1::1 dev veth0 &>/dev/null
+
+    if [ $? == 0 ]
+    then
+      run_test "input_bit$i" "${descr}" 2001:db8:1::2 \
+        ${bit2type[$i]} ${bit2size[$i]} $ns $1
+    else
+      log_test_failed "${descr}"
+    fi
+  done
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+
+  bit2size[22]=$tmp
+}
+
+input_sizes()
+{
+  ##############################################################################
+  # Make sure an IOAM node handles all supported sizes correctly.              #
+  ##############################################################################
+  local desc="Trace Size of <n> bytes"
+  local ns=123
+  local tr_type=0x800000
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  local i
+  for i in $(seq 4 4 244)
+  do
+    local descr="${desc/<n>/$i}"
+
+    if [[ "$1" == "encap" && $encap_tests != 0 ]]
+    then
+      log_test_skipped "${descr}"
+      continue
+    fi
+
+    ip -netns $ioam_node_alpha \
+      route change 2001:db8:2::/64 \
+      encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $i \
+      via 2001:db8:1::1 dev veth0 &>/dev/null
+
+    if [ $? == 0 ]
+    then
+      run_test "input_size$i" "${descr}" 2001:db8:1::2 $tr_type $i $ns $1
+    else
+      log_test_failed "${descr}"
+    fi
+  done
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+input_full_supp_trace()
+{
+  ##############################################################################
+  # Make sure an IOAM node correctly fills a trace when all supported bits are #
+  # set.                                                                       #
+  ##############################################################################
+  local desc="Full supported trace"
+  local ns=123
+  local tr_type=0xfff002
+  local tr_size
+  local mode="$1"
+
+  if [ "$1" == "encap" ]
+  then
+    if [ $encap_tests != 0 ]
+    then
+      log_test_skipped "${desc}"
+      return
+    fi
+
+    mode+=" tundst 2001:db8:2::2"
+    ip -netns $ioam_node_gamma link set ip6tnl0 up &>/dev/null
+  fi
+
+  local i
+  tr_size=$(( ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) ))
+  for i in {0..11} {22..22}
+  do
+    tr_size=$((tr_size + bit2size[$i]))
+  done
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 \
+    encap ioam6 mode $mode trace prealloc type $tr_type ns $ns size $tr_size \
+    via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  if [ $? == 0 ]
+  then
+    run_test ${FUNCNAME[0]} "${desc}" 2001:db8:1::2 $tr_type $tr_size $ns $1
+  else
+    log_test_failed "${desc}"
+  fi
+
+  ip -netns $ioam_node_alpha \
+    route change 2001:db8:2::/64 via 2001:db8:1::1 dev veth0 &>/dev/null
+
+  [ "$1" == "encap" ] && ip -netns $ioam_node_gamma \
+    link set ip6tnl0 down &>/dev/null
+}
+
+
+################################################################################
+#                                                                              #
+#                                     MAIN                                     #
+#                                                                              #
+################################################################################
+
+npassed=0
+nskipped=0
+nfailed=0
+
+if [ "$(id -u)" -ne 0 ]
+then
+  echo "SKIP: Need root privileges."
+  exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v ip)" ]
+then
+  echo "SKIP: Could not run test without ip tool."
+  exit $ksft_skip
+fi
+
+check_kernel_compatibility
+setup
+run
+cleanup
+
+if [ $nfailed != 0 ]
+then
+  exit $ksft_fail
+fi
+
+exit $ksft_pass
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
new file mode 100644
index 000000000000..de4b5c9e8a74
--- /dev/null
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -0,0 +1,1101 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Author: Justin Iurman (justin.iurman@uliege.be)
+ *
+ * IOAM tester for IPv6, see ioam6.sh for details on each test case.
+ */
+#include <arpa/inet.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/const.h>
+#include <linux/if_ether.h>
+#include <linux/ioam6.h>
+#include <linux/ipv6.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+struct ioam_config {
+	__u32 id;
+	__u64 wide;
+	__u16 ingr_id;
+	__u16 egr_id;
+	__u32 ingr_wide;
+	__u32 egr_wide;
+	__u32 ns_data;
+	__u64 ns_wide;
+	__u32 sc_id;
+	__u8 hlim;
+	char *sc_data;
+};
+
+/*
+ * Be careful if you modify structs below - everything MUST be kept synchronized
+ * with configurations inside ioam6.sh and always reflect the same.
+ */
+
+static struct ioam_config node1 = {
+	.id = 1,
+	.wide = 11111111,
+	.ingr_id = 0xffff, /* default value */
+	.egr_id = 101,
+	.ingr_wide = 0xffffffff, /* default value */
+	.egr_wide = 101101,
+	.ns_data = 0xdeadbeef,
+	.ns_wide = 0xcafec0caf00dc0de,
+	.sc_id = 777,
+	.sc_data = "something that will be 4n-aligned",
+	.hlim = 64,
+};
+
+static struct ioam_config node2 = {
+	.id = 2,
+	.wide = 22222222,
+	.ingr_id = 201,
+	.egr_id = 202,
+	.ingr_wide = 201201,
+	.egr_wide = 202202,
+	.ns_data = 0xffffffff, /* default value */
+	.ns_wide = 0xffffffffffffffff, /* default value */
+	.sc_id = 0xffffff, /* default value */
+	.sc_data = NULL,
+	.hlim = 63,
+};
+
+enum {
+	/**********
+	 * OUTPUT *
+	 **********/
+	__TEST_OUT_MIN,
+
+	TEST_OUT_UNDEF_NS,
+	TEST_OUT_NO_ROOM,
+	TEST_OUT_NO_ROOM_OSS,
+	TEST_OUT_BIT0,
+	TEST_OUT_BIT1,
+	TEST_OUT_BIT2,
+	TEST_OUT_BIT3,
+	TEST_OUT_BIT4,
+	TEST_OUT_BIT5,
+	TEST_OUT_BIT6,
+	TEST_OUT_BIT7,
+	TEST_OUT_BIT8,
+	TEST_OUT_BIT9,
+	TEST_OUT_BIT10,
+	TEST_OUT_BIT11,
+	TEST_OUT_BIT22,
+	TEST_OUT_SIZE4,
+	TEST_OUT_SIZE8,
+	TEST_OUT_SIZE12,
+	TEST_OUT_SIZE16,
+	TEST_OUT_SIZE20,
+	TEST_OUT_SIZE24,
+	TEST_OUT_SIZE28,
+	TEST_OUT_SIZE32,
+	TEST_OUT_SIZE36,
+	TEST_OUT_SIZE40,
+	TEST_OUT_SIZE44,
+	TEST_OUT_SIZE48,
+	TEST_OUT_SIZE52,
+	TEST_OUT_SIZE56,
+	TEST_OUT_SIZE60,
+	TEST_OUT_SIZE64,
+	TEST_OUT_SIZE68,
+	TEST_OUT_SIZE72,
+	TEST_OUT_SIZE76,
+	TEST_OUT_SIZE80,
+	TEST_OUT_SIZE84,
+	TEST_OUT_SIZE88,
+	TEST_OUT_SIZE92,
+	TEST_OUT_SIZE96,
+	TEST_OUT_SIZE100,
+	TEST_OUT_SIZE104,
+	TEST_OUT_SIZE108,
+	TEST_OUT_SIZE112,
+	TEST_OUT_SIZE116,
+	TEST_OUT_SIZE120,
+	TEST_OUT_SIZE124,
+	TEST_OUT_SIZE128,
+	TEST_OUT_SIZE132,
+	TEST_OUT_SIZE136,
+	TEST_OUT_SIZE140,
+	TEST_OUT_SIZE144,
+	TEST_OUT_SIZE148,
+	TEST_OUT_SIZE152,
+	TEST_OUT_SIZE156,
+	TEST_OUT_SIZE160,
+	TEST_OUT_SIZE164,
+	TEST_OUT_SIZE168,
+	TEST_OUT_SIZE172,
+	TEST_OUT_SIZE176,
+	TEST_OUT_SIZE180,
+	TEST_OUT_SIZE184,
+	TEST_OUT_SIZE188,
+	TEST_OUT_SIZE192,
+	TEST_OUT_SIZE196,
+	TEST_OUT_SIZE200,
+	TEST_OUT_SIZE204,
+	TEST_OUT_SIZE208,
+	TEST_OUT_SIZE212,
+	TEST_OUT_SIZE216,
+	TEST_OUT_SIZE220,
+	TEST_OUT_SIZE224,
+	TEST_OUT_SIZE228,
+	TEST_OUT_SIZE232,
+	TEST_OUT_SIZE236,
+	TEST_OUT_SIZE240,
+	TEST_OUT_SIZE244,
+	TEST_OUT_FULL_SUPP_TRACE,
+
+	__TEST_OUT_MAX,
+
+	/*********
+	 * INPUT *
+	 *********/
+	__TEST_IN_MIN,
+
+	TEST_IN_UNDEF_NS,
+	TEST_IN_NO_ROOM,
+	TEST_IN_NO_ROOM_OSS,
+	TEST_IN_DISABLED,
+	TEST_IN_OFLAG,
+	TEST_IN_BIT0,
+	TEST_IN_BIT1,
+	TEST_IN_BIT2,
+	TEST_IN_BIT3,
+	TEST_IN_BIT4,
+	TEST_IN_BIT5,
+	TEST_IN_BIT6,
+	TEST_IN_BIT7,
+	TEST_IN_BIT8,
+	TEST_IN_BIT9,
+	TEST_IN_BIT10,
+	TEST_IN_BIT11,
+	TEST_IN_BIT22,
+	TEST_IN_SIZE4,
+	TEST_IN_SIZE8,
+	TEST_IN_SIZE12,
+	TEST_IN_SIZE16,
+	TEST_IN_SIZE20,
+	TEST_IN_SIZE24,
+	TEST_IN_SIZE28,
+	TEST_IN_SIZE32,
+	TEST_IN_SIZE36,
+	TEST_IN_SIZE40,
+	TEST_IN_SIZE44,
+	TEST_IN_SIZE48,
+	TEST_IN_SIZE52,
+	TEST_IN_SIZE56,
+	TEST_IN_SIZE60,
+	TEST_IN_SIZE64,
+	TEST_IN_SIZE68,
+	TEST_IN_SIZE72,
+	TEST_IN_SIZE76,
+	TEST_IN_SIZE80,
+	TEST_IN_SIZE84,
+	TEST_IN_SIZE88,
+	TEST_IN_SIZE92,
+	TEST_IN_SIZE96,
+	TEST_IN_SIZE100,
+	TEST_IN_SIZE104,
+	TEST_IN_SIZE108,
+	TEST_IN_SIZE112,
+	TEST_IN_SIZE116,
+	TEST_IN_SIZE120,
+	TEST_IN_SIZE124,
+	TEST_IN_SIZE128,
+	TEST_IN_SIZE132,
+	TEST_IN_SIZE136,
+	TEST_IN_SIZE140,
+	TEST_IN_SIZE144,
+	TEST_IN_SIZE148,
+	TEST_IN_SIZE152,
+	TEST_IN_SIZE156,
+	TEST_IN_SIZE160,
+	TEST_IN_SIZE164,
+	TEST_IN_SIZE168,
+	TEST_IN_SIZE172,
+	TEST_IN_SIZE176,
+	TEST_IN_SIZE180,
+	TEST_IN_SIZE184,
+	TEST_IN_SIZE188,
+	TEST_IN_SIZE192,
+	TEST_IN_SIZE196,
+	TEST_IN_SIZE200,
+	TEST_IN_SIZE204,
+	TEST_IN_SIZE208,
+	TEST_IN_SIZE212,
+	TEST_IN_SIZE216,
+	TEST_IN_SIZE220,
+	TEST_IN_SIZE224,
+	TEST_IN_SIZE228,
+	TEST_IN_SIZE232,
+	TEST_IN_SIZE236,
+	TEST_IN_SIZE240,
+	TEST_IN_SIZE244,
+	TEST_IN_FULL_SUPP_TRACE,
+
+	__TEST_IN_MAX,
+
+	__TEST_MAX,
+};
+
+static int check_header(int tid, struct ioam6_trace_hdr *trace,
+			__u32 trace_type, __u8 trace_size, __u16 ioam_ns)
+{
+	if (__be16_to_cpu(trace->namespace_id) != ioam_ns ||
+	    __be32_to_cpu(trace->type_be32) != (trace_type << 8))
+		return 1;
+
+	switch (tid) {
+	case TEST_OUT_UNDEF_NS:
+	case TEST_IN_UNDEF_NS:
+	case TEST_IN_DISABLED:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 1 ||
+		       trace->remlen != 1;
+
+	case TEST_OUT_NO_ROOM:
+	case TEST_IN_NO_ROOM:
+	case TEST_IN_OFLAG:
+		return trace->overflow == 0 ||
+		       trace->nodelen != 2 ||
+		       trace->remlen != 1;
+
+	case TEST_OUT_NO_ROOM_OSS:
+		return trace->overflow == 0 ||
+		       trace->nodelen != 0 ||
+		       trace->remlen != 1;
+
+	case TEST_IN_NO_ROOM_OSS:
+	case TEST_OUT_BIT22:
+	case TEST_IN_BIT22:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 0 ||
+		       trace->remlen != 0;
+
+	case TEST_OUT_BIT0:
+	case TEST_IN_BIT0:
+	case TEST_OUT_BIT1:
+	case TEST_IN_BIT1:
+	case TEST_OUT_BIT2:
+	case TEST_IN_BIT2:
+	case TEST_OUT_BIT3:
+	case TEST_IN_BIT3:
+	case TEST_OUT_BIT4:
+	case TEST_IN_BIT4:
+	case TEST_OUT_BIT5:
+	case TEST_IN_BIT5:
+	case TEST_OUT_BIT6:
+	case TEST_IN_BIT6:
+	case TEST_OUT_BIT7:
+	case TEST_IN_BIT7:
+	case TEST_OUT_BIT11:
+	case TEST_IN_BIT11:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 1 ||
+		       trace->remlen != 0;
+
+	case TEST_OUT_BIT8:
+	case TEST_IN_BIT8:
+	case TEST_OUT_BIT9:
+	case TEST_IN_BIT9:
+	case TEST_OUT_BIT10:
+	case TEST_IN_BIT10:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 2 ||
+		       trace->remlen != 0;
+
+	case TEST_OUT_SIZE4:
+	case TEST_OUT_SIZE8:
+	case TEST_OUT_SIZE12:
+	case TEST_OUT_SIZE16:
+	case TEST_OUT_SIZE20:
+	case TEST_OUT_SIZE24:
+	case TEST_OUT_SIZE28:
+	case TEST_OUT_SIZE32:
+	case TEST_OUT_SIZE36:
+	case TEST_OUT_SIZE40:
+	case TEST_OUT_SIZE44:
+	case TEST_OUT_SIZE48:
+	case TEST_OUT_SIZE52:
+	case TEST_OUT_SIZE56:
+	case TEST_OUT_SIZE60:
+	case TEST_OUT_SIZE64:
+	case TEST_OUT_SIZE68:
+	case TEST_OUT_SIZE72:
+	case TEST_OUT_SIZE76:
+	case TEST_OUT_SIZE80:
+	case TEST_OUT_SIZE84:
+	case TEST_OUT_SIZE88:
+	case TEST_OUT_SIZE92:
+	case TEST_OUT_SIZE96:
+	case TEST_OUT_SIZE100:
+	case TEST_OUT_SIZE104:
+	case TEST_OUT_SIZE108:
+	case TEST_OUT_SIZE112:
+	case TEST_OUT_SIZE116:
+	case TEST_OUT_SIZE120:
+	case TEST_OUT_SIZE124:
+	case TEST_OUT_SIZE128:
+	case TEST_OUT_SIZE132:
+	case TEST_OUT_SIZE136:
+	case TEST_OUT_SIZE140:
+	case TEST_OUT_SIZE144:
+	case TEST_OUT_SIZE148:
+	case TEST_OUT_SIZE152:
+	case TEST_OUT_SIZE156:
+	case TEST_OUT_SIZE160:
+	case TEST_OUT_SIZE164:
+	case TEST_OUT_SIZE168:
+	case TEST_OUT_SIZE172:
+	case TEST_OUT_SIZE176:
+	case TEST_OUT_SIZE180:
+	case TEST_OUT_SIZE184:
+	case TEST_OUT_SIZE188:
+	case TEST_OUT_SIZE192:
+	case TEST_OUT_SIZE196:
+	case TEST_OUT_SIZE200:
+	case TEST_OUT_SIZE204:
+	case TEST_OUT_SIZE208:
+	case TEST_OUT_SIZE212:
+	case TEST_OUT_SIZE216:
+	case TEST_OUT_SIZE220:
+	case TEST_OUT_SIZE224:
+	case TEST_OUT_SIZE228:
+	case TEST_OUT_SIZE232:
+	case TEST_OUT_SIZE236:
+	case TEST_OUT_SIZE240:
+	case TEST_OUT_SIZE244:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 1 ||
+		       trace->remlen != trace_size / 4;
+
+	case TEST_IN_SIZE4:
+	case TEST_IN_SIZE8:
+	case TEST_IN_SIZE12:
+	case TEST_IN_SIZE16:
+	case TEST_IN_SIZE20:
+	case TEST_IN_SIZE24:
+	case TEST_IN_SIZE28:
+	case TEST_IN_SIZE32:
+	case TEST_IN_SIZE36:
+	case TEST_IN_SIZE40:
+	case TEST_IN_SIZE44:
+	case TEST_IN_SIZE48:
+	case TEST_IN_SIZE52:
+	case TEST_IN_SIZE56:
+	case TEST_IN_SIZE60:
+	case TEST_IN_SIZE64:
+	case TEST_IN_SIZE68:
+	case TEST_IN_SIZE72:
+	case TEST_IN_SIZE76:
+	case TEST_IN_SIZE80:
+	case TEST_IN_SIZE84:
+	case TEST_IN_SIZE88:
+	case TEST_IN_SIZE92:
+	case TEST_IN_SIZE96:
+	case TEST_IN_SIZE100:
+	case TEST_IN_SIZE104:
+	case TEST_IN_SIZE108:
+	case TEST_IN_SIZE112:
+	case TEST_IN_SIZE116:
+	case TEST_IN_SIZE120:
+	case TEST_IN_SIZE124:
+	case TEST_IN_SIZE128:
+	case TEST_IN_SIZE132:
+	case TEST_IN_SIZE136:
+	case TEST_IN_SIZE140:
+	case TEST_IN_SIZE144:
+	case TEST_IN_SIZE148:
+	case TEST_IN_SIZE152:
+	case TEST_IN_SIZE156:
+	case TEST_IN_SIZE160:
+	case TEST_IN_SIZE164:
+	case TEST_IN_SIZE168:
+	case TEST_IN_SIZE172:
+	case TEST_IN_SIZE176:
+	case TEST_IN_SIZE180:
+	case TEST_IN_SIZE184:
+	case TEST_IN_SIZE188:
+	case TEST_IN_SIZE192:
+	case TEST_IN_SIZE196:
+	case TEST_IN_SIZE200:
+	case TEST_IN_SIZE204:
+	case TEST_IN_SIZE208:
+	case TEST_IN_SIZE212:
+	case TEST_IN_SIZE216:
+	case TEST_IN_SIZE220:
+	case TEST_IN_SIZE224:
+	case TEST_IN_SIZE228:
+	case TEST_IN_SIZE232:
+	case TEST_IN_SIZE236:
+	case TEST_IN_SIZE240:
+	case TEST_IN_SIZE244:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 1 ||
+		       trace->remlen != (trace_size / 4) - trace->nodelen;
+
+	case TEST_OUT_FULL_SUPP_TRACE:
+	case TEST_IN_FULL_SUPP_TRACE:
+		return trace->overflow == 1 ||
+		       trace->nodelen != 15 ||
+		       trace->remlen != 0;
+
+	default:
+		break;
+	}
+
+	return 1;
+}
+
+static int check_data(struct ioam6_trace_hdr *trace, __u8 trace_size,
+		      const struct ioam_config cnf, bool is_output)
+{
+	unsigned int len, i;
+	__u8 aligned;
+	__u64 raw64;
+	__u32 raw32;
+	__u8 *p;
+
+	if (trace->type.bit12 | trace->type.bit13 | trace->type.bit14 |
+	    trace->type.bit15 | trace->type.bit16 | trace->type.bit17 |
+	    trace->type.bit18 | trace->type.bit19 | trace->type.bit20 |
+	    trace->type.bit21 | trace->type.bit23)
+		return 1;
+
+	for (i = 0; i < trace->remlen * 4; i++) {
+		if (trace->data[i] != 0)
+			return 1;
+	}
+
+	if (trace->remlen * 4 == trace_size)
+		return 0;
+
+	p = trace->data + trace->remlen * 4;
+
+	if (trace->type.bit0) {
+		raw32 = __be32_to_cpu(*((__u32 *)p));
+		if (cnf.hlim != (raw32 >> 24) || cnf.id != (raw32 & 0xffffff))
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit1) {
+		raw32 = __be32_to_cpu(*((__u32 *)p));
+		if (cnf.ingr_id != (raw32 >> 16) ||
+		    cnf.egr_id != (raw32 & 0xffff))
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit2) {
+		raw32 = __be32_to_cpu(*((__u32 *)p));
+		if ((is_output && raw32 != 0xffffffff) ||
+		    (!is_output && (raw32 == 0 || raw32 == 0xffffffff)))
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit3) {
+		raw32 = __be32_to_cpu(*((__u32 *)p));
+		if ((is_output && raw32 != 0xffffffff) ||
+		    (!is_output && (raw32 == 0 || raw32 == 0xffffffff)))
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit4) {
+		if (__be32_to_cpu(*((__u32 *)p)) != 0xffffffff)
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit5) {
+		if (__be32_to_cpu(*((__u32 *)p)) != cnf.ns_data)
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit6) {
+		if (__be32_to_cpu(*((__u32 *)p)) == 0xffffffff)
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit7) {
+		if (__be32_to_cpu(*((__u32 *)p)) != 0xffffffff)
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit8) {
+		raw64 = __be64_to_cpu(*((__u64 *)p));
+		if (cnf.hlim != (raw64 >> 56) ||
+		    cnf.wide != (raw64 & 0xffffffffffffff))
+			return 1;
+		p += sizeof(__u64);
+	}
+
+	if (trace->type.bit9) {
+		if (__be32_to_cpu(*((__u32 *)p)) != cnf.ingr_wide)
+			return 1;
+		p += sizeof(__u32);
+
+		if (__be32_to_cpu(*((__u32 *)p)) != cnf.egr_wide)
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit10) {
+		if (__be64_to_cpu(*((__u64 *)p)) != cnf.ns_wide)
+			return 1;
+		p += sizeof(__u64);
+	}
+
+	if (trace->type.bit11) {
+		if (__be32_to_cpu(*((__u32 *)p)) != 0xffffffff)
+			return 1;
+		p += sizeof(__u32);
+	}
+
+	if (trace->type.bit22) {
+		len = cnf.sc_data ? strlen(cnf.sc_data) : 0;
+		aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0;
+
+		raw32 = __be32_to_cpu(*((__u32 *)p));
+		if (aligned != (raw32 >> 24) * 4 ||
+		    cnf.sc_id != (raw32 & 0xffffff))
+			return 1;
+		p += sizeof(__u32);
+
+		if (cnf.sc_data) {
+			if (strncmp((char *)p, cnf.sc_data, len))
+				return 1;
+
+			p += len;
+			aligned -= len;
+
+			while (aligned--) {
+				if (*p != '\0')
+					return 1;
+				p += sizeof(__u8);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int check_ioam_trace(int tid, struct ioam6_trace_hdr *trace,
+			    __u32 trace_type, __u8 trace_size, __u16 ioam_ns)
+{
+	if (check_header(tid, trace, trace_type, trace_size, ioam_ns))
+		return 1;
+
+	if (tid > __TEST_OUT_MIN && tid < __TEST_OUT_MAX)
+		return check_data(trace, trace_size, node1, true);
+
+	if (tid > __TEST_IN_MIN && tid < __TEST_IN_MAX)
+		return check_data(trace, trace_size, node2, false);
+
+	return 1;
+}
+
+static int str2id(const char *tname)
+{
+	if (!strcmp("output_undef_ns", tname))
+		return TEST_OUT_UNDEF_NS;
+	if (!strcmp("output_no_room", tname))
+		return TEST_OUT_NO_ROOM;
+	if (!strcmp("output_no_room_oss", tname))
+		return TEST_OUT_NO_ROOM_OSS;
+	if (!strcmp("output_bit0", tname))
+		return TEST_OUT_BIT0;
+	if (!strcmp("output_bit1", tname))
+		return TEST_OUT_BIT1;
+	if (!strcmp("output_bit2", tname))
+		return TEST_OUT_BIT2;
+	if (!strcmp("output_bit3", tname))
+		return TEST_OUT_BIT3;
+	if (!strcmp("output_bit4", tname))
+		return TEST_OUT_BIT4;
+	if (!strcmp("output_bit5", tname))
+		return TEST_OUT_BIT5;
+	if (!strcmp("output_bit6", tname))
+		return TEST_OUT_BIT6;
+	if (!strcmp("output_bit7", tname))
+		return TEST_OUT_BIT7;
+	if (!strcmp("output_bit8", tname))
+		return TEST_OUT_BIT8;
+	if (!strcmp("output_bit9", tname))
+		return TEST_OUT_BIT9;
+	if (!strcmp("output_bit10", tname))
+		return TEST_OUT_BIT10;
+	if (!strcmp("output_bit11", tname))
+		return TEST_OUT_BIT11;
+	if (!strcmp("output_bit22", tname))
+		return TEST_OUT_BIT22;
+	if (!strcmp("output_size4", tname))
+		return TEST_OUT_SIZE4;
+	if (!strcmp("output_size8", tname))
+		return TEST_OUT_SIZE8;
+	if (!strcmp("output_size12", tname))
+		return TEST_OUT_SIZE12;
+	if (!strcmp("output_size16", tname))
+		return TEST_OUT_SIZE16;
+	if (!strcmp("output_size20", tname))
+		return TEST_OUT_SIZE20;
+	if (!strcmp("output_size24", tname))
+		return TEST_OUT_SIZE24;
+	if (!strcmp("output_size28", tname))
+		return TEST_OUT_SIZE28;
+	if (!strcmp("output_size32", tname))
+		return TEST_OUT_SIZE32;
+	if (!strcmp("output_size36", tname))
+		return TEST_OUT_SIZE36;
+	if (!strcmp("output_size40", tname))
+		return TEST_OUT_SIZE40;
+	if (!strcmp("output_size44", tname))
+		return TEST_OUT_SIZE44;
+	if (!strcmp("output_size48", tname))
+		return TEST_OUT_SIZE48;
+	if (!strcmp("output_size52", tname))
+		return TEST_OUT_SIZE52;
+	if (!strcmp("output_size56", tname))
+		return TEST_OUT_SIZE56;
+	if (!strcmp("output_size60", tname))
+		return TEST_OUT_SIZE60;
+	if (!strcmp("output_size64", tname))
+		return TEST_OUT_SIZE64;
+	if (!strcmp("output_size68", tname))
+		return TEST_OUT_SIZE68;
+	if (!strcmp("output_size72", tname))
+		return TEST_OUT_SIZE72;
+	if (!strcmp("output_size76", tname))
+		return TEST_OUT_SIZE76;
+	if (!strcmp("output_size80", tname))
+		return TEST_OUT_SIZE80;
+	if (!strcmp("output_size84", tname))
+		return TEST_OUT_SIZE84;
+	if (!strcmp("output_size88", tname))
+		return TEST_OUT_SIZE88;
+	if (!strcmp("output_size92", tname))
+		return TEST_OUT_SIZE92;
+	if (!strcmp("output_size96", tname))
+		return TEST_OUT_SIZE96;
+	if (!strcmp("output_size100", tname))
+		return TEST_OUT_SIZE100;
+	if (!strcmp("output_size104", tname))
+		return TEST_OUT_SIZE104;
+	if (!strcmp("output_size108", tname))
+		return TEST_OUT_SIZE108;
+	if (!strcmp("output_size112", tname))
+		return TEST_OUT_SIZE112;
+	if (!strcmp("output_size116", tname))
+		return TEST_OUT_SIZE116;
+	if (!strcmp("output_size120", tname))
+		return TEST_OUT_SIZE120;
+	if (!strcmp("output_size124", tname))
+		return TEST_OUT_SIZE124;
+	if (!strcmp("output_size128", tname))
+		return TEST_OUT_SIZE128;
+	if (!strcmp("output_size132", tname))
+		return TEST_OUT_SIZE132;
+	if (!strcmp("output_size136", tname))
+		return TEST_OUT_SIZE136;
+	if (!strcmp("output_size140", tname))
+		return TEST_OUT_SIZE140;
+	if (!strcmp("output_size144", tname))
+		return TEST_OUT_SIZE144;
+	if (!strcmp("output_size148", tname))
+		return TEST_OUT_SIZE148;
+	if (!strcmp("output_size152", tname))
+		return TEST_OUT_SIZE152;
+	if (!strcmp("output_size156", tname))
+		return TEST_OUT_SIZE156;
+	if (!strcmp("output_size160", tname))
+		return TEST_OUT_SIZE160;
+	if (!strcmp("output_size164", tname))
+		return TEST_OUT_SIZE164;
+	if (!strcmp("output_size168", tname))
+		return TEST_OUT_SIZE168;
+	if (!strcmp("output_size172", tname))
+		return TEST_OUT_SIZE172;
+	if (!strcmp("output_size176", tname))
+		return TEST_OUT_SIZE176;
+	if (!strcmp("output_size180", tname))
+		return TEST_OUT_SIZE180;
+	if (!strcmp("output_size184", tname))
+		return TEST_OUT_SIZE184;
+	if (!strcmp("output_size188", tname))
+		return TEST_OUT_SIZE188;
+	if (!strcmp("output_size192", tname))
+		return TEST_OUT_SIZE192;
+	if (!strcmp("output_size196", tname))
+		return TEST_OUT_SIZE196;
+	if (!strcmp("output_size200", tname))
+		return TEST_OUT_SIZE200;
+	if (!strcmp("output_size204", tname))
+		return TEST_OUT_SIZE204;
+	if (!strcmp("output_size208", tname))
+		return TEST_OUT_SIZE208;
+	if (!strcmp("output_size212", tname))
+		return TEST_OUT_SIZE212;
+	if (!strcmp("output_size216", tname))
+		return TEST_OUT_SIZE216;
+	if (!strcmp("output_size220", tname))
+		return TEST_OUT_SIZE220;
+	if (!strcmp("output_size224", tname))
+		return TEST_OUT_SIZE224;
+	if (!strcmp("output_size228", tname))
+		return TEST_OUT_SIZE228;
+	if (!strcmp("output_size232", tname))
+		return TEST_OUT_SIZE232;
+	if (!strcmp("output_size236", tname))
+		return TEST_OUT_SIZE236;
+	if (!strcmp("output_size240", tname))
+		return TEST_OUT_SIZE240;
+	if (!strcmp("output_size244", tname))
+		return TEST_OUT_SIZE244;
+	if (!strcmp("output_full_supp_trace", tname))
+		return TEST_OUT_FULL_SUPP_TRACE;
+	if (!strcmp("input_undef_ns", tname))
+		return TEST_IN_UNDEF_NS;
+	if (!strcmp("input_no_room", tname))
+		return TEST_IN_NO_ROOM;
+	if (!strcmp("input_no_room_oss", tname))
+		return TEST_IN_NO_ROOM_OSS;
+	if (!strcmp("input_disabled", tname))
+		return TEST_IN_DISABLED;
+	if (!strcmp("input_oflag", tname))
+		return TEST_IN_OFLAG;
+	if (!strcmp("input_bit0", tname))
+		return TEST_IN_BIT0;
+	if (!strcmp("input_bit1", tname))
+		return TEST_IN_BIT1;
+	if (!strcmp("input_bit2", tname))
+		return TEST_IN_BIT2;
+	if (!strcmp("input_bit3", tname))
+		return TEST_IN_BIT3;
+	if (!strcmp("input_bit4", tname))
+		return TEST_IN_BIT4;
+	if (!strcmp("input_bit5", tname))
+		return TEST_IN_BIT5;
+	if (!strcmp("input_bit6", tname))
+		return TEST_IN_BIT6;
+	if (!strcmp("input_bit7", tname))
+		return TEST_IN_BIT7;
+	if (!strcmp("input_bit8", tname))
+		return TEST_IN_BIT8;
+	if (!strcmp("input_bit9", tname))
+		return TEST_IN_BIT9;
+	if (!strcmp("input_bit10", tname))
+		return TEST_IN_BIT10;
+	if (!strcmp("input_bit11", tname))
+		return TEST_IN_BIT11;
+	if (!strcmp("input_bit22", tname))
+		return TEST_IN_BIT22;
+	if (!strcmp("input_size4", tname))
+		return TEST_IN_SIZE4;
+	if (!strcmp("input_size8", tname))
+		return TEST_IN_SIZE8;
+	if (!strcmp("input_size12", tname))
+		return TEST_IN_SIZE12;
+	if (!strcmp("input_size16", tname))
+		return TEST_IN_SIZE16;
+	if (!strcmp("input_size20", tname))
+		return TEST_IN_SIZE20;
+	if (!strcmp("input_size24", tname))
+		return TEST_IN_SIZE24;
+	if (!strcmp("input_size28", tname))
+		return TEST_IN_SIZE28;
+	if (!strcmp("input_size32", tname))
+		return TEST_IN_SIZE32;
+	if (!strcmp("input_size36", tname))
+		return TEST_IN_SIZE36;
+	if (!strcmp("input_size40", tname))
+		return TEST_IN_SIZE40;
+	if (!strcmp("input_size44", tname))
+		return TEST_IN_SIZE44;
+	if (!strcmp("input_size48", tname))
+		return TEST_IN_SIZE48;
+	if (!strcmp("input_size52", tname))
+		return TEST_IN_SIZE52;
+	if (!strcmp("input_size56", tname))
+		return TEST_IN_SIZE56;
+	if (!strcmp("input_size60", tname))
+		return TEST_IN_SIZE60;
+	if (!strcmp("input_size64", tname))
+		return TEST_IN_SIZE64;
+	if (!strcmp("input_size68", tname))
+		return TEST_IN_SIZE68;
+	if (!strcmp("input_size72", tname))
+		return TEST_IN_SIZE72;
+	if (!strcmp("input_size76", tname))
+		return TEST_IN_SIZE76;
+	if (!strcmp("input_size80", tname))
+		return TEST_IN_SIZE80;
+	if (!strcmp("input_size84", tname))
+		return TEST_IN_SIZE84;
+	if (!strcmp("input_size88", tname))
+		return TEST_IN_SIZE88;
+	if (!strcmp("input_size92", tname))
+		return TEST_IN_SIZE92;
+	if (!strcmp("input_size96", tname))
+		return TEST_IN_SIZE96;
+	if (!strcmp("input_size100", tname))
+		return TEST_IN_SIZE100;
+	if (!strcmp("input_size104", tname))
+		return TEST_IN_SIZE104;
+	if (!strcmp("input_size108", tname))
+		return TEST_IN_SIZE108;
+	if (!strcmp("input_size112", tname))
+		return TEST_IN_SIZE112;
+	if (!strcmp("input_size116", tname))
+		return TEST_IN_SIZE116;
+	if (!strcmp("input_size120", tname))
+		return TEST_IN_SIZE120;
+	if (!strcmp("input_size124", tname))
+		return TEST_IN_SIZE124;
+	if (!strcmp("input_size128", tname))
+		return TEST_IN_SIZE128;
+	if (!strcmp("input_size132", tname))
+		return TEST_IN_SIZE132;
+	if (!strcmp("input_size136", tname))
+		return TEST_IN_SIZE136;
+	if (!strcmp("input_size140", tname))
+		return TEST_IN_SIZE140;
+	if (!strcmp("input_size144", tname))
+		return TEST_IN_SIZE144;
+	if (!strcmp("input_size148", tname))
+		return TEST_IN_SIZE148;
+	if (!strcmp("input_size152", tname))
+		return TEST_IN_SIZE152;
+	if (!strcmp("input_size156", tname))
+		return TEST_IN_SIZE156;
+	if (!strcmp("input_size160", tname))
+		return TEST_IN_SIZE160;
+	if (!strcmp("input_size164", tname))
+		return TEST_IN_SIZE164;
+	if (!strcmp("input_size168", tname))
+		return TEST_IN_SIZE168;
+	if (!strcmp("input_size172", tname))
+		return TEST_IN_SIZE172;
+	if (!strcmp("input_size176", tname))
+		return TEST_IN_SIZE176;
+	if (!strcmp("input_size180", tname))
+		return TEST_IN_SIZE180;
+	if (!strcmp("input_size184", tname))
+		return TEST_IN_SIZE184;
+	if (!strcmp("input_size188", tname))
+		return TEST_IN_SIZE188;
+	if (!strcmp("input_size192", tname))
+		return TEST_IN_SIZE192;
+	if (!strcmp("input_size196", tname))
+		return TEST_IN_SIZE196;
+	if (!strcmp("input_size200", tname))
+		return TEST_IN_SIZE200;
+	if (!strcmp("input_size204", tname))
+		return TEST_IN_SIZE204;
+	if (!strcmp("input_size208", tname))
+		return TEST_IN_SIZE208;
+	if (!strcmp("input_size212", tname))
+		return TEST_IN_SIZE212;
+	if (!strcmp("input_size216", tname))
+		return TEST_IN_SIZE216;
+	if (!strcmp("input_size220", tname))
+		return TEST_IN_SIZE220;
+	if (!strcmp("input_size224", tname))
+		return TEST_IN_SIZE224;
+	if (!strcmp("input_size228", tname))
+		return TEST_IN_SIZE228;
+	if (!strcmp("input_size232", tname))
+		return TEST_IN_SIZE232;
+	if (!strcmp("input_size236", tname))
+		return TEST_IN_SIZE236;
+	if (!strcmp("input_size240", tname))
+		return TEST_IN_SIZE240;
+	if (!strcmp("input_size244", tname))
+		return TEST_IN_SIZE244;
+	if (!strcmp("input_full_supp_trace", tname))
+		return TEST_IN_FULL_SUPP_TRACE;
+
+	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;
+	char *ptr;
+
+	if (!arg || !*arg)
+		return -1;
+	res = strtoul(arg, &ptr, base);
+
+	if (!ptr || ptr == arg || *ptr)
+		return -1;
+
+	if (res == ULONG_MAX && errno == ERANGE)
+		return -1;
+
+	if (res > 0xFFFFFFFFUL)
+		return -1;
+
+	*val = res;
+	return 0;
+}
+
+static int get_u16(__u16 *val, const char *arg, int base)
+{
+	unsigned long res;
+	char *ptr;
+
+	if (!arg || !*arg)
+		return -1;
+	res = strtoul(arg, &ptr, base);
+
+	if (!ptr || ptr == arg || *ptr)
+		return -1;
+
+	if (res == ULONG_MAX && errno == ERANGE)
+		return -1;
+
+	if (res > 0xFFFFUL)
+		return -1;
+
+	*val = res;
+	return 0;
+}
+
+static int get_u8(__u8 *val, const char *arg, int base)
+{
+	unsigned long res;
+	char *ptr;
+
+	if (!arg || !*arg)
+		return -1;
+	res = strtoul(arg, &ptr, base);
+
+	if (!ptr || ptr == arg || *ptr)
+		return -1;
+
+	if (res == ULONG_MAX && errno == ERANGE)
+		return -1;
+
+	if (res > 0xFFUL)
+		return -1;
+
+	*val = res;
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	__u8 buffer[512], *ptr, nexthdr, tr_size;
+	struct ioam6_trace_hdr *trace;
+	unsigned int hoplen, ret = 1;
+	struct ipv6_hopopt_hdr *hbh;
+	int fd, size, testname_id;
+	struct in6_addr src, dst;
+	struct ioam6_hdr *ioam6;
+	struct timeval timeout;
+	struct ipv6hdr *ipv6;
+	__u32 tr_type;
+	__u16 ioam_ns;
+
+	if (argc != 9)
+		goto out;
+
+	testname_id = str2id(argv[2]);
+
+	if (testname_id < 0 ||
+	    inet_pton(AF_INET6, argv[3], &src) != 1 ||
+	    inet_pton(AF_INET6, argv[4], &dst) != 1 ||
+	    get_u32(&tr_type, argv[5], 16) ||
+	    get_u8(&tr_size, argv[6], 0) ||
+	    get_u16(&ioam_ns, argv[7], 0))
+		goto out;
+
+	nexthdr = (!strcmp(argv[8], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6);
+
+	hoplen = sizeof(*hbh);
+	hoplen += 2; // 2-byte padding for alignment
+	hoplen += sizeof(*ioam6); // IOAM option header
+	hoplen += sizeof(*trace); // IOAM trace header
+	hoplen += tr_size; // IOAM trace size
+	hoplen += (tr_size % 8); // optional padding
+
+	fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6));
+	if (fd < 0)
+		goto out;
+
+	if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
+		       argv[1], strlen(argv[1])))
+		goto close;
+
+	timeout.tv_sec = 1;
+	timeout.tv_usec = 0;
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO,
+		       (const char *)&timeout, sizeof(timeout)))
+		goto close;
+recv:
+	size = recv(fd, buffer, sizeof(buffer), 0);
+	if (size <= 0)
+		goto close;
+
+	ipv6 = (struct ipv6hdr *)buffer;
+
+	/* Skip packets that do not have the expected src/dst address or that
+	 * do not have a Hop-by-hop.
+	 */
+	if (!ipv6_addr_equal(&ipv6->saddr, &src) ||
+	    !ipv6_addr_equal(&ipv6->daddr, &dst) ||
+	    ipv6->nexthdr != IPPROTO_HOPOPTS)
+		goto recv;
+
+	/* Check Hbh's Next Header and Size. */
+	hbh = (struct ipv6_hopopt_hdr *)(buffer + sizeof(*ipv6));
+	if (hbh->nexthdr != nexthdr || hbh->hdrlen != (hoplen >> 3) - 1)
+		goto close;
+
+	/* Check we have a 2-byte padding for alignment. */
+	ptr = (__u8 *)hbh + sizeof(*hbh);
+	if (ptr[0] != IPV6_TLV_PADN && ptr[1] != 0)
+		goto close;
+
+	/* Check we now have the IOAM option. */
+	ptr += 2;
+	if (ptr[0] != IPV6_TLV_IOAM)
+		goto close;
+
+	/* Check its size and the IOAM option type. */
+	ioam6 = (struct ioam6_hdr *)ptr;
+	if (ioam6->opt_len != sizeof(*ioam6) - 2 + sizeof(*trace) + tr_size ||
+	    ioam6->type != IOAM6_TYPE_PREALLOC)
+		goto close;
+
+	trace = (struct ioam6_trace_hdr *)(ptr + sizeof(*ioam6));
+
+	/* Check the trailing 4-byte padding (potentially). */
+	ptr = (__u8 *)trace + sizeof(*trace) + tr_size;
+	if (tr_size % 8 && ptr[0] != IPV6_TLV_PADN && ptr[1] != 2 &&
+	    ptr[2] != 0 && ptr[3] != 0)
+		goto close;
+
+	/* Check the IOAM header and data. */
+	ret = check_ioam_trace(testname_id, trace, tr_type, tr_size, ioam_ns);
+close:
+	close(fd);
+out:
+	return ret;
+}
-- 
cgit v1.2.3


From 3d07b691ee707c00afaf365440975e81bb96cd9b Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Thu, 3 Oct 2024 03:15:06 -0700
Subject: selftest/ptp: update ptp selftest to exercise the gettimex options

With the inclusion of commit c259acab839e ("ptp/ioctl: support
MONOTONIC{,_RAW} timestamps for PTP_SYS_OFFSET_EXTENDED") clock_gettime()
now allows retrieval of pre/post timestamps for CLOCK_MONOTONIC and
CLOCK_MONOTONIC_RAW timebases along with the previously supported
CLOCK_REALTIME.

This patch adds a command line option 'y' to the testptp program to
choose one of the allowed timebases [realtime aka system, monotonic,
and monotonic-raw).

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://patch.msgid.link/20241003101506.769418-1-maheshb@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/ptp/testptp.c | 62 ++++++++++++++++++++++++++++++++---
 1 file changed, 57 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index 011252fe238c..58064151f2c8 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -146,6 +146,7 @@ static void usage(char *progname)
 		" -T val     set the ptp clock time to 'val' seconds\n"
 		" -x val     get an extended ptp clock time with the desired number of samples (up to %d)\n"
 		" -X         get a ptp clock cross timestamp\n"
+		" -y val     pre/post tstamp timebase to use {realtime|monotonic|monotonic-raw}\n"
 		" -z         test combinations of rising/falling external time stamp flags\n",
 		progname, PTP_MAX_SAMPLES);
 }
@@ -189,6 +190,7 @@ int main(int argc, char *argv[])
 	int seconds = 0;
 	int settime = 0;
 	int channel = -1;
+	clockid_t ext_clockid = CLOCK_REALTIME;
 
 	int64_t t1, t2, tp;
 	int64_t interval, offset;
@@ -198,7 +200,7 @@ int main(int argc, char *argv[])
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xz"))) {
+	while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xy:z"))) {
 		switch (c) {
 		case 'c':
 			capabilities = 1;
@@ -278,6 +280,21 @@ int main(int argc, char *argv[])
 		case 'X':
 			getcross = 1;
 			break;
+		case 'y':
+			if (!strcasecmp(optarg, "realtime"))
+				ext_clockid = CLOCK_REALTIME;
+			else if (!strcasecmp(optarg, "monotonic"))
+				ext_clockid = CLOCK_MONOTONIC;
+			else if (!strcasecmp(optarg, "monotonic-raw"))
+				ext_clockid = CLOCK_MONOTONIC_RAW;
+			else {
+				fprintf(stderr,
+					"type needs to be realtime, monotonic or monotonic-raw; was given %s\n",
+					optarg);
+				return -1;
+			}
+			break;
+
 		case 'z':
 			flagtest = 1;
 			break;
@@ -566,6 +583,7 @@ int main(int argc, char *argv[])
 		}
 
 		soe->n_samples = getextended;
+		soe->clockid = ext_clockid;
 
 		if (ioctl(fd, PTP_SYS_OFFSET_EXTENDED, soe)) {
 			perror("PTP_SYS_OFFSET_EXTENDED");
@@ -574,12 +592,46 @@ int main(int argc, char *argv[])
 			       getextended);
 
 			for (i = 0; i < getextended; i++) {
-				printf("sample #%2d: system time before: %lld.%09u\n",
-				       i, soe->ts[i][0].sec, soe->ts[i][0].nsec);
+				switch (ext_clockid) {
+				case CLOCK_REALTIME:
+					printf("sample #%2d: real time before: %lld.%09u\n",
+					       i, soe->ts[i][0].sec,
+					       soe->ts[i][0].nsec);
+					break;
+				case CLOCK_MONOTONIC:
+					printf("sample #%2d: monotonic time before: %lld.%09u\n",
+					       i, soe->ts[i][0].sec,
+					       soe->ts[i][0].nsec);
+					break;
+				case CLOCK_MONOTONIC_RAW:
+					printf("sample #%2d: monotonic-raw time before: %lld.%09u\n",
+					       i, soe->ts[i][0].sec,
+					       soe->ts[i][0].nsec);
+					break;
+				default:
+					break;
+				}
 				printf("            phc time: %lld.%09u\n",
 				       soe->ts[i][1].sec, soe->ts[i][1].nsec);
-				printf("            system time after: %lld.%09u\n",
-				       soe->ts[i][2].sec, soe->ts[i][2].nsec);
+				switch (ext_clockid) {
+				case CLOCK_REALTIME:
+					printf("            real time after: %lld.%09u\n",
+					       soe->ts[i][2].sec,
+					       soe->ts[i][2].nsec);
+					break;
+				case CLOCK_MONOTONIC:
+					printf("            monotonic time after: %lld.%09u\n",
+					       soe->ts[i][2].sec,
+					       soe->ts[i][2].nsec);
+					break;
+				case CLOCK_MONOTONIC_RAW:
+					printf("            monotonic-raw time after: %lld.%09u\n",
+					       soe->ts[i][2].sec,
+					       soe->ts[i][2].nsec);
+					break;
+				default:
+					break;
+				}
 			}
 		}
 
-- 
cgit v1.2.3


From 716fa7dadf116ec4a27f56558b2a5bdd7e8decab Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:35 +0200
Subject: selftests/bpf: Extend netkit tests to validate skb meta data

Add a small netkit test to validate skb mark and priority under the
default scrubbing as well as with mark and priority scrubbing off.

  # ./vmtest.sh -- ./test_progs -t netkit
  [...]
  ./test_progs -t netkit
  [    1.419662] tsc: Refined TSC clocksource calibration: 3407.993 MHz
  [    1.420151] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fcd52370, max_idle_ns: 440795242006 ns
  [    1.420897] clocksource: Switched to clocksource tsc
  [    1.447996] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.448447] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  #357     tc_netkit_basic:OK
  #358     tc_netkit_device:OK
  #359     tc_netkit_multi_links:OK
  #360     tc_netkit_multi_opts:OK
  #361     tc_netkit_neigh_links:OK
  #362     tc_netkit_pkt_type:OK
  #363     tc_netkit_scrub:OK
  Summary: 7/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-5-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/tc_netkit.c | 94 +++++++++++++++++++---
 tools/testing/selftests/bpf/progs/test_tc_link.c   | 12 +++
 2 files changed, 97 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
index b9135720024c..151a4210028f 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -14,7 +14,9 @@
 #include "netlink_helpers.h"
 #include "tc_helpers.h"
 
-#define ICMP_ECHO 8
+#define MARK		42
+#define PRIO		0xeb9f
+#define ICMP_ECHO	8
 
 struct icmphdr {
 	__u8		type;
@@ -33,7 +35,7 @@ struct iplink_req {
 };
 
 static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
-			 bool same_netns)
+			 bool same_netns, int scrub, int peer_scrub)
 {
 	struct rtnl_handle rth = { .fd = -1 };
 	struct iplink_req req = {};
@@ -58,6 +60,8 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
 	addattr_nest_end(&req.n, data);
 	addattr_nest_end(&req.n, linkinfo);
@@ -118,9 +122,9 @@ static void destroy_netkit(void)
 
 static int __send_icmp(__u32 dest)
 {
+	int sock, ret, mark = MARK, prio = PRIO;
 	struct sockaddr_in addr;
 	struct icmphdr icmp;
-	int sock, ret;
 
 	ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0");
 	if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)"))
@@ -135,6 +139,15 @@ static int __send_icmp(__u32 dest)
 	if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)"))
 		goto out;
 
+	ret = setsockopt(sock, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (!ASSERT_OK(ret, "setsockopt(SO_MARK)"))
+		goto out;
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
+			 &prio, sizeof(prio));
+	if (!ASSERT_OK(ret, "setsockopt(SO_PRIORITY)"))
+		goto out;
+
 	memset(&addr, 0, sizeof(addr));
 	addr.sin_family = AF_INET;
 	addr.sin_addr.s_addr = htonl(dest);
@@ -171,7 +184,8 @@ void serial_test_tc_netkit_basic(void)
 	int err, ifindex;
 
 	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -285,7 +299,8 @@ static void serial_test_tc_netkit_multi_links_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -413,7 +428,8 @@ static void serial_test_tc_netkit_multi_opts_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -527,7 +543,8 @@ void serial_test_tc_netkit_device(void)
 	int err, ifindex, ifindex2;
 
 	err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, true);
+			    &ifindex, true, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -638,7 +655,8 @@ static void serial_test_tc_netkit_neigh_links_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false);
+			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -715,7 +733,8 @@ static void serial_test_tc_netkit_pkt_type_mode(int mode)
 	struct bpf_link *link;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, true);
+			    &ifindex, true, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT);
 	if (err)
 		return;
 
@@ -779,3 +798,60 @@ void serial_test_tc_netkit_pkt_type(void)
 	serial_test_tc_netkit_pkt_type_mode(NETKIT_L2);
 	serial_test_tc_netkit_pkt_type_mode(NETKIT_L3);
 }
+
+static void serial_test_tc_netkit_scrub_type(int scrub)
+{
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, false, scrub, scrub);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc8,
+		  BPF_NETKIT_PRIMARY), 0, "tc8_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc8, false, "seen_tc8");
+
+	link = bpf_program__attach_netkit(skel->progs.tc8, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc8 = link;
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8");
+	ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark");
+	ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_scrub(void)
+{
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT);
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
index ab3eae3d6af8..10d825928499 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_link.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -18,6 +18,7 @@ bool seen_tc4;
 bool seen_tc5;
 bool seen_tc6;
 bool seen_tc7;
+bool seen_tc8;
 
 bool set_type;
 
@@ -25,6 +26,8 @@ bool seen_eth;
 bool seen_host;
 bool seen_mcast;
 
+int mark, prio;
+
 SEC("tc/ingress")
 int tc1(struct __sk_buff *skb)
 {
@@ -100,3 +103,12 @@ out:
 	seen_tc7 = true;
 	return TCX_PASS;
 }
+
+SEC("tc/egress")
+int tc8(struct __sk_buff *skb)
+{
+	seen_tc8 = true;
+	mark = skb->mark;
+	prio = skb->priority;
+	return TCX_PASS;
+}
-- 
cgit v1.2.3


From bc9b3fb827fceec4e05564d6e668280f4470ab5b Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Tue, 8 Oct 2024 16:50:57 +0200
Subject: selftests/bpf: add missing header include for htons
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Including the network_helpers.h header in tests can lead to the following
build error:

./network_helpers.h: In function ‘csum_tcpudp_magic’:
./network_helpers.h:116:14: error: implicit declaration of function \
  ‘htons’ [-Werror=implicit-function-declaration]
  116 |         s += htons(proto + len);

The error is avoided in many cases thanks to some other headers included
earlier and bringing in arpa/inet.h (ie: test_progs.h).

Make sure that test_progs build success does not depend on header ordering
by adding the missing header include in network_helpers.h

Fixes: f6642de0c3e9 ("selftests/bpf: Add csum helpers")
Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241008-network_helpers_fix-v1-1-2c2ae03df7ef@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index c72c16e1aff8..5764155b6d25 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NETWORK_HELPERS_H
 #define __NETWORK_HELPERS_H
+#include <arpa/inet.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <linux/types.h>
-- 
cgit v1.2.3


From 693fe954d61d4696aa06f631fd0bce0b3b3e8027 Mon Sep 17 00:00:00 2001
From: Mahe Tardy <mahe.tardy@gmail.com>
Date: Mon, 7 Oct 2024 09:59:58 +0000
Subject: selftests/bpf: add tcx netns cookie tests

Add netns cookie test that verifies the helper is now supported and work
in the context of tc programs.

Signed-off-by: Mahe Tardy <mahe.tardy@gmail.com>
Link: https://lore.kernel.org/r/20241007095958.97442-2-mahe.tardy@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/netns_cookie.c        | 29 ++++++++++++++++------
 .../selftests/bpf/progs/netns_cookie_prog.c        | 10 ++++++++
 2 files changed, 32 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
index 71d8f3ba7d6b..ac3c3c097c0e 100644
--- a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
@@ -8,12 +8,16 @@
 #define SO_NETNS_COOKIE 71
 #endif
 
+#define loopback 1
+
 static int duration;
 
 void test_netns_cookie(void)
 {
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
 	int server_fd = -1, client_fd = -1, cgroup_fd = -1;
-	int err, val, ret, map, verdict;
+	int err, val, ret, map, verdict, tc_fd;
 	struct netns_cookie_prog *skel;
 	uint64_t cookie_expected_value;
 	socklen_t vallen = sizeof(cookie_expected_value);
@@ -38,36 +42,47 @@ void test_netns_cookie(void)
 	if (!ASSERT_OK(err, "prog_attach"))
 		goto done;
 
+	tc_fd = bpf_program__fd(skel->progs.get_netns_cookie_tcx);
+	err = bpf_prog_attach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &opta);
+	if (!ASSERT_OK(err, "prog_attach"))
+		goto done;
+
 	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
 	if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno))
-		goto done;
+		goto cleanup_tc;
 
 	client_fd = connect_to_fd(server_fd, 0);
 	if (CHECK(client_fd < 0, "connect_to_fd", "errno %d\n", errno))
-		goto done;
+		goto cleanup_tc;
 
 	ret = send(client_fd, send_msg, sizeof(send_msg), 0);
 	if (CHECK(ret != sizeof(send_msg), "send(msg)", "ret:%d\n", ret))
-		goto done;
+		goto cleanup_tc;
 
 	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sockops_netns_cookies),
 				  &client_fd, &val);
 	if (!ASSERT_OK(err, "map_lookup(sockops_netns_cookies)"))
-		goto done;
+		goto cleanup_tc;
 
 	err = getsockopt(client_fd, SOL_SOCKET, SO_NETNS_COOKIE,
 			 &cookie_expected_value, &vallen);
 	if (!ASSERT_OK(err, "getsockopt"))
-		goto done;
+		goto cleanup_tc;
 
 	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
 
 	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies),
 				  &client_fd, &val);
 	if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)"))
-		goto done;
+		goto cleanup_tc;
 
 	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+	ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value");
+	ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value");
+
+cleanup_tc:
+	err = bpf_prog_detach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &optd);
+	ASSERT_OK(err, "prog_detach");
 
 done:
 	if (server_fd != -1)
diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
index aeff3a4f9287..c6edf8dbefeb 100644
--- a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
@@ -27,6 +27,8 @@ struct {
 	__type(value, __u64);
 } sock_map SEC(".maps");
 
+int tcx_init_netns_cookie, tcx_netns_cookie;
+
 SEC("sockops")
 int get_netns_cookie_sockops(struct bpf_sock_ops *ctx)
 {
@@ -81,4 +83,12 @@ int get_netns_cookie_sk_msg(struct sk_msg_md *msg)
 	return 1;
 }
 
+SEC("tcx/ingress")
+int get_netns_cookie_tcx(struct __sk_buff *skb)
+{
+	tcx_init_netns_cookie = bpf_get_netns_cookie(NULL);
+	tcx_netns_cookie = bpf_get_netns_cookie(skb);
+	return TCX_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 870dd51117cb901f560ea5a85b9876956e6f35b8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 7 Oct 2024 18:26:05 +0200
Subject: selftests: mlxsw: sch_red_ets: Increase required backlog

Backlog fluctuates on Spectrum-4 much more than on <4. Increasing the
desired backlog seems to help, as the constant fluctuations do not overlap
into the territory where packets are marked.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Link: https://patch.msgid.link/0821fb3aa8bb6a6c0d3000baab04995517c9a0cc.1728316370.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index 8ecddafa79b3..576067b207a8 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -20,8 +20,8 @@ source sch_red_core.sh
 # $BACKLOG2 are far enough not to overlap, so that we can assume that if we do
 # see (do not see) marking, it is actually due to the configuration of that one
 # TC, and not due to configuration of the other TC leaking over.
-BACKLOG1=200000
-BACKLOG2=500000
+BACKLOG1=400000
+BACKLOG2=1000000
 
 install_root_qdisc()
 {
@@ -35,7 +35,7 @@ install_qdisc_tc0()
 
 	tc qdisc add dev $swp3 parent 10:8 handle 108: red \
 	   limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \
-	   probability 1.0 avpkt 8000 burst 38 "${args[@]}"
+	   probability 1.0 avpkt 8000 burst 51 "${args[@]}"
 }
 
 install_qdisc_tc1()
@@ -44,7 +44,7 @@ install_qdisc_tc1()
 
 	tc qdisc add dev $swp3 parent 10:7 handle 107: red \
 	   limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \
-	   probability 1.0 avpkt 8000 burst 63 "${args[@]}"
+	   probability 1.0 avpkt 8000 burst 126 "${args[@]}"
 }
 
 install_qdisc()
-- 
cgit v1.2.3


From 8fb5b60734564473c72ca85d617cd685738948f0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 7 Oct 2024 18:26:06 +0200
Subject: selftests: mlxsw: sch_red_core: Increase backlog size tolerance

Backlog fluctuates on Spectrum-4 much more than on <4. In practice we can
sample queue depth values going from about -12% to about +7% of the
configured RED limit. The test which checks the queue size has a limit of
+-10%, and as a result often fails. We attempted to fix the issue by
busywaiting for several seconds hoping to get within the bounds, but that
still proved to be too noisy (or the wait time would be impractically
long). Unfortunately we have to bump the value tolerance from 10% to 15%,
which in this patch do.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Link: https://patch.msgid.link/f54950df2a8fcba46c3ddc1053376352fa2e592b.1728316370.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 299e06a5808c..a25a15eb6d31 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -532,10 +532,11 @@ do_red_test()
 	check_fail $? "Traffic went into backlog instead of being early-dropped"
 	pct=$(check_marking get_nmarked $vlan "== 0")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+	backlog=$(get_qdisc_backlog $vlan)
 	local diff=$((limit - backlog))
 	pct=$((100 * diff / limit))
-	((-10 <= pct && pct <= 10))
-	check_err $? "backlog $backlog / $limit expected <= 10% distance"
+	((-15 <= pct && pct <= 15))
+	check_err $? "backlog $backlog / $limit expected <= 15% distance"
 	log_test "TC $((vlan - 10)): RED backlog > limit"
 
 	stop_traffic
-- 
cgit v1.2.3


From 787f148cec340114dc22c49d8b045ff3ff0adad6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 7 Oct 2024 18:26:07 +0200
Subject: selftests: mlxsw: sch_red_core: Sleep before querying queue depth

The qdisc stats are taken from the port's periodic HW stats, which are
updated once a second. We try to accommodate the latency by using busywait
in build_backlog().

The issue in that seems to be that when do_mark_test() builds the backlog,
it makes the decision whether to send more packets based on the first
instance of the queue depth stat exceeding the current value, when in fact
more traffic is on the way and the queue depth would increase further. This
leads to failures in TC 1 of mark-mirror test, where we see the following
failure:

TEST: TC 0: marked packets mirror'd                                 [ OK ]
TEST: TC 1: marked packets mirror'd                                 [FAIL]
        Spurious packets (1680 -> 2290) observed without buffer pressure

Fix by waiting for the full second before reading the queue depth for the
first time, to make sure it reflects all in-flight traffic.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Link: https://patch.msgid.link/321dcf8b3e9a1f0766429c8cf3e3f1746f1bc375.1728316370.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index a25a15eb6d31..b1ff395b3880 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -372,6 +372,7 @@ build_backlog()
 	local i=0
 
 	while :; do
+		sleep 1
 		local cur=$(busywait 1100 until_counter_is "> $cur" \
 					    get_qdisc_backlog $vlan)
 		local diff=$((size - cur))
-- 
cgit v1.2.3


From 7049166e51bc2b854935eda72f7fb8c3f4492f6f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 7 Oct 2024 18:26:08 +0200
Subject: selftests: mlxsw: sch_red_core: Send more packets for drop tests

This test works by injecting into a port with a maxed-out queue a couple
packets and checks if a corresponding number of packets were dropped. This
has worked well on Spectrum<4, but on Spectrum-4 it has been noisy. This
is in line with the observation that on Spectrum-4, queue size tends to
fluctuate more. A handful of packets could then still be accepted to the
queue even though it was nominally full just recently.

In order to accommodate this behavior, send many more packets. The buffer
can fit N extra packets, but not N% packets. This therefore allows us to
set wider absolute margins, while actually narrowing them relatively.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/abc869b9f6003d400d6293ddd5edb2f4517f44d5.1728316370.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/mlxsw/sch_red_core.sh  | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index b1ff395b3880..316444389c4e 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -653,20 +653,22 @@ do_drop_test()
 	build_backlog $vlan $((3 * limit / 2)) udp >/dev/null
 
 	base=$($fetch_counter)
-	send_packets $vlan udp 11
+	send_packets $vlan udp 100
 
-	now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter)
-	check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen"
+	now=$(busywait 1100 until_counter_is ">= $((base + 95))" $fetch_counter)
+	check_err $? "${trigger}ped packets not observed: 100 expected, $((now - base)) seen"
 
 	# When no extra traffic is injected, there should be no mirroring.
-	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
+	busywait 1100 until_counter_is ">= $((base + 110))" \
+		 $fetch_counter >/dev/null
 	check_fail $? "Spurious packets observed"
 
 	# When the rule is uninstalled, there should be no mirroring.
 	qevent_rule_uninstall_$subtest
-	send_packets $vlan udp 11
-	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
-	check_fail $? "Spurious packets observed after uninstall"
+	send_packets $vlan udp 100
+	now=$(busywait 1100 until_counter_is ">= $((base + 110))" \
+		       $fetch_counter)
+	check_fail $? "$((now - base)) spurious packets observed after uninstall"
 
 	log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd"
 
-- 
cgit v1.2.3


From 501fa2426b5ffbe08c2571b6f5c3f3afa1970aa2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Mon, 7 Oct 2024 18:26:09 +0200
Subject: selftests: mlxsw: sch_red_core: Lower TBF rate

The RED test uses a pair of TBF shapers. The first to get predictably-sized
stream of traffic, and second to get a 100% saturated chokepoint. To this
chokepoint it injects individual packets. Because the chokepoint is
saturated, these additional packets go straight to the backlog. This allows
the test to check RED behavior across various queue sizes.

The shapers are rated at 1Gbps, for historical reasons (before mlxsw
supported TBF offload, the test used port speed to create the chokepoints).
Machines with a low-power CPU may have trouble consistently generating
1Gbps of traffic, and the test then spuriously fails.

Instead, drop the rate to 200Mbps (Spectrum has a guaranteed shaper rate
granularity of 200Mbps, so anything lower is not guaranteed to work well).
Because that means fewer packets will be mirrored in the ECN-mark test,
adjust the passing condition accordingly.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/c6712f9c5de75ae0bc2ab3d8ea7d92aaaf93af95.1728316370.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 316444389c4e..f4c324957dcc 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -137,7 +137,7 @@ h2_create()
 	# Prevent this by adding a shaper which limits the traffic in $h2 to
 	# 1Gbps.
 
-	tc qdisc replace dev $h2 root handle 10: tbf rate 1gbit \
+	tc qdisc replace dev $h2 root handle 10: tbf rate 200mbit \
 		burst 128K limit 1G
 }
 
@@ -199,7 +199,7 @@ switch_create()
 	done
 
 	for intf in $swp3 $swp4; do
-		tc qdisc replace dev $intf root handle 1: tbf rate 1gbit \
+		tc qdisc replace dev $intf root handle 1: tbf rate 200mbit \
 			burst 128K limit 1G
 	done
 
@@ -602,7 +602,7 @@ do_mark_test()
 	# Above limit, everything should be mirrored, we should see lots of
 	# packets.
 	build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null
-	busywait_for_counter 1100 +10000 \
+	busywait_for_counter 1100 +2500 \
 		 $fetch_counter > /dev/null
 	check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd"
 
-- 
cgit v1.2.3


From b3ea416419c83ba4a042163f17e0fd8bac417f1a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 9 Oct 2024 10:09:57 +0200
Subject: testing: net-drv: add basic shaper test

Leverage a basic/dummy netdevsim implementation to do functional
coverage for NL interface.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/43092afbf38365c796088bf8fc155e523ab434ae.1728460186.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/Kconfig                            |   1 +
 drivers/net/netdevsim/ethtool.c                |   2 +
 drivers/net/netdevsim/netdev.c                 |  39 +++
 tools/testing/selftests/drivers/net/Makefile   |   1 +
 tools/testing/selftests/drivers/net/shaper.py  | 461 +++++++++++++++++++++++++
 tools/testing/selftests/net/lib/py/__init__.py |   1 +
 tools/testing/selftests/net/lib/py/ynl.py      |   5 +
 7 files changed, 510 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/shaper.py

(limited to 'tools/testing')

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 9920b3a68ed1..1fd5acdc73c6 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -641,6 +641,7 @@ config NETDEVSIM
 	depends on PTP_1588_CLOCK_MOCK || PTP_1588_CLOCK_MOCK=n
 	select NET_DEVLINK
 	select PAGE_POOL
+	select NET_SHAPER
 	help
 	  This driver is a developer testing tool and software model that can
 	  be used to test various control path networking APIs, especially
diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 1436905bc106..5fe1eaef99b5 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -103,8 +103,10 @@ nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
+	mutex_lock(&dev->lock);
 	err = netif_set_real_num_queues(dev, ch->combined_count,
 					ch->combined_count);
+	mutex_unlock(&dev->lock);
 	if (err)
 		return err;
 
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 017a6102be0a..cad85bb0cf54 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -22,6 +22,7 @@
 #include <net/netdev_queues.h>
 #include <net/page_pool/helpers.h>
 #include <net/netlink.h>
+#include <net/net_shaper.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/udp_tunnel.h>
@@ -475,6 +476,43 @@ static int nsim_stop(struct net_device *dev)
 	return 0;
 }
 
+static int nsim_shaper_set(struct net_shaper_binding *binding,
+			   const struct net_shaper *shaper,
+			   struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static int nsim_shaper_del(struct net_shaper_binding *binding,
+			   const struct net_shaper_handle *handle,
+			   struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static int nsim_shaper_group(struct net_shaper_binding *binding,
+			     int leaves_count,
+			     const struct net_shaper *leaves,
+			     const struct net_shaper *root,
+			     struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static void nsim_shaper_cap(struct net_shaper_binding *binding,
+			    enum net_shaper_scope scope,
+			    unsigned long *flags)
+{
+	*flags = ULONG_MAX;
+}
+
+static const struct net_shaper_ops nsim_shaper_ops = {
+	.set			= nsim_shaper_set,
+	.delete			= nsim_shaper_del,
+	.group			= nsim_shaper_group,
+	.capabilities		= nsim_shaper_cap,
+};
+
 static const struct net_device_ops nsim_netdev_ops = {
 	.ndo_start_xmit		= nsim_start_xmit,
 	.ndo_set_rx_mode	= nsim_set_rx_mode,
@@ -496,6 +534,7 @@ static const struct net_device_ops nsim_netdev_ops = {
 	.ndo_bpf		= nsim_bpf,
 	.ndo_open		= nsim_open,
 	.ndo_stop		= nsim_stop,
+	.net_shaper_ops		= &nsim_shaper_ops,
 };
 
 static const struct net_device_ops nsim_vf_netdev_ops = {
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 39fb97a8c1df..25aec5c081df 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -9,6 +9,7 @@ TEST_PROGS := \
 	ping.py \
 	queues.py \
 	stats.py \
+	shaper.py
 # end of TEST_PROGS
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/shaper.py b/tools/testing/selftests/drivers/net/shaper.py
new file mode 100755
index 000000000000..11310f19bfa0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/shaper.py
@@ -0,0 +1,461 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true, KsftSkipEx
+from lib.py import EthtoolFamily, NetshaperFamily
+from lib.py import NetDrvEnv
+from lib.py import NlError
+from lib.py import cmd
+
+def get_shapers(cfg, nl_shaper) -> None:
+    try:
+        shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+
+    # Default configuration: no shapers configured.
+    ksft_eq(len(shapers), 0)
+
+def get_caps(cfg, nl_shaper) -> None:
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex}, dump=True)
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+
+    # Each device implementing shaper support must support some
+    # features in at least a scope.
+    ksft_true(len(caps)> 0)
+
+def set_qshapers(cfg, nl_shaper) -> None:
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                 'scope':'queue'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-bw-max' in caps or not 'support-metric-bps' in caps:
+        raise KsftSkipEx("device does not support queue scope shapers with bw_max and metric bps")
+
+    cfg.queues = True;
+    netnl = EthtoolFamily()
+    channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    if channels['combined-count'] == 0:
+        cfg.rx_type = 'rx'
+        cfg.nr_queues = channels['rx-count']
+    else:
+        cfg.rx_type = 'combined'
+        cfg.nr_queues = channels['combined-count']
+    if cfg.nr_queues < 3:
+        raise KsftSkipEx(f"device does not support enough queues min 3 found {cfg.nr_queues}")
+
+    nl_shaper.set({'ifindex': cfg.ifindex,
+                   'handle': {'scope': 'queue', 'id': 1},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+    nl_shaper.set({'ifindex': cfg.ifindex,
+                   'handle': {'scope': 'queue', 'id': 2},
+                   'metric': 'bps',
+                   'bw-max': 20000})
+
+    # Querying a specific shaper not yet configured must fail.
+    raised = False
+    try:
+        shaper_q0 = nl_shaper.get({'ifindex': cfg.ifindex,
+                                   'handle': {'scope': 'queue', 'id': 0}})
+    except (NlError):
+        raised = True
+    ksft_eq(raised, True)
+
+    shaper_q1 = nl_shaper.get({'ifindex': cfg.ifindex,
+                              'handle': {'scope': 'queue', 'id': 1}})
+    ksft_eq(shaper_q1, {'ifindex': cfg.ifindex,
+                        'parent': {'scope': 'netdev'},
+                        'handle': {'scope': 'queue', 'id': 1},
+                        'metric': 'bps',
+                        'bw-max': 10000})
+
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 10000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'metric': 'bps',
+                       'bw-max': 20000}])
+
+def del_qshapers(cfg, nl_shaper) -> None:
+    if not cfg.queues:
+        raise KsftSkipEx("queue shapers not supported by device, skipping delete")
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 2}})
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 1}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def set_nshapers(cfg, nl_shaper) -> None:
+    # Check required features.
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'netdev'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-bw-max' in caps or not 'support-metric-bps' in caps:
+        raise KsftSkipEx("device does not support nested netdev scope shapers with weight")
+
+    cfg.netdev = True;
+    nl_shaper.set({'ifindex': cfg.ifindex,
+                   'handle': {'scope': 'netdev', 'id': 0},
+                   'bw-max': 100000})
+
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'handle': {'scope': 'netdev'},
+                       'metric': 'bps',
+                       'bw-max': 100000}])
+
+def del_nshapers(cfg, nl_shaper) -> None:
+    if not cfg.netdev:
+        raise KsftSkipEx("netdev shaper not supported by device, skipping delete")
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'netdev'}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def basic_groups(cfg, nl_shaper) -> None:
+    if not cfg.netdev:
+        raise KsftSkipEx("netdev shaper not supported by the device")
+    if cfg.nr_queues < 3:
+        raise KsftSkipEx(f"netdev does not have enough queues min 3 reported {cfg.nr_queues}")
+
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'queue'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-weight' in caps:
+        raise KsftSkipEx("device does not support queue scope shapers with weight")
+
+    node_handle = nl_shaper.group({
+                        'ifindex': cfg.ifindex,
+                        'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                                   'weight': 1},
+                                  {'handle': {'scope': 'queue', 'id': 2},
+                                   'weight': 2}],
+                         'handle': {'scope':'netdev'},
+                         'metric': 'bps',
+                         'bw-max': 10000})
+    ksft_eq(node_handle, {'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'netdev'}})
+
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'queue', 'id': 1}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'parent': {'scope': 'netdev'},
+                     'handle': {'scope': 'queue', 'id': 1},
+                     'weight': 1 })
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 2}})
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 1}})
+
+    # Deleting all the leaves shaper does not affect the node one
+    # when the latter has 'netdev' scope.
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 1)
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'netdev'}})
+
+def qgroups(cfg, nl_shaper) -> None:
+    if cfg.nr_queues < 4:
+        raise KsftSkipEx(f"netdev does not have enough queues min 4 reported {cfg.nr_queues}")
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'node'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-bw-max' in caps or not 'support-metric-bps' in caps:
+        raise KsftSkipEx("device does not support node scope shapers with bw_max and metric bps")
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'queue'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-nesting' in caps or not 'support-weight' in caps or not 'support-metric-bps' in caps:
+            raise KsftSkipEx("device does not support nested queue scope shapers with weight")
+
+    cfg.groups = True;
+    node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                              'weight': 3},
+                             {'handle': {'scope': 'queue', 'id': 2},
+                              'weight': 2}],
+                   'handle': {'scope':'node'},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+    node_id = node_handle['handle']['id']
+
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'queue', 'id': 1}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'parent': {'scope': 'node', 'id': node_id},
+                     'handle': {'scope': 'queue', 'id': 1},
+                     'weight': 3})
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'node', 'id': node_id}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'handle': {'scope': 'node', 'id': node_id},
+                     'parent': {'scope': 'netdev'},
+                     'metric': 'bps',
+                     'bw-max': 10000})
+
+    # Grouping to a specified, not existing node scope shaper must fail
+    raised = False
+    try:
+        nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 3},
+                              'weight': 3}],
+                   'handle': {'scope':'node', 'id': node_id + 1},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+
+    except (NlError):
+        raised = True
+    ksft_eq(raised, True)
+
+    # Add to an existing node
+    node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 3},
+                              'weight': 4}],
+                   'handle': {'scope':'node', 'id': node_id}})
+    ksft_eq(node_handle, {'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'node', 'id': node_id}})
+
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'queue', 'id': 3}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'parent': {'scope': 'node', 'id': node_id},
+                     'handle': {'scope': 'queue', 'id': 3},
+                     'weight': 4})
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 2}})
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 1}})
+
+    # Deleting a non empty node will move the leaves downstream.
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'node', 'id': node_id}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 3},
+                       'weight': 4}])
+
+    # Finish and verify the complete cleanup.
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 3}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def delegation(cfg, nl_shaper) -> None:
+    if not cfg.groups:
+        raise KsftSkipEx("device does not support node scope")
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'node'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("node scope shapers not supported by the device")
+        raise
+    if not 'support-nesting' in caps:
+        raise KsftSkipEx("device does not support node scope shapers nesting")
+
+    node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                              'weight': 3},
+                             {'handle': {'scope': 'queue', 'id': 2},
+                              'weight': 2},
+                             {'handle': {'scope': 'queue', 'id': 3},
+                              'weight': 1}],
+                   'handle': {'scope':'node'},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+    node_id = node_handle['handle']['id']
+
+    # Create the nested node and validate the hierarchy
+    nested_node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                              'weight': 3},
+                             {'handle': {'scope': 'queue', 'id': 2},
+                              'weight': 2}],
+                   'handle': {'scope':'node'},
+                   'metric': 'bps',
+                   'bw-max': 5000})
+    nested_node_id = nested_node_handle['handle']['id']
+    ksft_true(nested_node_id != node_id)
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': nested_node_id},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'weight': 3},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': nested_node_id},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'weight': 2},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 3},
+                       'weight': 1},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'node', 'id': node_id},
+                       'metric': 'bps',
+                       'bw-max': 10000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'node', 'id': nested_node_id},
+                       'metric': 'bps',
+                       'bw-max': 5000}])
+
+    # Deleting a non empty node will move the leaves downstream.
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'node', 'id': nested_node_id}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'weight': 3},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'weight': 2},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 3},
+                       'weight': 1},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'node', 'id': node_id},
+                       'metric': 'bps',
+                       'bw-max': 10000}])
+
+    # Final cleanup.
+    for i in range(1, 4):
+        nl_shaper.delete({'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'queue', 'id': i}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def queue_update(cfg, nl_shaper) -> None:
+    if cfg.nr_queues < 4:
+        raise KsftSkipEx(f"netdev does not have enough queues min 4 reported {cfg.nr_queues}")
+    if not cfg.queues:
+        raise KsftSkipEx("device does not support queue scope")
+
+    for i in range(3):
+        nl_shaper.set({'ifindex': cfg.ifindex,
+                       'handle': {'scope': 'queue', 'id': i},
+                       'metric': 'bps',
+                       'bw-max': (i + 1) * 1000})
+    # Delete a channel, with no shapers configured on top of the related
+    # queue: no changes expected
+    cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} 3", timeout=10)
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 0},
+                       'metric': 'bps',
+                       'bw-max': 1000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 2000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'metric': 'bps',
+                       'bw-max': 3000}])
+
+    # Delete a channel, with a shaper configured on top of the related
+    # queue: the shaper must be deleted, too
+    cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} 2", timeout=10)
+
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 0},
+                       'metric': 'bps',
+                       'bw-max': 1000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 2000}])
+
+    # Restore the original channels number, no expected changes
+    cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} {cfg.nr_queues}", timeout=10)
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 0},
+                       'metric': 'bps',
+                       'bw-max': 1000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 2000}])
+
+    # Final cleanup.
+    for i in range(0, 2):
+        nl_shaper.delete({'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'queue', 'id': i}})
+
+def main() -> None:
+    with NetDrvEnv(__file__, queue_count=4) as cfg:
+        cfg.queues = False
+        cfg.netdev = False
+        cfg.groups = False
+        cfg.nr_queues = 0
+        ksft_run([get_shapers,
+                  get_caps,
+                  set_qshapers,
+                  del_qshapers,
+                  set_nshapers,
+                  del_nshapers,
+                  basic_groups,
+                  qgroups,
+                  delegation,
+                  queue_update], args=(cfg, NetshaperFamily()))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index b6d498d125fe..54d8f5eba810 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -6,3 +6,4 @@ from .netns import NetNS
 from .nsim import *
 from .utils import *
 from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily
+from .ynl import NetshaperFamily
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index 1ace58370c06..a0d689d58c57 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -47,3 +47,8 @@ class NetdevFamily(YnlFamily):
     def __init__(self):
         super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(),
                          schema='')
+
+class NetshaperFamily(YnlFamily):
+    def __init__(self):
+        super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(),
+                         schema='')
-- 
cgit v1.2.3


From ac8d16b2d3772934f4cba44cb01bad05b4b2864c Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Wed, 9 Oct 2024 12:12:07 +0200
Subject: selftests/bpf: fix bpf_map_redirect call for cpu map test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

xdp_redir_prog currently redirects packets based on the entry at index 1
in cpu_map, but the corresponding test only manipulates the entry at
index 0. This does not really affect the test in its current form since
the program is detached before having the opportunity to execute, but it
needs to be fixed before being able improve the corresponding test (ie,
not only test attach/detach but also the redirect feature)

Fix this XDP program by making it redirect packets based on entry 0 in
cpu_map instead of entry 1.

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241009-convert_xdp_tests-v3-1-51cea913710c@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
index 20ec6723df18..d848fe96924e 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
@@ -15,7 +15,7 @@ struct {
 SEC("xdp")
 int xdp_redir_prog(struct xdp_md *ctx)
 {
-	return bpf_redirect_map(&cpu_map, 1, 0);
+	return bpf_redirect_map(&cpu_map, 0, 0);
 }
 
 SEC("xdp")
-- 
cgit v1.2.3


From d5fbcf46ee82574aee443423f3e4132d1154372b Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Wed, 9 Oct 2024 12:12:08 +0200
Subject: selftests/bpf: make xdp_cpumap_attach keep redirect prog attached
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current test only checks attach/detach on cpu map type program, and so
does not check that it can be properly executed, neither that it
redirects correctly.

Update the existing test to extend its coverage:
- keep the redirected program loaded
- try to execute it through bpf_prog_test_run_opts with some dummy
  context

While at it, bring the following minor improvements:
- isolate test interface in its own namespace

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241009-convert_xdp_tests-v3-2-51cea913710c@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/xdp_cpumap_attach.c   | 41 +++++++++++++++++-----
 1 file changed, 33 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index 481626a875d1..88e8a886d1e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -2,35 +2,41 @@
 #include <uapi/linux/bpf.h>
 #include <linux/if_link.h>
 #include <test_progs.h>
+#include <network_helpers.h>
 
 #include "test_xdp_with_cpumap_frags_helpers.skel.h"
 #include "test_xdp_with_cpumap_helpers.skel.h"
 
 #define IFINDEX_LO	1
+#define TEST_NS "cpu_attach_ns"
 
 static void test_xdp_with_cpumap_helpers(void)
 {
-	struct test_xdp_with_cpumap_helpers *skel;
+	struct test_xdp_with_cpumap_helpers *skel = NULL;
 	struct bpf_prog_info info = {};
 	__u32 len = sizeof(info);
 	struct bpf_cpumap_val val = {
 		.qsize = 192,
 	};
-	int err, prog_fd, map_fd;
+	int err, prog_fd, prog_redir_fd, map_fd;
+	struct nstoken *nstoken = NULL;
 	__u32 idx = 0;
 
+	SYS(out_close, "ip netns add %s", TEST_NS);
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto out_close;
+	SYS(out_close, "ip link set dev lo up");
+
 	skel = test_xdp_with_cpumap_helpers__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
-	err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL);
+	prog_redir_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_xdp_attach(IFINDEX_LO, prog_redir_fd, XDP_FLAGS_SKB_MODE, NULL);
 	if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP"))
 		goto out_close;
 
-	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
-	ASSERT_OK(err, "XDP program detach");
-
 	prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
 	map_fd = bpf_map__fd(skel->maps.cpu_map);
 	err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
@@ -45,6 +51,23 @@ static void test_xdp_with_cpumap_helpers(void)
 	ASSERT_OK(err, "Read cpumap entry");
 	ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id");
 
+	/* send a packet to trigger any potential bugs in there */
+	char data[10] = {};
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .data_in = &data,
+			    .data_size_in = 10,
+			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
+			    .repeat = 1,
+		);
+	err = bpf_prog_test_run_opts(prog_redir_fd, &opts);
+	ASSERT_OK(err, "XDP test run");
+
+	/* wait for the packets to be flushed */
+	kern_sync_rcu();
+
+	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
+	ASSERT_OK(err, "XDP program detach");
+
 	/* can not attach BPF_XDP_CPUMAP program to a device */
 	err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL);
 	if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program"))
@@ -65,6 +88,8 @@ static void test_xdp_with_cpumap_helpers(void)
 	ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry");
 
 out_close:
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
 	test_xdp_with_cpumap_helpers__destroy(skel);
 }
 
@@ -111,7 +136,7 @@ out_close:
 	test_xdp_with_cpumap_frags_helpers__destroy(skel);
 }
 
-void serial_test_xdp_cpumap_attach(void)
+void test_xdp_cpumap_attach(void)
 {
 	if (test__start_subtest("CPUMAP with programs in entries"))
 		test_xdp_with_cpumap_helpers();
-- 
cgit v1.2.3


From d124d984c8a2d677e1cea6740a01ccdd0371a38d Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Wed, 9 Oct 2024 12:12:09 +0200
Subject: selftests/bpf: check program redirect in xdp_cpumap_attach
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

xdp_cpumap_attach, in its current form, only checks that an xdp cpumap
program can be executed, but not that it performs correctly the cpu
redirect as configured by userspace (bpf_prog_test_run_opts will return
success even if the redirect program returns an error)

Add a check to ensure that the program performs the configured redirect
as well. The check is based on a global variable incremented by a
chained program executed only if the redirect program properly executes.

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241009-convert_xdp_tests-v3-3-51cea913710c@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c       | 5 ++++-
 tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c | 5 +++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index 88e8a886d1e6..c7f74f068e78 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -62,8 +62,11 @@ static void test_xdp_with_cpumap_helpers(void)
 	err = bpf_prog_test_run_opts(prog_redir_fd, &opts);
 	ASSERT_OK(err, "XDP test run");
 
-	/* wait for the packets to be flushed */
+	/* wait for the packets to be flushed, then check that redirect has been
+	 * performed
+	 */
 	kern_sync_rcu();
+	ASSERT_NEQ(skel->bss->redirect_count, 0, "redirected packets");
 
 	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
 	ASSERT_OK(err, "XDP program detach");
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
index d848fe96924e..3619239b01b7 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
@@ -12,6 +12,8 @@ struct {
 	__uint(max_entries, 4);
 } cpu_map SEC(".maps");
 
+__u32 redirect_count = 0;
+
 SEC("xdp")
 int xdp_redir_prog(struct xdp_md *ctx)
 {
@@ -27,6 +29,9 @@ int xdp_dummy_prog(struct xdp_md *ctx)
 SEC("xdp/cpumap")
 int xdp_dummy_cm(struct xdp_md *ctx)
 {
+	if (bpf_get_smp_processor_id() == 0)
+		redirect_count++;
+
 	if (ctx->ingress_ifindex == IFINDEX_LO)
 		return XDP_DROP;
 
-- 
cgit v1.2.3


From 3ec920bb978ccdc68a7dfb304d303d598d038cb1 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 10 Oct 2024 04:00:27 +0000
Subject: selftests: rtnetlink: update netdevsim ipsec output format

After the netdevsim update to use human-readable IP address formats for
IPsec, we can now use the source and destination IPs directly in testing.
Here is the result:
  # ./rtnetlink.sh -t kci_test_ipsec_offload
  PASS: ipsec_offload

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241010040027.21440-4-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rtnetlink.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index bdf6f10d0558..87dce3efe31e 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -809,10 +809,10 @@ kci_test_ipsec_offload()
 	# does driver have correct offload info
 	run_cmd diff $sysfsf - << EOF
 SA count=2 tx=3
-sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000
+sa[0] tx ipaddr=$dstip
 sa[0]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
 sa[0]    key=0x34333231 38373635 32313039 36353433
-sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0
+sa[1] rx ipaddr=$srcip
 sa[1]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
 sa[1]    key=0x34333231 38373635 32313039 36353433
 EOF
-- 
cgit v1.2.3


From ec35b0c53cc7398143315d42342a9798094dada7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 10 Oct 2024 14:18:57 -0700
Subject: selftests: drv-net: add missing trailing backslash

Commit b3ea416419c8 ("testing: net-drv: add basic shaper test")
removed the trailing backslash from the last entry. We have
a terminating comment here to avoid having to modify the last
line when adding at the end.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20241010211857.2193076-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 25aec5c081df..0fec8f9801ad 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -9,7 +9,7 @@ TEST_PROGS := \
 	ping.py \
 	queues.py \
 	stats.py \
-	shaper.py
+	shaper.py \
 # end of TEST_PROGS
 
 include ../../lib.mk
-- 
cgit v1.2.3


From 0cb06dc6c42b1b2940e01f207ddf980f2d637545 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 11 Oct 2024 16:03:10 -0700
Subject: selftests: net: rebuild YNL if dependencies changed

Try to rebuild YNL if either user added a new family or the specs
of the families have changed. Stanislav's ncdevmem cause a false
positive build failure in NIPA because libynl.a isn't rebuilt
after ethtool is added to YNL_GENS.

Note that sha1sum is already used in other parts of the build system.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241011230311.2529760-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ynl.mk | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk
index 1ef24119def0..add5c0cdeac4 100644
--- a/tools/testing/selftests/net/ynl.mk
+++ b/tools/testing/selftests/net/ynl.mk
@@ -9,6 +9,8 @@
 # YNL_GEN_FILES: TEST_GEN_FILES which need YNL
 
 YNL_OUTPUTS := $(patsubst %,$(OUTPUT)/%,$(YNL_GEN_FILES))
+YNL_SPECS := \
+	$(patsubst %,$(top_srcdir)/Documentation/netlink/specs/%.yaml,$(YNL_GENS))
 
 $(YNL_OUTPUTS): $(OUTPUT)/libynl.a
 $(YNL_OUTPUTS): CFLAGS += \
@@ -16,10 +18,19 @@ $(YNL_OUTPUTS): CFLAGS += \
 	-I$(top_srcdir)/tools/net/ynl/lib/ \
 	-I$(top_srcdir)/tools/net/ynl/generated/
 
-$(OUTPUT)/libynl.a:
+# Make sure we rebuild libynl if user added a new family. We can't easily
+# depend on the contents of a variable so create a fake file with a hash.
+YNL_GENS_HASH := $(shell echo $(YNL_GENS) | sha1sum | cut -c1-8)
+$(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig:
+	$(Q)rm -f $(OUTPUT)/.libynl-*.sig
+	$(Q)touch $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig
+
+$(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig
+	$(Q)rm -f $(top_srcdir)/tools/net/ynl/libynl.a
 	$(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a
 	$(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a
 
 EXTRA_CLEAN += \
 	$(top_srcdir)/tools/net/ynl/lib/__pycache__ \
-	$(top_srcdir)/tools/net/ynl/lib/*.[ado]
+	$(top_srcdir)/tools/net/ynl/lib/*.[ado] \
+	$(OUTPUT)/.libynl-*.sig
-- 
cgit v1.2.3


From 60b4d49b9621db4b000c9065dd6457c9a0eda80b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 11 Oct 2024 16:03:11 -0700
Subject: selftests: net: move EXTRA_CLEAN of libynl.a into ynl.mk

Commit 1fd9e4f25782 ("selftests: make kselftest-clean remove libynl outputs")
added EXTRA_CLEAN of YNL generated files to ynl.mk. We already had
a EXTRA_CLEAN in the file including the snippet. Consolidate them.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241011230311.2529760-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile | 1 -
 tools/testing/selftests/net/ynl.mk   | 3 ++-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 649f1fe0dc46..26a4883a65c9 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -98,7 +98,6 @@ TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
 
 # YNL files, must be before "include ..lib.mk"
-EXTRA_CLEAN += $(OUTPUT)/libynl.a
 YNL_GEN_FILES := ncdevmem
 TEST_GEN_FILES += $(YNL_GEN_FILES)
 
diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk
index add5c0cdeac4..d43afe243779 100644
--- a/tools/testing/selftests/net/ynl.mk
+++ b/tools/testing/selftests/net/ynl.mk
@@ -33,4 +33,5 @@ $(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig
 EXTRA_CLEAN += \
 	$(top_srcdir)/tools/net/ynl/lib/__pycache__ \
 	$(top_srcdir)/tools/net/ynl/lib/*.[ado] \
-	$(OUTPUT)/.libynl-*.sig
+	$(OUTPUT)/.libynl-*.sig \
+	$(OUTPUT)/libynl.a
-- 
cgit v1.2.3


From 9317e8933e27501575cbef923dfab30867484e7e Mon Sep 17 00:00:00 2001
From: Gur Stavi <gur.stavi@huawei.com>
Date: Sun, 13 Oct 2024 10:15:26 +0300
Subject: selftests: net/psock_fanout: socket joins fanout when link is down

Modify test_control_group to have toggle parameter.
When toggle is non-zero, loopback device will be set down for the
initialization of fd[1] which is still expected to successfully join
the fanout.

Signed-off-by: Gur Stavi <gur.stavi@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/6f4a506ed5f08f8fc00a966dec8febd1030c6e98.1728802323.git.gur.stavi@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/psock_fanout.c | 42 +++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 4f31e92ebd96..acdfae8f8a9a 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -48,6 +48,7 @@
 #include <string.h>
 #include <sys/mman.h>
 #include <sys/socket.h>
+#include <sys/ioctl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <unistd.h>
@@ -59,6 +60,33 @@
 
 static uint32_t cfg_max_num_members;
 
+static void loopback_set_up_down(int state_up)
+{
+	struct ifreq ifreq = {};
+	int fd, err;
+
+	fd = socket(AF_PACKET, SOCK_RAW, 0);
+	if (fd < 0) {
+		perror("socket loopback");
+		exit(1);
+	}
+	strcpy(ifreq.ifr_name, "lo");
+	err = ioctl(fd, SIOCGIFFLAGS, &ifreq);
+	if (err) {
+		perror("SIOCGIFFLAGS");
+		exit(1);
+	}
+	if (state_up != !!(ifreq.ifr_flags & IFF_UP)) {
+		ifreq.ifr_flags ^= IFF_UP;
+		err = ioctl(fd, SIOCSIFFLAGS, &ifreq);
+		if (err) {
+			perror("SIOCSIFFLAGS");
+			exit(1);
+		}
+	}
+	close(fd);
+}
+
 /* Open a socket in a given fanout mode.
  * @return -1 if mode is bad, a valid socket otherwise */
 static int sock_fanout_open(uint16_t typeflags, uint16_t group_id)
@@ -264,17 +292,22 @@ static void test_control_single(void)
 }
 
 /* Test illegal group with different modes or flags */
-static void test_control_group(void)
+static void test_control_group(int toggle)
 {
 	int fds[2];
 
-	fprintf(stderr, "test: control multiple sockets\n");
+	if (toggle)
+		fprintf(stderr, "test: control multiple sockets with link down toggle\n");
+	else
+		fprintf(stderr, "test: control multiple sockets\n");
 
 	fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
 	if (fds[0] == -1) {
 		fprintf(stderr, "ERROR: failed to open HASH socket\n");
 		exit(1);
 	}
+	if (toggle)
+		loopback_set_up_down(0);
 	if (sock_fanout_open(PACKET_FANOUT_HASH |
 			       PACKET_FANOUT_FLAG_DEFRAG, 0) != -1) {
 		fprintf(stderr, "ERROR: joined group with wrong flag defrag\n");
@@ -294,6 +327,8 @@ static void test_control_group(void)
 		fprintf(stderr, "ERROR: failed to join group\n");
 		exit(1);
 	}
+	if (toggle)
+		loopback_set_up_down(1);
 	if (close(fds[1]) || close(fds[0])) {
 		fprintf(stderr, "ERROR: closing sockets\n");
 		exit(1);
@@ -489,7 +524,8 @@ int main(int argc, char **argv)
 	int port_off = 2, tries = 20, ret;
 
 	test_control_single();
-	test_control_group();
+	test_control_group(0);
+	test_control_group(1);
 	test_control_group_max_num_members();
 	test_unique_fanout_group_ids();
 
-- 
cgit v1.2.3


From 7ec02a3aef05098a413e1d1c7326c15b92189d0c Mon Sep 17 00:00:00 2001
From: Gur Stavi <gur.stavi@huawei.com>
Date: Sun, 13 Oct 2024 10:15:27 +0300
Subject: selftests: net/psock_fanout: unbound socket fanout

Add a test that validates that an unbound packet socket cannot create/join
a fanout group.

Signed-off-by: Gur Stavi <gur.stavi@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/7612fa90f613100e2b64c563cab3d7fdf36010db.1728802323.git.gur.stavi@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/psock_fanout.c | 36 ++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index acdfae8f8a9a..84c524357075 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -279,6 +279,41 @@ static int sock_fanout_read(int fds[], char *rings[], const int expect[])
 	return 0;
 }
 
+/* Test that creating/joining a fanout group fails for unbound socket without
+ * a specified protocol
+ */
+static void test_unbound_fanout(void)
+{
+	int val, fd0, fd1, err;
+
+	fprintf(stderr, "test: unbound fanout\n");
+	fd0 = socket(PF_PACKET, SOCK_RAW, 0);
+	if (fd0 < 0) {
+		perror("socket packet");
+		exit(1);
+	}
+	/* Try to create a new fanout group. Should fail. */
+	val = (PACKET_FANOUT_HASH << 16) | 1;
+	err = setsockopt(fd0, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val));
+	if (!err) {
+		fprintf(stderr, "ERROR: unbound socket fanout create\n");
+		exit(1);
+	}
+	fd1 = sock_fanout_open(PACKET_FANOUT_HASH, 1);
+	if (fd1 == -1) {
+		fprintf(stderr, "ERROR: failed to open HASH socket\n");
+		exit(1);
+	}
+	/* Try to join an existing fanout group. Should fail. */
+	err = setsockopt(fd0, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val));
+	if (!err) {
+		fprintf(stderr, "ERROR: unbound socket fanout join\n");
+		exit(1);
+	}
+	close(fd0);
+	close(fd1);
+}
+
 /* Test illegal mode + flag combination */
 static void test_control_single(void)
 {
@@ -523,6 +558,7 @@ int main(int argc, char **argv)
 	const int expect_uniqueid[2][2] = { { 20, 20},  { 20, 20 } };
 	int port_off = 2, tries = 20, ret;
 
+	test_unbound_fanout();
 	test_control_single();
 	test_control_group(0);
 	test_control_group(1);
-- 
cgit v1.2.3


From ee9b352ce4650ffc0d8ca0ac373d7c009c7e561e Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Sat, 12 Oct 2024 20:37:30 +0000
Subject: selftests/bpf: Fix msg_verify_data in test_sockmap

Function msg_verify_data should have context of bytes_cnt and k instead of
assuming they are zero. Otherwise, test_sockmap with data integrity test
will report some errors. I also fix the logic related to size and index j

1/ 6  sockmap::txmsg test passthrough:FAIL
2/ 6  sockmap::txmsg test redirect:FAIL
7/12  sockmap::txmsg test apply:FAIL
10/11  sockmap::txmsg test push_data:FAIL
11/17  sockmap::txmsg test pull-data:FAIL
12/ 9  sockmap::txmsg test pop-data:FAIL
13/ 1  sockmap::txmsg test push/pop data:FAIL
...
Pass: 24 Fail: 52

After applying this patch, some of the errors are solved, but for push,
pull and pop, we may need more fixes to msg_verify_data, added a TODO

10/11  sockmap::txmsg test push_data:FAIL
11/17  sockmap::txmsg test pull-data:FAIL
12/ 9  sockmap::txmsg test pop-data:FAIL
...
Pass: 37 Fail: 15

Besides, added a custom errno EDATAINTEGRITY for msg_verify_data, we
shall not ignore the error in txmsg_cork case.

Fixes: 753fb2ee0934 ("bpf: sockmap, add msg_peek tests to test_sockmap")
Fixes: 16edddfe3c5d ("selftests/bpf: test_sockmap, check test failure")
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Link: https://lore.kernel.org/r/20241012203731.1248619-2-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 3e02d7267de8..8249f3c1fbd6 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -56,6 +56,8 @@ static void running_handler(int a);
 #define BPF_SOCKHASH_FILENAME "test_sockhash_kern.bpf.o"
 #define CG_PATH "/sockmap"
 
+#define EDATAINTEGRITY 2001
+
 /* global sockets */
 int s1, s2, c1, c2, p1, p2;
 int test_cnt;
@@ -510,23 +512,25 @@ unwind_iov:
 	return -ENOMEM;
 }
 
-static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
+/* TODO: Add verification logic for push, pull and pop data */
+static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz,
+				 unsigned char *k_p, int *bytes_cnt_p)
 {
-	int i, j = 0, bytes_cnt = 0;
-	unsigned char k = 0;
+	int i, j, bytes_cnt = *bytes_cnt_p;
+	unsigned char k = *k_p;
 
-	for (i = 0; i < msg->msg_iovlen; i++) {
+	for (i = 0, j = 0; i < msg->msg_iovlen && size; i++, j = 0) {
 		unsigned char *d = msg->msg_iov[i].iov_base;
 
 		/* Special case test for skb ingress + ktls */
 		if (i == 0 && txmsg_ktls_skb) {
 			if (msg->msg_iov[i].iov_len < 4)
-				return -EIO;
+				return -EDATAINTEGRITY;
 			if (memcmp(d, "PASS", 4) != 0) {
 				fprintf(stderr,
 					"detected skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n",
 					i, 0, d[0], d[1], d[2], d[3]);
-				return -EIO;
+				return -EDATAINTEGRITY;
 			}
 			j = 4; /* advance index past PASS header */
 		}
@@ -536,7 +540,7 @@ static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
 				fprintf(stderr,
 					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
 					i, j, d[j], k - 1, d[j+1], k);
-				return -EIO;
+				return -EDATAINTEGRITY;
 			}
 			bytes_cnt++;
 			if (bytes_cnt == chunk_sz) {
@@ -546,6 +550,8 @@ static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
 			size--;
 		}
 	}
+	*k_p = k;
+	*bytes_cnt_p = bytes_cnt;
 	return 0;
 }
 
@@ -602,6 +608,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		float total_bytes, txmsg_pop_total;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
+		unsigned char k = 0;
+		int bytes_cnt = 0;
 		fd_set w;
 
 		fcntl(fd, fd_flags);
@@ -696,7 +704,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 						iov_length * cnt :
 						iov_length * iov_count;
 
-				errno = msg_verify_data(&msg, recv, chunk_sz);
+				errno = msg_verify_data(&msg, recv, chunk_sz, &k, &bytes_cnt);
 				if (errno) {
 					perror("data verify msg failed");
 					goto out_errno;
@@ -704,7 +712,9 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				if (recvp) {
 					errno = msg_verify_data(&msg_peek,
 								recvp,
-								chunk_sz);
+								chunk_sz,
+								&k,
+								&bytes_cnt);
 					if (errno) {
 						perror("data verify msg_peek failed");
 						goto out_errno;
@@ -812,7 +822,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
 				s.bytes_recvd, recvd_Bps, recvd_Bps/giga,
 				peek_flag ? "(peek_msg)" : "");
-		if (err && txmsg_cork)
+		if (err && err != -EDATAINTEGRITY && txmsg_cork)
 			err = 0;
 		exit(err ? 1 : 0);
 	} else if (rxpid == -1) {
-- 
cgit v1.2.3


From b29e231d66303c12b7b8ac3ac2a057df06b161e8 Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Sat, 12 Oct 2024 20:37:31 +0000
Subject: selftests/bpf: Fix txmsg_redir of test_txmsg_pull in test_sockmap

txmsg_redir in "Test pull + redirect" case of test_txmsg_pull should be
1 instead of 0.

Fixes: 328aa08a081b ("bpf: Selftests, break down test_sockmap into subtests")
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Link: https://lore.kernel.org/r/20241012203731.1248619-3-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 8249f3c1fbd6..075c93ed143e 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1606,7 +1606,7 @@ static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 	test_send_large(opt, cgrp);
 
 	/* Test pull + redirect */
-	txmsg_redir = 0;
+	txmsg_redir = 1;
 	txmsg_start = 1;
 	txmsg_end = 2;
 	test_send(opt, cgrp);
-- 
cgit v1.2.3


From 1ec43493c94f1661e5db79743bc720e1fe5ddb7f Mon Sep 17 00:00:00 2001
From: Daniel Zahka <daniel.zahka@gmail.com>
Date: Fri, 11 Oct 2024 11:35:48 -0700
Subject: selftests: drv-net: rss_ctx: add rss ctx busy testcase

It should be invalid to delete an rss context while it is being
referenced from an ntuple filter. ethtool core should prevent this
from happening. This patch adds a testcase to verify this behavior.

Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 32 +++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 9d7adb3cf33b..29995586993c 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -6,7 +6,7 @@ import random
 from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
-from lib.py import KsftSkipEx
+from lib.py import KsftSkipEx, KsftFailEx
 from lib.py import rand_port
 from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure
 
@@ -606,6 +606,33 @@ def test_rss_context_overlap2(cfg):
     test_rss_context_overlap(cfg, True)
 
 
+def test_delete_rss_context_busy(cfg):
+    """
+    Test that deletion returns -EBUSY when an rss context is being used
+    by an ntuple filter.
+    """
+
+    require_ntuple(cfg)
+
+    # create additional rss context
+    ctx_id = ethtool_create(cfg, "-X", "context new")
+    ctx_deleter = defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    # utilize context from ntuple filter
+    port = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    # attempt to delete in-use context
+    try:
+        ctx_deleter.exec_only()
+        ctx_deleter.cancel()
+        raise KsftFailEx(f"deleted context {ctx_id} used by rule {ntuple_id}")
+    except CmdExitFailure:
+        pass
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         cfg.ethnl = EthtoolFamily()
@@ -616,7 +643,8 @@ def main() -> None:
                   test_rss_context, test_rss_context4, test_rss_context32,
                   test_rss_context_dump, test_rss_context_queue_reconfigure,
                   test_rss_context_overlap, test_rss_context_overlap2,
-                  test_rss_context_out_of_order, test_rss_context4_create_with_cfg],
+                  test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
+                  test_delete_rss_context_busy],
                  args=(cfg, ))
     ksft_exit()
 
-- 
cgit v1.2.3


From 6414b3e5d5d44cd214161abf2ce2221d9e9de7bf Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Sun, 20 Oct 2024 21:22:53 +0200
Subject: selftests/bpf: factorize conn and syncookies tests in a single runner
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

btf_skc_cls_ingress currently describe two tests, both running a simple
tcp server and then initializing a connection to it. The sole difference
between the tests is about the tcp_syncookie configuration, and some
checks around this feature being enabled/disabled.

Share the common code between those two tests by moving the code into a
single runner, parameterized by a "gen_cookies" argument. Split the
performed checks accordingly.

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241020-syncookie-v2-1-2db240225fed@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 106 +++++++--------------
 1 file changed, 37 insertions(+), 69 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index ef4d6a3ae423..5d8d7736edc0 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -71,13 +71,14 @@ static void print_err_line(void)
 		printf("bpf prog error at line %u\n", skel->bss->linum);
 }
 
-static void test_conn(void)
+static void run_test(bool gen_cookies)
 {
+	const char *tcp_syncookies = gen_cookies ? "2" : "1";
 	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
 	socklen_t addrlen = sizeof(srv_sa6);
 	int srv_port;
 
-	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1"))
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", tcp_syncookies))
 		return;
 
 	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
@@ -99,19 +100,36 @@ static void test_conn(void)
 	if (CHECK_FAIL(srv_fd == -1))
 		goto done;
 
-	if (CHECK(skel->bss->listen_tp_sport != srv_port ||
-		  skel->bss->req_sk_sport != srv_port,
-		  "Unexpected sk src port",
-		  "listen_tp_sport:%u req_sk_sport:%u expected:%u\n",
-		  skel->bss->listen_tp_sport, skel->bss->req_sk_sport,
-		  srv_port))
+	if (CHECK(skel->bss->listen_tp_sport != srv_port,
+		  "Unexpected listen tp src port",
+		  "listen_tp_sport:%u expected:%u\n",
+		  skel->bss->listen_tp_sport, srv_port))
 		goto done;
 
-	if (CHECK(skel->bss->gen_cookie || skel->bss->recv_cookie,
-		  "Unexpected syncookie states",
-		  "gen_cookie:%u recv_cookie:%u\n",
-		  skel->bss->gen_cookie, skel->bss->recv_cookie))
-		goto done;
+	if (!gen_cookies) {
+		if (CHECK(skel->bss->req_sk_sport != srv_port,
+			  "Unexpected req_sk src port",
+			  "req_sk_sport:%u expected:%u\n",
+			  skel->bss->req_sk_sport, srv_port))
+			goto done;
+		if (CHECK(skel->bss->gen_cookie || skel->bss->recv_cookie,
+			  "Unexpected syncookie states",
+			  "gen_cookie:%u recv_cookie:%u\n",
+			  skel->bss->gen_cookie, skel->bss->recv_cookie))
+			goto done;
+	} else {
+		if (CHECK(skel->bss->req_sk_sport,
+			  "Unexpected req_sk src port",
+			  "req_sk_sport:%u expected:0\n",
+			  skel->bss->req_sk_sport))
+			goto done;
+		if (CHECK(!skel->bss->gen_cookie ||
+			  skel->bss->gen_cookie != skel->bss->recv_cookie,
+			  "Unexpected syncookie states",
+			  "gen_cookie:%u recv_cookie:%u\n",
+			  skel->bss->gen_cookie, skel->bss->recv_cookie))
+			goto done;
+	}
 
 	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
 	      skel->bss->linum);
@@ -125,64 +143,14 @@ done:
 		close(srv_fd);
 }
 
-static void test_syncookie(void)
+static void test_conn(void)
 {
-	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
-	socklen_t addrlen = sizeof(srv_sa6);
-	int srv_port;
-
-	/* Enforce syncookie mode */
-	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "2"))
-		return;
-
-	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
-	if (CHECK_FAIL(listen_fd == -1))
-		return;
-
-	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
-	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
-		  errno))
-		goto done;
-	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
-	srv_port = ntohs(srv_sa6.sin6_port);
-
-	cli_fd = connect_to_fd(listen_fd, 0);
-	if (CHECK_FAIL(cli_fd == -1))
-		goto done;
-
-	srv_fd = accept(listen_fd, NULL, NULL);
-	if (CHECK_FAIL(srv_fd == -1))
-		goto done;
-
-	if (CHECK(skel->bss->listen_tp_sport != srv_port,
-		  "Unexpected tp src port",
-		  "listen_tp_sport:%u expected:%u\n",
-		  skel->bss->listen_tp_sport, srv_port))
-		goto done;
-
-	if (CHECK(skel->bss->req_sk_sport,
-		  "Unexpected req_sk src port",
-		  "req_sk_sport:%u expected:0\n",
-		   skel->bss->req_sk_sport))
-		goto done;
-
-	if (CHECK(!skel->bss->gen_cookie ||
-		  skel->bss->gen_cookie != skel->bss->recv_cookie,
-		  "Unexpected syncookie states",
-		  "gen_cookie:%u recv_cookie:%u\n",
-		  skel->bss->gen_cookie, skel->bss->recv_cookie))
-		goto done;
-
-	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
-	      skel->bss->linum);
+	run_test(false);
+}
 
-done:
-	if (listen_fd != -1)
-		close(listen_fd);
-	if (cli_fd != -1)
-		close(cli_fd);
-	if (srv_fd != -1)
-		close(srv_fd);
+static void test_syncookie(void)
+{
+	run_test(true);
 }
 
 struct test {
-- 
cgit v1.2.3


From 0335dd6b5a4c178d9ae34694a0be7862873378bd Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Sun, 20 Oct 2024 21:22:54 +0200
Subject: selftests/bpf: add missing ns cleanups in btf_skc_cls_ingress
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

btf_skc_cls_ingress.c currently runs two subtests, and create a
dedicated network namespace for each, but never cleans up the created
namespace once the test has ended.

Add missing namespace cleanup after each subtest to avoid accumulating
namespaces for each new subtest. While at it, switch namespace
management to netns_{new,free}

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241020-syncookie-v2-2-2db240225fed@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 33 +++++++++++++---------
 1 file changed, 19 insertions(+), 14 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index 5d8d7736edc0..c88fb0e3048c 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -17,32 +17,30 @@
 #include "test_progs.h"
 #include "test_btf_skc_cls_ingress.skel.h"
 
+#define TEST_NS "skc_cls_ingress"
+
 static struct test_btf_skc_cls_ingress *skel;
 static struct sockaddr_in6 srv_sa6;
 static __u32 duration;
 
-static int prepare_netns(void)
+static struct netns_obj *prepare_netns(void)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
 	LIBBPF_OPTS(bpf_tc_opts, tc_attach,
 		    .prog_fd = bpf_program__fd(skel->progs.cls_ingress));
+	struct netns_obj *ns = NULL;
 
-	if (CHECK(unshare(CLONE_NEWNET), "create netns",
-		  "unshare(CLONE_NEWNET): %s (%d)",
-		  strerror(errno), errno))
-		return -1;
-
-	if (CHECK(system("ip link set dev lo up"),
-		  "ip link set dev lo up", "failed\n"))
-		return -1;
+	ns = netns_new(TEST_NS, true);
+	if (!ASSERT_OK_PTR(ns, "create and join netns"))
+		return ns;
 
 	qdisc_lo.ifindex = if_nametoindex("lo");
 	if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact"))
-		return -1;
+		goto free_ns;
 
 	if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach),
 		       "filter add dev lo ingress"))
-		return -1;
+		goto free_ns;
 
 	/* Ensure 20 bytes options (i.e. in total 40 bytes tcp header) for the
 	 * bpf_tcp_gen_syncookie() helper.
@@ -50,9 +48,13 @@ static int prepare_netns(void)
 	if (write_sysctl("/proc/sys/net/ipv4/tcp_window_scaling", "1") ||
 	    write_sysctl("/proc/sys/net/ipv4/tcp_timestamps", "1") ||
 	    write_sysctl("/proc/sys/net/ipv4/tcp_sack", "1"))
-		return -1;
+		goto free_ns;
+
+	return ns;
 
-	return 0;
+free_ns:
+	netns_free(ns);
+	return NULL;
 }
 
 static void reset_test(void)
@@ -169,6 +171,7 @@ void test_btf_skc_cls_ingress(void)
 	int i;
 
 	skel = test_btf_skc_cls_ingress__open_and_load();
+	struct netns_obj *ns;
 	if (CHECK(!skel, "test_btf_skc_cls_ingress__open_and_load", "failed\n"))
 		return;
 
@@ -176,13 +179,15 @@ void test_btf_skc_cls_ingress(void)
 		if (!test__start_subtest(tests[i].desc))
 			continue;
 
-		if (prepare_netns())
+		ns = prepare_netns();
+		if (!ns)
 			break;
 
 		tests[i].run();
 
 		print_err_line();
 		reset_test();
+		netns_free(ns);
 	}
 
 	test_btf_skc_cls_ingress__destroy(skel);
-- 
cgit v1.2.3


From 0da0a75cf649e1e5a688af1763653206260f17a9 Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Sun, 20 Oct 2024 21:22:55 +0200
Subject: selftests/bpf: get rid of global vars in btf_skc_cls_ingress
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are a few global variables in btf_skc_cls_ingress.c, which are not
really used by different tests. Get rid of those global variables, by
performing the following updates:
- make srv_sa6 local to the main runner function
- make skel local to the main function, and propagate it through
  function arguments
- get rid of duration by replacing CHECK macros with the ASSERT_XXX
  macros. While updating those assert macros:
  - do not return early on asserts performing some actual tests, let the
    other tests run as well (keep the early return for parts handling
    test setup)
  - instead of converting the CHECK on skel->bss->linum, just remove it,
    since there is already a call to print_err_line after the test to
    print the failing line in the bpf program

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241020-syncookie-v2-3-2db240225fed@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 87 +++++++++-------------
 1 file changed, 34 insertions(+), 53 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index c88fb0e3048c..426c9d5402fa 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -19,11 +19,7 @@
 
 #define TEST_NS "skc_cls_ingress"
 
-static struct test_btf_skc_cls_ingress *skel;
-static struct sockaddr_in6 srv_sa6;
-static __u32 duration;
-
-static struct netns_obj *prepare_netns(void)
+static struct netns_obj *prepare_netns(struct test_btf_skc_cls_ingress *skel)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
 	LIBBPF_OPTS(bpf_tc_opts, tc_attach,
@@ -57,7 +53,7 @@ free_ns:
 	return NULL;
 }
 
-static void reset_test(void)
+static void reset_test(struct test_btf_skc_cls_ingress *skel)
 {
 	memset(&skel->bss->srv_sa6, 0, sizeof(skel->bss->srv_sa6));
 	skel->bss->listen_tp_sport = 0;
@@ -67,16 +63,17 @@ static void reset_test(void)
 	skel->bss->linum = 0;
 }
 
-static void print_err_line(void)
+static void print_err_line(struct test_btf_skc_cls_ingress *skel)
 {
 	if (skel->bss->linum)
 		printf("bpf prog error at line %u\n", skel->bss->linum);
 }
 
-static void run_test(bool gen_cookies)
+static void run_test(struct test_btf_skc_cls_ingress *skel, bool gen_cookies)
 {
 	const char *tcp_syncookies = gen_cookies ? "2" : "1";
 	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
+	struct sockaddr_in6 srv_sa6;
 	socklen_t addrlen = sizeof(srv_sa6);
 	int srv_port;
 
@@ -84,58 +81,41 @@ static void run_test(bool gen_cookies)
 		return;
 
 	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
-	if (CHECK_FAIL(listen_fd == -1))
+	if (!ASSERT_OK_FD(listen_fd, "start server"))
 		return;
 
 	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
-	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
-		  errno))
+	if (!ASSERT_OK(err, "getsockname(listen_fd)"))
 		goto done;
 	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
 	srv_port = ntohs(srv_sa6.sin6_port);
 
 	cli_fd = connect_to_fd(listen_fd, 0);
-	if (CHECK_FAIL(cli_fd == -1))
+	if (!ASSERT_OK_FD(cli_fd, "connect client"))
 		goto done;
 
 	srv_fd = accept(listen_fd, NULL, NULL);
-	if (CHECK_FAIL(srv_fd == -1))
+	if (!ASSERT_OK_FD(srv_fd, "accept connection"))
 		goto done;
 
-	if (CHECK(skel->bss->listen_tp_sport != srv_port,
-		  "Unexpected listen tp src port",
-		  "listen_tp_sport:%u expected:%u\n",
-		  skel->bss->listen_tp_sport, srv_port))
-		goto done;
+	ASSERT_EQ(skel->bss->listen_tp_sport, srv_port, "listen tp src port");
 
 	if (!gen_cookies) {
-		if (CHECK(skel->bss->req_sk_sport != srv_port,
-			  "Unexpected req_sk src port",
-			  "req_sk_sport:%u expected:%u\n",
-			  skel->bss->req_sk_sport, srv_port))
-			goto done;
-		if (CHECK(skel->bss->gen_cookie || skel->bss->recv_cookie,
-			  "Unexpected syncookie states",
-			  "gen_cookie:%u recv_cookie:%u\n",
-			  skel->bss->gen_cookie, skel->bss->recv_cookie))
-			goto done;
+		ASSERT_EQ(skel->bss->req_sk_sport, srv_port,
+			  "request socket source port with syncookies disabled");
+		ASSERT_EQ(skel->bss->gen_cookie, 0,
+			  "generated syncookie with syncookies disabled");
+		ASSERT_EQ(skel->bss->recv_cookie, 0,
+			  "received syncookie with syncookies disabled");
 	} else {
-		if (CHECK(skel->bss->req_sk_sport,
-			  "Unexpected req_sk src port",
-			  "req_sk_sport:%u expected:0\n",
-			  skel->bss->req_sk_sport))
-			goto done;
-		if (CHECK(!skel->bss->gen_cookie ||
-			  skel->bss->gen_cookie != skel->bss->recv_cookie,
-			  "Unexpected syncookie states",
-			  "gen_cookie:%u recv_cookie:%u\n",
-			  skel->bss->gen_cookie, skel->bss->recv_cookie))
-			goto done;
+		ASSERT_EQ(skel->bss->req_sk_sport, 0,
+			  "request socket source port with syncookies enabled");
+		ASSERT_NEQ(skel->bss->gen_cookie, 0,
+			   "syncookie properly generated");
+		ASSERT_EQ(skel->bss->gen_cookie, skel->bss->recv_cookie,
+			  "matching syncookies on client and server");
 	}
 
-	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
-	      skel->bss->linum);
-
 done:
 	if (listen_fd != -1)
 		close(listen_fd);
@@ -145,19 +125,19 @@ done:
 		close(srv_fd);
 }
 
-static void test_conn(void)
+static void test_conn(struct test_btf_skc_cls_ingress *skel)
 {
-	run_test(false);
+	run_test(skel, false);
 }
 
-static void test_syncookie(void)
+static void test_syncookie(struct test_btf_skc_cls_ingress *skel)
 {
-	run_test(true);
+	run_test(skel, true);
 }
 
 struct test {
 	const char *desc;
-	void (*run)(void);
+	void (*run)(struct test_btf_skc_cls_ingress *skel);
 };
 
 #define DEF_TEST(name) { #name, test_##name }
@@ -168,25 +148,26 @@ static struct test tests[] = {
 
 void test_btf_skc_cls_ingress(void)
 {
+	struct test_btf_skc_cls_ingress *skel;
+	struct netns_obj *ns;
 	int i;
 
 	skel = test_btf_skc_cls_ingress__open_and_load();
-	struct netns_obj *ns;
-	if (CHECK(!skel, "test_btf_skc_cls_ingress__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(skel, "test_btf_skc_cls_ingress__open_and_load"))
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		if (!test__start_subtest(tests[i].desc))
 			continue;
 
-		ns = prepare_netns();
+		ns = prepare_netns(skel);
 		if (!ns)
 			break;
 
-		tests[i].run();
+		tests[i].run(skel);
 
-		print_err_line();
-		reset_test();
+		print_err_line(skel);
+		reset_test(skel);
 		netns_free(ns);
 	}
 
-- 
cgit v1.2.3


From 8a5cd986023547b3499072e17ff1ddae2c7c66a4 Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Sun, 20 Oct 2024 21:22:56 +0200
Subject: selftests/bpf: add ipv4 and dual ipv4/ipv6 support in
 btf_skc_cls_ingress
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

btf_skc_cls_ingress test currently checks that syncookie and
bpf_sk_assign/release helpers behave correctly in multiple scenarios,
but only with ipv6 socket.

Increase those helpers coverage by adding testing support for IPv4
sockets and IPv4/IPv6 sockets. The rework is mostly based on features
brought earlier in test_tcp_check_syncookie.sh to cover some fixes
performed on those helpers, but test_tcp_check_syncookie.sh is not
integrated in test_progs. The most notable changes linked to this are:
- some rework in the corresponding eBPF program to support both types of
  traffic
- the switch from start_server to start_server_str to allow to check
  some socket options
- the introduction of new subtests for ipv4 and ipv4/ipv6

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241020-syncookie-v2-4-2db240225fed@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 117 ++++++++++++++++++---
 .../selftests/bpf/progs/test_btf_skc_cls_ingress.c |  80 +++++++++-----
 2 files changed, 158 insertions(+), 39 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index 426c9d5402fa..29b946d84816 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -19,6 +19,15 @@
 
 #define TEST_NS "skc_cls_ingress"
 
+#define BIT(n)		(1 << (n))
+#define TEST_MODE_IPV4	BIT(0)
+#define TEST_MODE_IPV6	BIT(1)
+#define TEST_MODE_DUAL	(TEST_MODE_IPV4 | TEST_MODE_IPV6)
+
+#define SERVER_ADDR_IPV4	"127.0.0.1"
+#define SERVER_ADDR_IPV6	"::1"
+#define SERVER_ADDR_DUAL	"::0"
+
 static struct netns_obj *prepare_netns(struct test_btf_skc_cls_ingress *skel)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
@@ -55,6 +64,7 @@ free_ns:
 
 static void reset_test(struct test_btf_skc_cls_ingress *skel)
 {
+	memset(&skel->bss->srv_sa4, 0, sizeof(skel->bss->srv_sa4));
 	memset(&skel->bss->srv_sa6, 0, sizeof(skel->bss->srv_sa6));
 	skel->bss->listen_tp_sport = 0;
 	skel->bss->req_sk_sport = 0;
@@ -69,26 +79,85 @@ static void print_err_line(struct test_btf_skc_cls_ingress *skel)
 		printf("bpf prog error at line %u\n", skel->bss->linum);
 }
 
-static void run_test(struct test_btf_skc_cls_ingress *skel, bool gen_cookies)
+static int v6only_true(int fd, void *opts)
+{
+	int mode = true;
+
+	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
+}
+
+static int v6only_false(int fd, void *opts)
+{
+	int mode = false;
+
+	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
+}
+
+static void run_test(struct test_btf_skc_cls_ingress *skel, bool gen_cookies,
+		     int ip_mode)
 {
 	const char *tcp_syncookies = gen_cookies ? "2" : "1";
 	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
+	struct network_helper_opts opts = { 0 };
+	struct sockaddr_storage *addr;
 	struct sockaddr_in6 srv_sa6;
-	socklen_t addrlen = sizeof(srv_sa6);
+	struct sockaddr_in srv_sa4;
+	socklen_t addr_len;
+	int sock_family;
+	char *srv_addr;
 	int srv_port;
 
+	switch (ip_mode) {
+	case TEST_MODE_IPV4:
+		sock_family = AF_INET;
+		srv_addr = SERVER_ADDR_IPV4;
+		addr = (struct sockaddr_storage *)&srv_sa4;
+		addr_len = sizeof(srv_sa4);
+		break;
+	case TEST_MODE_IPV6:
+		opts.post_socket_cb = v6only_true;
+		sock_family = AF_INET6;
+		srv_addr = SERVER_ADDR_IPV6;
+		addr = (struct sockaddr_storage *)&srv_sa6;
+		addr_len = sizeof(srv_sa6);
+		break;
+	case TEST_MODE_DUAL:
+		opts.post_socket_cb = v6only_false;
+		sock_family = AF_INET6;
+		srv_addr = SERVER_ADDR_DUAL;
+		addr = (struct sockaddr_storage *)&srv_sa6;
+		addr_len = sizeof(srv_sa6);
+		break;
+	default:
+		PRINT_FAIL("Unknown IP mode %d", ip_mode);
+		return;
+	}
+
 	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", tcp_syncookies))
 		return;
 
-	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	listen_fd = start_server_str(sock_family, SOCK_STREAM, srv_addr,  0,
+				     &opts);
 	if (!ASSERT_OK_FD(listen_fd, "start server"))
 		return;
 
-	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
+	err = getsockname(listen_fd, (struct sockaddr *)addr, &addr_len);
 	if (!ASSERT_OK(err, "getsockname(listen_fd)"))
 		goto done;
-	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
-	srv_port = ntohs(srv_sa6.sin6_port);
+
+	switch (ip_mode) {
+	case TEST_MODE_IPV4:
+		memcpy(&skel->bss->srv_sa4, &srv_sa4, sizeof(srv_sa4));
+		srv_port = ntohs(srv_sa4.sin_port);
+		break;
+	case TEST_MODE_IPV6:
+	case TEST_MODE_DUAL:
+		memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
+		srv_port = ntohs(srv_sa6.sin6_port);
+		break;
+	default:
+		goto done;
+	}
 
 	cli_fd = connect_to_fd(listen_fd, 0);
 	if (!ASSERT_OK_FD(cli_fd, "connect client"))
@@ -125,14 +194,34 @@ done:
 		close(srv_fd);
 }
 
-static void test_conn(struct test_btf_skc_cls_ingress *skel)
+static void test_conn_ipv4(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, false, TEST_MODE_IPV4);
+}
+
+static void test_conn_ipv6(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, false, TEST_MODE_IPV6);
+}
+
+static void test_conn_dual(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, false, TEST_MODE_DUAL);
+}
+
+static void test_syncookie_ipv4(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, true, TEST_MODE_IPV4);
+}
+
+static void test_syncookie_ipv6(struct test_btf_skc_cls_ingress *skel)
 {
-	run_test(skel, false);
+	run_test(skel, true, TEST_MODE_IPV6);
 }
 
-static void test_syncookie(struct test_btf_skc_cls_ingress *skel)
+static void test_syncookie_dual(struct test_btf_skc_cls_ingress *skel)
 {
-	run_test(skel, true);
+	run_test(skel, true, TEST_MODE_DUAL);
 }
 
 struct test {
@@ -142,8 +231,12 @@ struct test {
 
 #define DEF_TEST(name) { #name, test_##name }
 static struct test tests[] = {
-	DEF_TEST(conn),
-	DEF_TEST(syncookie),
+	DEF_TEST(conn_ipv4),
+	DEF_TEST(conn_ipv6),
+	DEF_TEST(conn_dual),
+	DEF_TEST(syncookie_ipv4),
+	DEF_TEST(syncookie_ipv6),
+	DEF_TEST(syncookie_dual),
 };
 
 void test_btf_skc_cls_ingress(void)
diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
index f0759efff6ef..b38ca3c35994 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
@@ -10,6 +10,7 @@
 #endif
 
 struct sockaddr_in6 srv_sa6 = {};
+struct sockaddr_in srv_sa4 = {};
 __u16 listen_tp_sport = 0;
 __u16 req_sk_sport = 0;
 __u32 recv_cookie = 0;
@@ -18,8 +19,8 @@ __u32 linum = 0;
 
 #define LOG() ({ if (!linum) linum = __LINE__; })
 
-static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
-				  struct tcp_sock *tp,
+static void test_syncookie_helper(void *iphdr, int iphdr_size,
+				  struct tcphdr *th, struct tcp_sock *tp,
 				  struct __sk_buff *skb)
 {
 	if (th->syn) {
@@ -38,7 +39,7 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
 			return;
 		}
 
-		mss_cookie = bpf_tcp_gen_syncookie(tp, ip6h, sizeof(*ip6h),
+		mss_cookie = bpf_tcp_gen_syncookie(tp, iphdr, iphdr_size,
 						   th, 40);
 		if (mss_cookie < 0) {
 			if (mss_cookie != -ENOENT)
@@ -48,7 +49,7 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
 		}
 	} else if (gen_cookie) {
 		/* It was in cookie mode */
-		int ret = bpf_tcp_check_syncookie(tp, ip6h, sizeof(*ip6h),
+		int ret = bpf_tcp_check_syncookie(tp, iphdr, iphdr_size,
 						  th, sizeof(*th));
 
 		if (ret < 0) {
@@ -60,26 +61,58 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
 	}
 }
 
-static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb)
+static int handle_ip_tcp(struct ethhdr *eth, struct __sk_buff *skb)
 {
-	struct bpf_sock_tuple *tuple;
+	struct bpf_sock_tuple *tuple = NULL;
+	unsigned int tuple_len = 0;
 	struct bpf_sock *bpf_skc;
-	unsigned int tuple_len;
+	void *data_end, *iphdr;
+	struct ipv6hdr *ip6h;
+	struct iphdr *ip4h;
 	struct tcphdr *th;
-	void *data_end;
+	int iphdr_size;
 
 	data_end = (void *)(long)(skb->data_end);
 
-	th = (struct tcphdr *)(ip6h + 1);
-	if (th + 1 > data_end)
-		return TC_ACT_OK;
-
-	/* Is it the testing traffic? */
-	if (th->dest != srv_sa6.sin6_port)
+	switch (eth->h_proto) {
+	case bpf_htons(ETH_P_IP):
+		ip4h = (struct iphdr *)(eth + 1);
+		if (ip4h + 1 > data_end)
+			return TC_ACT_OK;
+		if (ip4h->protocol != IPPROTO_TCP)
+			return TC_ACT_OK;
+		th = (struct tcphdr *)(ip4h + 1);
+		if (th + 1 > data_end)
+			return TC_ACT_OK;
+		/* Is it the testing traffic? */
+		if (th->dest != srv_sa4.sin_port)
+			return TC_ACT_OK;
+		tuple_len = sizeof(tuple->ipv4);
+		tuple = (struct bpf_sock_tuple *)&ip4h->saddr;
+		iphdr = ip4h;
+		iphdr_size = sizeof(*ip4h);
+		break;
+	case bpf_htons(ETH_P_IPV6):
+		ip6h = (struct ipv6hdr *)(eth + 1);
+		if (ip6h + 1 > data_end)
+			return TC_ACT_OK;
+		if (ip6h->nexthdr != IPPROTO_TCP)
+			return TC_ACT_OK;
+		th = (struct tcphdr *)(ip6h + 1);
+		if (th + 1 > data_end)
+			return TC_ACT_OK;
+		/* Is it the testing traffic? */
+		if (th->dest != srv_sa6.sin6_port)
+			return TC_ACT_OK;
+		tuple_len = sizeof(tuple->ipv6);
+		tuple = (struct bpf_sock_tuple *)&ip6h->saddr;
+		iphdr = ip6h;
+		iphdr_size = sizeof(*ip6h);
+		break;
+	default:
 		return TC_ACT_OK;
+	}
 
-	tuple_len = sizeof(tuple->ipv6);
-	tuple = (struct bpf_sock_tuple *)&ip6h->saddr;
 	if ((void *)tuple + tuple_len > data_end) {
 		LOG();
 		return TC_ACT_OK;
@@ -126,7 +159,7 @@ static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb)
 
 		listen_tp_sport = tp->inet_conn.icsk_inet.sk.__sk_common.skc_num;
 
-		test_syncookie_helper(ip6h, th, tp, skb);
+		test_syncookie_helper(iphdr, iphdr_size, th, tp, skb);
 		bpf_sk_release(tp);
 		return TC_ACT_OK;
 	}
@@ -142,7 +175,6 @@ release:
 SEC("tc")
 int cls_ingress(struct __sk_buff *skb)
 {
-	struct ipv6hdr *ip6h;
 	struct ethhdr *eth;
 	void *data_end;
 
@@ -152,17 +184,11 @@ int cls_ingress(struct __sk_buff *skb)
 	if (eth + 1 > data_end)
 		return TC_ACT_OK;
 
-	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
-		return TC_ACT_OK;
-
-	ip6h = (struct ipv6hdr *)(eth + 1);
-	if (ip6h + 1 > data_end)
+	if (eth->h_proto != bpf_htons(ETH_P_IP) &&
+	    eth->h_proto != bpf_htons(ETH_P_IPV6))
 		return TC_ACT_OK;
 
-	if (ip6h->nexthdr == IPPROTO_TCP)
-		return handle_ip6_tcp(ip6h, skb);
-
-	return TC_ACT_OK;
+	return handle_ip_tcp(eth, skb);
 }
 
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 3845ce74777eeb94892cdeedaf4b76e2341f3f42 Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Sun, 20 Oct 2024 21:22:57 +0200
Subject: selftests/bpf: test MSS value returned with bpf_tcp_gen_syncookie
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

One remaining difference between test_tcp_check_syncookie.sh and
btf_skc_cls_ingress is a small test on the mss value embedded in the
cookie generated with the eBPF helper.

Bring the corresponding test in btf_skc_cls_ingress.

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241020-syncookie-v2-5-2db240225fed@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 7 +++++++
 tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c | 2 ++
 2 files changed, 9 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index 29b946d84816..cf15cc3be491 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -27,6 +27,8 @@
 #define SERVER_ADDR_IPV4	"127.0.0.1"
 #define SERVER_ADDR_IPV6	"::1"
 #define SERVER_ADDR_DUAL	"::0"
+/* RFC791, 576 for minimal IPv4 datagram, minus 40 bytes of TCP header */
+#define MIN_IPV4_MSS		536
 
 static struct netns_obj *prepare_netns(struct test_btf_skc_cls_ingress *skel)
 {
@@ -71,6 +73,7 @@ static void reset_test(struct test_btf_skc_cls_ingress *skel)
 	skel->bss->recv_cookie = 0;
 	skel->bss->gen_cookie = 0;
 	skel->bss->linum = 0;
+	skel->bss->mss = 0;
 }
 
 static void print_err_line(struct test_btf_skc_cls_ingress *skel)
@@ -183,6 +186,10 @@ static void run_test(struct test_btf_skc_cls_ingress *skel, bool gen_cookies,
 			   "syncookie properly generated");
 		ASSERT_EQ(skel->bss->gen_cookie, skel->bss->recv_cookie,
 			  "matching syncookies on client and server");
+		ASSERT_GT(skel->bss->mss, MIN_IPV4_MSS,
+			  "MSS in cookie min value");
+		ASSERT_LT(skel->bss->mss, USHRT_MAX,
+			  "MSS in cookie max value");
 	}
 
 done:
diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
index b38ca3c35994..1cd1a1b72cb5 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
@@ -15,6 +15,7 @@ __u16 listen_tp_sport = 0;
 __u16 req_sk_sport = 0;
 __u32 recv_cookie = 0;
 __u32 gen_cookie = 0;
+__u32 mss = 0;
 __u32 linum = 0;
 
 #define LOG() ({ if (!linum) linum = __LINE__; })
@@ -46,6 +47,7 @@ static void test_syncookie_helper(void *iphdr, int iphdr_size,
 				LOG();
 		} else {
 			gen_cookie = (__u32)mss_cookie;
+			mss = mss_cookie >> 32;
 		}
 	} else if (gen_cookie) {
 		/* It was in cookie mode */
-- 
cgit v1.2.3


From c3566ee6c66c3d6113739ec00cda7e23f39a3744 Mon Sep 17 00:00:00 2001
From: "Alexis Lothoré (eBPF Foundation)" <alexis.lothore@bootlin.com>
Date: Sun, 20 Oct 2024 21:22:58 +0200
Subject: selftests/bpf: remove test_tcp_check_syncookie
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that btf_skc_cls_ingress has the same coverage as
test_tcp_check_syncookie, remove the second one and keep the first one
as it is integrated in test_progs

Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore@bootlin.com>
Link: https://lore.kernel.org/r/20241020-syncookie-v2-6-2db240225fed@bootlin.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore             |   1 -
 tools/testing/selftests/bpf/Makefile               |   9 +-
 .../bpf/progs/test_tcp_check_syncookie_kern.c      | 167 ----------------
 .../selftests/bpf/test_tcp_check_syncookie.sh      |  85 --------
 .../selftests/bpf/test_tcp_check_syncookie_user.c  | 213 ---------------------
 5 files changed, 3 insertions(+), 472 deletions(-)
 delete mode 100644 tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
 delete mode 100755 tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
 delete mode 100644 tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index e6533b3400de..7e88551f2d38 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -24,7 +24,6 @@ test_flow_dissector
 flow_dissector_load
 test_tcpnotify_user
 test_libbpf
-test_tcp_check_syncookie_user
 test_sysctl
 xdping
 test_cpp
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f04af11df8eb..46924f406d06 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -137,7 +137,6 @@ TEST_PROGS := test_kmod.sh \
 	test_xdp_vlan_mode_generic.sh \
 	test_xdp_vlan_mode_native.sh \
 	test_lwt_ip_encap.sh \
-	test_tcp_check_syncookie.sh \
 	test_tc_tunnel.sh \
 	test_tc_edt.sh \
 	test_xdping.sh \
@@ -154,10 +153,9 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = \
-	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
-	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
-	xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
-	xdp_features bpf_test_no_cfi.ko
+	flow_dissector_load test_flow_dissector	test_lirc_mode2_user xdping \
+	test_cpp runqslower bench bpf_testmod.ko xskxceiver xdp_redirect_multi \
+	xdp_synproxy veristat xdp_hw_metadata xdp_features bpf_test_no_cfi.ko
 
 TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi
 
@@ -347,7 +345,6 @@ $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS)
 $(OUTPUT)/test_maps: $(TESTING_HELPERS)
 $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(UNPRIV_HELPERS)
 $(OUTPUT)/xsk.o: $(BPFOBJ)
-$(OUTPUT)/test_tcp_check_syncookie_user: $(NETWORK_HELPERS)
 
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
 $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
deleted file mode 100644
index 6edebce563b5..000000000000
--- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
+++ /dev/null
@@ -1,167 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-// Copyright (c) 2019 Cloudflare
-
-#include <string.h>
-
-#include <linux/bpf.h>
-#include <linux/pkt_cls.h>
-#include <linux/if_ether.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <sys/socket.h>
-#include <linux/tcp.h>
-
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_endian.h>
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, __u32);
-	__type(value, __u32);
-	__uint(max_entries, 3);
-} results SEC(".maps");
-
-static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk,
-					   void *iph, __u32 ip_size,
-					   struct tcphdr *tcph)
-{
-	__u32 thlen = tcph->doff * 4;
-
-	if (tcph->syn && !tcph->ack) {
-		// packet should only have an MSS option
-		if (thlen != 24)
-			return 0;
-
-		if ((void *)tcph + thlen > data_end)
-			return 0;
-
-		return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen);
-	}
-	return 0;
-}
-
-static __always_inline void check_syncookie(void *ctx, void *data,
-					    void *data_end)
-{
-	struct bpf_sock_tuple tup;
-	struct bpf_sock *sk;
-	struct ethhdr *ethh;
-	struct iphdr *ipv4h;
-	struct ipv6hdr *ipv6h;
-	struct tcphdr *tcph;
-	int ret;
-	__u32 key_mss = 2;
-	__u32 key_gen = 1;
-	__u32 key = 0;
-	__s64 seq_mss;
-
-	ethh = data;
-	if (ethh + 1 > data_end)
-		return;
-
-	switch (bpf_ntohs(ethh->h_proto)) {
-	case ETH_P_IP:
-		ipv4h = data + sizeof(struct ethhdr);
-		if (ipv4h + 1 > data_end)
-			return;
-
-		if (ipv4h->ihl != 5)
-			return;
-
-		tcph = data + sizeof(struct ethhdr) + sizeof(struct iphdr);
-		if (tcph + 1 > data_end)
-			return;
-
-		tup.ipv4.saddr = ipv4h->saddr;
-		tup.ipv4.daddr = ipv4h->daddr;
-		tup.ipv4.sport = tcph->source;
-		tup.ipv4.dport = tcph->dest;
-
-		sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv4),
-					BPF_F_CURRENT_NETNS, 0);
-		if (!sk)
-			return;
-
-		if (sk->state != BPF_TCP_LISTEN)
-			goto release;
-
-		seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h),
-					tcph);
-
-		ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h),
-					      tcph, sizeof(*tcph));
-		break;
-
-	case ETH_P_IPV6:
-		ipv6h = data + sizeof(struct ethhdr);
-		if (ipv6h + 1 > data_end)
-			return;
-
-		if (ipv6h->nexthdr != IPPROTO_TCP)
-			return;
-
-		tcph = data + sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
-		if (tcph + 1 > data_end)
-			return;
-
-		memcpy(tup.ipv6.saddr, &ipv6h->saddr, sizeof(tup.ipv6.saddr));
-		memcpy(tup.ipv6.daddr, &ipv6h->daddr, sizeof(tup.ipv6.daddr));
-		tup.ipv6.sport = tcph->source;
-		tup.ipv6.dport = tcph->dest;
-
-		sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv6),
-					BPF_F_CURRENT_NETNS, 0);
-		if (!sk)
-			return;
-
-		if (sk->state != BPF_TCP_LISTEN)
-			goto release;
-
-		seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h),
-					tcph);
-
-		ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h),
-					      tcph, sizeof(*tcph));
-		break;
-
-	default:
-		return;
-	}
-
-	if (seq_mss > 0) {
-		__u32 cookie = (__u32)seq_mss;
-		__u32 mss = seq_mss >> 32;
-
-		bpf_map_update_elem(&results, &key_gen, &cookie, 0);
-		bpf_map_update_elem(&results, &key_mss, &mss, 0);
-	}
-
-	if (ret == 0) {
-		__u32 cookie = bpf_ntohl(tcph->ack_seq) - 1;
-
-		bpf_map_update_elem(&results, &key, &cookie, 0);
-	}
-
-release:
-	bpf_sk_release(sk);
-}
-
-SEC("tc")
-int check_syncookie_clsact(struct __sk_buff *skb)
-{
-	check_syncookie(skb, (void *)(long)skb->data,
-			(void *)(long)skb->data_end);
-	return TC_ACT_OK;
-}
-
-SEC("xdp")
-int check_syncookie_xdp(struct xdp_md *ctx)
-{
-	check_syncookie(ctx, (void *)(long)ctx->data,
-			(void *)(long)ctx->data_end);
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
deleted file mode 100755
index b42c24282c25..000000000000
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
+++ /dev/null
@@ -1,85 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Copyright (c) 2018 Facebook
-# Copyright (c) 2019 Cloudflare
-
-set -eu
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-
-wait_for_ip()
-{
-	local _i
-	printf "Wait for IP %s to become available " "$1"
-	for _i in $(seq ${MAX_PING_TRIES}); do
-		printf "."
-		if ns1_exec ping -c 1 -W 1 "$1" >/dev/null 2>&1; then
-			echo " OK"
-			return
-		fi
-		sleep 1
-	done
-	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
-	exit 1
-}
-
-get_prog_id()
-{
-	awk '/ id / {sub(/.* id /, "", $0); print($1)}'
-}
-
-ns1_exec()
-{
-	ip netns exec ${NS1} "$@"
-}
-
-setup()
-{
-	ip netns add ${NS1}
-	ns1_exec ip link set lo up
-
-	ns1_exec sysctl -w net.ipv4.tcp_syncookies=2
-	ns1_exec sysctl -w net.ipv4.tcp_window_scaling=0
-	ns1_exec sysctl -w net.ipv4.tcp_timestamps=0
-	ns1_exec sysctl -w net.ipv4.tcp_sack=0
-
-	wait_for_ip 127.0.0.1
-	wait_for_ip ::1
-}
-
-cleanup()
-{
-	ip netns del ns1 2>/dev/null || :
-}
-
-main()
-{
-	trap cleanup EXIT 2 3 6 15
-	setup
-
-	printf "Testing clsact..."
-	ns1_exec tc qdisc add dev "${TEST_IF}" clsact
-	ns1_exec tc filter add dev "${TEST_IF}" ingress \
-		bpf obj "${BPF_PROG_OBJ}" sec "${CLSACT_SECTION}" da
-
-	BPF_PROG_ID=$(ns1_exec tc filter show dev "${TEST_IF}" ingress | \
-		      get_prog_id)
-	ns1_exec "${PROG}" "${BPF_PROG_ID}"
-	ns1_exec tc qdisc del dev "${TEST_IF}" clsact
-
-	printf "Testing XDP..."
-	ns1_exec ip link set "${TEST_IF}" xdp \
-		object "${BPF_PROG_OBJ}" section "${XDP_SECTION}"
-	BPF_PROG_ID=$(ns1_exec ip link show "${TEST_IF}" | get_prog_id)
-	ns1_exec "${PROG}" "${BPF_PROG_ID}"
-}
-
-DIR=$(dirname $0)
-TEST_IF=lo
-MAX_PING_TRIES=5
-BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.bpf.o"
-CLSACT_SECTION="tc"
-XDP_SECTION="xdp"
-BPF_PROG_ID=0
-PROG="${DIR}/test_tcp_check_syncookie_user"
-
-main
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
deleted file mode 100644
index 3844f9b8232a..000000000000
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
+++ /dev/null
@@ -1,213 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-// Copyright (c) 2019 Cloudflare
-
-#include <limits.h>
-#include <string.h>
-#include <stdlib.h>
-#include <unistd.h>
-
-#include <arpa/inet.h>
-#include <netinet/in.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "network_helpers.h"
-
-static int get_map_fd_by_prog_id(int prog_id, bool *xdp)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 map_ids[1];
-	int prog_fd = -1;
-	int map_fd = -1;
-
-	prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (prog_fd < 0) {
-		log_err("Failed to get fd by prog id %d", prog_id);
-		goto err;
-	}
-
-	info.nr_map_ids = 1;
-	info.map_ids = (__u64)(unsigned long)map_ids;
-
-	if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) {
-		log_err("Failed to get info by prog fd %d", prog_fd);
-		goto err;
-	}
-
-	if (!info.nr_map_ids) {
-		log_err("No maps found for prog fd %d", prog_fd);
-		goto err;
-	}
-
-	*xdp = info.type == BPF_PROG_TYPE_XDP;
-
-	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
-	if (map_fd < 0)
-		log_err("Failed to get fd by map id %d", map_ids[0]);
-err:
-	if (prog_fd >= 0)
-		close(prog_fd);
-	return map_fd;
-}
-
-static int run_test(int server_fd, int results_fd, bool xdp)
-{
-	int client = -1, srv_client = -1;
-	int ret = 0;
-	__u32 key = 0;
-	__u32 key_gen = 1;
-	__u32 key_mss = 2;
-	__u32 value = 0;
-	__u32 value_gen = 0;
-	__u32 value_mss = 0;
-
-	if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) {
-		log_err("Can't clear results");
-		goto err;
-	}
-
-	if (bpf_map_update_elem(results_fd, &key_gen, &value_gen, 0) < 0) {
-		log_err("Can't clear results");
-		goto err;
-	}
-
-	if (bpf_map_update_elem(results_fd, &key_mss, &value_mss, 0) < 0) {
-		log_err("Can't clear results");
-		goto err;
-	}
-
-	client = connect_to_fd(server_fd, 0);
-	if (client == -1)
-		goto err;
-
-	srv_client = accept(server_fd, NULL, 0);
-	if (srv_client == -1) {
-		log_err("Can't accept connection");
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(results_fd, &key, &value) < 0) {
-		log_err("Can't lookup result");
-		goto err;
-	}
-
-	if (value == 0) {
-		log_err("Didn't match syncookie: %u", value);
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(results_fd, &key_gen, &value_gen) < 0) {
-		log_err("Can't lookup result");
-		goto err;
-	}
-
-	if (xdp && value_gen == 0) {
-		// SYN packets do not get passed through generic XDP, skip the
-		// rest of the test.
-		printf("Skipping XDP cookie check\n");
-		goto out;
-	}
-
-	if (bpf_map_lookup_elem(results_fd, &key_mss, &value_mss) < 0) {
-		log_err("Can't lookup result");
-		goto err;
-	}
-
-	if (value != value_gen) {
-		log_err("BPF generated cookie does not match kernel one");
-		goto err;
-	}
-
-	if (value_mss < 536 || value_mss > USHRT_MAX) {
-		log_err("Unexpected MSS retrieved");
-		goto err;
-	}
-
-	goto out;
-
-err:
-	ret = 1;
-out:
-	close(client);
-	close(srv_client);
-	return ret;
-}
-
-static int v6only_true(int fd, void *opts)
-{
-	int mode = true;
-
-	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
-}
-
-static int v6only_false(int fd, void *opts)
-{
-	int mode = false;
-
-	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
-}
-
-int main(int argc, char **argv)
-{
-	struct network_helper_opts opts = { 0 };
-	int server = -1;
-	int server_v6 = -1;
-	int server_dual = -1;
-	int results = -1;
-	int err = 0;
-	bool xdp;
-
-	if (argc < 2) {
-		fprintf(stderr, "Usage: %s prog_id\n", argv[0]);
-		exit(1);
-	}
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	results = get_map_fd_by_prog_id(atoi(argv[1]), &xdp);
-	if (results < 0) {
-		log_err("Can't get map");
-		goto err;
-	}
-
-	server = start_server_str(AF_INET, SOCK_STREAM, "127.0.0.1", 0, NULL);
-	if (server == -1)
-		goto err;
-
-	opts.post_socket_cb = v6only_true;
-	server_v6 = start_server_str(AF_INET6, SOCK_STREAM, "::1", 0, &opts);
-	if (server_v6 == -1)
-		goto err;
-
-	opts.post_socket_cb = v6only_false;
-	server_dual = start_server_str(AF_INET6, SOCK_STREAM, "::0", 0, &opts);
-	if (server_dual == -1)
-		goto err;
-
-	if (run_test(server, results, xdp))
-		goto err;
-
-	if (run_test(server_v6, results, xdp))
-		goto err;
-
-	if (run_test(server_dual, results, xdp))
-		goto err;
-
-	printf("ok\n");
-	goto out;
-err:
-	err = 1;
-out:
-	close(server);
-	close(server_v6);
-	close(server_dual);
-	close(results);
-	return err;
-}
-- 
cgit v1.2.3


From a6e263f125cd7b10614a83159c453c061dbf6877 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:43 +0200
Subject: selftests: net: lib: Introduce deferred commands

In commit 8510801a9dbd ("selftests: drv-net: add ability to schedule
cleanup with defer()"), a defer helper was added to Python selftests.
The idea is to keep cleanup commands close to their dirtying counterparts,
thereby making it more transparent what is cleaning up what, making it
harder to miss a cleanup, and make the whole cleanup business exception
safe. All these benefits are applicable to bash as well, exception safety
can be interpreted in terms of safety vs. a SIGINT.

This patch therefore introduces a framework of several helpers that serve
to schedule cleanups in bash selftests:

- defer_scope_push(), defer_scope_pop(): Deferred statements can be batched
  together in scopes. When a scope is popped, the deferred commands
  scheduled in that scope are executed in the order opposite to order of
  their scheduling.

- defer(): Schedules a defer to the most recently pushed scope (or the
  default scope if none was pushed.)

- defer_prio(): Schedules a defer on the priority track. The priority defer
  queue is run before the default defer queue when scope is popped.

  The issue that this is addressing is specifically the one of restoring
  devlink shared buffer threshold type. When setting up static thresholds,
  one has to first change the threshold type to static, then override the
  individual thresholds. When cleaning up, it would be natural to reset the
  threshold values first, then change the threshold type. But the values
  that are valid for dynamic thresholds are generally invalid for static
  thresholds and vice versa. Attempts to restore the values first would be
  bounced. Thus one has to first reset the threshold type, then adjust the
  thresholds.

  (You could argue that the shared buffer threshold type API is broken and
  you would be right, but here we are.)

  This cannot be solved by pure defers easily. I considered making it
  possible to disable an existing defer, so that one could then schedule a
  new defer and disable the original. But this forward-shifting of the
  defer job would have to take place after every threshold-adjusting
  command, which would make it very awkward to schedule these jobs.

- defer_scopes_cleanup(): Pops any unpopped scopes, including the default
  one. The selftests that use defer should run this in their exit trap.
  This is important to get cleanups of interrupted scripts.

- in_defer_scope(): Sometimes a function would like to introduce a new
  defer scope, then run whatever it is that it wants to run, and then pop
  the scope to run the deferred cleanups. The helper in_defer_scope() can
  be used to run another command within such environment, such that any
  scheduled defers run after the command finishes.

The framework is added as a separate file lib/sh/defer.sh so that it can be
used by all bash selftests, including those that do not currently use
lib.sh. lib.sh however includes the file by default, because ideally all
tests would use these helpers instead of hand-rolling their cleanups.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/forwarding/lib.sh |   3 +-
 tools/testing/selftests/net/lib.sh            |   3 +
 tools/testing/selftests/net/lib/Makefile      |   2 +-
 tools/testing/selftests/net/lib/sh/defer.sh   | 115 ++++++++++++++++++++++++++
 4 files changed, 121 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/net/lib/sh/defer.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index c992e385159c..d24b6af7ebfa 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1403,7 +1403,8 @@ tests_run()
 	local current_test
 
 	for current_test in ${TESTS:-$ALL_TESTS}; do
-		$current_test
+		in_defer_scope \
+			$current_test
 	done
 }
 
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index be8707bfb46e..c8991cc6bf28 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -1,6 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+net_dir=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+source "$net_dir/lib/sh/defer.sh"
+
 ##############################################################################
 # Defines
 
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index 82c3264b115e..18b9443454a9 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -10,6 +10,6 @@ TEST_FILES += ../../../../net/ynl
 
 TEST_GEN_FILES += csum
 
-TEST_INCLUDES := $(wildcard py/*.py)
+TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/net/lib/sh/defer.sh b/tools/testing/selftests/net/lib/sh/defer.sh
new file mode 100644
index 000000000000..082f5d38321b
--- /dev/null
+++ b/tools/testing/selftests/net/lib/sh/defer.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# map[(scope_id,track,cleanup_id) -> cleanup_command]
+# track={d=default | p=priority}
+declare -A __DEFER__JOBS
+
+# map[(scope_id,track) -> # cleanup_commands]
+declare -A __DEFER__NJOBS
+
+# scope_id of the topmost scope.
+__DEFER__SCOPE_ID=0
+
+__defer__ndefer_key()
+{
+	local track=$1; shift
+
+	echo $__DEFER__SCOPE_ID,$track
+}
+
+__defer__defer_key()
+{
+	local track=$1; shift
+	local defer_ix=$1; shift
+
+	echo $__DEFER__SCOPE_ID,$track,$defer_ix
+}
+
+__defer__ndefers()
+{
+	local track=$1; shift
+
+	echo ${__DEFER__NJOBS[$(__defer__ndefer_key $track)]}
+}
+
+__defer__run()
+{
+	local track=$1; shift
+	local defer_ix=$1; shift
+	local defer_key=$(__defer__defer_key $track $defer_ix)
+
+	${__DEFER__JOBS[$defer_key]}
+	unset __DEFER__JOBS[$defer_key]
+}
+
+__defer__schedule()
+{
+	local track=$1; shift
+	local ndefers=$(__defer__ndefers $track)
+	local ndefers_key=$(__defer__ndefer_key $track)
+	local defer_key=$(__defer__defer_key $track $ndefers)
+	local defer="$@"
+
+	__DEFER__JOBS[$defer_key]="$defer"
+	__DEFER__NJOBS[$ndefers_key]=$((ndefers + 1))
+}
+
+__defer__scope_wipe()
+{
+	__DEFER__NJOBS[$(__defer__ndefer_key d)]=0
+	__DEFER__NJOBS[$(__defer__ndefer_key p)]=0
+}
+
+defer_scope_push()
+{
+	((__DEFER__SCOPE_ID++))
+	__defer__scope_wipe
+}
+
+defer_scope_pop()
+{
+	local defer_ix
+
+	for ((defer_ix=$(__defer__ndefers p); defer_ix-->0; )); do
+		__defer__run p $defer_ix
+	done
+
+	for ((defer_ix=$(__defer__ndefers d); defer_ix-->0; )); do
+		__defer__run d $defer_ix
+	done
+
+	__defer__scope_wipe
+	((__DEFER__SCOPE_ID--))
+}
+
+defer()
+{
+	__defer__schedule d "$@"
+}
+
+defer_prio()
+{
+	__defer__schedule p "$@"
+}
+
+defer_scopes_cleanup()
+{
+	while ((__DEFER__SCOPE_ID >= 0)); do
+		defer_scope_pop
+	done
+}
+
+in_defer_scope()
+{
+	local ret
+
+	defer_scope_push
+	"$@"
+	ret=$?
+	defer_scope_pop
+
+	return $ret
+}
+
+__defer__scope_wipe
-- 
cgit v1.2.3


From b4b0549a4e59747b49619b2edabfb0d04e37c0b9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:44 +0200
Subject: selftests: forwarding: Add a fallback cleanup()

Consistent use of defers obviates the need for a separate test-specific
cleanup function -- everything is just taken care of in defers. So in this
patch, introduce a cleanup() helper in the forwarding lib.sh, which calls
just pre_cleanup() and defer_scopes_cleanup(). Selftests are obviously
still free to override the function.

Since pre_cleanup() is too entangled with forwarding-specific minutia, the
function cannot currently be in net/lib.sh.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/forwarding/lib.sh | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index d24b6af7ebfa..76e6d7698caf 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1408,6 +1408,12 @@ tests_run()
 	done
 }
 
+cleanup()
+{
+	pre_cleanup
+	defer_scopes_cleanup
+}
+
 multipath_eval()
 {
 	local desc="$1"
-- 
cgit v1.2.3


From 0e07d5dbfbd9b0441ae4ec07a2a72738121356e2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:45 +0200
Subject: selftests: forwarding: lib: Allow passing PID to stop_traffic()

Now that it is possible to schedule a deferral of stop_traffic() right
after the traffic is started, we do not have to rely on the %% magic to
kill the background process that was started last. Instead we can just give
the PID explicitly. This makes it possible to start other background
processes after the traffic is started without confusing the cleanup.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/forwarding/lib.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 76e6d7698caf..89c25f72b10c 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1768,8 +1768,10 @@ start_tcp_traffic()
 
 stop_traffic()
 {
+	local pid=${1-%%}; shift
+
 	# Suppress noise from killing mausezahn.
-	{ kill %% && wait %%; } 2>/dev/null
+	{ kill $pid && wait $pid; } 2>/dev/null
 }
 
 declare -A cappid
-- 
cgit v1.2.3


From 7f46615d59373b65dcd0fea7784bf20f93c169f0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:46 +0200
Subject: selftests: RED: Use defer for test cleanup

Instead of having a suite of dedicated cleanup functions, use the defer
framework to schedule cleanups right as their setup functions are run.

The sleep after stop_traffic() in mlxsw selftests is necessary, but
scheduling it as "defer sleep; defer stop_traffic" is silly. Instead, add a
local helper to stop traffic and sleep afterwards.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/mlxsw/sch_red_core.sh    | 185 ++++++++++-----------
 .../selftests/drivers/net/mlxsw/sch_red_ets.sh     |  24 +--
 .../selftests/drivers/net/mlxsw/sch_red_root.sh    |  18 +-
 tools/testing/selftests/net/forwarding/sch_red.sh  | 103 +++++-------
 4 files changed, 149 insertions(+), 181 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index f4c324957dcc..537d6baa77b7 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -75,6 +75,18 @@ source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
 source mlxsw_lib.sh
 
+stop_traffic_sleep()
+{
+	local pid=$1; shift
+
+	# Issuing a kill still leaves a bunch of packets lingering in the
+	# buffers. This traffic then arrives at the point where a follow-up test
+	# is already running, and can confuse the test. Therefore sleep after
+	# stopping traffic to flush any leftover packets.
+	stop_traffic "$pid"
+	sleep 1
+}
+
 ipaddr()
 {
 	local host=$1; shift
@@ -89,39 +101,31 @@ host_create()
 	local host=$1; shift
 
 	simple_if_init $dev
+	defer simple_if_fini $dev
+
 	mtu_set $dev 10000
+	defer mtu_restore $dev
 
 	vlan_create $dev 10 v$dev $(ipaddr $host 10)/28
+	defer vlan_destroy $dev 10
 	ip link set dev $dev.10 type vlan egress 0:0
 
 	vlan_create $dev 11 v$dev $(ipaddr $host 11)/28
+	defer vlan_destroy $dev 11
 	ip link set dev $dev.11 type vlan egress 0:1
 }
 
-host_destroy()
-{
-	local dev=$1; shift
-
-	vlan_destroy $dev 11
-	vlan_destroy $dev 10
-	mtu_restore $dev
-	simple_if_fini $dev
-}
-
 h1_create()
 {
 	host_create $h1 1
 }
 
-h1_destroy()
-{
-	host_destroy $h1
-}
-
 h2_create()
 {
 	host_create $h2 2
+
 	tc qdisc add dev $h2 clsact
+	defer tc qdisc del dev $h2 clsact
 
 	# Some of the tests in this suite use multicast traffic. As this traffic
 	# enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus
@@ -139,13 +143,7 @@ h2_create()
 
 	tc qdisc replace dev $h2 root handle 10: tbf rate 200mbit \
 		burst 128K limit 1G
-}
-
-h2_destroy()
-{
-	tc qdisc del dev $h2 root handle 10:
-	tc qdisc del dev $h2 clsact
-	host_destroy $h2
+	defer tc qdisc del dev $h2 root handle 10:
 }
 
 h3_create()
@@ -153,40 +151,54 @@ h3_create()
 	host_create $h3 3
 }
 
-h3_destroy()
-{
-	host_destroy $h3
-}
-
 switch_create()
 {
 	local intf
 	local vlan
 
 	ip link add dev br1_10 type bridge
+	defer ip link del dev br1_10
+
 	ip link add dev br1_11 type bridge
+	defer ip link del dev br1_11
 
 	ip link add dev br2_10 type bridge
+	defer ip link del dev br2_10
+
 	ip link add dev br2_11 type bridge
+	defer ip link del dev br2_11
 
 	for intf in $swp1 $swp2 $swp3 $swp4 $swp5; do
 		ip link set dev $intf up
+		defer ip link set dev $intf down
+
 		mtu_set $intf 10000
+		defer mtu_restore $intf
 	done
 
 	for intf in $swp1 $swp4; do
 		for vlan in 10 11; do
 			vlan_create $intf $vlan
+			defer vlan_destroy $intf $vlan
+
 			ip link set dev $intf.$vlan master br1_$vlan
+			defer ip link set dev $intf.$vlan nomaster
+
 			ip link set dev $intf.$vlan up
+			defer ip link set dev $intf.$vlan up
 		done
 	done
 
 	for intf in $swp2 $swp3 $swp5; do
 		for vlan in 10 11; do
 			vlan_create $intf $vlan
+			defer vlan_destroy $intf $vlan
+
 			ip link set dev $intf.$vlan master br2_$vlan
+			defer ip link set dev $intf.$vlan nomaster
+
 			ip link set dev $intf.$vlan up
+			defer ip link set dev $intf.$vlan up
 		done
 	done
 
@@ -201,49 +213,25 @@ switch_create()
 	for intf in $swp3 $swp4; do
 		tc qdisc replace dev $intf root handle 1: tbf rate 200mbit \
 			burst 128K limit 1G
+		defer tc qdisc del dev $intf root handle 1:
 	done
 
 	ip link set dev br1_10 up
+	defer ip link set dev br1_10 down
+
 	ip link set dev br1_11 up
+	defer ip link set dev br1_11 down
+
 	ip link set dev br2_10 up
+	defer ip link set dev br2_10 down
+
 	ip link set dev br2_11 up
+	defer ip link set dev br2_11 down
 
 	local size=$(devlink_pool_size_thtype 0 | cut -d' ' -f 1)
 	devlink_port_pool_th_save $swp3 8
 	devlink_port_pool_th_set $swp3 8 $size
-}
-
-switch_destroy()
-{
-	local intf
-	local vlan
-
-	devlink_port_pool_th_restore $swp3 8
-
-	ip link set dev br2_11 down
-	ip link set dev br2_10 down
-	ip link set dev br1_11 down
-	ip link set dev br1_10 down
-
-	for intf in $swp4 $swp3; do
-		tc qdisc del dev $intf root handle 1:
-	done
-
-	for intf in $swp5 $swp3 $swp2 $swp4 $swp1; do
-		for vlan in 11 10; do
-			ip link set dev $intf.$vlan down
-			ip link set dev $intf.$vlan nomaster
-			vlan_destroy $intf $vlan
-		done
-
-		mtu_restore $intf
-		ip link set dev $intf down
-	done
-
-	ip link del dev br2_11
-	ip link del dev br2_10
-	ip link del dev br1_11
-	ip link del dev br1_10
+	defer devlink_port_pool_th_restore $swp3 8
 }
 
 setup_prepare()
@@ -263,6 +251,7 @@ setup_prepare()
 	h3_mac=$(mac_get $h3)
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
@@ -270,18 +259,6 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1.10 $(ipaddr 3 10) " from host 1, vlan 10"
@@ -450,6 +427,7 @@ __do_ecn_test()
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 	sleep 1
 
 	ecn_test_common "$name" "$get_nmarked" $vlan $limit
@@ -461,9 +439,6 @@ __do_ecn_test()
 	build_backlog $vlan $((2 * limit)) udp >/dev/null
 	check_fail $? "UDP traffic went into backlog instead of being early-dropped"
 	log_test "TC $((vlan - 10)): $name backlog > limit: UDP early-dropped"
-
-	stop_traffic
-	sleep 1
 }
 
 do_ecn_test()
@@ -471,7 +446,8 @@ do_ecn_test()
 	local vlan=$1; shift
 	local limit=$1; shift
 
-	__do_ecn_test get_nmarked "$vlan" "$limit"
+	in_defer_scope \
+		__do_ecn_test get_nmarked "$vlan" "$limit"
 }
 
 do_ecn_test_perband()
@@ -480,10 +456,11 @@ do_ecn_test_perband()
 	local limit=$1; shift
 
 	mlxsw_only_on_spectrum 3+ || return
-	__do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN"
+	in_defer_scope \
+		__do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN"
 }
 
-do_ecn_nodrop_test()
+__do_ecn_nodrop_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -491,6 +468,7 @@ do_ecn_nodrop_test()
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 	sleep 1
 
 	ecn_test_common "$name" get_nmarked $vlan $limit
@@ -502,12 +480,15 @@ do_ecn_nodrop_test()
 	build_backlog $vlan $((2 * limit)) udp >/dev/null
 	check_err $? "UDP traffic was early-dropped instead of getting into backlog"
 	log_test "TC $((vlan - 10)): $name backlog > limit: UDP not dropped"
+}
 
-	stop_traffic
-	sleep 1
+do_ecn_nodrop_test()
+{
+	in_defer_scope \
+		__do_ecn_nodrop_test "$@"
 }
 
-do_red_test()
+__do_red_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -518,6 +499,7 @@ do_red_test()
 	# is above limit.
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 
 	# Pushing below the queue limit should work.
 	RET=0
@@ -539,12 +521,15 @@ do_red_test()
 	((-15 <= pct && pct <= 15))
 	check_err $? "backlog $backlog / $limit expected <= 15% distance"
 	log_test "TC $((vlan - 10)): RED backlog > limit"
+}
 
-	stop_traffic
-	sleep 1
+do_red_test()
+{
+	in_defer_scope \
+		__do_red_test "$@"
 }
 
-do_mc_backlog_test()
+__do_mc_backlog_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -554,7 +539,10 @@ do_mc_backlog_test()
 	RET=0
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) bc
+	defer stop_traffic_sleep $!
+
 	start_tcp_traffic $h2.$vlan $(ipaddr 2 $vlan) $(ipaddr 3 $vlan) bc
+	defer stop_traffic_sleep $!
 
 	qbl=$(busywait 5000 until_counter_is ">= 500000" \
 		       get_qdisc_backlog $vlan)
@@ -567,13 +555,16 @@ do_mc_backlog_test()
 		       get_mc_transmit_queue $vlan)
 	check_err $? "MC backlog reported by qdisc not visible in ethtool"
 
-	stop_traffic
-	stop_traffic
-
 	log_test "TC $((vlan - 10)): Qdisc reports MC backlog"
 }
 
-do_mark_test()
+do_mc_backlog_test()
+{
+	in_defer_scope \
+		__do_mc_backlog_test "$@"
+}
+
+__do_mark_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -588,6 +579,7 @@ do_mark_test()
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 
 	# Create a bit of a backlog and observe no mirroring due to marks.
 	qevent_rule_install_$subtest
@@ -617,12 +609,15 @@ do_mark_test()
 	else
 		log_test "TC $((vlan - 10)): marked packets $subtest'd"
 	fi
+}
 
-	stop_traffic
-	sleep 1
+do_mark_test()
+{
+	in_defer_scope \
+		__do_mark_test "$@"
 }
 
-do_drop_test()
+__do_drop_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -637,6 +632,7 @@ do_drop_test()
 	RET=0
 
 	start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac
+	defer stop_traffic_sleep $!
 
 	# Create a bit of a backlog and observe no mirroring due to drops.
 	qevent_rule_install_$subtest
@@ -671,9 +667,12 @@ do_drop_test()
 	check_fail $? "$((now - base)) spurious packets observed after uninstall"
 
 	log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd"
+}
 
-	stop_traffic
-	sleep 1
+do_drop_test()
+{
+	in_defer_scope \
+		__do_drop_test "$@"
 }
 
 qevent_rule_install_mirror()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index 576067b207a8..8902a115d9cd 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -80,36 +80,34 @@ uninstall_qdisc()
 ecn_test()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
 
 	do_ecn_test 10 $BACKLOG1
 	do_ecn_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 ecn_test_perband()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
 
 	do_ecn_test_perband 10 $BACKLOG1
 	do_ecn_test_perband 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
+	defer uninstall_qdisc
 
 	do_ecn_nodrop_test 10 $BACKLOG1
 	do_ecn_nodrop_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 red_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
 
 	# Make sure that we get the non-zero value if there is any.
 	local cur=$(busywait 1100 until_counter_is "> 0" \
@@ -120,50 +118,44 @@ red_test()
 
 	do_red_test 10 $BACKLOG1
 	do_red_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 mc_backlog_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
 
 	# Note that the backlog numbers here do not correspond to RED
 	# configuration, but are arbitrary.
 	do_mc_backlog_test 10 $BACKLOG1
 	do_mc_backlog_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 red_mirror_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
 
 	do_drop_mirror_test 10 $BACKLOG1 early_drop
 	do_drop_mirror_test 11 $BACKLOG2 early_drop
-
-	uninstall_qdisc
 }
 
 red_trap_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
 
 	do_drop_trap_test 10 $BACKLOG1 early_drop
 	do_drop_trap_test 11 $BACKLOG2 early_drop
-
-	uninstall_qdisc
 }
 
 ecn_mirror_test()
 {
 	install_qdisc ecn qevent mark block 10
+	defer uninstall_qdisc
 
 	do_mark_mirror_test 10 $BACKLOG1
 	do_mark_mirror_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 bail_on_lldpad "configure DCB" "configure Qdiscs"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
index 159108d02895..e9043771787b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
@@ -32,45 +32,51 @@ uninstall_qdisc()
 ecn_test()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
+
 	do_ecn_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 ecn_test_perband()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
+
 	do_ecn_test_perband 10 $BACKLOG
-	uninstall_qdisc
 }
 
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
+	defer uninstall_qdisc
+
 	do_ecn_nodrop_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 red_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
+
 	do_red_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 mc_backlog_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
+
 	# Note that the backlog value here does not correspond to RED
 	# configuration, but is arbitrary.
 	do_mc_backlog_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 red_mirror_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
+
 	do_drop_mirror_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 bail_on_lldpad "configure DCB" "configure Qdiscs"
diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh
index 17f28644568e..af166662b78a 100755
--- a/tools/testing/selftests/net/forwarding/sch_red.sh
+++ b/tools/testing/selftests/net/forwarding/sch_red.sh
@@ -53,71 +53,63 @@ PKTSZ=1400
 h1_create()
 {
 	simple_if_init $h1 192.0.2.1/28
+	defer simple_if_fini $h1 192.0.2.1/28
+
 	mtu_set $h1 10000
+	defer mtu_restore $h1
+
 	tc qdisc replace dev $h1 root handle 1: tbf \
 	   rate 10Mbit burst 10K limit 1M
-}
-
-h1_destroy()
-{
-	tc qdisc del dev $h1 root
-	mtu_restore $h1
-	simple_if_fini $h1 192.0.2.1/28
+	defer tc qdisc del dev $h1 root
 }
 
 h2_create()
 {
 	simple_if_init $h2 192.0.2.2/28
-	mtu_set $h2 10000
-}
+	defer simple_if_fini $h2 192.0.2.2/28
 
-h2_destroy()
-{
-	mtu_restore $h2
-	simple_if_fini $h2 192.0.2.2/28
+	mtu_set $h2 10000
+	defer mtu_restore $h2
 }
 
 h3_create()
 {
 	simple_if_init $h3 192.0.2.3/28
-	mtu_set $h3 10000
-}
+	defer simple_if_fini $h3 192.0.2.3/28
 
-h3_destroy()
-{
-	mtu_restore $h3
-	simple_if_fini $h3 192.0.2.3/28
+	mtu_set $h3 10000
+	defer mtu_restore $h3
 }
 
 switch_create()
 {
 	ip link add dev br up type bridge
+	defer ip link del dev br
+
 	ip link set dev $swp1 up master br
+	defer ip link set dev $swp1 down nomaster
+
 	ip link set dev $swp2 up master br
+	defer ip link set dev $swp2 down nomaster
+
 	ip link set dev $swp3 up master br
+	defer ip link set dev $swp3 down nomaster
 
 	mtu_set $swp1 10000
+	defer mtu_restore $h1
+
 	mtu_set $swp2 10000
+	defer mtu_restore $h2
+
 	mtu_set $swp3 10000
+	defer mtu_restore $h3
 
 	tc qdisc replace dev $swp3 root handle 1: tbf \
 	   rate 10Mbit burst 10K limit 1M
-	ip link add name _drop_test up type dummy
-}
+	defer tc qdisc del dev $swp3 root
 
-switch_destroy()
-{
-	ip link del dev _drop_test
-	tc qdisc del dev $swp3 root
-
-	mtu_restore $h3
-	mtu_restore $h2
-	mtu_restore $h1
-
-	ip link set dev $swp3 down nomaster
-	ip link set dev $swp2 down nomaster
-	ip link set dev $swp1 down nomaster
-	ip link del dev br
+	ip link add name _drop_test up type dummy
+	defer ip link del dev _drop_test
 }
 
 setup_prepare()
@@ -134,6 +126,7 @@ setup_prepare()
 	h3_mac=$(mac_get $h3)
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
@@ -141,18 +134,6 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.3 " from host 1"
@@ -287,6 +268,7 @@ do_ecn_test()
 
 	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
 		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	defer stop_traffic $!
 	sleep 1
 
 	ecn_test_common "$name" $limit
@@ -298,9 +280,6 @@ do_ecn_test()
 	build_backlog $((2 * limit)) udp >/dev/null
 	check_fail $? "UDP traffic went into backlog instead of being early-dropped"
 	log_test "$name backlog > limit: UDP early-dropped"
-
-	stop_traffic
-	sleep 1
 }
 
 do_ecn_nodrop_test()
@@ -310,6 +289,7 @@ do_ecn_nodrop_test()
 
 	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
 		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	defer stop_traffic $!
 	sleep 1
 
 	ecn_test_common "$name" $limit
@@ -321,9 +301,6 @@ do_ecn_nodrop_test()
 	build_backlog $((2 * limit)) udp >/dev/null
 	check_err $? "UDP traffic was early-dropped instead of getting into backlog"
 	log_test "$name backlog > limit: UDP not dropped"
-
-	stop_traffic
-	sleep 1
 }
 
 do_red_test()
@@ -336,6 +313,7 @@ do_red_test()
 	# is above limit.
 	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
 		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	defer stop_traffic $!
 
 	# Pushing below the queue limit should work.
 	RET=0
@@ -352,9 +330,6 @@ do_red_test()
 	pct=$(check_marking "== 0")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
 	log_test "RED backlog > limit"
-
-	stop_traffic
-	sleep 1
 }
 
 do_red_qevent_test()
@@ -369,6 +344,7 @@ do_red_qevent_test()
 
 	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
 		-a own -b $h3_mac -t udp -q &
+	defer stop_traffic $!
 	sleep 1
 
 	tc filter add block 10 pref 1234 handle 102 matchall skip_hw \
@@ -396,9 +372,6 @@ do_red_qevent_test()
 	check_err $? "Dropped packets still observed: 0 expected, $((now - base)) seen"
 
 	log_test "RED early_dropped packets mirrored"
-
-	stop_traffic
-	sleep 1
 }
 
 do_ecn_qevent_test()
@@ -410,6 +383,7 @@ do_ecn_qevent_test()
 
 	$MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \
 		-a own -b $h3_mac -t tcp -q tos=0x01 &
+	defer stop_traffic $!
 	sleep 1
 
 	tc filter add block 10 pref 1234 handle 102 matchall skip_hw \
@@ -428,9 +402,6 @@ do_ecn_qevent_test()
 	tc filter del block 10 pref 1234 handle 102 matchall
 
 	log_test "ECN marked packets mirrored"
-
-	stop_traffic
-	sleep 1
 }
 
 install_qdisc()
@@ -451,36 +422,36 @@ uninstall_qdisc()
 ecn_test()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
 	xfail_on_slow do_ecn_test $BACKLOG
-	uninstall_qdisc
 }
 
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
+	defer uninstall_qdisc
 	xfail_on_slow do_ecn_nodrop_test $BACKLOG
-	uninstall_qdisc
 }
 
 red_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
 	xfail_on_slow do_red_test $BACKLOG
-	uninstall_qdisc
 }
 
 red_qevent_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
 	xfail_on_slow do_red_qevent_test $BACKLOG
-	uninstall_qdisc
 }
 
 ecn_qevent_test()
 {
 	install_qdisc ecn qevent mark block 10
+	defer uninstall_qdisc
 	xfail_on_slow do_ecn_qevent_test $BACKLOG
-	uninstall_qdisc
 }
 
 trap cleanup EXIT
-- 
cgit v1.2.3


From a1b3741dcfd16bf1e337c89b9fca5fbb9110fbed Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:47 +0200
Subject: selftests: TBF: Use defer for test cleanup

Use the defer framework to schedule cleanups as soon as the command is
executed.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/forwarding/sch_tbf_core.sh       | 91 +++++++---------------
 .../selftests/net/forwarding/sch_tbf_etsprio.sh    |  7 +-
 .../selftests/net/forwarding/sch_tbf_root.sh       |  3 +-
 3 files changed, 36 insertions(+), 65 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
index 9cd884d4a5de..ec309a5086bc 100644
--- a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh
@@ -60,68 +60,65 @@ host_create()
 	local host=$1; shift
 
 	simple_if_init $dev
+	defer simple_if_fini $dev
+
 	mtu_set $dev 10000
+	defer mtu_restore $dev
 
 	vlan_create $dev 10 v$dev $(ipaddr $host 10)/28
+	defer vlan_destroy $dev 10
 	ip link set dev $dev.10 type vlan egress 0:0
 
 	vlan_create $dev 11 v$dev $(ipaddr $host 11)/28
+	defer vlan_destroy $dev 11
 	ip link set dev $dev.11 type vlan egress 0:1
 }
 
-host_destroy()
-{
-	local dev=$1; shift
-
-	vlan_destroy $dev 11
-	vlan_destroy $dev 10
-	mtu_restore $dev
-	simple_if_fini $dev
-}
-
 h1_create()
 {
 	host_create $h1 1
 }
 
-h1_destroy()
-{
-	host_destroy $h1
-}
-
 h2_create()
 {
 	host_create $h2 2
 
 	tc qdisc add dev $h2 clsact
+	defer tc qdisc del dev $h2 clsact
+
 	tc filter add dev $h2 ingress pref 1010 prot 802.1q \
 	   flower $TCFLAGS vlan_id 10 action pass
 	tc filter add dev $h2 ingress pref 1011 prot 802.1q \
 	   flower $TCFLAGS vlan_id 11 action pass
 }
 
-h2_destroy()
-{
-	tc qdisc del dev $h2 clsact
-	host_destroy $h2
-}
-
 switch_create()
 {
 	local intf
 	local vlan
 
 	ip link add dev br10 type bridge
+	defer ip link del dev br10
+
 	ip link add dev br11 type bridge
+	defer ip link del dev br11
 
 	for intf in $swp1 $swp2; do
 		ip link set dev $intf up
+		defer ip link set dev $intf down
+
 		mtu_set $intf 10000
+		defer mtu_restore $intf
 
 		for vlan in 10 11; do
 			vlan_create $intf $vlan
+			defer vlan_destroy $intf $vlan
+
 			ip link set dev $intf.$vlan master br$vlan
+			defer ip link set dev $intf.$vlan nomaster
+
 			ip link set dev $intf.$vlan up
+			defer ip link set dev $intf.$vlan down
 		done
 	done
 
@@ -130,34 +127,10 @@ switch_create()
 	done
 
 	ip link set dev br10 up
-	ip link set dev br11 up
-}
-
-switch_destroy()
-{
-	local intf
-	local vlan
-
-	# A test may have been interrupted mid-run, with Qdisc installed. Delete
-	# it here.
-	tc qdisc del dev $swp2 root 2>/dev/null
-
-	ip link set dev br11 down
-	ip link set dev br10 down
+	defer ip link set dev br10 down
 
-	for intf in $swp2 $swp1; do
-		for vlan in 11 10; do
-			ip link set dev $intf.$vlan down
-			ip link set dev $intf.$vlan nomaster
-			vlan_destroy $intf $vlan
-		done
-
-		mtu_restore $intf
-		ip link set dev $intf down
-	done
-
-	ip link del dev br11
-	ip link del dev br10
+	ip link set dev br11 up
+	defer ip link set dev br11 down
 }
 
 setup_prepare()
@@ -177,23 +150,13 @@ setup_prepare()
 	h2_mac=$(mac_get $h2)
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1.10 $(ipaddr 2 10) " vlan 10"
@@ -207,18 +170,18 @@ tbf_get_counter()
 	tc_rule_stats_get $h2 10$vlan ingress .bytes
 }
 
-do_tbf_test()
+__tbf_test()
 {
 	local vlan=$1; shift
 	local mbit=$1; shift
 
 	start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 2 $vlan) $h2_mac
+	defer stop_traffic $!
 	sleep 5 # Wait for the burst to dwindle
 
 	local t2=$(busywait_for_counter 1000 +1 tbf_get_counter $vlan)
 	sleep 10
 	local t3=$(tbf_get_counter $vlan)
-	stop_traffic
 
 	RET=0
 
@@ -231,3 +194,9 @@ do_tbf_test()
 
 	log_test "TC $((vlan - 10)): TBF rate ${mbit}Mbit"
 }
+
+do_tbf_test()
+{
+	in_defer_scope \
+		__tbf_test "$@"
+}
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
index df9bcd6a811a..c182a04282bc 100644
--- a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
@@ -30,8 +30,9 @@ tbf_test()
 	# This test is used for both ETS and PRIO. Even though we only need two
 	# bands, PRIO demands a minimum of three.
 	tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0
+	defer tc qdisc del dev $swp2 root
+
 	tbf_test_one 128K
-	tc qdisc del dev $swp2 root
 }
 
 tbf_root_test()
@@ -42,6 +43,8 @@ tbf_root_test()
 
 	tc qdisc replace dev $swp2 root handle 1: \
 		tbf rate 400Mbit burst $bs limit 1M
+	defer tc qdisc del dev $swp2 root
+
 	tc qdisc replace dev $swp2 parent 1:1 handle 10: \
 		$QDISC 3 priomap 2 1 0
 	tc qdisc replace dev $swp2 parent 10:3 handle 103: \
@@ -53,8 +56,6 @@ tbf_root_test()
 
 	do_tbf_test 10 400 $bs
 	do_tbf_test 11 400 $bs
-
-	tc qdisc del dev $swp2 root
 }
 
 if type -t sch_tbf_pre_hook >/dev/null; then
diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_root.sh b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh
index 96c997be0d03..9f20320f8d84 100755
--- a/tools/testing/selftests/net/forwarding/sch_tbf_root.sh
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh
@@ -14,13 +14,14 @@ tbf_test_one()
 
 	tc qdisc replace dev $swp2 root handle 108: tbf \
 	   rate 400Mbit burst $bs limit 1M
+	defer tc qdisc del dev $swp2 root
+
 	do_tbf_test 10 400 $bs
 }
 
 tbf_test()
 {
 	tbf_test_one 128K
-	tc qdisc del dev $swp2 root
 }
 
 if type -t sch_tbf_pre_hook >/dev/null; then
-- 
cgit v1.2.3


From cc3e7ee15ddd0d37251127b7802d4483d7f6cad3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:48 +0200
Subject: selftests: ETS: Use defer for test cleanup

Use the defer framework to schedule cleanups as soon as the command is
executed.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../testing/selftests/drivers/net/mlxsw/sch_ets.sh | 26 ++++---
 tools/testing/selftests/net/forwarding/sch_ets.sh  |  7 +-
 .../selftests/net/forwarding/sch_ets_core.sh       | 81 ++++++++--------------
 .../selftests/net/forwarding/sch_ets_tests.sh      | 14 ++--
 4 files changed, 50 insertions(+), 78 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
index 139175fd03e7..4aaceb6b2b60 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
@@ -21,6 +21,7 @@ switch_create()
 	# Create a bottleneck so that the DWRR process can kick in.
 	tc qdisc replace dev $swp2 root handle 3: tbf rate 1gbit \
 		burst 128K limit 1G
+	defer tc qdisc del dev $swp2 root handle 3:
 
 	ets_switch_create
 
@@ -30,16 +31,27 @@ switch_create()
 	# for the DWRR process.
 	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 12
+	defer devlink_port_pool_th_restore $swp1 0
+
 	devlink_tc_bind_pool_th_save $swp1 0 ingress
 	devlink_tc_bind_pool_th_set $swp1 0 ingress 0 12
+	defer devlink_tc_bind_pool_th_restore $swp1 0 ingress
+
 	devlink_port_pool_th_save $swp2 4
 	devlink_port_pool_th_set $swp2 4 12
+	defer devlink_port_pool_th_restore $swp2 4
+
 	devlink_tc_bind_pool_th_save $swp2 7 egress
 	devlink_tc_bind_pool_th_set $swp2 7 egress 4 5
+	defer devlink_tc_bind_pool_th_restore $swp2 7 egress
+
 	devlink_tc_bind_pool_th_save $swp2 6 egress
 	devlink_tc_bind_pool_th_set $swp2 6 egress 4 5
+	defer devlink_tc_bind_pool_th_restore $swp2 6 egress
+
 	devlink_tc_bind_pool_th_save $swp2 5 egress
 	devlink_tc_bind_pool_th_set $swp2 5 egress 4 5
+	defer devlink_tc_bind_pool_th_restore $swp2 5 egress
 
 	# Note: sch_ets_core.sh uses VLAN ingress-qos-map to assign packet
 	# priorities at $swp1 based on their 802.1p headers. ingress-qos-map is
@@ -47,20 +59,6 @@ switch_create()
 	# 1:1, which is the mapping currently hard-coded by the driver.
 }
 
-switch_destroy()
-{
-	devlink_tc_bind_pool_th_restore $swp2 5 egress
-	devlink_tc_bind_pool_th_restore $swp2 6 egress
-	devlink_tc_bind_pool_th_restore $swp2 7 egress
-	devlink_port_pool_th_restore $swp2 4
-	devlink_tc_bind_pool_th_restore $swp1 0 ingress
-	devlink_port_pool_th_restore $swp1 0
-
-	ets_switch_destroy
-
-	tc qdisc del dev $swp2 root handle 3:
-}
-
 # Callback from sch_ets_tests.sh
 collect_stats()
 {
diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh
index e60c8b4818cc..1f6f53e284b5 100755
--- a/tools/testing/selftests/net/forwarding/sch_ets.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets.sh
@@ -24,15 +24,10 @@ switch_create()
 	# Create a bottleneck so that the DWRR process can kick in.
 	tc qdisc add dev $swp2 root handle 1: tbf \
 	   rate 1Gbit burst 1Mbit latency 100ms
+	defer tc qdisc del dev $swp2 root
 	PARENT="parent 1:"
 }
 
-switch_destroy()
-{
-	ets_switch_destroy
-	tc qdisc del dev $swp2 root
-}
-
 # Callback from sch_ets_tests.sh
 collect_stats()
 {
diff --git a/tools/testing/selftests/net/forwarding/sch_ets_core.sh b/tools/testing/selftests/net/forwarding/sch_ets_core.sh
index f906fcc66572..8f9922c695b0 100644
--- a/tools/testing/selftests/net/forwarding/sch_ets_core.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets_core.sh
@@ -166,44 +166,32 @@ h1_create()
 	local i;
 
 	simple_if_init $h1
+	defer simple_if_fini $h1
+
 	mtu_set $h1 9900
+	defer mtu_restore $h1
+
 	for i in {0..2}; do
 		vlan_create $h1 1$i v$h1 $(sip $i)/28
+		defer vlan_destroy $h1 1$i
 		ip link set dev $h1.1$i type vlan egress 0:$i
 	done
 }
 
-h1_destroy()
-{
-	local i
-
-	for i in {0..2}; do
-		vlan_destroy $h1 1$i
-	done
-	mtu_restore $h1
-	simple_if_fini $h1
-}
-
 h2_create()
 {
 	local i
 
 	simple_if_init $h2
-	mtu_set $h2 9900
-	for i in {0..2}; do
-		vlan_create $h2 1$i v$h2 $(dip $i)/28
-	done
-}
+	defer simple_if_fini $h2
 
-h2_destroy()
-{
-	local i
+	mtu_set $h2 9900
+	defer mtu_restore $h2
 
 	for i in {0..2}; do
-		vlan_destroy $h2 1$i
+		vlan_create $h2 1$i v$h2 $(dip $i)/28
+		defer vlan_destroy $h2 1$i
 	done
-	mtu_restore $h2
-	simple_if_fini $h2
 }
 
 ets_switch_create()
@@ -211,44 +199,45 @@ ets_switch_create()
 	local i
 
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	mtu_set $swp1 9900
+	defer mtu_restore $swp1
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	mtu_set $swp2 9900
+	defer mtu_restore $swp2
 
 	for i in {0..2}; do
 		vlan_create $swp1 1$i
+		defer vlan_destroy $swp1 1$i
 		ip link set dev $swp1.1$i type vlan ingress 0:0 1:1 2:2
 
 		vlan_create $swp2 1$i
+		defer vlan_destroy $swp2 1$i
 
 		ip link add dev br1$i type bridge
+		defer ip link del dev br1$i
+
 		ip link set dev $swp1.1$i master br1$i
+		defer ip link set dev $swp1.1$i nomaster
+
 		ip link set dev $swp2.1$i master br1$i
+		defer ip link set dev $swp2.1$i nomaster
 
 		ip link set dev br1$i up
-		ip link set dev $swp1.1$i up
-		ip link set dev $swp2.1$i up
-	done
-}
+		defer ip link set dev br1$i down
 
-ets_switch_destroy()
-{
-	local i
-
-	ets_delete_qdisc
+		ip link set dev $swp1.1$i up
+		defer ip link set dev $swp1.1$i down
 
-	for i in {0..2}; do
-		ip link del dev br1$i
-		vlan_destroy $swp2 1$i
-		vlan_destroy $swp1 1$i
+		ip link set dev $swp2.1$i up
+		defer ip link set dev $swp2.1$i down
 	done
 
-	mtu_restore $swp2
-	ip link set dev $swp2 down
-
-	mtu_restore $swp1
-	ip link set dev $swp1 down
+	defer ets_delete_qdisc
 }
 
 setup_prepare()
@@ -263,23 +252,13 @@ setup_prepare()
 	hut=$h2
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1.10 $(dip 0) " vlan 10"
diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
index f9d26a7911bb..08240d3e3c87 100644
--- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
@@ -90,6 +90,7 @@ __ets_dwrr_test()
 
 	for stream in ${streams[@]}; do
 		ets_start_traffic $stream
+		defer stop_traffic $!
 	done
 
 	sleep 10
@@ -120,25 +121,24 @@ __ets_dwrr_test()
 				       ${d[0]} ${d[$i]}
 		fi
 	done
-
-	for stream in ${streams[@]}; do
-		stop_traffic
-	done
 }
 
 ets_dwrr_test_012()
 {
-	__ets_dwrr_test 0 1 2
+	in_defer_scope \
+		__ets_dwrr_test 0 1 2
 }
 
 ets_dwrr_test_01()
 {
-	__ets_dwrr_test 0 1
+	in_defer_scope \
+		__ets_dwrr_test 0 1
 }
 
 ets_dwrr_test_12()
 {
-	__ets_dwrr_test 1 2
+	in_defer_scope \
+		__ets_dwrr_test 1 2
 }
 
 ets_qdisc_setup()
-- 
cgit v1.2.3


From 979154e90ff83ab63bb1a52f48e442c953452adb Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:49 +0200
Subject: selftests: mlxsw: qos_mc_aware: Use defer for test cleanup

Use the defer framework to schedule cleanups as soon as the command is
executed.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/mlxsw/qos_mc_aware.sh    | 138 ++++++++++-----------
 1 file changed, 64 insertions(+), 74 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 6d892de43fa8..cd4a5c21360c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -73,122 +73,114 @@ source qos_lib.sh
 h1_create()
 {
 	simple_if_init $h1 192.0.2.65/28
-	mtu_set $h1 10000
-}
+	defer simple_if_fini $h1 192.0.2.65/28
 
-h1_destroy()
-{
-	mtu_restore $h1
-	simple_if_fini $h1 192.0.2.65/28
+	mtu_set $h1 10000
+	defer mtu_restore $h1
 }
 
 h2_create()
 {
 	simple_if_init $h2
+	defer simple_if_fini $h2
+
 	mtu_set $h2 10000
+	defer mtu_restore $h2
 
 	vlan_create $h2 111 v$h2 192.0.2.129/28
+	defer vlan_destroy $h2 111
 	ip link set dev $h2.111 type vlan egress-qos-map 0:1
 }
 
-h2_destroy()
-{
-	vlan_destroy $h2 111
-
-	mtu_restore $h2
-	simple_if_fini $h2
-}
-
 h3_create()
 {
 	simple_if_init $h3 192.0.2.66/28
+	defer simple_if_fini $h3 192.0.2.66/28
+
 	mtu_set $h3 10000
+	defer mtu_restore $h3
 
 	vlan_create $h3 111 v$h3 192.0.2.130/28
-}
-
-h3_destroy()
-{
-	vlan_destroy $h3 111
-
-	mtu_restore $h3
-	simple_if_fini $h3 192.0.2.66/28
+	defer vlan_destroy $h3 111
 }
 
 switch_create()
 {
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	mtu_set $swp1 10000
+	defer mtu_restore $swp1
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	mtu_set $swp2 10000
+	defer mtu_restore $swp2
 
 	ip link set dev $swp3 up
+	defer ip link set dev $swp3 down
+
 	mtu_set $swp3 10000
+	defer mtu_restore $swp3
 
 	vlan_create $swp2 111
+	defer vlan_destroy $swp2 111
+
 	vlan_create $swp3 111
+	defer vlan_destroy $swp3 111
 
 	tc qdisc replace dev $swp3 root handle 3: tbf rate 1gbit \
 		burst 128K limit 1G
+	defer tc qdisc del dev $swp3 root handle 3:
+
 	tc qdisc replace dev $swp3 parent 3:3 handle 33: \
 		prio bands 8 priomap 7 7 7 7 7 7 7 7
+	defer tc qdisc del dev $swp3 parent 3:3 handle 33:
 
 	ip link add name br1 type bridge vlan_filtering 0
+	defer ip link del dev br1
 	ip link set dev br1 addrgenmode none
 	ip link set dev br1 up
+
 	ip link set dev $swp1 master br1
+	defer ip link set dev $swp1 nomaster
+
 	ip link set dev $swp3 master br1
+	defer ip link set dev $swp3 nomaster
 
 	ip link add name br111 type bridge vlan_filtering 0
+	defer ip link del dev br111
 	ip link set dev br111 addrgenmode none
 	ip link set dev br111 up
+
 	ip link set dev $swp2.111 master br111
+	defer ip link set dev $swp2.111 nomaster
+
 	ip link set dev $swp3.111 master br111
+	defer ip link set dev $swp3.111 nomaster
 
 	# Make sure that ingress quotas are smaller than egress so that there is
 	# room for both streams of traffic to be admitted to shared buffer.
 	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 5
+	defer devlink_port_pool_th_restore $swp1 0
+
 	devlink_tc_bind_pool_th_save $swp1 0 ingress
 	devlink_tc_bind_pool_th_set $swp1 0 ingress 0 5
+	defer devlink_tc_bind_pool_th_restore $swp1 0 ingress
 
 	devlink_port_pool_th_save $swp2 0
 	devlink_port_pool_th_set $swp2 0 5
+	defer devlink_port_pool_th_restore $swp2 0
+
 	devlink_tc_bind_pool_th_save $swp2 1 ingress
 	devlink_tc_bind_pool_th_set $swp2 1 ingress 0 5
+	defer devlink_tc_bind_pool_th_restore $swp2 1 ingress
 
 	devlink_port_pool_th_save $swp3 4
 	devlink_port_pool_th_set $swp3 4 12
-}
-
-switch_destroy()
-{
-	devlink_port_pool_th_restore $swp3 4
-
-	devlink_tc_bind_pool_th_restore $swp2 1 ingress
-	devlink_port_pool_th_restore $swp2 0
-
-	devlink_tc_bind_pool_th_restore $swp1 0 ingress
-	devlink_port_pool_th_restore $swp1 0
-
-	ip link del dev br111
-	ip link del dev br1
-
-	tc qdisc del dev $swp3 parent 3:3 handle 33:
-	tc qdisc del dev $swp3 root handle 3:
-
-	vlan_destroy $swp3 111
-	vlan_destroy $swp2 111
-
-	mtu_restore $swp3
-	ip link set dev $swp3 down
-
-	mtu_restore $swp2
-	ip link set dev $swp2 down
-
-	mtu_restore $swp1
-	ip link set dev $swp1 down
+	defer devlink_port_pool_th_restore $swp3 4
 }
 
 setup_prepare()
@@ -205,6 +197,7 @@ setup_prepare()
 	h3mac=$(mac_get $h3)
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
@@ -212,45 +205,45 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
+ping_ipv4()
 {
-	pre_cleanup
+	ping_test $h2 192.0.2.130
+}
 
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
+__run_uc_measure_rate()
+{
+	local what=$1; shift
+	local -a uc_rate
+
+	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
+	defer stop_traffic $!
+
+	uc_rate=($(measure_rate $swp2 $h3 rx_octets_prio_1 "$what"))
+	check_err $? "Could not get high enough $what ingress rate"
 
-	vrf_cleanup
+	echo ${uc_rate[@]}
 }
 
-ping_ipv4()
+run_uc_measure_rate()
 {
-	ping_test $h2 192.0.2.130
+	in_defer_scope __run_uc_measure_rate "$@"
 }
 
 test_mc_aware()
 {
 	RET=0
 
-	local -a uc_rate
-	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
-	uc_rate=($(measure_rate $swp2 $h3 rx_octets_prio_1 "UC-only"))
-	check_err $? "Could not get high enough UC-only ingress rate"
-	stop_traffic
+	local -a uc_rate=($(run_uc_measure_rate "UC-only"))
 	local ucth1=${uc_rate[1]}
 
 	start_traffic $h1 192.0.2.65 bc bc
+	defer stop_traffic $!
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
 	local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0)
 
-	local -a uc_rate_2
-	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
-	uc_rate_2=($(measure_rate $swp2 $h3 rx_octets_prio_1 "UC+MC"))
-	check_err $? "Could not get high enough UC+MC ingress rate"
-	stop_traffic
+	local -a uc_rate_2=($(run_uc_measure_rate "UC+MC"))
 	local ucth2=${uc_rate_2[1]}
 
 	local d1=$(date +%s)
@@ -272,8 +265,6 @@ test_mc_aware()
 	local mc_ir=$(rate $u0 $u1 $interval)
 	local mc_er=$(rate $t0 $t1 $interval)
 
-	stop_traffic
-
 	log_test "UC performance under MC overload"
 
 	echo "UC-only throughput  $(humanize $ucth1)"
@@ -297,6 +288,7 @@ test_uc_aware()
 	RET=0
 
 	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
+	defer stop_traffic $!
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
@@ -326,8 +318,6 @@ test_uc_aware()
 	((attempts == passes))
 	check_err $?
 
-	stop_traffic
-
 	log_test "MC performance under UC overload"
 	echo "    ingress UC throughput $(humanize ${uc_ir})"
 	echo "    egress UC throughput  $(humanize ${uc_er})"
-- 
cgit v1.2.3


From 424745af5271a5990caa25358b9710db0349221c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:50 +0200
Subject: selftests: mlxsw: qos_ets_strict: Use defer for test cleanup

Use the defer framework to schedule cleanups as soon as the command is
executed.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/mlxsw/qos_ets_strict.sh  | 167 +++++++++++----------
 1 file changed, 85 insertions(+), 82 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
index fee74f215cec..d5b6f2cc9a29 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
@@ -58,65 +58,62 @@ source qos_lib.sh
 h1_create()
 {
 	simple_if_init $h1
+	defer simple_if_fini $h1
+
 	mtu_set $h1 10000
+	defer mtu_restore $h1
 
 	vlan_create $h1 111 v$h1 192.0.2.33/28
+	defer vlan_destroy $h1 111
 	ip link set dev $h1.111 type vlan egress-qos-map 0:1
 }
 
-h1_destroy()
-{
-	vlan_destroy $h1 111
-
-	mtu_restore $h1
-	simple_if_fini $h1
-}
-
 h2_create()
 {
 	simple_if_init $h2
+	defer simple_if_fini $h2
+
 	mtu_set $h2 10000
+	defer mtu_restore $h2
 
 	vlan_create $h2 222 v$h2 192.0.2.65/28
+	defer vlan_destroy $h2 222
 	ip link set dev $h2.222 type vlan egress-qos-map 0:2
 }
 
-h2_destroy()
-{
-	vlan_destroy $h2 222
-
-	mtu_restore $h2
-	simple_if_fini $h2
-}
-
 h3_create()
 {
 	simple_if_init $h3
+	defer simple_if_fini $h3
+
 	mtu_set $h3 10000
+	defer mtu_restore $h3
 
 	vlan_create $h3 111 v$h3 192.0.2.34/28
-	vlan_create $h3 222 v$h3 192.0.2.66/28
-}
-
-h3_destroy()
-{
-	vlan_destroy $h3 222
-	vlan_destroy $h3 111
+	defer vlan_destroy $h3 111
 
-	mtu_restore $h3
-	simple_if_fini $h3
+	vlan_create $h3 222 v$h3 192.0.2.66/28
+	defer vlan_destroy $h3 222
 }
 
 switch_create()
 {
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	mtu_set $swp1 10000
+	defer mtu_restore $swp1
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	mtu_set $swp2 10000
+	defer mtu_restore $swp2
 
 	# prio n -> TC n, strict scheduling
 	lldptool -T -i $swp3 -V ETS-CFG up2tc=0:0,1:1,2:2,3:3,4:4,5:5,6:6,7:7
+	defer lldptool -T -i $swp3 -V ETS-CFG up2tc=0:0,1:0,2:0,3:0,4:0,5:0,6:0,7:0
+
 	lldptool -T -i $swp3 -V ETS-CFG tsa=$(
 			)"0:strict,"$(
 			)"1:strict,"$(
@@ -129,85 +126,90 @@ switch_create()
 	sleep 1
 
 	ip link set dev $swp3 up
+	defer ip link set dev $swp3 down
+
 	mtu_set $swp3 10000
+	defer mtu_restore $swp3
+
 	tc qdisc replace dev $swp3 root handle 101: tbf rate 1gbit \
 		burst 128K limit 1G
+	defer tc qdisc del dev $swp3 root handle 101:
 
 	vlan_create $swp1 111
+	defer vlan_destroy $swp1 111
+
 	vlan_create $swp2 222
+	defer vlan_destroy $swp2 222
+
 	vlan_create $swp3 111
+	defer vlan_destroy $swp3 111
+
 	vlan_create $swp3 222
+	defer vlan_destroy $swp3 222
 
 	ip link add name br111 type bridge vlan_filtering 0
+	defer ip link del dev br111
 	ip link set dev br111 addrgenmode none
+
 	ip link set dev br111 up
+	defer ip link set dev br111 down
+
 	ip link set dev $swp1.111 master br111
+	defer ip link set dev $swp1.111 nomaster
+
 	ip link set dev $swp3.111 master br111
+	defer ip link set dev $swp3.111 nomaster
 
 	ip link add name br222 type bridge vlan_filtering 0
+	defer ip link del dev br222
 	ip link set dev br222 addrgenmode none
+
 	ip link set dev br222 up
+	defer ip link set dev br222 down
+
 	ip link set dev $swp2.222 master br222
+	defer ip link set dev $swp2.222 nomaster
+
 	ip link set dev $swp3.222 master br222
+	defer ip link set dev $swp3.222 nomaster
 
 	# Make sure that ingress quotas are smaller than egress so that there is
 	# room for both streams of traffic to be admitted to shared buffer.
 	devlink_pool_size_thtype_save 0
 	devlink_pool_size_thtype_set 0 dynamic 10000000
+	defer devlink_pool_size_thtype_restore 0
+
 	devlink_pool_size_thtype_save 4
 	devlink_pool_size_thtype_set 4 dynamic 10000000
+	defer devlink_pool_size_thtype_restore 4
 
 	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 6
+	defer devlink_port_pool_th_restore $swp1 0
+
 	devlink_tc_bind_pool_th_save $swp1 1 ingress
 	devlink_tc_bind_pool_th_set $swp1 1 ingress 0 6
+	defer devlink_tc_bind_pool_th_restore $swp1 1 ingress
 
 	devlink_port_pool_th_save $swp2 0
 	devlink_port_pool_th_set $swp2 0 6
+	defer devlink_port_pool_th_restore $swp2 0
+
 	devlink_tc_bind_pool_th_save $swp2 2 ingress
 	devlink_tc_bind_pool_th_set $swp2 2 ingress 0 6
+	defer devlink_tc_bind_pool_th_restore $swp2 2 ingress
 
 	devlink_tc_bind_pool_th_save $swp3 1 egress
 	devlink_tc_bind_pool_th_set $swp3 1 egress 4 7
+	defer devlink_tc_bind_pool_th_restore $swp3 1 egress
+
 	devlink_tc_bind_pool_th_save $swp3 2 egress
 	devlink_tc_bind_pool_th_set $swp3 2 egress 4 7
+	defer devlink_tc_bind_pool_th_restore $swp3 2 egress
+
 	devlink_port_pool_th_save $swp3 4
 	devlink_port_pool_th_set $swp3 4 7
-}
-
-switch_destroy()
-{
-	devlink_port_pool_th_restore $swp3 4
-	devlink_tc_bind_pool_th_restore $swp3 2 egress
-	devlink_tc_bind_pool_th_restore $swp3 1 egress
-
-	devlink_tc_bind_pool_th_restore $swp2 2 ingress
-	devlink_port_pool_th_restore $swp2 0
-
-	devlink_tc_bind_pool_th_restore $swp1 1 ingress
-	devlink_port_pool_th_restore $swp1 0
-
-	devlink_pool_size_thtype_restore 4
-	devlink_pool_size_thtype_restore 0
-
-	ip link del dev br222
-	ip link del dev br111
-
-	vlan_destroy $swp3 222
-	vlan_destroy $swp3 111
-	vlan_destroy $swp2 222
-	vlan_destroy $swp1 111
-
-	tc qdisc del dev $swp3 root handle 101:
-	mtu_restore $swp3
-	ip link set dev $swp3 down
-	lldptool -T -i $swp3 -V ETS-CFG up2tc=0:0,1:0,2:0,3:0,4:0,5:0,6:0,7:0
-
-	mtu_restore $swp2
-	ip link set dev $swp2 down
-
-	mtu_restore $swp1
-	ip link set dev $swp1 down
+	defer devlink_port_pool_th_restore $swp3 4
 }
 
 setup_prepare()
@@ -224,6 +226,7 @@ setup_prepare()
 	h3mac=$(mac_get $h3)
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
@@ -231,18 +234,6 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.34 " from H1"
@@ -261,21 +252,38 @@ rel()
 	"
 }
 
+__run_hi_measure_rate()
+{
+	local what=$1; shift
+	local -a uc_rate
+
+	start_traffic $h2.222 192.0.2.65 192.0.2.66 $h3mac
+	defer stop_traffic $!
+
+	uc_rate=($(measure_rate $swp2 $h3 rx_octets_prio_2 "$what"))
+	check_err $? "Could not get high enough $what ingress rate"
+
+	echo ${uc_rate[@]}
+}
+
+run_hi_measure_rate()
+{
+	in_defer_scope __run_hi_measure_rate "$@"
+}
+
 test_ets_strict()
 {
 	RET=0
 
 	# Run high-prio traffic on its own.
-	start_traffic $h2.222 192.0.2.65 192.0.2.66 $h3mac
 	local -a rate_2
-	rate_2=($(measure_rate $swp2 $h3 rx_octets_prio_2 "prio 2"))
-	check_err $? "Could not get high enough prio-2 ingress rate"
+	rate_2=($(run_hi_measure_rate "prio 2"))
 	local rate_2_in=${rate_2[0]}
 	local rate_2_eg=${rate_2[1]}
-	stop_traffic # $h2.222
 
 	# Start low-prio stream.
 	start_traffic $h1.111 192.0.2.33 192.0.2.34 $h3mac
+	defer stop_traffic $!
 
 	local -a rate_1
 	rate_1=($(measure_rate $swp1 $h3 rx_octets_prio_1 "prio 1"))
@@ -290,14 +298,9 @@ test_ets_strict()
 	check_err $(bc <<< "$rel21 > 105")
 
 	# Start the high-prio stream--now both streams run.
-	start_traffic $h2.222 192.0.2.65 192.0.2.66 $h3mac
-	rate_3=($(measure_rate $swp2 $h3 rx_octets_prio_2 "prio 2 w/ 1"))
-	check_err $? "Could not get high enough prio-2 ingress rate with prio-1"
+	rate_3=($(run_hi_measure_rate "prio 2+1"))
 	local rate_3_in=${rate_3[0]}
 	local rate_3_eg=${rate_3[1]}
-	stop_traffic # $h2.222
-
-	stop_traffic # $h1.111
 
 	# High-prio should have about the same throughput whether or not
 	# low-prio is in the system.
-- 
cgit v1.2.3


From 919419a8870b33405ef9b0e34e837d407e3888f5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:51 +0200
Subject: selftests: mlxsw: qos_max_descriptors: Use defer for test cleanup

Use the defer framework to schedule cleanups as soon as the command is
executed.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../drivers/net/mlxsw/qos_max_descriptors.sh       | 118 +++++++--------------
 1 file changed, 41 insertions(+), 77 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
index 5ac4f795e333..2b5d2c2751d5 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
@@ -69,127 +69,103 @@ mlxsw_only_on_spectrum 2+ || exit
 h1_create()
 {
 	simple_if_init $h1
+	defer simple_if_fini $h1
 
 	vlan_create $h1 111 v$h1 192.0.2.33/28
+	defer vlan_destroy $h1 111
 	ip link set dev $h1.111 type vlan egress-qos-map 0:1
 }
 
-h1_destroy()
-{
-	vlan_destroy $h1 111
-
-	simple_if_fini $h1
-}
-
 h2_create()
 {
 	simple_if_init $h2
+	defer simple_if_fini $h2
 
 	vlan_create $h2 111 v$h2 192.0.2.34/28
-}
-
-h2_destroy()
-{
-	vlan_destroy $h2 111
-
-	simple_if_fini $h2
+	defer vlan_destroy $h2 111
 }
 
 switch_create()
 {
 	# pools
 	# -----
+	# devlink_pool_size_thtype_restore needs to be done first so that we can
+	# reset the various limits to values that are only valid for the
+	# original static / dynamic setting.
 
 	devlink_pool_size_thtype_save 1
-	devlink_pool_size_thtype_save 6
-
-	devlink_port_pool_th_save $swp1 1
-	devlink_port_pool_th_save $swp2 6
-
-	devlink_tc_bind_pool_th_save $swp1 1 ingress
-	devlink_tc_bind_pool_th_save $swp2 1 egress
-
 	devlink_pool_size_thtype_set 1 dynamic $MAX_POOL_SIZE
+	defer_prio devlink_pool_size_thtype_restore 1
+
+	devlink_pool_size_thtype_save 6
 	devlink_pool_size_thtype_set 6 static $MAX_POOL_SIZE
+	defer_prio devlink_pool_size_thtype_restore 6
 
 	# $swp1
 	# -----
 
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	vlan_create $swp1 111
+	defer vlan_destroy $swp1 111
 	ip link set dev $swp1.111 type vlan ingress-qos-map 0:0 1:1
 
+	devlink_port_pool_th_save $swp1 1
 	devlink_port_pool_th_set $swp1 1 16
+	defer devlink_tc_bind_pool_th_restore $swp1 1 ingress
+
+	devlink_tc_bind_pool_th_save $swp1 1 ingress
 	devlink_tc_bind_pool_th_set $swp1 1 ingress 1 16
+	defer devlink_port_pool_th_restore $swp1 1
 
 	tc qdisc replace dev $swp1 root handle 1: \
 	   ets bands 8 strict 8 priomap 7 6
+	defer tc qdisc del dev $swp1 root
+
 	dcb buffer set dev $swp1 prio-buffer all:0 1:1
+	defer dcb buffer set dev $swp1 prio-buffer all:0
 
 	# $swp2
 	# -----
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	vlan_create $swp2 111
+	defer vlan_destroy $swp2 111
 	ip link set dev $swp2.111 type vlan egress-qos-map 0:0 1:1
 
+	devlink_port_pool_th_save $swp2 6
 	devlink_port_pool_th_set $swp2 6 $MAX_POOL_SIZE
+	defer devlink_tc_bind_pool_th_restore $swp2 1 egress
+
+	devlink_tc_bind_pool_th_save $swp2 1 egress
 	devlink_tc_bind_pool_th_set $swp2 1 egress 6 $MAX_POOL_SIZE
+	defer devlink_port_pool_th_restore $swp2 6
 
 	tc qdisc replace dev $swp2 root handle 1: tbf rate $SHAPER_RATE \
 		burst 128K limit 500M
+	defer tc qdisc del dev $swp2 root
+
 	tc qdisc replace dev $swp2 parent 1:1 handle 11: \
 		ets bands 8 strict 8 priomap 7 6
+	defer tc qdisc del dev $swp2 parent 1:1 handle 11:
 
 	# bridge
 	# ------
 
 	ip link add name br1 type bridge vlan_filtering 0
+	defer ip link del dev br1
+
 	ip link set dev $swp1.111 master br1
+	defer ip link set dev $swp1.111 nomaster
+
 	ip link set dev br1 up
+	defer ip link set dev br1 down
 
 	ip link set dev $swp2.111 master br1
-}
-
-switch_destroy()
-{
-	# Do this first so that we can reset the limits to values that are only
-	# valid for the original static / dynamic setting.
-	devlink_pool_size_thtype_restore 6
-	devlink_pool_size_thtype_restore 1
-
-	# bridge
-	# ------
-
-	ip link set dev $swp2.111 nomaster
-
-	ip link set dev br1 down
-	ip link set dev $swp1.111 nomaster
-	ip link del dev br1
-
-	# $swp2
-	# -----
-
-	tc qdisc del dev $swp2 parent 1:1 handle 11:
-	tc qdisc del dev $swp2 root
-
-	devlink_tc_bind_pool_th_restore $swp2 1 egress
-	devlink_port_pool_th_restore $swp2 6
-
-	vlan_destroy $swp2 111
-	ip link set dev $swp2 down
-
-	# $swp1
-	# -----
-
-	dcb buffer set dev $swp1 prio-buffer all:0
-	tc qdisc del dev $swp1 root
-
-	devlink_tc_bind_pool_th_restore $swp1 1 ingress
-	devlink_port_pool_th_restore $swp1 1
-
-	vlan_destroy $swp1 111
-	ip link set dev $swp1 down
+	defer ip link set dev $swp2.111 nomaster
 }
 
 setup_prepare()
@@ -203,23 +179,13 @@ setup_prepare()
 	h2mac=$(mac_get $h2)
 
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.34 " h1->h2"
@@ -251,6 +217,7 @@ max_descriptors()
 
 	log_info "Send many small packets, packet size = $pktsize bytes"
 	start_traffic_pktsize $pktsize $h1.111 192.0.2.33 192.0.2.34 $h2mac
+	defer stop_traffic $!
 
 	# Sleep to wait for congestion.
 	sleep 5
@@ -268,9 +235,6 @@ max_descriptors()
 	check_err $(bc <<< "$perc_used < $exp_perc_used") \
 		"Expected > $exp_perc_used% of descriptors, handle $perc_used%"
 
-	stop_traffic
-	sleep 1
-
 	log_test "Maximum descriptors usage. The percentage used is $perc_used%"
 }
 
-- 
cgit v1.2.3


From cebd281f3c753dcbd48b455bdbc6549889196aa0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 17 Oct 2024 11:45:52 +0200
Subject: selftests: mlxsw: devlink_trap_police: Use defer for test cleanup

Use the defer framework to schedule cleanups as soon as the command is
executed.

Note that the start_traffic commands in __burst_test() are each sending a
fixed number of packets (note the -c flag) and then ending. They therefore
do not need a matching stop_traffic.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../drivers/net/mlxsw/devlink_trap_policer.sh      | 85 +++++++++-------------
 1 file changed, 36 insertions(+), 49 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
index 0bd5ffc218ac..29a672c2270f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
@@ -45,63 +45,52 @@ source $lib_dir/devlink_lib.sh
 h1_create()
 {
 	simple_if_init $h1 192.0.2.1/24
+	defer simple_if_fini $h1 192.0.2.1/24
+
 	mtu_set $h1 10000
+	defer mtu_restore $h1
 
 	ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
-}
-
-h1_destroy()
-{
-	ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
-
-	mtu_restore $h1
-	simple_if_fini $h1 192.0.2.1/24
+	defer ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
 }
 
 h2_create()
 {
 	simple_if_init $h2 198.51.100.1/24
+	defer simple_if_fini $h2 198.51.100.1/24
+
 	mtu_set $h2 10000
+	defer mtu_restore $h2
 
 	ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
-}
-
-h2_destroy()
-{
-	ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
-
-	mtu_restore $h2
-	simple_if_fini $h2 198.51.100.1/24
+	defer ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
 }
 
 router_create()
 {
 	ip link set dev $rp1 up
+	defer ip link set dev $rp1 down
+
 	ip link set dev $rp2 up
+	defer ip link set dev $rp2 down
 
 	__addr_add_del $rp1 add 192.0.2.2/24
+	defer __addr_add_del $rp1 del 192.0.2.2/24
+
 	__addr_add_del $rp2 add 198.51.100.2/24
+	defer __addr_add_del $rp2 del 198.51.100.2/24
+
 	mtu_set $rp1 10000
+	defer mtu_restore $rp1
+
 	mtu_set $rp2 10000
+	defer mtu_restore $rp2
 
 	ip -4 route add blackhole 198.51.100.100
+	defer ip -4 route del blackhole 198.51.100.100
 
 	devlink trap set $DEVLINK_DEV trap blackhole_route action trap
-}
-
-router_destroy()
-{
-	devlink trap set $DEVLINK_DEV trap blackhole_route action drop
-
-	ip -4 route del blackhole 198.51.100.100
-
-	mtu_restore $rp2
-	mtu_restore $rp1
-	__addr_add_del $rp2 del 198.51.100.2/24
-	__addr_add_del $rp1 del 192.0.2.2/24
-
-	ip link set dev $rp2 down
-	ip link set dev $rp1 down
+	defer devlink trap set $DEVLINK_DEV trap blackhole_route action drop
 }
 
 setup_prepare()
@@ -114,7 +103,11 @@ setup_prepare()
 
 	rp1_mac=$(mac_get $rp1)
 
+	# Reload to ensure devlink-trap settings are back to default.
+	defer devlink_reload
+
 	vrf_prepare
+	defer vrf_cleanup
 
 	h1_create
 	h2_create
@@ -122,21 +115,6 @@ setup_prepare()
 	router_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	router_destroy
-
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-
-	# Reload to ensure devlink-trap settings are back to default.
-	devlink_reload
-}
-
 rate_limits_test()
 {
 	RET=0
@@ -214,7 +192,10 @@ __rate_test()
 	# by the policer. Make sure measured received rate is about 1000 pps
 	log_info "=== Tx rate: Highest, Policer rate: 1000 pps ==="
 
+	defer_scope_push
+
 	start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac
+	defer stop_traffic $!
 
 	sleep 5 # Take measurements when rate is stable
 
@@ -229,13 +210,16 @@ __rate_test()
 	check_err $? "Expected non-zero policer drop rate, got 0"
 	log_info "Measured policer drop rate of $drop_rate pps"
 
-	stop_traffic
+	defer_scope_pop
 
 	# Send packets at a rate of 1000 pps and make sure they are not dropped
 	# by the policer
 	log_info "=== Tx rate: 1000 pps, Policer rate: 1000 pps ==="
 
+	defer_scope_push
+
 	start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -d 1msec
+	defer stop_traffic $!
 
 	sleep 5 # Take measurements when rate is stable
 
@@ -244,7 +228,7 @@ __rate_test()
 	check_err $? "Expected zero policer drop rate, got a drop rate of $drop_rate pps"
 	log_info "Measured policer drop rate of $drop_rate pps"
 
-	stop_traffic
+	defer_scope_pop
 
 	# Unbind the policer and send packets at highest possible rate. Make
 	# sure they are not dropped by the policer and that the measured
@@ -253,7 +237,10 @@ __rate_test()
 
 	devlink trap group set $DEVLINK_DEV group l3_drops nopolicer
 
+	defer_scope_push
+
 	start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac
+	defer stop_traffic $!
 
 	rate=$(trap_rate_get)
 	(( rate > 1000 ))
@@ -265,7 +252,7 @@ __rate_test()
 	check_err $? "Expected zero policer drop rate, got a drop rate of $drop_rate pps"
 	log_info "Measured policer drop rate of $drop_rate pps"
 
-	stop_traffic
+	defer_scope_pop
 
 	log_test "Trap policer rate"
 }
-- 
cgit v1.2.3


From 81bc949f640f78b507c7523de7c750bcc87c1bb8 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 18 Oct 2024 12:55:58 +0200
Subject: selftests: tls: add a selftest for wrapping rec_seq

Set the initial rec_seq to 0xffffffffffffffff so that it wraps
immediately. The send() call should fail with EBADMSG.

A bug in this code was fixed in commit cfaa80c91f6f ("net/tls: do not
free tls_rec on async operation in bpf_exec_tx_verdict()").

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20775fcfd0371422921ee60a42de170c0398ac10.1729244987.git.sd@queasysnail.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/tls.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index f27a12d2a2c9..1a706d03bb6b 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -266,6 +266,25 @@ TEST_F(tls_basic, bad_cipher)
 	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, sizeof(struct tls12_crypto_info_aes_gcm_128)), -1);
 }
 
+TEST_F(tls_basic, recseq_wrap)
+{
+	struct tls_crypto_info_keys tls12;
+	char const *test_str = "test_read";
+	int send_len = 10;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12);
+	memset(&tls12.aes128.rec_seq, 0xff, sizeof(tls12.aes128.rec_seq));
+
+	ASSERT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+	ASSERT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
 FIXTURE(tls)
 {
 	int fd, cfd;
-- 
cgit v1.2.3


From 47e99f30730c0167cd32c9a2fd4a74f0a024cb2b Mon Sep 17 00:00:00 2001
From: Leo Stone <leocstone@gmail.com>
Date: Mon, 21 Oct 2024 10:46:44 -0700
Subject: selftest/tcp-ao: Add filter tests

Add tests that check if getsockopt(TCP_AO_GET_KEYS) returns the right
keys when using different filters.

Sample output:

> # ok 114 filter keys: by sndid, rcvid, address
> # ok 115 filter keys: by is_current
> # ok 116 filter keys: by is_rnext
> # ok 117 filter keys: by sndid, rcvid
> # ok 118 filter keys: correct nkeys when in.nkeys < matches

Acked-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: Leo Stone <leocstone@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20241021174652.6949-1-leocstone@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/tcp_ao/setsockopt-closed.c       | 186 ++++++++++++++++++++-
 1 file changed, 181 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
index 084db4ecdff6..0abb9807d742 100644
--- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
+++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
@@ -6,6 +6,8 @@
 
 static union tcp_addr tcp_md5_client;
 
+#define FILTER_TEST_NKEYS 16
+
 static int test_port = 7788;
 static void make_listen(int sk)
 {
@@ -813,23 +815,197 @@ static void duplicate_tests(void)
 	setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: SendID differs");
 }
 
+static void fetch_all_keys(int sk, struct tcp_ao_getsockopt *keys)
+{
+	socklen_t optlen = sizeof(struct tcp_ao_getsockopt);
+
+	memset(keys, 0, sizeof(struct tcp_ao_getsockopt) * FILTER_TEST_NKEYS);
+	keys[0].get_all = 1;
+	keys[0].nkeys = FILTER_TEST_NKEYS;
+	if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, &keys[0], &optlen))
+		test_error("getsockopt");
+}
+
+static int prepare_test_keys(struct tcp_ao_getsockopt *keys)
+{
+	const char *test_password = "Test password number ";
+	struct tcp_ao_add test_ao[FILTER_TEST_NKEYS];
+	char test_password_scratch[64] = {};
+	u8 rcvid = 100, sndid = 100;
+	int sk;
+
+	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0)
+		test_error("socket()");
+
+	for (int i = 0; i < FILTER_TEST_NKEYS; i++) {
+		snprintf(test_password_scratch, 64, "%s %d", test_password, i);
+		test_prepare_key(&test_ao[i], DEFAULT_TEST_ALGO, this_ip_dest,
+			  false, false, DEFAULT_TEST_PREFIX, 0, sndid++,
+			  rcvid++, 0, 0, strlen(test_password_scratch),
+			  test_password_scratch);
+	}
+	test_ao[0].set_current = 1;
+	test_ao[1].set_rnext = 1;
+	/* One key with a different addr and overlapping sndid, rcvid */
+	tcp_addr_to_sockaddr_in(&test_ao[2].addr, &this_ip_addr, 0);
+	test_ao[2].sndid = 100;
+	test_ao[2].rcvid = 100;
+
+	/* Add keys in a random order */
+	for (int i = 0; i < FILTER_TEST_NKEYS; i++) {
+		int randidx = rand() % (FILTER_TEST_NKEYS - i);
+
+		if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY,
+			       &test_ao[randidx], sizeof(struct tcp_ao_add)))
+			test_error("setsockopt()");
+		memcpy(&test_ao[randidx], &test_ao[FILTER_TEST_NKEYS - 1 - i],
+		       sizeof(struct tcp_ao_add));
+	}
+
+	fetch_all_keys(sk, keys);
+
+	return sk;
+}
+
+/* Assumes passwords are unique */
+static int compare_mkts(struct tcp_ao_getsockopt *expected, int nexpected,
+			struct tcp_ao_getsockopt *actual, int nactual)
+{
+	int matches = 0;
+
+	for (int i = 0; i < nexpected; i++) {
+		for (int j = 0; j < nactual; j++) {
+			if (memcmp(expected[i].key, actual[j].key,
+				   TCP_AO_MAXKEYLEN) == 0)
+				matches++;
+		}
+	}
+	return nexpected - matches;
+}
+
+static void filter_keys_checked(int sk, struct tcp_ao_getsockopt *filter,
+				struct tcp_ao_getsockopt *expected,
+				unsigned int nexpected, const char *tst)
+{
+	struct tcp_ao_getsockopt filtered_keys[FILTER_TEST_NKEYS] = {};
+	struct tcp_ao_getsockopt all_keys[FILTER_TEST_NKEYS] = {};
+	socklen_t len = sizeof(struct tcp_ao_getsockopt);
+
+	fetch_all_keys(sk, all_keys);
+	memcpy(&filtered_keys[0], filter, sizeof(struct tcp_ao_getsockopt));
+	filtered_keys[0].nkeys = FILTER_TEST_NKEYS;
+	if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, filtered_keys, &len))
+		test_error("getsockopt");
+	if (filtered_keys[0].nkeys != nexpected) {
+		test_fail("wrong nr of keys, expected %u got %u", nexpected,
+			  filtered_keys[0].nkeys);
+		goto out_close;
+	}
+	if (compare_mkts(expected, nexpected, filtered_keys,
+			 filtered_keys[0].nkeys)) {
+		test_fail("got wrong keys back");
+		goto out_close;
+	}
+	test_ok("filter keys: %s", tst);
+
+out_close:
+	close(sk);
+	memset(filter, 0, sizeof(struct tcp_ao_getsockopt));
+}
+
+static void filter_tests(void)
+{
+	struct tcp_ao_getsockopt original_keys[FILTER_TEST_NKEYS];
+	struct tcp_ao_getsockopt expected_keys[FILTER_TEST_NKEYS];
+	struct tcp_ao_getsockopt filter = {};
+	int sk, f, nmatches;
+	socklen_t len;
+
+	f = 2;
+	sk = prepare_test_keys(original_keys);
+	filter.rcvid = original_keys[f].rcvid;
+	filter.sndid = original_keys[f].sndid;
+	memcpy(&filter.addr, &original_keys[f].addr,
+	       sizeof(original_keys[f].addr));
+	filter.prefix = original_keys[f].prefix;
+	filter_keys_checked(sk, &filter, &original_keys[f], 1,
+			    "by sndid, rcvid, address");
+
+	f = -1;
+	sk = prepare_test_keys(original_keys);
+	for (int i = 0; i < original_keys[0].nkeys; i++) {
+		if (original_keys[i].is_current) {
+			f = i;
+			break;
+		}
+	}
+	if (f < 0)
+		test_error("No current key after adding one");
+	filter.is_current = 1;
+	filter_keys_checked(sk, &filter, &original_keys[f], 1, "by is_current");
+
+	f = -1;
+	sk = prepare_test_keys(original_keys);
+	for (int i = 0; i < original_keys[0].nkeys; i++) {
+		if (original_keys[i].is_rnext) {
+			f = i;
+			break;
+		}
+	}
+	if (f < 0)
+		test_error("No rnext key after adding one");
+	filter.is_rnext = 1;
+	filter_keys_checked(sk, &filter, &original_keys[f], 1, "by is_rnext");
+
+	f = -1;
+	nmatches = 0;
+	sk = prepare_test_keys(original_keys);
+	for (int i = 0; i < original_keys[0].nkeys; i++) {
+		if (original_keys[i].sndid == 100) {
+			f = i;
+			memcpy(&expected_keys[nmatches], &original_keys[i],
+			       sizeof(struct tcp_ao_getsockopt));
+			nmatches++;
+		}
+	}
+	if (f < 0)
+		test_error("No key for sndid 100");
+	if (nmatches != 2)
+		test_error("Should have 2 keys with sndid 100");
+	filter.rcvid = original_keys[f].rcvid;
+	filter.sndid = original_keys[f].sndid;
+	filter.addr.ss_family = test_family;
+	filter_keys_checked(sk, &filter, expected_keys, nmatches,
+			    "by sndid, rcvid");
+
+	sk = prepare_test_keys(original_keys);
+	filter.get_all = 1;
+	filter.nkeys = FILTER_TEST_NKEYS / 2;
+	len = sizeof(struct tcp_ao_getsockopt);
+	if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, &filter, &len))
+		test_error("getsockopt");
+	if (filter.nkeys == FILTER_TEST_NKEYS)
+		test_ok("filter keys: correct nkeys when in.nkeys < matches");
+	else
+		test_fail("filter keys: wrong nkeys, expected %u got %u",
+			  FILTER_TEST_NKEYS, filter.nkeys);
+}
+
 static void *client_fn(void *arg)
 {
 	if (inet_pton(TEST_FAMILY, __TEST_CLIENT_IP(2), &tcp_md5_client) != 1)
 		test_error("Can't convert ip address");
 	extend_tests();
 	einval_tests();
+	filter_tests();
 	duplicate_tests();
-	/*
-	 * TODO: check getsockopt(TCP_AO_GET_KEYS) with different filters
-	 * returning proper nr & keys;
-	 */
 
 	return NULL;
 }
 
 int main(int argc, char *argv[])
 {
-	test_init(121, client_fn, NULL);
+	test_init(126, client_fn, NULL);
 	return 0;
 }
-- 
cgit v1.2.3


From 9a1036389fa25cf90d58e3ae1bb0b1ad877ef1c8 Mon Sep 17 00:00:00 2001
From: Karan Sanghavi <karansanghvi98@gmail.com>
Date: Tue, 22 Oct 2024 18:30:52 +0000
Subject: selftests: tc-testing: Fix typo error

Correct the typo errors in json files

- "diffferent" is corrected to "different".
- "muliple" and "miltiple" is corrected to "multiple".

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Karan Sanghavi <karansanghvi98@gmail.com>
Link: https://patch.msgid.link/20241022-multiple_spell_error-v2-1-7e5036506fe5@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/tc-testing/tc-tests/filters/basic.json  | 6 +++---
 tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json | 6 +++---
 tools/testing/selftests/tc-testing/tc-tests/filters/flow.json   | 2 +-
 tools/testing/selftests/tc-testing/tc-tests/filters/route.json  | 2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
index d1278de8ebc3..c9309a44a87e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
@@ -67,7 +67,7 @@
     },
     {
         "id": "4943",
-        "name": "Add basic filter with cmp ematch u32/link layer and miltiple actions",
+        "name": "Add basic filter with cmp ematch u32/link layer and multiple actions",
         "category": [
             "filter",
             "basic"
@@ -155,7 +155,7 @@
     },
     {
         "id": "32d8",
-        "name": "Add basic filter with cmp ematch u32/network layer and miltiple actions",
+        "name": "Add basic filter with cmp ematch u32/network layer and multiple actions",
         "category": [
             "filter",
             "basic"
@@ -243,7 +243,7 @@
     },
     {
         "id": "62d7",
-        "name": "Add basic filter with cmp ematch u32/transport layer and miltiple actions",
+        "name": "Add basic filter with cmp ematch u32/transport layer and multiple actions",
         "category": [
             "filter",
             "basic"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json b/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json
index 03723cf84379..35c9a7dbe1c4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json
@@ -67,7 +67,7 @@
     },
     {
         "id": "0234",
-        "name": "Add cgroup filter with cmp ematch u32/link layer and miltiple actions",
+        "name": "Add cgroup filter with cmp ematch u32/link layer and multiple actions",
         "category": [
             "filter",
             "cgroup"
@@ -155,7 +155,7 @@
     },
     {
         "id": "2733",
-        "name": "Add cgroup filter with cmp ematch u32/network layer and miltiple actions",
+        "name": "Add cgroup filter with cmp ematch u32/network layer and multiple actions",
         "category": [
             "filter",
             "cgroup"
@@ -1189,7 +1189,7 @@
     },
     {
         "id": "4319",
-        "name": "Replace cgroup filter with diffferent match",
+        "name": "Replace cgroup filter with different match",
         "category": [
             "filter",
             "cgroup"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
index 58189327f644..996448afe31b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
@@ -507,7 +507,7 @@
     },
     {
         "id": "4341",
-        "name": "Add flow filter with muliple ops",
+        "name": "Add flow filter with multiple ops",
         "category": [
             "filter",
             "flow"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json
index 8d8de8f65aef..05cedca67cca 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json
@@ -111,7 +111,7 @@
     },
     {
         "id": "7994",
-        "name": "Add route filter with miltiple actions",
+        "name": "Add route filter with multiple actions",
         "category": [
             "filter",
             "route"
-- 
cgit v1.2.3


From 0ab7cd1f18648ab50c4685553ca92e8cdc4a42da Mon Sep 17 00:00:00 2001
From: Vincent Li <vincent.mc.li@gmail.com>
Date: Fri, 25 Oct 2024 03:19:52 +0000
Subject: selftests/bpf: remove xdp_synproxy IP_DF check

In real world production websites, the IP_DF flag
is not always set for each packet from these websites.
the IP_DF flag check breaks Internet connection to
these websites for home based firewall like BPFire
when XDP synproxy program is attached to firewall
Internet facing side interface. see [0]

[0] https://github.com/vincentmli/BPFire/issues/59

Signed-off-by: Vincent Li <vincent.mc.li@gmail.com>
Link: https://lore.kernel.org/r/20241025031952.1351150-1-vincent.mc.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index f8f5dc9f72b8..62b8e29ced9f 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -21,7 +21,6 @@
 
 #define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
 
-#define IP_DF 0x4000
 #define IP_MF 0x2000
 #define IP_OFFSET 0x1fff
 
@@ -442,7 +441,7 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo
 		/* TCP doesn't normally use fragments, and XDP can't reassemble
 		 * them.
 		 */
-		if ((hdr->ipv4->frag_off & bpf_htons(IP_DF | IP_MF | IP_OFFSET)) != bpf_htons(IP_DF))
+		if ((hdr->ipv4->frag_off & bpf_htons(IP_MF | IP_OFFSET)) != 0)
 			return XDP_DROP;
 
 		tup.ipv4.saddr = hdr->ipv4->saddr;
-- 
cgit v1.2.3


From b87f584024e1df289027cb7671de6af0d97b5de9 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay@kernel.org>
Date: Sat, 26 Oct 2024 12:53:38 +0000
Subject: selftests/bpf: Don't mask result of bpf_csum_diff() in test_verifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bpf_csum_diff() helper has been fixed to return a 16-bit value for
all archs, so now we don't need to mask the result.

This commit is basically reverting the below:

commit 6185266c5a85 ("selftests/bpf: Mask bpf_csum_diff() return value
to 16 bits in test_verifier")

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20241026125339.26459-4-puranjay@kernel.org
---
 tools/testing/selftests/bpf/progs/verifier_array_access.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c
index 95d7ecc12963..4195aa824ba5 100644
--- a/tools/testing/selftests/bpf/progs/verifier_array_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c
@@ -368,8 +368,7 @@ __naked void a_read_only_array_2_1(void)
 	r4 = 0;						\
 	r5 = 0;						\
 	call %[bpf_csum_diff];				\
-l0_%=:	r0 &= 0xffff;					\
-	exit;						\
+l0_%=:	exit;						\
 "	:
 	: __imm(bpf_csum_diff),
 	  __imm(bpf_map_lookup_elem),
-- 
cgit v1.2.3


From 00c1f3dc66a38cf65c3cfd0cb4fe7acfc7f60e37 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay@kernel.org>
Date: Sat, 26 Oct 2024 12:53:39 +0000
Subject: selftests/bpf: Add a selftest for bpf_csum_diff()

Add a selftest for the bpf_csum_diff() helper. This selftests runs the
helper in all three configurations(push, pull, and diff) and verifies
its output. The correct results have been computed by hand and by the
helper's older implementation.

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20241026125339.26459-5-puranjay@kernel.org
---
 .../selftests/bpf/prog_tests/test_csum_diff.c      | 408 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/csum_diff_test.c |  42 +++
 2 files changed, 450 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/test_csum_diff.c
 create mode 100644 tools/testing/selftests/bpf/progs/csum_diff_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c b/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c
new file mode 100644
index 000000000000..107b20d43e83
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates */
+#include <test_progs.h>
+#include "csum_diff_test.skel.h"
+
+#define BUFF_SZ 512
+
+struct testcase {
+	unsigned long long to_buff[BUFF_SZ / 8];
+	unsigned int to_buff_len;
+	unsigned long long from_buff[BUFF_SZ / 8];
+	unsigned int from_buff_len;
+	unsigned short seed;
+	unsigned short result;
+};
+
+#define NUM_PUSH_TESTS 4
+
+struct testcase push_tests[NUM_PUSH_TESTS] = {
+	{
+		.to_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.to_buff_len = 8,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0,
+		.result = 0x3b3b
+	},
+	{
+		.to_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.to_buff_len = 16,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0x1234,
+		.result = 0x88aa
+	},
+	{
+		.to_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.to_buff_len = 15,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0x1234,
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		.result = 0xcaa9
+#else
+		.result = 0x87fd
+#endif
+	},
+	{
+		.to_buff = {
+			0x327b23c66b8b4567,
+			0x66334873643c9869,
+			0x19495cff74b0dc51,
+			0x625558ec2ae8944a,
+			0x46e87ccd238e1f29,
+			0x507ed7ab3d1b58ba,
+			0x41b71efb2eb141f2,
+			0x7545e14679e2a9e3,
+			0x5bd062c2515f007c,
+			0x4db127f812200854,
+			0x1f16e9e80216231b,
+			0x66ef438d1190cde7,
+			0x3352255a140e0f76,
+			0x0ded7263109cf92e,
+			0x1befd79f7fdcc233,
+			0x6b68079a41a7c4c9,
+			0x25e45d324e6afb66,
+			0x431bd7b7519b500d,
+			0x7c83e4583f2dba31,
+			0x62bbd95a257130a3,
+			0x628c895d436c6125,
+			0x721da317333ab105,
+			0x2d1d5ae92443a858,
+			0x75a2a8d46763845e,
+			0x79838cb208edbdab,
+			0x0b03e0c64353d0cd,
+			0x54e49eb4189a769b,
+			0x2ca8861171f32454,
+			0x02901d820836c40e,
+			0x081386413a95f874,
+			0x7c3dbd3d1e7ff521,
+			0x6ceaf087737b8ddc,
+			0x4516dde922221a70,
+			0x614fd4a13006c83e,
+			0x5577f8e1419ac241,
+			0x05072367440badfc,
+			0x77465f013804823e,
+			0x5c482a977724c67e,
+			0x5e884adc2463b9ea,
+			0x2d51779651ead36b,
+			0x153ea438580bd78f,
+			0x70a64e2a3855585c,
+			0x2a487cb06a2342ec,
+			0x725a06fb1d4ed43b,
+			0x57e4ccaf2cd89a32,
+			0x4b588f547a6d8d3c,
+			0x6de91b18542289ec,
+			0x7644a45c38437fdb,
+			0x684a481a32fff902,
+			0x749abb43579478fe,
+			0x1ba026fa3dc240fb,
+			0x75c6c33a79a1deaa,
+			0x70c6a52912e685fb,
+			0x374a3fe6520eedd1,
+			0x23f9c13c4f4ef005,
+			0x275ac794649bb77c,
+			0x1cf10fd839386575,
+			0x235ba861180115be,
+			0x354fe9f947398c89,
+			0x741226bb15b5af5c,
+			0x10233c990d34b6a8,
+			0x615740953f6ab60f,
+			0x77ae35eb7e0c57b1,
+			0x310c50b3579be4f1,
+		},
+		.to_buff_len = 512,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0xffff,
+		.result = 0xca45
+	},
+};
+
+#define NUM_PULL_TESTS 4
+
+struct testcase pull_tests[NUM_PULL_TESTS] = {
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.from_buff_len = 8,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0,
+		.result = 0xc4c4
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.from_buff_len = 16,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0x1234,
+		.result = 0x9bbd
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.from_buff_len = 15,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0x1234,
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		.result = 0x59be
+#else
+		.result = 0x9c6a
+#endif
+	},
+	{
+		.from_buff = {
+			0x327b23c66b8b4567,
+			0x66334873643c9869,
+			0x19495cff74b0dc51,
+			0x625558ec2ae8944a,
+			0x46e87ccd238e1f29,
+			0x507ed7ab3d1b58ba,
+			0x41b71efb2eb141f2,
+			0x7545e14679e2a9e3,
+			0x5bd062c2515f007c,
+			0x4db127f812200854,
+			0x1f16e9e80216231b,
+			0x66ef438d1190cde7,
+			0x3352255a140e0f76,
+			0x0ded7263109cf92e,
+			0x1befd79f7fdcc233,
+			0x6b68079a41a7c4c9,
+			0x25e45d324e6afb66,
+			0x431bd7b7519b500d,
+			0x7c83e4583f2dba31,
+			0x62bbd95a257130a3,
+			0x628c895d436c6125,
+			0x721da317333ab105,
+			0x2d1d5ae92443a858,
+			0x75a2a8d46763845e,
+			0x79838cb208edbdab,
+			0x0b03e0c64353d0cd,
+			0x54e49eb4189a769b,
+			0x2ca8861171f32454,
+			0x02901d820836c40e,
+			0x081386413a95f874,
+			0x7c3dbd3d1e7ff521,
+			0x6ceaf087737b8ddc,
+			0x4516dde922221a70,
+			0x614fd4a13006c83e,
+			0x5577f8e1419ac241,
+			0x05072367440badfc,
+			0x77465f013804823e,
+			0x5c482a977724c67e,
+			0x5e884adc2463b9ea,
+			0x2d51779651ead36b,
+			0x153ea438580bd78f,
+			0x70a64e2a3855585c,
+			0x2a487cb06a2342ec,
+			0x725a06fb1d4ed43b,
+			0x57e4ccaf2cd89a32,
+			0x4b588f547a6d8d3c,
+			0x6de91b18542289ec,
+			0x7644a45c38437fdb,
+			0x684a481a32fff902,
+			0x749abb43579478fe,
+			0x1ba026fa3dc240fb,
+			0x75c6c33a79a1deaa,
+			0x70c6a52912e685fb,
+			0x374a3fe6520eedd1,
+			0x23f9c13c4f4ef005,
+			0x275ac794649bb77c,
+			0x1cf10fd839386575,
+			0x235ba861180115be,
+			0x354fe9f947398c89,
+			0x741226bb15b5af5c,
+			0x10233c990d34b6a8,
+			0x615740953f6ab60f,
+			0x77ae35eb7e0c57b1,
+			0x310c50b3579be4f1,
+		},
+		.from_buff_len = 512,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0xffff,
+		.result = 0x35ba
+	},
+};
+
+#define NUM_DIFF_TESTS 4
+
+struct testcase diff_tests[NUM_DIFF_TESTS] = {
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.from_buff_len = 8,
+		.to_buff = {
+			0xabababababababab,
+		},
+		.to_buff_len = 8,
+		.seed = 0,
+		.result = 0x7373
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.from_buff_len = 7,
+		.to_buff = {
+			0xabababababababab,
+		},
+		.to_buff_len = 7,
+		.seed = 0,
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		.result = 0xa673
+#else
+		.result = 0x73b7
+#endif
+	},
+	{
+		.from_buff = {
+			0,
+		},
+		.from_buff_len = 8,
+		.to_buff = {
+			0xabababababababab,
+		},
+		.to_buff_len = 8,
+		.seed = 0,
+		.result = 0xaeae
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef
+		},
+		.from_buff_len = 8,
+		.to_buff = {
+			0,
+		},
+		.to_buff_len = 8,
+		.seed = 0xffff,
+		.result = 0xc4c4
+	},
+};
+
+#define NUM_EDGE_TESTS 4
+
+struct testcase edge_tests[NUM_EDGE_TESTS] = {
+	{
+		.from_buff = {},
+		.from_buff_len = 0,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0,
+		.result = 0
+	},
+	{
+		.from_buff = {
+			0x1234
+		},
+		.from_buff_len = 0,
+		.to_buff = {
+			0x1234
+		},
+		.to_buff_len = 0,
+		.seed = 0,
+		.result = 0
+	},
+	{
+		.from_buff = {},
+		.from_buff_len = 0,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0x1234,
+		.result = 0x1234
+	},
+	{
+		.from_buff = {},
+		.from_buff_len = 512,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0xffff,
+		.result = 0xffff
+	},
+};
+
+static unsigned short trigger_csum_diff(const struct csum_diff_test *skel)
+{
+	u8 tmp_out[64 << 2] = {};
+	u8 tmp_in[64] = {};
+	int err;
+	int pfd;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = tmp_in,
+		.data_size_in = sizeof(tmp_in),
+		.data_out = tmp_out,
+		.data_size_out = sizeof(tmp_out),
+		.repeat = 1,
+	);
+	pfd = bpf_program__fd(skel->progs.compute_checksum);
+	err = bpf_prog_test_run_opts(pfd, &topts);
+	if (err)
+		return -1;
+
+	return skel->bss->result;
+}
+
+static void test_csum_diff(struct testcase *tests, int num_tests)
+{
+	struct csum_diff_test *skel;
+	unsigned short got;
+	int err;
+
+	for (int i = 0; i < num_tests; i++) {
+		skel = csum_diff_test__open();
+		if (!ASSERT_OK_PTR(skel, "csum_diff_test open"))
+			return;
+
+		skel->rodata->to_buff_len = tests[i].to_buff_len;
+		skel->rodata->from_buff_len = tests[i].from_buff_len;
+
+		err = csum_diff_test__load(skel);
+		if (!ASSERT_EQ(err, 0, "csum_diff_test load"))
+			goto out;
+
+		memcpy(skel->bss->to_buff, tests[i].to_buff, tests[i].to_buff_len);
+		memcpy(skel->bss->from_buff, tests[i].from_buff, tests[i].from_buff_len);
+		skel->bss->seed = tests[i].seed;
+
+		got = trigger_csum_diff(skel);
+		ASSERT_EQ(got, tests[i].result, "csum_diff result");
+
+		csum_diff_test__destroy(skel);
+	}
+
+	return;
+out:
+	csum_diff_test__destroy(skel);
+}
+
+void test_test_csum_diff(void)
+{
+	if (test__start_subtest("csum_diff_push"))
+		test_csum_diff(push_tests, NUM_PUSH_TESTS);
+	if (test__start_subtest("csum_diff_pull"))
+		test_csum_diff(pull_tests, NUM_PULL_TESTS);
+	if (test__start_subtest("csum_diff_diff"))
+		test_csum_diff(diff_tests, NUM_DIFF_TESTS);
+	if (test__start_subtest("csum_diff_edge"))
+		test_csum_diff(edge_tests, NUM_EDGE_TESTS);
+}
diff --git a/tools/testing/selftests/bpf/progs/csum_diff_test.c b/tools/testing/selftests/bpf/progs/csum_diff_test.c
new file mode 100644
index 000000000000..9438f1773a58
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/csum_diff_test.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates */
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define BUFF_SZ 512
+
+/* Will be updated by benchmark before program loading */
+char to_buff[BUFF_SZ];
+const volatile unsigned int to_buff_len = 0;
+char from_buff[BUFF_SZ];
+const volatile unsigned int from_buff_len = 0;
+unsigned short seed = 0;
+
+short result;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tc")
+int compute_checksum(void *ctx)
+{
+	int to_len_half = to_buff_len / 2;
+	int from_len_half = from_buff_len / 2;
+	short result2;
+
+	/* Calculate checksum in one go */
+	result2 = bpf_csum_diff((void *)from_buff, from_buff_len,
+				(void *)to_buff, to_buff_len, seed);
+
+	/* Calculate checksum by concatenating bpf_csum_diff()*/
+	result = bpf_csum_diff((void *)from_buff, from_buff_len - from_len_half,
+			       (void *)to_buff, to_buff_len - to_len_half, seed);
+
+	result = bpf_csum_diff((void *)from_buff + (from_buff_len - from_len_half), from_len_half,
+			       (void *)to_buff + (to_buff_len - to_len_half), to_len_half, result);
+
+	result = (result == result2) ? result : 0;
+
+	return 0;
+}
-- 
cgit v1.2.3


From 365836e010a131cce62e3e0bab0348d08ca08490 Mon Sep 17 00:00:00 2001
From: Yunshui Jiang <jiangyunshui@kylinos.cn>
Date: Mon, 28 Oct 2024 16:27:56 +0800
Subject: tests: hsr: Increase timeout to 50 seconds

The HSR test, hsr_ping.sh, actually needs 7 min to run. Around 375s to
be exact, and even more on a debug kernel or kernel with other network
security limits. The timeout setting for the kselftest is currently 45
seconds, which is way too short to integrate hsr tests to run_kselftest
infrastructure. However, timeout of hundreds of seconds is quite a long
time, especially in a CI/CD environment. It seems that we need
accelerate the test and balance with timeout setting.

The most time-consuming func is do_ping_long, where ping command sends
10 packages to the given address. The default interval between two ping
packages is 1s according to the ping Mannual. There isn't any operation
between pings thus we could pass -i 0.1 to ping to make it 10 times
faster.

While even with this short interval, the test still need about 46.4
seconds to finish because of the two HSR interfaces, each of which is
tested by calling do_ping func 12 times and do_ping_long func 19 times
and sleep for 3s.

So, an explicit setting is also needed to slightly increase the
timeout. And to leave us some slack, use 50 as default timeout.

Signed-off-by: Yunshui Jiang <jiangyunshui@kylinos.cn>
Link: https://patch.msgid.link/20241028082757.2945232-1-jiangyunshui@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/hsr/hsr_common.sh | 4 ++--
 tools/testing/selftests/net/hsr/settings      | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/net/hsr/settings

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/hsr/hsr_common.sh b/tools/testing/selftests/net/hsr/hsr_common.sh
index 8e97b1f2e7e5..1dc882ac1c74 100644
--- a/tools/testing/selftests/net/hsr/hsr_common.sh
+++ b/tools/testing/selftests/net/hsr/hsr_common.sh
@@ -15,7 +15,7 @@ do_ping()
 {
 	local netns="$1"
 	local connect_addr="$2"
-	local ping_args="-q -c 2"
+	local ping_args="-q -c 2 -i 0.1"
 
 	if is_v6 "${connect_addr}"; then
 		$ipv6 || return 0
@@ -36,7 +36,7 @@ do_ping_long()
 {
 	local netns="$1"
 	local connect_addr="$2"
-	local ping_args="-q -c 10"
+	local ping_args="-q -c 10 -i 0.1"
 
 	if is_v6 "${connect_addr}"; then
 		$ipv6 || return 0
diff --git a/tools/testing/selftests/net/hsr/settings b/tools/testing/selftests/net/hsr/settings
new file mode 100644
index 000000000000..0fbc037f2aa8
--- /dev/null
+++ b/tools/testing/selftests/net/hsr/settings
@@ -0,0 +1 @@
+timeout=50
-- 
cgit v1.2.3


From 7f66456d776a0c44b5e2b932bf8ed186ccec3bc1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 29 Oct 2024 12:26:03 -0700
Subject: selftests: netdevsim: add fib_notifications to Makefile

Commit 19d36d2971e6 ("selftests: netdevsim: Add fib_notifications test")
added the test but didn't include it in the Makefile.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20241029192603.509295-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/netdevsim/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile
index 5bace0b7fb57..cc08b220323f 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/Makefile
+++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile
@@ -8,6 +8,7 @@ TEST_PROGS = devlink.sh \
 	ethtool-pause.sh \
 	ethtool-ring.sh \
 	fib.sh \
+	fib_notifications.sh \
 	hw_stats_l3.sh \
 	nexthop.sh \
 	peer.sh \
-- 
cgit v1.2.3


From d3774a4b21e98c336d71d67b7605d91f344524c9 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Wed, 30 Oct 2024 08:59:43 +0800
Subject: selftests/net: Fix ./ns-XXXXXX not cleanup

```
readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
readonly BASE=`basename $STATS`
```
It could be a mistake to write to $BASE rather than $STATS, where $STATS
is used to save the NSTAT_HISTORY and it will be cleaned up before exit.

Although since we've been creating the wrong file this whole time and
everything worked, it's fine to remove these 2 lines completely

Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Link: https://patch.msgid.link/20241030005943.400225-1-lizhijian@fujitsu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/veth.sh | 2 --
 1 file changed, 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 4f1edbafb946..6bb7dfaa30b6 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -46,8 +46,6 @@ create_ns() {
 		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
 		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
 	done
-	echo "#kernel" > $BASE
-	chmod go-rw $BASE
 }
 
 __chk_flag() {
-- 
cgit v1.2.3


From d051cd72dcb769c842494b1dbe29067aba45474f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 29 Oct 2024 02:00:28 -0700
Subject: net: netconsole: selftests: Change the IP subnet

Use a less populated IP range to run the tests, as suggested by Petr in
Link: https://lore.kernel.org/netdev/87ikvukv3s.fsf@nvidia.com/.

Suggested-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20241029090030.1793551-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/netcons_basic.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh
index 06021b2059b7..8d28e5189e91 100755
--- a/tools/testing/selftests/drivers/net/netcons_basic.sh
+++ b/tools/testing/selftests/drivers/net/netcons_basic.sh
@@ -20,9 +20,9 @@ SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
 
 # Simple script to test dynamic targets in netconsole
 SRCIF="" # to be populated later
-SRCIP=192.168.1.1
+SRCIP=192.0.2.1
 DSTIF="" # to be populated later
-DSTIP=192.168.1.2
+DSTIP=192.0.2.2
 
 PORT="6666"
 MSG="netconsole selftest"
-- 
cgit v1.2.3


From afa4ceb0fb648655c9f04921ccc801feb034109c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 29 Oct 2024 02:00:29 -0700
Subject: net: netconsole: selftests: Add userdata validation

Extend netcons_basic selftest to verify the userdata functionality by:
 1. Creating a test key in the userdata configfs directory
 2. Writing a known value to the key
 3. Validating the key-value pair appears in the captured network output

This ensures the userdata feature is properly tested during selftests.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20241029090030.1793551-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/netcons_basic.sh | 29 ++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh
index 8d28e5189e91..182eb1a97e59 100755
--- a/tools/testing/selftests/drivers/net/netcons_basic.sh
+++ b/tools/testing/selftests/drivers/net/netcons_basic.sh
@@ -26,10 +26,13 @@ DSTIP=192.0.2.2
 
 PORT="6666"
 MSG="netconsole selftest"
+USERDATA_KEY="key"
+USERDATA_VALUE="value"
 TARGET=$(mktemp -u netcons_XXXXX)
 DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk)
 NETCONS_CONFIGFS="/sys/kernel/config/netconsole"
 NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}"
+KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}"
 # NAMESPACE will be populated by setup_ns with a random value
 NAMESPACE=""
 
@@ -122,6 +125,8 @@ function cleanup() {
 
 	# delete netconsole dynamic reconfiguration
 	echo 0 > "${NETCONS_PATH}"/enabled
+	# Remove key
+	rmdir "${KEY_PATH}"
 	# Remove the configfs entry
 	rmdir "${NETCONS_PATH}"
 
@@ -136,6 +141,18 @@ function cleanup() {
 	echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk
 }
 
+function set_user_data() {
+	if [[ ! -d "${NETCONS_PATH}""/userdata" ]]
+	then
+		echo "Userdata path not available in ${NETCONS_PATH}/userdata"
+		exit "${ksft_skip}"
+	fi
+
+	mkdir -p "${KEY_PATH}"
+	VALUE_PATH="${KEY_PATH}""/value"
+	echo "${USERDATA_VALUE}" > "${VALUE_PATH}"
+}
+
 function listen_port_and_save_to() {
 	local OUTPUT=${1}
 	# Just wait for 2 seconds
@@ -146,6 +163,10 @@ function listen_port_and_save_to() {
 function validate_result() {
 	local TMPFILENAME="$1"
 
+	# TMPFILENAME will contain something like:
+	# 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM
+	#  key=value
+
 	# Check if the file exists
 	if [ ! -f "$TMPFILENAME" ]; then
 		echo "FAIL: File was not generated." >&2
@@ -158,6 +179,12 @@ function validate_result() {
 		exit "${ksft_fail}"
 	fi
 
+	if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then
+		echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2
+		cat "${TMPFILENAME}" >&2
+		exit "${ksft_fail}"
+	fi
+
 	# Delete the file once it is validated, otherwise keep it
 	# for debugging purposes
 	rm "${TMPFILENAME}"
@@ -220,6 +247,8 @@ trap cleanup EXIT
 set_network
 # Create a dynamic target for netconsole
 create_dynamic_target
+# Set userdata "key" with the "value" value
+set_user_data
 # Listed for netconsole port inside the namespace and destination interface
 listen_port_and_save_to "${OUTPUT_FILE}" &
 # Wait for socat to start and listen to the port.
-- 
cgit v1.2.3


From 9ff75a23dff3622451057b2ccd88c19bbb293841 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 1 Nov 2024 11:31:48 -0300
Subject: selftests/tc-testing: add tests for qdisc_tree_reduce_backlog

Add 3 tests to check for the expected behaviour of
qdisc_tree_reduce_backlog in special scenarios.

- The first test checks if the qdisc class is notified of deletion for
major handle 'ffff:'.
- The second test checks the same as the first test but with 'ffff:' as the root
qdisc.
- The third test checks if everything works if ingress is active.

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Cong Wang <cong.wang@bytedance.com>
Link: https://patch.msgid.link/20241101143148.1218890-1-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/infra/qdiscs.json          | 98 ++++++++++++++++++++++
 1 file changed, 98 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
new file mode 100644
index 000000000000..d3dd65b05b5f
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -0,0 +1,98 @@
+[
+    {
+        "id": "ca5e",
+        "name": "Check class delete notification for ffff:",
+        "category": [
+            "qdisc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: drr",
+            "$TC filter add dev $DUMMY parent 1: basic classid 1:1",
+            "$TC class add dev $DUMMY parent 1: classid 1:1 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle ffff: drr",
+            "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1",
+            "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr",
+            "$TC qdisc add dev $DUMMY parent ffff:1 netem delay 1s",
+            "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true",
+            "$TC class del dev $DUMMY classid ffff:1",
+            "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC -s qdisc ls dev $DUMMY",
+        "matchPattern": "drr 1: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle 1: drr",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY"
+        ]
+    },
+    {
+        "id": "e4b7",
+        "name": "Check class delete notification for root ffff:",
+        "category": [
+            "qdisc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle ffff: drr",
+            "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1",
+            "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr",
+            "$TC qdisc add dev $DUMMY parent ffff:1 netem delay 1s",
+            "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true",
+            "$TC class del dev $DUMMY classid ffff:1",
+            "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC qdisc ls dev $DUMMY",
+        "matchPattern": "drr ffff: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle ffff: drr",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY"
+        ]
+    },
+    {
+        "id": "33a9",
+        "name": "Check ingress is not searchable on backlog update",
+        "category": [
+            "qdisc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY ingress",
+            "$TC qdisc add dev $DUMMY root handle 1: drr",
+            "$TC filter add dev $DUMMY parent 1: basic classid 1:1",
+            "$TC class add dev $DUMMY parent 1: classid 1:1 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2: drr",
+            "$TC filter add dev $DUMMY parent 2: basic classid 2:1",
+            "$TC class add dev $DUMMY parent 2: classid 2:1 drr",
+            "$TC qdisc add dev $DUMMY parent 2:1 netem delay 1s",
+            "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true"
+        ],
+        "cmdUnderTest": "$TC class del dev $DUMMY classid 2:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc ls dev $DUMMY",
+        "matchPattern": "drr 1: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle 1: drr",
+            "$TC qdisc del dev $DUMMY ingress",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY"
+        ]
+    }
+]
-- 
cgit v1.2.3


From ac1bd50164b7995d0b8337b25d52ae79eefb9487 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 31 Oct 2024 09:40:46 +0800
Subject: selftests/bpf: Drop netns helpers in mptcp

New netns selftest helpers netns_new() and netns_free() has been added
in network_helpers.c, let's use them in mptcp selftests too instead of
using MPTCP's own helpers create_netns() and cleanup_netns().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/c02fda3177b34f9e74a044833fda9761627f4d07.1730338692.git.tanggeliang@kylinos.cn
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/mptcp.c | 42 ++++++++------------------
 1 file changed, 12 insertions(+), 30 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index be3cad2aff77..f8eb7f9d4fd2 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -69,24 +69,6 @@ struct mptcp_storage {
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
-static struct nstoken *create_netns(void)
-{
-	SYS(fail, "ip netns add %s", NS_TEST);
-	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
-
-	return open_netns(NS_TEST);
-fail:
-	return NULL;
-}
-
-static void cleanup_netns(struct nstoken *nstoken)
-{
-	if (nstoken)
-		close_netns(nstoken);
-
-	SYS_NOFAIL("ip netns del %s", NS_TEST);
-}
-
 static int start_mptcp_server(int family, const char *addr_str, __u16 port,
 			      int timeout_ms)
 {
@@ -206,15 +188,15 @@ out:
 
 static void test_base(void)
 {
-	struct nstoken *nstoken = NULL;
+	struct netns_obj *netns = NULL;
 	int server_fd, cgroup_fd;
 
 	cgroup_fd = test__join_cgroup("/mptcp");
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
-	nstoken = create_netns();
-	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
 		goto fail;
 
 	/* without MPTCP */
@@ -237,7 +219,7 @@ with_mptcp:
 	close(server_fd);
 
 fail:
-	cleanup_netns(nstoken);
+	netns_free(netns);
 	close(cgroup_fd);
 }
 
@@ -322,21 +304,21 @@ out:
 
 static void test_mptcpify(void)
 {
-	struct nstoken *nstoken = NULL;
+	struct netns_obj *netns = NULL;
 	int cgroup_fd;
 
 	cgroup_fd = test__join_cgroup("/mptcpify");
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
-	nstoken = create_netns();
-	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
 		goto fail;
 
 	ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify");
 
 fail:
-	cleanup_netns(nstoken);
+	netns_free(netns);
 	close(cgroup_fd);
 }
 
@@ -414,7 +396,7 @@ close_server:
 static void test_subflow(void)
 {
 	struct mptcp_subflow *skel;
-	struct nstoken *nstoken;
+	struct netns_obj *netns;
 	int cgroup_fd;
 
 	cgroup_fd = test__join_cgroup("/mptcp_subflow");
@@ -437,8 +419,8 @@ static void test_subflow(void)
 	if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow"))
 		goto skel_destroy;
 
-	nstoken = create_netns();
-	if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow"))
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_subflow"))
 		goto skel_destroy;
 
 	if (endpoint_init("subflow") < 0)
@@ -447,7 +429,7 @@ static void test_subflow(void)
 	run_subflow();
 
 close_netns:
-	cleanup_netns(nstoken);
+	netns_free(netns);
 skel_destroy:
 	mptcp_subflow__destroy(skel);
 close_cgroup:
-- 
cgit v1.2.3


From f72aa1b276281b4e4f75261af8425bc99d903f3e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 4 Nov 2024 12:34:26 +0100
Subject: selftests: net: include lib/sh/*.sh with lib.sh

Recently, the net/lib.sh file has been modified to include defer.sh from
net/lib/sh/ directory. The Makefile from net/lib has been modified
accordingly, but not the ones from the sub-targets using net/lib.sh.

Because of that, the new file is not installed as expected when
installing the Forwarding, MPTCP, and Netfilter targets, e.g.

  # make -C tools/testing/selftests TARGETS=net/mptcp install \
        INSTALL_PATH=/tmp/kself
  # cd /tmp/kself/
  # ./run_kselftest.sh -c net/mptcp
    TAP version 13
    1..7
    # timeout set to 1800
    # selftests: net/mptcp: mptcp_connect.sh
    # ./../lib.sh: line 5: /tmp/kself/net/lib/sh/defer.sh: No such file
      or directory
    # (...)

This can be fixed simply by adding all the .sh files from net/lib/sh
directory to the TEST_INCLUDES variable in the different Makefile's.

Fixes: a6e263f125cd ("selftests: net: lib: Introduce deferred commands")
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20241104-net-next-selftests-lib-sh-deps-v1-1-7c9f7d939fc2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/Makefile | 3 ++-
 tools/testing/selftests/net/mptcp/Makefile      | 2 +-
 tools/testing/selftests/net/netfilter/Makefile  | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 224346426ef2..7d885cff8d79 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -126,6 +126,7 @@ TEST_FILES := devlink_lib.sh \
 	tc_common.sh
 
 TEST_INCLUDES := \
-	../lib.sh
+	../lib.sh \
+	$(wildcard ../lib/sh/*.sh)
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 5d796622e730..8e3fc05a5397 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -11,7 +11,7 @@ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq
 
 TEST_FILES := mptcp_lib.sh settings
 
-TEST_INCLUDES := ../lib.sh ../net_helper.sh
+TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) ../net_helper.sh
 
 EXTRA_CLEAN := *.pcap
 
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index 542f7886a0bc..9d009f74cfc2 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -55,4 +55,5 @@ TEST_FILES := lib.sh
 TEST_FILES += packetdrill
 
 TEST_INCLUDES := \
-	../lib.sh
+	../lib.sh \
+	$(wildcard ../lib/sh/*.sh)
-- 
cgit v1.2.3


From fc49b804967e5b1cc1665efd4de112945e1ab4c6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 4 Nov 2024 15:25:24 +0100
Subject: selftests: netfilter: run conntrack_dump_flush in netns

This test will fail if the initial namespace has conntrack
active due to unexpected number of flows returned on dump:

  conntrack_dump_flush.c:451:test_flush_by_zone:Expected ret (7) == 2 (2)
  test_flush_by_zone: Test failed
  FAIL  conntrack_dump_flush.test_flush_by_zone
  not ok 2 conntrack_dump_flush.test_flush_by_zone

Add a wrapper that unshares this program to avoid this problem.

Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20241104142529.2352-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netfilter/Makefile                | 4 ++--
 tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)
 create mode 100755 tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index 9d009f74cfc2..ffe161fac8b5 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -8,6 +8,7 @@ MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl)
 
 TEST_PROGS := br_netfilter.sh bridge_brouter.sh
 TEST_PROGS += br_netfilter_queue.sh
+TEST_PROGS += conntrack_dump_flush.sh
 TEST_PROGS += conntrack_icmp_related.sh
 TEST_PROGS += conntrack_ipip_mtu.sh
 TEST_PROGS += conntrack_tcp_unreplied.sh
@@ -36,10 +37,9 @@ TEST_PROGS += xt_string.sh
 
 TEST_PROGS_EXTENDED = nft_concat_range_perf.sh
 
-TEST_GEN_PROGS = conntrack_dump_flush
-
 TEST_GEN_FILES = audit_logread
 TEST_GEN_FILES += connect_close nf_queue
+TEST_GEN_FILES += conntrack_dump_flush
 TEST_GEN_FILES += conntrack_reverse_clash
 TEST_GEN_FILES += sctp_collision
 
diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh
new file mode 100755
index 000000000000..8b0935385849
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+
+exec unshare -n ./conntrack_dump_flush
-- 
cgit v1.2.3


From a84e8c05f58305dfa808bc5465c5175c29d7c9b6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 4 Nov 2024 15:28:18 +0100
Subject: selftests: netfilter: nft_queue.sh: fix warnings with socat 1.8.0.0

Updated to a more recent socat release and saw this:
 socat E xioopen_ipdgram_listen(): unknown address family 0
 socat W address is opened in read-write mode but only supports read-only

First error is avoided via pf=ipv4 option, second one via -u
(unidirectional) mode.

Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20241104142821.2608-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netfilter/nft_queue.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index a9d109fcc15c..785e3875a6da 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -512,10 +512,10 @@ EOF
 	:> "$TMPFILE1"
 	:> "$TMPFILE2"
 
-	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE1",trunc &
+	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12345,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc &
 	local rpid1=$!
 
-	timeout 10 ip netns exec "$ns3" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE2",trunc &
+	timeout 10 ip netns exec "$ns3" socat UDP-LISTEN:12345,fork,pf=ipv4 OPEN:"$TMPFILE2",trunc &
 	local rpid2=$!
 
 	ip netns exec "$nsrouter" ./nf_queue -q 12 -d 1000 &
@@ -528,8 +528,8 @@ EOF
 	# Send two packets, one should end up in ns1, other in ns2.
 	# This is because nfqueue will delay packet for long enough so that
 	# second packet will not find existing conntrack entry.
-	echo "Packet 1" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
-	echo "Packet 2" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
+	echo "Packet 1" | ip netns exec "$ns1" socat -u STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
+	echo "Packet 2" | ip netns exec "$ns1" socat -u STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
 
 	busywait 10000 output_files_written "$TMPFILE1" "$TMPFILE2"
 
-- 
cgit v1.2.3


From 66c54c20408d994be34be2c070fba08472f69eee Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Wed, 6 Nov 2024 22:25:13 +0000
Subject: selftests/bpf: Add txmsg_pass to pull/push/pop in test_sockmap

Add txmsg_pass to test_txmsg_pull/push/pop. If txmsg_pass is missing,
tx_prog will be NULL, and no program will be attached to the sockmap.
As a result, pull/push/pop are never invoked.

Fixes: 328aa08a081b ("bpf: Selftests, break down test_sockmap into subtests")
Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20241106222520.527076-2-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 075c93ed143e..0f065273fde3 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1596,11 +1596,13 @@ static void test_txmsg_cork_hangs(int cgrp, struct sockmap_options *opt)
 static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 {
 	/* Test basic start/end */
+	txmsg_pass = 1;
 	txmsg_start = 1;
 	txmsg_end = 2;
 	test_send(opt, cgrp);
 
 	/* Test >4k pull */
+	txmsg_pass = 1;
 	txmsg_start = 4096;
 	txmsg_end = 9182;
 	test_send_large(opt, cgrp);
@@ -1629,11 +1631,13 @@ static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 {
 	/* Test basic pop */
+	txmsg_pass = 1;
 	txmsg_start_pop = 1;
 	txmsg_pop = 2;
 	test_send_many(opt, cgrp);
 
 	/* Test pop with >4k */
+	txmsg_pass = 1;
 	txmsg_start_pop = 4096;
 	txmsg_pop = 4096;
 	test_send_large(opt, cgrp);
@@ -1662,11 +1666,13 @@ static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 {
 	/* Test basic push */
+	txmsg_pass = 1;
 	txmsg_start_push = 1;
 	txmsg_end_push = 1;
 	test_send(opt, cgrp);
 
 	/* Test push 4kB >4k */
+	txmsg_pass = 1;
 	txmsg_start_push = 4096;
 	txmsg_end_push = 4096;
 	test_send_large(opt, cgrp);
@@ -1687,6 +1693,7 @@ static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 
 static void test_txmsg_push_pop(int cgrp, struct sockmap_options *opt)
 {
+	txmsg_pass = 1;
 	txmsg_start_push = 1;
 	txmsg_end_push = 10;
 	txmsg_start_pop = 5;
-- 
cgit v1.2.3


From 4095031463d4e99b534d2cd82035a417295764ae Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Wed, 6 Nov 2024 22:25:14 +0000
Subject: selftests/bpf: Fix SENDPAGE data logic in test_sockmap

In the SENDPAGE test, "opt->iov_length * cnt" size of data will be sent
cnt times by sendfile.
1. In push/pop tests, they will be invoked cnt times, for the simplicity of
msg_verify_data, change chunk_sz to iov_length
2. Change iov_length in test_send_large from 1024 to 8192. We have pop test
where txmsg_start_pop is 4096. 4096 > 1024, an error will be returned.

Fixes: 328aa08a081b ("bpf: Selftests, break down test_sockmap into subtests")
Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20241106222520.527076-3-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 0f065273fde3..1d59bed90d80 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -420,16 +420,18 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 {
 	bool drop = opt->drop_expected;
 	unsigned char k = 0;
+	int i, j, fp;
 	FILE *file;
-	int i, fp;
 
 	file = tmpfile();
 	if (!file) {
 		perror("create file for sendpage");
 		return 1;
 	}
-	for (i = 0; i < iov_length * cnt; i++, k++)
-		fwrite(&k, sizeof(char), 1, file);
+	for (i = 0; i < cnt; i++, k = 0) {
+		for (j = 0; j < iov_length; j++, k++)
+			fwrite(&k, sizeof(char), 1, file);
+	}
 	fflush(file);
 	fseek(file, 0, SEEK_SET);
 
@@ -623,7 +625,9 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		 * This is really only useful for testing edge cases in code
 		 * paths.
 		 */
-		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
+		total_bytes = (float)iov_length * (float)cnt;
+		if (!opt->sendpage)
+			total_bytes *= (float)iov_count;
 		if (txmsg_apply)
 			txmsg_pop_total = txmsg_pop * (total_bytes / txmsg_apply);
 		else
@@ -701,7 +705,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 			if (data) {
 				int chunk_sz = opt->sendpage ?
-						iov_length * cnt :
+						iov_length :
 						iov_length * iov_count;
 
 				errno = msg_verify_data(&msg, recv, chunk_sz, &k, &bytes_cnt);
@@ -1466,8 +1470,8 @@ static void test_send_many(struct sockmap_options *opt, int cgrp)
 
 static void test_send_large(struct sockmap_options *opt, int cgrp)
 {
-	opt->iov_length = 256;
-	opt->iov_count = 1024;
+	opt->iov_length = 8192;
+	opt->iov_count = 32;
 	opt->rate = 2;
 	test_exec(cgrp, opt);
 }
-- 
cgit v1.2.3


From 523dffccbadea0cfd65f1ff04944b864c558c4a8 Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Wed, 6 Nov 2024 22:25:15 +0000
Subject: selftests/bpf: Fix total_bytes in msg_loop_rx in test_sockmap

total_bytes in msg_loop_rx should also take push into account, otherwise
total_bytes will be a smaller value, which makes the msg_loop_rx end early.

Besides, total_bytes has already taken pop into account, so we don't need
to subtract some bytes from iov_buf in sendmsg_test. The additional
subtraction may make total_bytes a negative number, and msg_loop_rx will
just end without checking anything.

Fixes: 18d4e900a450 ("bpf: Selftests, improve test_sockmap total bytes counter")
Fixes: d69672147faa ("selftests, bpf: Add one test for sockmap with strparser")
Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20241106222520.527076-4-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 1d59bed90d80..5f4558f1f004 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -606,8 +606,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
+		float total_bytes, txmsg_pop_total, txmsg_push_total;
 		int slct, recvp = 0, recv, max_fd = fd;
-		float total_bytes, txmsg_pop_total;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
 		unsigned char k = 0;
@@ -628,10 +628,14 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		total_bytes = (float)iov_length * (float)cnt;
 		if (!opt->sendpage)
 			total_bytes *= (float)iov_count;
-		if (txmsg_apply)
+		if (txmsg_apply) {
+			txmsg_push_total = txmsg_end_push * (total_bytes / txmsg_apply);
 			txmsg_pop_total = txmsg_pop * (total_bytes / txmsg_apply);
-		else
+		} else {
+			txmsg_push_total = txmsg_end_push * cnt;
 			txmsg_pop_total = txmsg_pop * cnt;
+		}
+		total_bytes += txmsg_push_total;
 		total_bytes -= txmsg_pop_total;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
@@ -800,8 +804,6 @@ static int sendmsg_test(struct sockmap_options *opt)
 
 	rxpid = fork();
 	if (rxpid == 0) {
-		if (txmsg_pop || txmsg_start_pop)
-			iov_buf -= (txmsg_pop - txmsg_start_pop + 1);
 		if (opt->drop_expected || txmsg_ktls_skb_drop)
 			_exit(0);
 
-- 
cgit v1.2.3


From 862087c3d36219ed44569666eb263efc97f00c9a Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Wed, 6 Nov 2024 22:25:16 +0000
Subject: selftests/bpf: Add push/pop checking for msg_verify_data in
 test_sockmap

Add push/pop checking for msg_verify_data in test_sockmap, except for
pop/push with cork tests, in these tests the logic will be different.
1. With corking, pop/push might not be invoked in each sendmsg, it makes
the layout of the received data difficult
2. It makes it hard to calculate the total_bytes in the recvmsg
Temporarily skip the data integrity test for these cases now, added a TODO

Fixes: ee9b352ce465 ("selftests/bpf: Fix msg_verify_data in test_sockmap")
Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20241106222520.527076-5-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 106 +++++++++++++++++++++++++++--
 1 file changed, 101 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 5f4558f1f004..61a747afcd05 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -88,6 +88,10 @@ int ktls;
 int peek_flag;
 int skb_use_parser;
 int txmsg_omit_skb_parser;
+int verify_push_start;
+int verify_push_len;
+int verify_pop_start;
+int verify_pop_len;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -514,12 +518,41 @@ unwind_iov:
 	return -ENOMEM;
 }
 
-/* TODO: Add verification logic for push, pull and pop data */
+/* In push or pop test, we need to do some calculations for msg_verify_data */
+static void msg_verify_date_prep(void)
+{
+	int push_range_end = txmsg_start_push + txmsg_end_push - 1;
+	int pop_range_end = txmsg_start_pop + txmsg_pop - 1;
+
+	if (txmsg_end_push && txmsg_pop &&
+	    txmsg_start_push <= pop_range_end && txmsg_start_pop <= push_range_end) {
+		/* The push range and the pop range overlap */
+		int overlap_len;
+
+		verify_push_start = txmsg_start_push;
+		verify_pop_start = txmsg_start_pop;
+		if (txmsg_start_push < txmsg_start_pop)
+			overlap_len = min(push_range_end - txmsg_start_pop + 1, txmsg_pop);
+		else
+			overlap_len = min(pop_range_end - txmsg_start_push + 1, txmsg_end_push);
+		verify_push_len = max(txmsg_end_push - overlap_len, 0);
+		verify_pop_len = max(txmsg_pop - overlap_len, 0);
+	} else {
+		/* Otherwise */
+		verify_push_start = txmsg_start_push;
+		verify_pop_start = txmsg_start_pop;
+		verify_push_len = txmsg_end_push;
+		verify_pop_len = txmsg_pop;
+	}
+}
+
 static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz,
-				 unsigned char *k_p, int *bytes_cnt_p)
+			   unsigned char *k_p, int *bytes_cnt_p,
+			   int *check_cnt_p, int *push_p)
 {
-	int i, j, bytes_cnt = *bytes_cnt_p;
+	int bytes_cnt = *bytes_cnt_p, check_cnt = *check_cnt_p, push = *push_p;
 	unsigned char k = *k_p;
+	int i, j;
 
 	for (i = 0, j = 0; i < msg->msg_iovlen && size; i++, j = 0) {
 		unsigned char *d = msg->msg_iov[i].iov_base;
@@ -538,6 +571,37 @@ static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz,
 		}
 
 		for (; j < msg->msg_iov[i].iov_len && size; j++) {
+			if (push > 0 &&
+			    check_cnt == verify_push_start + verify_push_len - push) {
+				int skipped;
+revisit_push:
+				skipped = push;
+				if (j + push >= msg->msg_iov[i].iov_len)
+					skipped = msg->msg_iov[i].iov_len - j;
+				push -= skipped;
+				size -= skipped;
+				j += skipped - 1;
+				check_cnt += skipped;
+				continue;
+			}
+
+			if (verify_pop_len > 0 && check_cnt == verify_pop_start) {
+				bytes_cnt += verify_pop_len;
+				check_cnt += verify_pop_len;
+				k += verify_pop_len;
+
+				if (bytes_cnt == chunk_sz) {
+					k = 0;
+					bytes_cnt = 0;
+					check_cnt = 0;
+					push = verify_push_len;
+				}
+
+				if (push > 0 &&
+				    check_cnt == verify_push_start + verify_push_len - push)
+					goto revisit_push;
+			}
+
 			if (d[j] != k++) {
 				fprintf(stderr,
 					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
@@ -545,15 +609,20 @@ static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz,
 				return -EDATAINTEGRITY;
 			}
 			bytes_cnt++;
+			check_cnt++;
 			if (bytes_cnt == chunk_sz) {
 				k = 0;
 				bytes_cnt = 0;
+				check_cnt = 0;
+				push = verify_push_len;
 			}
 			size--;
 		}
 	}
 	*k_p = k;
 	*bytes_cnt_p = bytes_cnt;
+	*check_cnt_p = check_cnt;
+	*push_p = push;
 	return 0;
 }
 
@@ -612,6 +681,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		struct timeval timeout;
 		unsigned char k = 0;
 		int bytes_cnt = 0;
+		int check_cnt = 0;
+		int push = 0;
 		fd_set w;
 
 		fcntl(fd, fd_flags);
@@ -637,6 +708,10 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		total_bytes += txmsg_push_total;
 		total_bytes -= txmsg_pop_total;
+		if (data) {
+			msg_verify_date_prep();
+			push = verify_push_len;
+		}
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
 			perror("recv start time");
@@ -712,7 +787,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 						iov_length :
 						iov_length * iov_count;
 
-				errno = msg_verify_data(&msg, recv, chunk_sz, &k, &bytes_cnt);
+				errno = msg_verify_data(&msg, recv, chunk_sz, &k, &bytes_cnt,
+							&check_cnt, &push);
 				if (errno) {
 					perror("data verify msg failed");
 					goto out_errno;
@@ -722,7 +798,9 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 								recvp,
 								chunk_sz,
 								&k,
-								&bytes_cnt);
+								&bytes_cnt,
+								&check_cnt,
+								&push);
 					if (errno) {
 						perror("data verify msg_peek failed");
 						goto out_errno;
@@ -1636,6 +1714,8 @@ static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 
 static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 {
+	bool data = opt->data_test;
+
 	/* Test basic pop */
 	txmsg_pass = 1;
 	txmsg_start_pop = 1;
@@ -1654,6 +1734,12 @@ static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 	txmsg_pop = 2;
 	test_send_many(opt, cgrp);
 
+	/* TODO: Test for pop + cork should be different,
+	 * - It makes the layout of the received data difficult
+	 * - It makes it hard to calculate the total_bytes in the recvmsg
+	 * Temporarily skip the data integrity test for this case now.
+	 */
+	opt->data_test = false;
 	/* Test pop + cork */
 	txmsg_redir = 0;
 	txmsg_cork = 512;
@@ -1667,10 +1753,13 @@ static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 	txmsg_start_pop = 1;
 	txmsg_pop = 2;
 	test_send_many(opt, cgrp);
+	opt->data_test = data;
 }
 
 static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 {
+	bool data = opt->data_test;
+
 	/* Test basic push */
 	txmsg_pass = 1;
 	txmsg_start_push = 1;
@@ -1689,12 +1778,19 @@ static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 	txmsg_end_push = 2;
 	test_send_many(opt, cgrp);
 
+	/* TODO: Test for push + cork should be different,
+	 * - It makes the layout of the received data difficult
+	 * - It makes it hard to calculate the total_bytes in the recvmsg
+	 * Temporarily skip the data integrity test for this case now.
+	 */
+	opt->data_test = false;
 	/* Test push + cork */
 	txmsg_redir = 0;
 	txmsg_cork = 512;
 	txmsg_start_push = 1;
 	txmsg_end_push = 2;
 	test_send_many(opt, cgrp);
+	opt->data_test = data;
 }
 
 static void test_txmsg_push_pop(int cgrp, struct sockmap_options *opt)
-- 
cgit v1.2.3


From 47eae080410b1de1d7f6c79b511aaa6be865c61e Mon Sep 17 00:00:00 2001
From: Zijian Zhang <zijianzhang@bytedance.com>
Date: Wed, 6 Nov 2024 22:25:17 +0000
Subject: selftests/bpf: Add more tests for test_txmsg_push_pop in test_sockmap

Add more tests for test_txmsg_push_pop in test_sockmap for better coverage

Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20241106222520.527076-6-zijianzhang@bytedance.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 37 ++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 61a747afcd05..e5c7ecbe57e3 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1795,12 +1795,49 @@ static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 
 static void test_txmsg_push_pop(int cgrp, struct sockmap_options *opt)
 {
+	/* Test push/pop range overlapping */
 	txmsg_pass = 1;
 	txmsg_start_push = 1;
 	txmsg_end_push = 10;
 	txmsg_start_pop = 5;
 	txmsg_pop = 4;
 	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 1;
+	txmsg_end_push = 10;
+	txmsg_start_pop = 5;
+	txmsg_pop = 16;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 5;
+	txmsg_end_push = 4;
+	txmsg_start_pop = 1;
+	txmsg_pop = 10;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 5;
+	txmsg_end_push = 16;
+	txmsg_start_pop = 1;
+	txmsg_pop = 10;
+	test_send_large(opt, cgrp);
+
+	/* Test push/pop range non-overlapping */
+	txmsg_pass = 1;
+	txmsg_start_push = 1;
+	txmsg_end_push = 10;
+	txmsg_start_pop = 16;
+	txmsg_pop = 4;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 16;
+	txmsg_end_push = 10;
+	txmsg_start_pop = 5;
+	txmsg_pop = 4;
+	test_send_large(opt, cgrp);
 }
 
 static void test_txmsg_apply(int cgrp, struct sockmap_options *opt)
-- 
cgit v1.2.3


From 52ed077aa6336dbef83a2d6d21c52d1706fb7f16 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 5 Nov 2024 19:23:51 +0100
Subject: selftests: net: really check for bg process completion

A recent refactor transformed the check for process completion
in a true statement, due to a typo.

As a result, the relevant test-case is unable to catch the
regression it was supposed to detect.

Restore the correct condition.

Fixes: 691bb4e49c98 ("selftests: net: avoid just another constant wait")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/0e6f213811f8e93a235307e683af8225cc6277ae.1730828007.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/pmtu.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 569bce8b6383..6c651c880fe8 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -2056,7 +2056,7 @@ check_running() {
 	pid=${1}
 	cmd=${2}
 
-	[ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ]
+	[ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "${cmd}" ]
 }
 
 test_cleanup_vxlanX_exception() {
-- 
cgit v1.2.3


From 774ca6d3bf24287ff60b7d6dd4171ebb6e47760a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 5 Nov 2024 15:39:54 +0200
Subject: bridge: Allow deleting FDB entries with non-existent VLAN

It is currently impossible to delete individual FDB entries (as opposed
to flushing) that were added with a VLAN that no longer exists:

 # ip link add name dummy1 up type dummy
 # ip link add name br1 up type bridge vlan_filtering 1
 # ip link set dev dummy1 master br1
 # bridge fdb add 00:11:22:33:44:55 dev dummy1 master static vlan 1
 # bridge vlan del vid 1 dev dummy1
 # bridge fdb get 00:11:22:33:44:55 br br1 vlan 1
 00:11:22:33:44:55 dev dummy1 vlan 1 master br1 static
 # bridge fdb del 00:11:22:33:44:55 dev dummy1 master vlan 1
 RTNETLINK answers: Invalid argument
 # bridge fdb get 00:11:22:33:44:55 br br1 vlan 1
 00:11:22:33:44:55 dev dummy1 vlan 1 master br1 static

This is in contrast to MDB entries that can be deleted after the VLAN
was deleted:

 # bridge vlan add vid 10 dev dummy1
 # bridge mdb add dev br1 port dummy1 grp 239.1.1.1 permanent vid 10
 # bridge vlan del vid 10 dev dummy1
 # bridge mdb get dev br1 grp 239.1.1.1 vid 10
 dev br1 port dummy1 grp 239.1.1.1 permanent vid 10
 # bridge mdb del dev br1 port dummy1 grp 239.1.1.1 permanent vid 10
 # bridge mdb get dev br1 grp 239.1.1.1 vid 10
 Error: bridge: MDB entry not found.

Align the two interfaces and allow user space to delete FDB entries that
were added with a VLAN that no longer exists:

 # ip link add name dummy1 up type dummy
 # ip link add name br1 up type bridge vlan_filtering 1
 # ip link set dev dummy1 master br1
 # bridge fdb add 00:11:22:33:44:55 dev dummy1 master static vlan 1
 # bridge vlan del vid 1 dev dummy1
 # bridge fdb get 00:11:22:33:44:55 br br1 vlan 1
 00:11:22:33:44:55 dev dummy1 vlan 1 master br1 static
 # bridge fdb del 00:11:22:33:44:55 dev dummy1 master vlan 1
 # bridge fdb get 00:11:22:33:44:55 br br1 vlan 1
 Error: Fdb entry not found.

Add a selftest to make sure this behavior does not regress:

 # ./rtnetlink.sh -t kci_test_fdb_del
 PASS: bridge fdb del

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Andy Roulin <aroulin@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20241105133954.350479-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_fdb.c                      |  9 ++-----
 tools/testing/selftests/net/rtnetlink.sh | 40 ++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 1cd7bade9b3b..77f110035df1 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -1319,7 +1319,6 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 {
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
-	struct net_bridge_vlan *v;
 	struct net_bridge *br;
 	int err;
 
@@ -1338,14 +1337,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	}
 
 	if (vid) {
-		v = br_vlan_find(vg, vid);
-		if (!v) {
-			pr_info("bridge: RTM_DELNEIGH with unconfigured vlan %d on %s\n", vid, dev->name);
-			return -EINVAL;
-		}
-
 		err = __br_fdb_delete(br, p, addr, vid);
 	} else {
+		struct net_bridge_vlan *v;
+
 		err = -ENOENT;
 		err &= __br_fdb_delete(br, p, addr, 0);
 		if (!vg || !vg->num_vlans)
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 87dce3efe31e..6e216d7a8e2f 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -25,6 +25,7 @@ ALL_TESTS="
 	kci_test_ipsec
 	kci_test_ipsec_offload
 	kci_test_fdb_get
+	kci_test_fdb_del
 	kci_test_neigh_get
 	kci_test_bridge_parent_id
 	kci_test_address_proto
@@ -1065,6 +1066,45 @@ kci_test_fdb_get()
 	end_test "PASS: bridge fdb get"
 }
 
+kci_test_fdb_del()
+{
+	local test_mac=de:ad:be:ef:13:37
+	local dummydev="dummy1"
+	local brdev="test-br0"
+	local ret=0
+
+	run_cmd_grep 'bridge fdb get' bridge fdb help
+	if [ $? -ne 0 ]; then
+		end_test "SKIP: fdb del tests: iproute2 too old"
+		return $ksft_skip
+	fi
+
+	setup_ns testns
+	if [ $? -ne 0 ]; then
+		end_test "SKIP fdb del tests: cannot add net namespace $testns"
+		return $ksft_skip
+	fi
+	IP="ip -netns $testns"
+	BRIDGE="bridge -netns $testns"
+	run_cmd $IP link add $dummydev type dummy
+	run_cmd $IP link add name $brdev type bridge vlan_filtering 1
+	run_cmd $IP link set dev $dummydev master $brdev
+	run_cmd $BRIDGE fdb add $test_mac dev $dummydev master static vlan 1
+	run_cmd $BRIDGE vlan del vid 1 dev $dummydev
+	run_cmd $BRIDGE fdb get $test_mac br $brdev vlan 1
+	run_cmd $BRIDGE fdb del $test_mac dev $dummydev master vlan 1
+	run_cmd_fail $BRIDGE fdb get $test_mac br $brdev vlan 1
+
+	ip netns del $testns &>/dev/null
+
+	if [ $ret -ne 0 ]; then
+		end_test "FAIL: bridge fdb del"
+		return 1
+	fi
+
+	end_test "PASS: bridge fdb del"
+}
+
 kci_test_neigh_get()
 {
 	dstmac=de:ad:be:ef:13:37
-- 
cgit v1.2.3


From 7fef0dec415c08c16c31dd2c2501a8c734a4b3b8 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Mon, 28 Oct 2024 19:53:36 +0800
Subject: mm: page_frag: add a test module for page_frag

The testing is done by ensuring that the fragment allocated
from a frag_frag_cache instance is pushed into a ptr_ring
instance in a kthread binded to a specified cpu, and a kthread
binded to a specified cpu will pop the fragment from the
ptr_ring and free the fragment.

CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/20241028115343.3405838-2-linyunsheng@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/mm/Makefile                |   3 +
 tools/testing/selftests/mm/page_frag/Makefile      |  18 ++
 .../selftests/mm/page_frag/page_frag_test.c        | 198 +++++++++++++++++++++
 tools/testing/selftests/mm/run_vmtests.sh          |   8 +
 tools/testing/selftests/mm/test_page_frag.sh       | 175 ++++++++++++++++++
 5 files changed, 402 insertions(+)
 create mode 100644 tools/testing/selftests/mm/page_frag/Makefile
 create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c
 create mode 100755 tools/testing/selftests/mm/test_page_frag.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 02e1204971b0..acec529baaca 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules
 CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS = -lrt -lpthread -lm
 
+TEST_GEN_MODS_DIR := page_frag
+
 TEST_GEN_FILES = cow
 TEST_GEN_FILES += compaction_test
 TEST_GEN_FILES += gup_longterm
@@ -126,6 +128,7 @@ TEST_FILES += test_hmm.sh
 TEST_FILES += va_high_addr_switch.sh
 TEST_FILES += charge_reserved_hugetlb.sh
 TEST_FILES += hugetlb_reparenting_test.sh
+TEST_FILES += test_page_frag.sh
 
 # required by charge_reserved_hugetlb.sh
 TEST_FILES += write_hugetlb_memory.sh
diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile
new file mode 100644
index 000000000000..58dda74d50a3
--- /dev/null
+++ b/tools/testing/selftests/mm/page_frag/Makefile
@@ -0,0 +1,18 @@
+PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..)
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+MODULES = page_frag_test.ko
+
+obj-m += page_frag_test.o
+
+all:
+	+$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules
+
+clean:
+	+$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
new file mode 100644
index 000000000000..912d97b99107
--- /dev/null
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test module for page_frag cache
+ *
+ * Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/completion.h>
+#include <linux/ptr_ring.h>
+#include <linux/kthread.h>
+
+#define TEST_FAILED_PREFIX	"page_frag_test failed: "
+
+static struct ptr_ring ptr_ring;
+static int nr_objs = 512;
+static atomic_t nthreads;
+static struct completion wait;
+static struct page_frag_cache test_nc;
+static int test_popped;
+static int test_pushed;
+static bool force_exit;
+
+static int nr_test = 2000000;
+module_param(nr_test, int, 0);
+MODULE_PARM_DESC(nr_test, "number of iterations to test");
+
+static bool test_align;
+module_param(test_align, bool, 0);
+MODULE_PARM_DESC(test_align, "use align API for testing");
+
+static int test_alloc_len = 2048;
+module_param(test_alloc_len, int, 0);
+MODULE_PARM_DESC(test_alloc_len, "alloc len for testing");
+
+static int test_push_cpu;
+module_param(test_push_cpu, int, 0);
+MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment");
+
+static int test_pop_cpu;
+module_param(test_pop_cpu, int, 0);
+MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment");
+
+static int page_frag_pop_thread(void *arg)
+{
+	struct ptr_ring *ring = arg;
+
+	pr_info("page_frag pop test thread begins on cpu %d\n",
+		smp_processor_id());
+
+	while (test_popped < nr_test) {
+		void *obj = __ptr_ring_consume(ring);
+
+		if (obj) {
+			test_popped++;
+			page_frag_free(obj);
+		} else {
+			if (force_exit)
+				break;
+
+			cond_resched();
+		}
+	}
+
+	if (atomic_dec_and_test(&nthreads))
+		complete(&wait);
+
+	pr_info("page_frag pop test thread exits on cpu %d\n",
+		smp_processor_id());
+
+	return 0;
+}
+
+static int page_frag_push_thread(void *arg)
+{
+	struct ptr_ring *ring = arg;
+
+	pr_info("page_frag push test thread begins on cpu %d\n",
+		smp_processor_id());
+
+	while (test_pushed < nr_test && !force_exit) {
+		void *va;
+		int ret;
+
+		if (test_align) {
+			va = page_frag_alloc_align(&test_nc, test_alloc_len,
+						   GFP_KERNEL, SMP_CACHE_BYTES);
+
+			if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) {
+				force_exit = true;
+				WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n");
+			}
+		} else {
+			va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL);
+		}
+
+		if (!va)
+			continue;
+
+		ret = __ptr_ring_produce(ring, va);
+		if (ret) {
+			page_frag_free(va);
+			cond_resched();
+		} else {
+			test_pushed++;
+		}
+	}
+
+	pr_info("page_frag push test thread exits on cpu %d\n",
+		smp_processor_id());
+
+	if (atomic_dec_and_test(&nthreads))
+		complete(&wait);
+
+	return 0;
+}
+
+static int __init page_frag_test_init(void)
+{
+	struct task_struct *tsk_push, *tsk_pop;
+	int last_pushed = 0, last_popped = 0;
+	ktime_t start;
+	u64 duration;
+	int ret;
+
+	test_nc.va = NULL;
+	atomic_set(&nthreads, 2);
+	init_completion(&wait);
+
+	if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 ||
+	    !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu))
+		return -EINVAL;
+
+	ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring,
+					 test_push_cpu, "page_frag_push");
+	if (IS_ERR(tsk_push))
+		return PTR_ERR(tsk_push);
+
+	tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring,
+					test_pop_cpu, "page_frag_pop");
+	if (IS_ERR(tsk_pop)) {
+		kthread_stop(tsk_push);
+		return PTR_ERR(tsk_pop);
+	}
+
+	start = ktime_get();
+	wake_up_process(tsk_push);
+	wake_up_process(tsk_pop);
+
+	pr_info("waiting for test to complete\n");
+
+	while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) {
+		/* exit if there is no progress for push or pop size */
+		if (last_pushed == test_pushed || last_popped == test_popped) {
+			WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n");
+			force_exit = true;
+			continue;
+		}
+
+		last_pushed = test_pushed;
+		last_popped = test_popped;
+		pr_info("page_frag_test progress: pushed = %d, popped = %d\n",
+			test_pushed, test_popped);
+	}
+
+	if (force_exit) {
+		pr_err(TEST_FAILED_PREFIX "exit with error\n");
+		goto out;
+	}
+
+	duration = (u64)ktime_us_delta(ktime_get(), start);
+	pr_info("%d of iterations for %s testing took: %lluus\n", nr_test,
+		test_align ? "aligned" : "non-aligned", duration);
+
+out:
+	ptr_ring_cleanup(&ptr_ring, NULL);
+	page_frag_cache_drain(&test_nc);
+
+	return -EAGAIN;
+}
+
+static void __exit page_frag_test_exit(void)
+{
+}
+
+module_init(page_frag_test_init);
+module_exit(page_frag_test_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yunsheng Lin <linyunsheng@huawei.com>");
+MODULE_DESCRIPTION("Test module for page_frag");
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index c5797ad1d37b..2c5394584af4 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -75,6 +75,8 @@ separated by spaces:
 	read-only VMAs
 - mdwe
 	test prctl(PR_SET_MDWE, ...)
+- page_frag
+	test handling of page fragment allocation and freeing
 
 example: ./run_vmtests.sh -t "hmm mmap ksm"
 EOF
@@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty
 
 CATEGORY="mdwe" run_test ./mdwe_test
 
+CATEGORY="page_frag" run_test ./test_page_frag.sh smoke
+
+CATEGORY="page_frag" run_test ./test_page_frag.sh aligned
+
+CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
+
 echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
 echo "1..${count_total}" | tap_output
 
diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh
new file mode 100755
index 000000000000..f55b105084cf
--- /dev/null
+++ b/tools/testing/selftests/mm/test_page_frag.sh
@@ -0,0 +1,175 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com>
+# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com>
+#
+# This is a test script for the kernel test driver to test the
+# correctness and performance of page_frag's implementation.
+# Therefore it is just a kernel module loader. You can specify
+# and pass different parameters in order to:
+#     a) analyse performance of page fragment allocations;
+#     b) stressing and stability check of page_frag subsystem.
+
+DRIVER="./page_frag/page_frag_test.ko"
+CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2)
+TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}')
+
+if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then
+	TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}')
+	NR_TEST=100000000
+else
+	TEST_CPU_1=$TEST_CPU_0
+	NR_TEST=1000000
+fi
+
+# 1 if fails
+exitcode=1
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+check_test_failed_prefix() {
+	if dmesg | grep -q 'page_frag_test failed:';then
+		echo "page_frag_test failed, please check dmesg"
+		exit $exitcode
+	fi
+}
+
+#
+# Static templates for testing of page_frag APIs.
+# Also it is possible to pass any supported parameters manually.
+#
+SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1"
+NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST"
+ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1"
+
+check_test_requirements()
+{
+	uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo "$0: Must be run as root"
+		exit $ksft_skip
+	fi
+
+	if ! which insmod > /dev/null 2>&1; then
+		echo "$0: You need insmod installed"
+		exit $ksft_skip
+	fi
+
+	if [ ! -f $DRIVER ]; then
+		echo "$0: You need to compile page_frag_test module"
+		exit $ksft_skip
+	fi
+}
+
+run_nonaligned_check()
+{
+	echo "Run performance tests to evaluate how fast nonaligned alloc API is."
+
+	insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1
+}
+
+run_aligned_check()
+{
+	echo "Run performance tests to evaluate how fast aligned alloc API is."
+
+	insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1
+}
+
+run_smoke_check()
+{
+	echo "Run smoke test."
+
+	insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1
+}
+
+usage()
+{
+	echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | "
+	echo "manual parameters"
+	echo
+	echo "Valid tests and parameters:"
+	echo
+	modinfo $DRIVER
+	echo
+	echo "Example usage:"
+	echo
+	echo "# Shows help message"
+	echo "$0"
+	echo
+	echo "# Smoke testing"
+	echo "$0 smoke"
+	echo
+	echo "# Performance testing for nonaligned alloc API"
+	echo "$0 nonaligned"
+	echo
+	echo "# Performance testing for aligned alloc API"
+	echo "$0 aligned"
+	echo
+	exit 0
+}
+
+function validate_passed_args()
+{
+	VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'`
+
+	#
+	# Something has been passed, check it.
+	#
+	for passed_arg in $@; do
+		key=${passed_arg//=*/}
+		valid=0
+
+		for valid_arg in $VALID_ARGS; do
+			if [[ $key = $valid_arg ]]; then
+				valid=1
+				break
+			fi
+		done
+
+		if [[ $valid -ne 1 ]]; then
+			echo "Error: key is not correct: ${key}"
+			exit $exitcode
+		fi
+	done
+}
+
+function run_manual_check()
+{
+	#
+	# Validate passed parameters. If there is wrong one,
+	# the script exists and does not execute further.
+	#
+	validate_passed_args $@
+
+	echo "Run the test with following parameters: $@"
+	insmod $DRIVER $@ > /dev/null 2>&1
+}
+
+function run_test()
+{
+	if [ $# -eq 0 ]; then
+		usage
+	else
+		if [[ "$1" = "smoke" ]]; then
+			run_smoke_check
+		elif [[ "$1" = "nonaligned" ]]; then
+			run_nonaligned_check
+		elif [[ "$1" = "aligned" ]]; then
+			run_aligned_check
+		else
+			run_manual_check $@
+		fi
+	fi
+
+	check_test_failed_prefix
+
+	echo "Done."
+	echo "Check the kernel ring buffer to see the summary."
+}
+
+check_test_requirements
+run_test $@
+
+exit 0
-- 
cgit v1.2.3


From 65941f10caf2c04781a7defa4ec0ab119dbd235a Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Mon, 28 Oct 2024 19:53:37 +0800
Subject: mm: move the page fragment allocator from page_alloc into its own
 file

Inspired by [1], move the page fragment allocator from page_alloc
into its own c file and header file, as we are about to make more
change for it to replace another page_frag implementation in
sock.c

As this patchset is going to replace 'struct page_frag' with
'struct page_frag_cache' in sched.h, including page_frag_cache.h
in sched.h has a compiler error caused by interdependence between
mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler
error by moving 'struct page_frag_cache' to mm_types_task.h as
suggested by Alexander, see [3].

1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/
2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.com/
3. https://lore.kernel.org/all/CAKgT0UdH1yD=LSCXFJ=YM_aiA4OomD-2wXykO42bizaWMt_HOA@mail.gmail.com/
CC: David Howells <dhowells@redhat.com>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/20241028115343.3405838-3-linyunsheng@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/gfp.h                                |  22 ----
 include/linux/mm_types.h                           |  18 ---
 include/linux/mm_types_task.h                      |  18 +++
 include/linux/page_frag_cache.h                    |  31 +++++
 include/linux/skbuff.h                             |   1 +
 mm/Makefile                                        |   1 +
 mm/page_alloc.c                                    | 136 -------------------
 mm/page_frag_cache.c                               | 145 +++++++++++++++++++++
 .../selftests/mm/page_frag/page_frag_test.c        |   2 +-
 9 files changed, 197 insertions(+), 177 deletions(-)
 create mode 100644 include/linux/page_frag_cache.h
 create mode 100644 mm/page_frag_cache.c

(limited to 'tools/testing')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index a951de920e20..a0a6d25f883f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
 
-struct page_frag_cache;
-void page_frag_cache_drain(struct page_frag_cache *nc);
-extern void __page_frag_cache_drain(struct page *page, unsigned int count);
-void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
-			      gfp_t gfp_mask, unsigned int align_mask);
-
-static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
-					  unsigned int fragsz, gfp_t gfp_mask,
-					  unsigned int align)
-{
-	WARN_ON_ONCE(!is_power_of_2(align));
-	return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
-}
-
-static inline void *page_frag_alloc(struct page_frag_cache *nc,
-			     unsigned int fragsz, gfp_t gfp_mask)
-{
-	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
-}
-
-extern void page_frag_free(void *addr);
-
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e3bdf8e38bc..92314ef2d978 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
  */
 #define STRUCT_PAGE_MAX_SHIFT	(order_base_2(sizeof(struct page)))
 
-#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
-#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
-
 /*
  * page_private can be used on tail pages.  However, PagePrivate is only
  * checked by the VM on the head page.  So page_private on the tail pages
@@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio)
 	return folio->private;
 }
 
-struct page_frag_cache {
-	void * va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	__u16 offset;
-	__u16 size;
-#else
-	__u32 offset;
-#endif
-	/* we maintain a pagecount bias, so that we dont dirty cache line
-	 * containing page->_refcount every time we allocate a fragment.
-	 */
-	unsigned int		pagecnt_bias;
-	bool pfmemalloc;
-};
-
 typedef unsigned long vm_flags_t;
 
 /*
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index bff5706b76e1..0ac6daebdd5c 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -8,6 +8,7 @@
  * (These are defined separately to decouple sched.h from mm_types.h as much as possible.)
  */
 
+#include <linux/align.h>
 #include <linux/types.h>
 
 #include <asm/page.h>
@@ -43,6 +44,23 @@ struct page_frag {
 #endif
 };
 
+#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
+#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
+struct page_frag_cache {
+	void *va;
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	__u16 offset;
+	__u16 size;
+#else
+	__u32 offset;
+#endif
+	/* we maintain a pagecount bias, so that we dont dirty cache line
+	 * containing page->_refcount every time we allocate a fragment.
+	 */
+	unsigned int		pagecnt_bias;
+	bool pfmemalloc;
+};
+
 /* Track pages that require TLB flushes */
 struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
new file mode 100644
index 000000000000..67ac8626ed9b
--- /dev/null
+++ b/include/linux/page_frag_cache.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PAGE_FRAG_CACHE_H
+#define _LINUX_PAGE_FRAG_CACHE_H
+
+#include <linux/log2.h>
+#include <linux/mm_types_task.h>
+#include <linux/types.h>
+
+void page_frag_cache_drain(struct page_frag_cache *nc);
+void __page_frag_cache_drain(struct page *page, unsigned int count);
+void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
+			      gfp_t gfp_mask, unsigned int align_mask);
+
+static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
+					  unsigned int fragsz, gfp_t gfp_mask,
+					  unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
+}
+
+static inline void *page_frag_alloc(struct page_frag_cache *nc,
+				    unsigned int fragsz, gfp_t gfp_mask)
+{
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
+}
+
+void page_frag_free(void *addr);
+
+#endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e5095d75abba..60535c706851 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -31,6 +31,7 @@
 #include <linux/in6.h>
 #include <linux/if_packet.h>
 #include <linux/llist.h>
+#include <linux/page_frag_cache.h>
 #include <net/flow.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
diff --git a/mm/Makefile b/mm/Makefile
index d5639b036166..dba52bb0da8a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o
 memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 
 obj-y += page-alloc.o
+obj-y += page_frag_cache.o
 obj-y += init-mm.o
 obj-y += memblock.o
 obj-y += $(memory-hotplug-y)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 94a2ffe28008..34b3eb74630a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4836,142 +4836,6 @@ void free_pages(unsigned long addr, unsigned int order)
 
 EXPORT_SYMBOL(free_pages);
 
-/*
- * Page Fragment:
- *  An arbitrary-length arbitrary-offset area of memory which resides
- *  within a 0 or higher order page.  Multiple fragments within that page
- *  are individually refcounted, in the page's reference counter.
- *
- * The page_frag functions below provide a simple allocation framework for
- * page fragments.  This is used by the network stack and network device
- * drivers to provide a backing region of memory for use as either an
- * sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
- */
-static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
-					     gfp_t gfp_mask)
-{
-	struct page *page = NULL;
-	gfp_t gfp = gfp_mask;
-
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
-		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
-	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
-				PAGE_FRAG_CACHE_MAX_ORDER);
-	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
-#endif
-	if (unlikely(!page))
-		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
-
-	nc->va = page ? page_address(page) : NULL;
-
-	return page;
-}
-
-void page_frag_cache_drain(struct page_frag_cache *nc)
-{
-	if (!nc->va)
-		return;
-
-	__page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
-	nc->va = NULL;
-}
-EXPORT_SYMBOL(page_frag_cache_drain);
-
-void __page_frag_cache_drain(struct page *page, unsigned int count)
-{
-	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
-
-	if (page_ref_sub_and_test(page, count))
-		free_unref_page(page, compound_order(page));
-}
-EXPORT_SYMBOL(__page_frag_cache_drain);
-
-void *__page_frag_alloc_align(struct page_frag_cache *nc,
-			      unsigned int fragsz, gfp_t gfp_mask,
-			      unsigned int align_mask)
-{
-	unsigned int size = PAGE_SIZE;
-	struct page *page;
-	int offset;
-
-	if (unlikely(!nc->va)) {
-refill:
-		page = __page_frag_cache_refill(nc, gfp_mask);
-		if (!page)
-			return NULL;
-
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-		/* if size can vary use size else just use PAGE_SIZE */
-		size = nc->size;
-#endif
-		/* Even if we own the page, we do not use atomic_set().
-		 * This would break get_page_unless_zero() users.
-		 */
-		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
-
-		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page_is_pfmemalloc(page);
-		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		nc->offset = size;
-	}
-
-	offset = nc->offset - fragsz;
-	if (unlikely(offset < 0)) {
-		page = virt_to_page(nc->va);
-
-		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
-			goto refill;
-
-		if (unlikely(nc->pfmemalloc)) {
-			free_unref_page(page, compound_order(page));
-			goto refill;
-		}
-
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-		/* if size can vary use size else just use PAGE_SIZE */
-		size = nc->size;
-#endif
-		/* OK, page count is 0, we can safely set it */
-		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
-
-		/* reset page count bias and offset to start of new frag */
-		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		offset = size - fragsz;
-		if (unlikely(offset < 0)) {
-			/*
-			 * The caller is trying to allocate a fragment
-			 * with fragsz > PAGE_SIZE but the cache isn't big
-			 * enough to satisfy the request, this may
-			 * happen in low memory conditions.
-			 * We don't release the cache page because
-			 * it could make memory pressure worse
-			 * so we simply return NULL here.
-			 */
-			return NULL;
-		}
-	}
-
-	nc->pagecnt_bias--;
-	offset &= align_mask;
-	nc->offset = offset;
-
-	return nc->va + offset;
-}
-EXPORT_SYMBOL(__page_frag_alloc_align);
-
-/*
- * Frees a page fragment allocated out of either a compound or order 0 page.
- */
-void page_frag_free(void *addr)
-{
-	struct page *page = virt_to_head_page(addr);
-
-	if (unlikely(put_page_testzero(page)))
-		free_unref_page(page, compound_order(page));
-}
-EXPORT_SYMBOL(page_frag_free);
-
 static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		size_t size)
 {
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
new file mode 100644
index 000000000000..609a485cd02a
--- /dev/null
+++ b/mm/page_frag_cache.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Page fragment allocator
+ *
+ * Page Fragment:
+ *  An arbitrary-length arbitrary-offset area of memory which resides within a
+ *  0 or higher order page.  Multiple fragments within that page are
+ *  individually refcounted, in the page's reference counter.
+ *
+ * The page_frag functions provide a simple allocation framework for page
+ * fragments.  This is used by the network stack and network device drivers to
+ * provide a backing region of memory for use as either an sk_buff->head, or to
+ * be used in the "frags" portion of skb_shared_info.
+ */
+
+#include <linux/export.h>
+#include <linux/gfp_types.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/page_frag_cache.h>
+#include "internal.h"
+
+static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
+					     gfp_t gfp_mask)
+{
+	struct page *page = NULL;
+	gfp_t gfp = gfp_mask;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
+		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
+				PAGE_FRAG_CACHE_MAX_ORDER);
+	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
+#endif
+	if (unlikely(!page))
+		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+	nc->va = page ? page_address(page) : NULL;
+
+	return page;
+}
+
+void page_frag_cache_drain(struct page_frag_cache *nc)
+{
+	if (!nc->va)
+		return;
+
+	__page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
+	nc->va = NULL;
+}
+EXPORT_SYMBOL(page_frag_cache_drain);
+
+void __page_frag_cache_drain(struct page *page, unsigned int count)
+{
+	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+
+	if (page_ref_sub_and_test(page, count))
+		free_unref_page(page, compound_order(page));
+}
+EXPORT_SYMBOL(__page_frag_cache_drain);
+
+void *__page_frag_alloc_align(struct page_frag_cache *nc,
+			      unsigned int fragsz, gfp_t gfp_mask,
+			      unsigned int align_mask)
+{
+	unsigned int size = PAGE_SIZE;
+	struct page *page;
+	int offset;
+
+	if (unlikely(!nc->va)) {
+refill:
+		page = __page_frag_cache_refill(nc, gfp_mask);
+		if (!page)
+			return NULL;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+		/* if size can vary use size else just use PAGE_SIZE */
+		size = nc->size;
+#endif
+		/* Even if we own the page, we do not use atomic_set().
+		 * This would break get_page_unless_zero() users.
+		 */
+		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pfmemalloc = page_is_pfmemalloc(page);
+		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+		nc->offset = size;
+	}
+
+	offset = nc->offset - fragsz;
+	if (unlikely(offset < 0)) {
+		page = virt_to_page(nc->va);
+
+		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
+			goto refill;
+
+		if (unlikely(nc->pfmemalloc)) {
+			free_unref_page(page, compound_order(page));
+			goto refill;
+		}
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+		/* if size can vary use size else just use PAGE_SIZE */
+		size = nc->size;
+#endif
+		/* OK, page count is 0, we can safely set it */
+		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+		offset = size - fragsz;
+		if (unlikely(offset < 0)) {
+			/*
+			 * The caller is trying to allocate a fragment
+			 * with fragsz > PAGE_SIZE but the cache isn't big
+			 * enough to satisfy the request, this may
+			 * happen in low memory conditions.
+			 * We don't release the cache page because
+			 * it could make memory pressure worse
+			 * so we simply return NULL here.
+			 */
+			return NULL;
+		}
+	}
+
+	nc->pagecnt_bias--;
+	offset &= align_mask;
+	nc->offset = offset;
+
+	return nc->va + offset;
+}
+EXPORT_SYMBOL(__page_frag_alloc_align);
+
+/*
+ * Frees a page fragment allocated out of either a compound or order 0 page.
+ */
+void page_frag_free(void *addr)
+{
+	struct page *page = virt_to_head_page(addr);
+
+	if (unlikely(put_page_testzero(page)))
+		free_unref_page(page, compound_order(page));
+}
+EXPORT_SYMBOL(page_frag_free);
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
index 912d97b99107..13c44133e009 100644
--- a/tools/testing/selftests/mm/page_frag/page_frag_test.c
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -6,12 +6,12 @@
  * Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com>
  */
 
-#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
 #include <linux/completion.h>
 #include <linux/ptr_ring.h>
 #include <linux/kthread.h>
+#include <linux/page_frag_cache.h>
 
 #define TEST_FAILED_PREFIX	"page_frag_test failed: "
 
-- 
cgit v1.2.3


From 3d18dfe69ce46f106af327736d2261d7e3ee81c0 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Mon, 28 Oct 2024 19:53:39 +0800
Subject: mm: page_frag: avoid caller accessing 'page_frag_cache' directly

Use appropriate frag_page API instead of caller accessing
'page_frag_cache' directly.

CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://patch.msgid.link/20241028115343.3405838-5-linyunsheng@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/vhost/net.c                                   |  2 +-
 include/linux/page_frag_cache.h                       | 10 ++++++++++
 net/core/skbuff.c                                     |  6 +++---
 net/rxrpc/conn_object.c                               |  4 +---
 net/rxrpc/local_object.c                              |  4 +---
 net/sunrpc/svcsock.c                                  |  6 ++----
 tools/testing/selftests/mm/page_frag/page_frag_test.c |  2 +-
 7 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f16279351db5..9ad37c012189 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1325,7 +1325,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 			vqs[VHOST_NET_VQ_RX]);
 
 	f->private_data = n;
-	n->pf_cache.va = NULL;
+	page_frag_cache_init(&n->pf_cache);
 
 	return 0;
 }
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 67ac8626ed9b..0a52f7a179c8 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -7,6 +7,16 @@
 #include <linux/mm_types_task.h>
 #include <linux/types.h>
 
+static inline void page_frag_cache_init(struct page_frag_cache *nc)
+{
+	nc->va = NULL;
+}
+
+static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
+{
+	return !!nc->pfmemalloc;
+}
+
 void page_frag_cache_drain(struct page_frag_cache *nc);
 void __page_frag_cache_drain(struct page *page, unsigned int count);
 void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 00afeb90c23a..6841e61a6bd0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -753,14 +753,14 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 	if (in_hardirq() || irqs_disabled()) {
 		nc = this_cpu_ptr(&netdev_alloc_cache);
 		data = page_frag_alloc(nc, len, gfp_mask);
-		pfmemalloc = nc->pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
 	} else {
 		local_bh_disable();
 		local_lock_nested_bh(&napi_alloc_cache.bh_lock);
 
 		nc = this_cpu_ptr(&napi_alloc_cache.page);
 		data = page_frag_alloc(nc, len, gfp_mask);
-		pfmemalloc = nc->pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
 
 		local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 		local_bh_enable();
@@ -850,7 +850,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 		len = SKB_HEAD_ALIGN(len);
 
 		data = page_frag_alloc(&nc->page, len, gfp_mask);
-		pfmemalloc = nc->page.pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page);
 	}
 	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 1539d315afe7..694c4df7a1a3 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -337,9 +337,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work)
 	 */
 	rxrpc_purge_queue(&conn->rx_queue);
 
-	if (conn->tx_data_alloc.va)
-		__page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va),
-					conn->tx_data_alloc.pagecnt_bias);
+	page_frag_cache_drain(&conn->tx_data_alloc);
 	call_rcu(&conn->rcu, rxrpc_rcu_free_connection);
 }
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index f9623ace2201..2792d2304605 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -452,9 +452,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local)
 #endif
 	rxrpc_purge_queue(&local->rx_queue);
 	rxrpc_purge_client_connections(local);
-	if (local->tx_alloc.va)
-		__page_frag_cache_drain(virt_to_page(local->tx_alloc.va),
-					local->tx_alloc.pagecnt_bias);
+	page_frag_cache_drain(&local->tx_alloc);
 }
 
 /*
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 825ec5357691..b785425c3315 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1608,7 +1608,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 static void svc_sock_free(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
-	struct page_frag_cache *pfc = &svsk->sk_frag_cache;
 	struct socket *sock = svsk->sk_sock;
 
 	trace_svcsock_free(svsk, sock);
@@ -1618,8 +1617,7 @@ static void svc_sock_free(struct svc_xprt *xprt)
 		sockfd_put(sock);
 	else
 		sock_release(sock);
-	if (pfc->va)
-		__page_frag_cache_drain(virt_to_head_page(pfc->va),
-					pfc->pagecnt_bias);
+
+	page_frag_cache_drain(&svsk->sk_frag_cache);
 	kfree(svsk);
 }
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
index 13c44133e009..e806c1866e36 100644
--- a/tools/testing/selftests/mm/page_frag/page_frag_test.c
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -126,7 +126,7 @@ static int __init page_frag_test_init(void)
 	u64 duration;
 	int ret;
 
-	test_nc.va = NULL;
+	page_frag_cache_init(&test_nc);
 	atomic_set(&nthreads, 2);
 	init_completion(&wait);
 
-- 
cgit v1.2.3


From 0189270117c3a3b43d226ed9da5d1ee4dc58b45c Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 7 Nov 2024 00:13:28 +0100
Subject: selftests: netdevsim: add a test checking ethtool features

Add a test checking that some features are active by default and
changeable.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/fff58fa70f8a300440958b5020f6a4eb2e9dad61.1730929545.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/netdevsim/Makefile       |  1 +
 .../drivers/net/netdevsim/ethtool-features.sh      | 31 ++++++++++++++++++++++
 2 files changed, 32 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile
index cc08b220323f..df167c637af9 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/Makefile
+++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile
@@ -4,6 +4,7 @@ TEST_PROGS = devlink.sh \
 	devlink_in_netns.sh \
 	devlink_trap.sh \
 	ethtool-coalesce.sh \
+	ethtool-features.sh \
 	ethtool-fec.sh \
 	ethtool-pause.sh \
 	ethtool-ring.sh \
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh
new file mode 100644
index 000000000000..bc210dc6ad2d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh
@@ -0,0 +1,31 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+NSIM_NETDEV=$(make_netdev)
+
+set -o pipefail
+
+FEATS="
+  tx-checksum-ip-generic
+  tx-scatter-gather
+  tx-tcp-segmentation
+  generic-segmentation-offload
+  generic-receive-offload"
+
+for feat in $FEATS ; do
+    s=$(ethtool --json -k $NSIM_NETDEV | jq ".[].\"$feat\".active" 2>/dev/null)
+    check $? "$s" true
+
+    s=$(ethtool --json -k $NSIM_NETDEV | jq ".[].\"$feat\".fixed" 2>/dev/null)
+    check $? "$s" false
+done
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $((num_passes)) checks"
+    exit 0
+else
+    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+    exit 1
+fi
-- 
cgit v1.2.3


From 415b7cef1c73590bb897fc3f6dd9a0fa4a79acd8 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 7 Nov 2024 00:13:32 +0100
Subject: selftests: move macsec offload tests from net/rtnetlink to
 drivers/net/netdvesim

We're going to expand this test, and macsec offload is only lightly
related to rtnetlink.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/a1f92c250cc129b4bb111a206c4b560bab4e24a5.1730929545.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/netdevsim/Makefile       |  1 +
 .../testing/selftests/drivers/net/netdevsim/config |  1 +
 .../drivers/net/netdevsim/macsec-offload.sh        | 63 ++++++++++++++++++++
 tools/testing/selftests/net/rtnetlink.sh           | 68 ----------------------
 4 files changed, 65 insertions(+), 68 deletions(-)
 create mode 100755 tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile
index df167c637af9..07b7c46d3311 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/Makefile
+++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile
@@ -11,6 +11,7 @@ TEST_PROGS = devlink.sh \
 	fib.sh \
 	fib_notifications.sh \
 	hw_stats_l3.sh \
+	macsec-offload.sh \
 	nexthop.sh \
 	peer.sh \
 	psample.sh \
diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config
index adf45a3a78b4..5117c78ddf0a 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/config
+++ b/tools/testing/selftests/drivers/net/netdevsim/config
@@ -1,6 +1,7 @@
 CONFIG_DUMMY=y
 CONFIG_GENEVE=m
 CONFIG_IPV6=y
+CONFIG_MACSEC=m
 CONFIG_NETDEVSIM=m
 CONFIG_NET_SCH_MQPRIO=y
 CONFIG_NET_SCH_MULTIQ=y
diff --git a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
new file mode 100755
index 000000000000..7babcfd76b22
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
@@ -0,0 +1,63 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+NSIM_NETDEV=$(make_netdev)
+MACSEC_NETDEV=macsec_nsim
+
+set -o pipefail
+
+if ! ethtool -k $NSIM_NETDEV | grep -q 'macsec-hw-offload: on'; then
+    echo "SKIP: netdevsim doesn't support MACsec offload"
+    exit 4
+fi
+
+if ! ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec offload mac 2>/dev/null; then
+    echo "SKIP: couldn't create macsec device"
+    exit 4
+fi
+ip link del $MACSEC_NETDEV
+
+#
+# test macsec offload API
+#
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}" type macsec port 4 offload mac
+check $?
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}2" type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac
+check $?
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}3" type macsec sci abbacdde01020304 offload mac
+check $?
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}4" type macsec port 8 offload mac 2> /dev/null
+check $? '' '' 1
+
+ip macsec add "${MACSEC_NETDEV}" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+check $?
+
+ip macsec add "${MACSEC_NETDEV}" rx port 1234 address "1c:ed:de:ad:be:ef"
+check $?
+
+ip macsec add "${MACSEC_NETDEV}" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \
+    key 00 0123456789abcdef0123456789abcdef
+check $?
+
+ip macsec add "${MACSEC_NETDEV}" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null
+check $? '' '' 1
+
+for dev in ${MACSEC_NETDEV}{,2,3} ; do
+    ip link del $dev
+    check $?
+done
+
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $((num_passes)) checks"
+    exit 0
+else
+    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+    exit 1
+fi
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 6e216d7a8e2f..7f05b5f9b76f 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -21,7 +21,6 @@ ALL_TESTS="
 	kci_test_vrf
 	kci_test_encap
 	kci_test_macsec
-	kci_test_macsec_offload
 	kci_test_ipsec
 	kci_test_ipsec_offload
 	kci_test_fdb_get
@@ -560,73 +559,6 @@ kci_test_macsec()
 	end_test "PASS: macsec"
 }
 
-kci_test_macsec_offload()
-{
-	sysfsd=/sys/kernel/debug/netdevsim/netdevsim0/ports/0/
-	sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/
-	probed=false
-	local ret=0
-	run_cmd_grep "^Usage: ip macsec" ip macsec help
-	if [ $? -ne 0 ]; then
-		end_test "SKIP: macsec: iproute2 too old"
-		return $ksft_skip
-	fi
-
-	if ! mount | grep -q debugfs; then
-		mount -t debugfs none /sys/kernel/debug/ &> /dev/null
-	fi
-
-	# setup netdevsim since dummydev doesn't have offload support
-	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
-		run_cmd modprobe -q netdevsim
-
-		if [ $ret -ne 0 ]; then
-			end_test "SKIP: macsec_offload can't load netdevsim"
-			return $ksft_skip
-		fi
-		probed=true
-	fi
-
-	echo "0" > /sys/bus/netdevsim/new_device
-	while [ ! -d $sysfsnet ] ; do :; done
-	udevadm settle
-	dev=`ls $sysfsnet`
-
-	ip link set $dev up
-	if [ ! -d $sysfsd ] ; then
-		end_test "FAIL: macsec_offload can't create device $dev"
-		return 1
-	fi
-	run_cmd_grep 'macsec-hw-offload: on' ethtool -k $dev
-	if [ $? -eq 1 ] ; then
-		end_test "FAIL: macsec_offload netdevsim doesn't support MACsec offload"
-		return 1
-	fi
-	run_cmd ip link add link $dev kci_macsec1 type macsec port 4 offload mac
-	run_cmd ip link add link $dev kci_macsec2 type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac
-	run_cmd ip link add link $dev kci_macsec3 type macsec sci abbacdde01020304 offload mac
-	run_cmd_fail ip link add link $dev kci_macsec4 type macsec port 8 offload mac
-
-	msname=kci_macsec1
-	run_cmd ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
-	run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
-	run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \
-		key 00 0123456789abcdef0123456789abcdef
-	run_cmd_fail ip macsec add "$msname" rx port 1235 address "1c:ed:de:ad:be:ef"
-	# clean up any leftovers
-	for msdev in kci_macsec{1,2,3,4} ; do
-	    ip link del $msdev 2> /dev/null
-	done
-	echo 0 > /sys/bus/netdevsim/del_device
-	$probed && rmmod netdevsim
-
-	if [ $ret -ne 0 ]; then
-		end_test "FAIL: macsec_offload"
-		return 1
-	fi
-	end_test "PASS: macsec_offload"
-}
-
 #-------------------------------------------------------------------
 # Example commands
 #   ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
-- 
cgit v1.2.3


From 29084ea5d0e806abb02a69e18bae3d562a9202a5 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 7 Nov 2024 00:13:33 +0100
Subject: selftests: netdevsim: add test toggling macsec offload

The test verifies that toggling offload works (both via rtnetlink and
macsec's genetlink APIs). This is only possible when no SA is
configured.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/bf8e27ee0d921caa4eb35f1e830eca6d4080ddb2.1730929545.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../drivers/net/netdevsim/macsec-offload.sh         | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
index 7babcfd76b22..1f2775846ea0 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
@@ -48,6 +48,27 @@ check $?
 ip macsec add "${MACSEC_NETDEV}" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null
 check $? '' '' 1
 
+# can't disable macsec offload when SAs are configured
+ip link set "${MACSEC_NETDEV}" type macsec offload off 2> /dev/null
+check $? '' '' 1
+
+ip macsec offload "${MACSEC_NETDEV}" off 2> /dev/null
+check $? '' '' 1
+
+# toggle macsec offload via rtnetlink
+ip link set "${MACSEC_NETDEV}2" type macsec offload off
+check $?
+
+ip link set "${MACSEC_NETDEV}2" type macsec offload mac
+check $?
+
+# toggle macsec offload via genetlink
+ip macsec offload "${MACSEC_NETDEV}2" off
+check $?
+
+ip macsec offload "${MACSEC_NETDEV}2" mac
+check $?
+
 for dev in ${MACSEC_NETDEV}{,2,3} ; do
     ip link del $dev
     check $?
-- 
cgit v1.2.3


From 0f8800eb67ae9160d144d803f4f8d26ba6385213 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 7 Nov 2024 00:13:34 +0100
Subject: selftests: netdevsim: add ethtool features to macsec offload tests

The test verifies that available features aren't changed by toggling
offload on the device. Creating a device with offload off and then
enabling it later should result in the same features as creating the
device with offload enabled directly.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/ba801bd0a75b02de2dddbfc77f9efceb8b3d8a2e.1730929545.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../drivers/net/netdevsim/macsec-offload.sh        | 33 ++++++++++++++++++++++
 1 file changed, 33 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
index 1f2775846ea0..98033e6667d2 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
@@ -75,6 +75,39 @@ for dev in ${MACSEC_NETDEV}{,2,3} ; do
 done
 
 
+#
+# test ethtool features when toggling offload
+#
+
+ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec offload mac
+TMP_FEATS_ON_1="$(ethtool -k $MACSEC_NETDEV)"
+
+ip link set $MACSEC_NETDEV type macsec offload off
+TMP_FEATS_OFF_1="$(ethtool -k $MACSEC_NETDEV)"
+
+ip link set $MACSEC_NETDEV type macsec offload mac
+TMP_FEATS_ON_2="$(ethtool -k $MACSEC_NETDEV)"
+
+[ "$TMP_FEATS_ON_1" = "$TMP_FEATS_ON_2" ]
+check $?
+
+ip link del $MACSEC_NETDEV
+
+ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec
+check $?
+
+TMP_FEATS_OFF_2="$(ethtool -k $MACSEC_NETDEV)"
+[ "$TMP_FEATS_OFF_1" = "$TMP_FEATS_OFF_2" ]
+check $?
+
+ip link set $MACSEC_NETDEV type macsec offload mac
+check $?
+
+TMP_FEATS_ON_3="$(ethtool -k $MACSEC_NETDEV)"
+[ "$TMP_FEATS_ON_1" = "$TMP_FEATS_ON_3" ]
+check $?
+
+
 if [ $num_errors -eq 0 ]; then
     echo "PASSED all $((num_passes)) checks"
     exit 0
-- 
cgit v1.2.3


From d9ccb18f83ea2bb654289b6ecf014fd267cc988b Mon Sep 17 00:00:00 2001
From: Omid Ehtemam-Haghighi <omid.ehtemamhaghighi@menlosecurity.com>
Date: Tue, 5 Nov 2024 17:02:36 -0800
Subject: ipv6: Fix soft lockups in fib6_select_path under high next hop churn
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Soft lockups have been observed on a cluster of Linux-based edge routers
located in a highly dynamic environment. Using the `bird` service, these
routers continuously update BGP-advertised routes due to frequently
changing nexthop destinations, while also managing significant IPv6
traffic. The lockups occur during the traversal of the multipath
circular linked-list in the `fib6_select_path` function, particularly
while iterating through the siblings in the list. The issue typically
arises when the nodes of the linked list are unexpectedly deleted
concurrently on a different core—indicated by their 'next' and
'previous' elements pointing back to the node itself and their reference
count dropping to zero. This results in an infinite loop, leading to a
soft lockup that triggers a system panic via the watchdog timer.

Apply RCU primitives in the problematic code sections to resolve the
issue. Where necessary, update the references to fib6_siblings to
annotate or use the RCU APIs.

Include a test script that reproduces the issue. The script
periodically updates the routing table while generating a heavy load
of outgoing IPv6 traffic through multiple iperf3 clients. It
consistently induces infinite soft lockups within a couple of minutes.

Kernel log:

 0 [ffffbd13003e8d30] machine_kexec at ffffffff8ceaf3eb
 1 [ffffbd13003e8d90] __crash_kexec at ffffffff8d0120e3
 2 [ffffbd13003e8e58] panic at ffffffff8cef65d4
 3 [ffffbd13003e8ed8] watchdog_timer_fn at ffffffff8d05cb03
 4 [ffffbd13003e8f08] __hrtimer_run_queues at ffffffff8cfec62f
 5 [ffffbd13003e8f70] hrtimer_interrupt at ffffffff8cfed756
 6 [ffffbd13003e8fd0] __sysvec_apic_timer_interrupt at ffffffff8cea01af
 7 [ffffbd13003e8ff0] sysvec_apic_timer_interrupt at ffffffff8df1b83d
-- <IRQ stack> --
 8 [ffffbd13003d3708] asm_sysvec_apic_timer_interrupt at ffffffff8e000ecb
    [exception RIP: fib6_select_path+299]
    RIP: ffffffff8ddafe7b  RSP: ffffbd13003d37b8  RFLAGS: 00000287
    RAX: ffff975850b43600  RBX: ffff975850b40200  RCX: 0000000000000000
    RDX: 000000003fffffff  RSI: 0000000051d383e4  RDI: ffff975850b43618
    RBP: ffffbd13003d3800   R8: 0000000000000000   R9: ffff975850b40200
    R10: 0000000000000000  R11: 0000000000000000  R12: ffffbd13003d3830
    R13: ffff975850b436a8  R14: ffff975850b43600  R15: 0000000000000007
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
 9 [ffffbd13003d3808] ip6_pol_route at ffffffff8ddb030c
10 [ffffbd13003d3888] ip6_pol_route_input at ffffffff8ddb068c
11 [ffffbd13003d3898] fib6_rule_lookup at ffffffff8ddf02b5
12 [ffffbd13003d3928] ip6_route_input at ffffffff8ddb0f47
13 [ffffbd13003d3a18] ip6_rcv_finish_core.constprop.0 at ffffffff8dd950d0
14 [ffffbd13003d3a30] ip6_list_rcv_finish.constprop.0 at ffffffff8dd96274
15 [ffffbd13003d3a98] ip6_sublist_rcv at ffffffff8dd96474
16 [ffffbd13003d3af8] ipv6_list_rcv at ffffffff8dd96615
17 [ffffbd13003d3b60] __netif_receive_skb_list_core at ffffffff8dc16fec
18 [ffffbd13003d3be0] netif_receive_skb_list_internal at ffffffff8dc176b3
19 [ffffbd13003d3c50] napi_gro_receive at ffffffff8dc565b9
20 [ffffbd13003d3c80] ice_receive_skb at ffffffffc087e4f5 [ice]
21 [ffffbd13003d3c90] ice_clean_rx_irq at ffffffffc0881b80 [ice]
22 [ffffbd13003d3d20] ice_napi_poll at ffffffffc088232f [ice]
23 [ffffbd13003d3d80] __napi_poll at ffffffff8dc18000
24 [ffffbd13003d3db8] net_rx_action at ffffffff8dc18581
25 [ffffbd13003d3e40] __do_softirq at ffffffff8df352e9
26 [ffffbd13003d3eb0] run_ksoftirqd at ffffffff8ceffe47
27 [ffffbd13003d3ec0] smpboot_thread_fn at ffffffff8cf36a30
28 [ffffbd13003d3ee8] kthread at ffffffff8cf2b39f
29 [ffffbd13003d3f28] ret_from_fork at ffffffff8ce5fa64
30 [ffffbd13003d3f50] ret_from_fork_asm at ffffffff8ce03cbb

Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table")
Reported-by: Adrian Oliver <kernel@aoliver.ca>
Signed-off-by: Omid Ehtemam-Haghighi <omid.ehtemamhaghighi@menlosecurity.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Ido Schimmel <idosch@idosch.org>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: Simon Horman <horms@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20241106010236.1239299-1-omid.ehtemamhaghighi@menlosecurity.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_fib.c                                 |   8 +-
 net/ipv6/route.c                                   |  45 ++--
 tools/testing/selftests/net/Makefile               |   1 +
 .../selftests/net/ipv6_route_update_soft_lockup.sh | 262 +++++++++++++++++++++
 4 files changed, 297 insertions(+), 19 deletions(-)
 create mode 100755 tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh

(limited to 'tools/testing')

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6383263bfd04..c134ba202c4c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1183,8 +1183,8 @@ next_iter:
 		while (sibling) {
 			if (sibling->fib6_metric == rt->fib6_metric &&
 			    rt6_qualify_for_ecmp(sibling)) {
-				list_add_tail(&rt->fib6_siblings,
-					      &sibling->fib6_siblings);
+				list_add_tail_rcu(&rt->fib6_siblings,
+						  &sibling->fib6_siblings);
 				break;
 			}
 			sibling = rcu_dereference_protected(sibling->fib6_next,
@@ -1245,7 +1245,7 @@ add:
 							 fib6_siblings)
 					sibling->fib6_nsiblings--;
 				rt->fib6_nsiblings = 0;
-				list_del_init(&rt->fib6_siblings);
+				list_del_rcu(&rt->fib6_siblings);
 				rt6_multipath_rebalance(next_sibling);
 				return err;
 			}
@@ -1963,7 +1963,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 					 &rt->fib6_siblings, fib6_siblings)
 			sibling->fib6_nsiblings--;
 		rt->fib6_nsiblings = 0;
-		list_del_init(&rt->fib6_siblings);
+		list_del_rcu(&rt->fib6_siblings);
 		rt6_multipath_rebalance(next_sibling);
 	}
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 038c1eeef0be..63d7681c929f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -416,8 +416,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		      struct flowi6 *fl6, int oif, bool have_oif_match,
 		      const struct sk_buff *skb, int strict)
 {
-	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
+	struct fib6_info *sibling;
 
 	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;
@@ -443,8 +443,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
 		goto out;
 
-	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
-				 fib6_siblings) {
+	list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+				fib6_siblings) {
 		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;
 
@@ -5195,14 +5195,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
 	 * nexthop. Since sibling routes are always added at the end of
 	 * the list, find the first sibling of the last route appended
 	 */
+	rcu_read_lock();
+
 	if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
-		rt = list_first_entry(&rt_last->fib6_siblings,
-				      struct fib6_info,
-				      fib6_siblings);
+		rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
+					    struct fib6_info,
+					    fib6_siblings);
 	}
 
 	if (rt)
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
+
+	rcu_read_unlock();
 }
 
 static bool ip6_route_mpath_should_notify(const struct fib6_info *rt)
@@ -5547,17 +5551,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i)
 		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
 					 &nexthop_len);
 	} else {
-		struct fib6_info *sibling, *next_sibling;
 		struct fib6_nh *nh = f6i->fib6_nh;
+		struct fib6_info *sibling;
 
 		nexthop_len = 0;
 		if (f6i->fib6_nsiblings) {
 			rt6_nh_nlmsg_size(nh, &nexthop_len);
 
-			list_for_each_entry_safe(sibling, next_sibling,
-						 &f6i->fib6_siblings, fib6_siblings) {
+			rcu_read_lock();
+
+			list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+						fib6_siblings) {
 				rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
 			}
+
+			rcu_read_unlock();
 		}
 		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
@@ -5721,7 +5729,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		    lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
 			goto nla_put_failure;
 	} else if (rt->fib6_nsiblings) {
-		struct fib6_info *sibling, *next_sibling;
+		struct fib6_info *sibling;
 		struct nlattr *mp;
 
 		mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
@@ -5733,14 +5741,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				    0) < 0)
 			goto nla_put_failure;
 
-		list_for_each_entry_safe(sibling, next_sibling,
-					 &rt->fib6_siblings, fib6_siblings) {
+		rcu_read_lock();
+
+		list_for_each_entry_rcu(sibling, &rt->fib6_siblings,
+					fib6_siblings) {
 			if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
 					    sibling->fib6_nh->fib_nh_weight,
-					    AF_INET6, 0) < 0)
+					    AF_INET6, 0) < 0) {
+				rcu_read_unlock();
+
 				goto nla_put_failure;
+			}
 		}
 
+		rcu_read_unlock();
+
 		nla_nest_end(skb, mp);
 	} else if (rt->nh) {
 		if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
@@ -6177,7 +6192,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
-	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+	skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
 
@@ -6190,7 +6205,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		goto errout;
 	}
 	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
-		    info->nlh, gfp_any());
+		    info->nlh, GFP_ATOMIC);
 	return;
 errout:
 	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 26a4883a65c9..8c4db5199a42 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -96,6 +96,7 @@ TEST_PROGS += fdb_flush.sh
 TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
+TEST_PROGS += ipv6_route_update_soft_lockup.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := ncdevmem
diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
new file mode 100755
index 000000000000..a6b2b1f9c641
--- /dev/null
+++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
@@ -0,0 +1,262 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Testing for potential kernel soft lockup during IPv6 routing table
+# refresh under heavy outgoing IPv6 traffic. If a kernel soft lockup
+# occurs, a kernel panic will be triggered to prevent associated issues.
+#
+#
+#                            Test Environment Layout
+#
+# ┌----------------┐                                         ┌----------------┐
+# |     SOURCE_NS  |                                         |     SINK_NS    |
+# |    NAMESPACE   |                                         |    NAMESPACE   |
+# |(iperf3 clients)|                                         |(iperf3 servers)|
+# |                |                                         |                |
+# |                |                                         |                |
+# |    ┌-----------|                             nexthops    |---------┐      |
+# |    |veth_source|<--------------------------------------->|veth_sink|<┐    |
+# |    └-----------|2001:0DB8:1::0:1/96  2001:0DB8:1::1:1/96 |---------┘ |    |
+# |                |         ^           2001:0DB8:1::1:2/96 |           |    |
+# |                |         .                   .           |       fwd |    |
+# |  ┌---------┐   |         .                   .           |           |    |
+# |  |   IPv6  |   |         .                   .           |           V    |
+# |  | routing |   |         .           2001:0DB8:1::1:80/96|        ┌-----┐ |
+# |  |  table  |   |         .                               |        | lo  | |
+# |  | nexthop |   |         .                               └--------┴-----┴-┘
+# |  | update  |   |         ............................> 2001:0DB8:2::1:1/128
+# |  └-------- ┘   |
+# └----------------┘
+#
+# The test script sets up two network namespaces, source_ns and sink_ns,
+# connected via a veth link. Within source_ns, it continuously updates the
+# IPv6 routing table by flushing and inserting IPV6_NEXTHOP_ADDR_COUNT nexthop
+# IPs destined for SINK_LOOPBACK_IP_ADDR in sink_ns. This refresh occurs at a
+# rate of 1/ROUTING_TABLE_REFRESH_PERIOD per second for TEST_DURATION seconds.
+#
+# Simultaneously, multiple iperf3 clients within source_ns generate heavy
+# outgoing IPv6 traffic. Each client is assigned a unique port number starting
+# at 5000 and incrementing sequentially. Each client targets a unique iperf3
+# server running in sink_ns, connected to the SINK_LOOPBACK_IFACE interface
+# using the same port number.
+#
+# The number of iperf3 servers and clients is set to half of the total
+# available cores on each machine.
+#
+# NOTE: We have tested this script on machines with various CPU specifications,
+# ranging from lower to higher performance as listed below. The test script
+# effectively triggered a kernel soft lockup on machines running an unpatched
+# kernel in under a minute:
+#
+# - 1x Intel Xeon E-2278G 8-Core Processor @ 3.40GHz
+# - 1x Intel Xeon E-2378G Processor 8-Core @ 2.80GHz
+# - 1x AMD EPYC 7401P 24-Core Processor @ 2.00GHz
+# - 1x AMD EPYC 7402P 24-Core Processor @ 2.80GHz
+# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz
+# - 1x Ampere Altra Q80-30 80-Core Processor @ 3.00GHz
+# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz
+# - 2x Intel Xeon Silver 4214 24-Core Processor @ 2.20GHz
+# - 1x AMD EPYC 7502P 32-Core @ 2.50GHz
+# - 1x Intel Xeon Gold 6314U 32-Core Processor @ 2.30GHz
+# - 2x Intel Xeon Gold 6338 32-Core Processor @ 2.00GHz
+#
+# On less performant machines, you may need to increase the TEST_DURATION
+# parameter to enhance the likelihood of encountering a race condition leading
+# to a kernel soft lockup and avoid a false negative result.
+#
+# NOTE: The test may not produce the expected result in virtualized
+# environments (e.g., qemu) due to differences in timing and CPU handling,
+# which can affect the conditions needed to trigger a soft lockup.
+
+source lib.sh
+source net_helper.sh
+
+TEST_DURATION=300
+ROUTING_TABLE_REFRESH_PERIOD=0.01
+
+IPERF3_BITRATE="300m"
+
+
+IPV6_NEXTHOP_ADDR_COUNT="128"
+IPV6_NEXTHOP_ADDR_MASK="96"
+IPV6_NEXTHOP_PREFIX="2001:0DB8:1"
+
+
+SOURCE_TEST_IFACE="veth_source"
+SOURCE_TEST_IP_ADDR="2001:0DB8:1::0:1/96"
+
+SINK_TEST_IFACE="veth_sink"
+# ${SINK_TEST_IFACE} is populated with the following range of IPv6 addresses:
+# 2001:0DB8:1::1:1  to 2001:0DB8:1::1:${IPV6_NEXTHOP_ADDR_COUNT}
+SINK_LOOPBACK_IFACE="lo"
+SINK_LOOPBACK_IP_MASK="128"
+SINK_LOOPBACK_IP_ADDR="2001:0DB8:2::1:1"
+
+nexthop_ip_list=""
+termination_signal=""
+kernel_softlokup_panic_prev_val=""
+
+terminate_ns_processes_by_pattern() {
+	local ns=$1
+	local pattern=$2
+
+	for pid in $(ip netns pids ${ns}); do
+		[ -e /proc/$pid/cmdline ] && grep -qe "${pattern}" /proc/$pid/cmdline && kill -9 $pid
+	done
+}
+
+cleanup() {
+	echo "info: cleaning up namespaces and terminating all processes within them..."
+
+
+	# Terminate iperf3 instances running in the source_ns. To avoid race
+	# conditions, first iterate over the PIDs and terminate those
+	# associated with the bash shells running the
+	# `while true; do iperf3 -c ...; done` loops. In a second iteration,
+	# terminate the individual `iperf3 -c ...` instances.
+	terminate_ns_processes_by_pattern ${source_ns} while
+	terminate_ns_processes_by_pattern ${source_ns} iperf3
+
+	# Repeat the same process for sink_ns
+	terminate_ns_processes_by_pattern ${sink_ns} while
+	terminate_ns_processes_by_pattern ${sink_ns} iperf3
+
+	# Check if any iperf3 instances are still running. This could happen
+	# if a core has entered an infinite loop and the timeout for detecting
+	# the soft lockup has not expired, but either the test interval has
+	# already elapsed or the test was terminated manually (e.g., with ^C)
+	for pid in $(ip netns pids ${source_ns}); do
+		if [ -e /proc/$pid/cmdline ] && grep -qe 'iperf3' /proc/$pid/cmdline; then
+			echo "FAIL: unable to terminate some iperf3 instances. Soft lockup is underway. A kernel panic is on the way!"
+			exit ${ksft_fail}
+		fi
+	done
+
+	if [ "$termination_signal" == "SIGINT" ]; then
+		echo "SKIP: Termination due to ^C (SIGINT)"
+	elif [ "$termination_signal" == "SIGALRM" ]; then
+		echo "PASS: No kernel soft lockup occurred during this ${TEST_DURATION} second test"
+	fi
+
+	cleanup_ns ${source_ns} ${sink_ns}
+
+	sysctl -qw kernel.softlockup_panic=${kernel_softlokup_panic_prev_val}
+}
+
+setup_prepare() {
+	setup_ns source_ns sink_ns
+
+	ip -n ${source_ns} link add name ${SOURCE_TEST_IFACE} type veth peer name ${SINK_TEST_IFACE} netns ${sink_ns}
+
+	# Setting up the Source namespace
+	ip -n ${source_ns} addr add ${SOURCE_TEST_IP_ADDR} dev ${SOURCE_TEST_IFACE}
+	ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} qlen 10000
+	ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} up
+	ip netns exec ${source_ns} sysctl -qw net.ipv6.fib_multipath_hash_policy=1
+
+	# Setting up the Sink namespace
+	ip -n ${sink_ns} addr add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} dev ${SINK_LOOPBACK_IFACE}
+	ip -n ${sink_ns} link set dev ${SINK_LOOPBACK_IFACE} up
+	ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_LOOPBACK_IFACE}.forwarding=1
+
+	ip -n ${sink_ns} link set ${SINK_TEST_IFACE} up
+	ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_TEST_IFACE}.forwarding=1
+
+
+	# Populate nexthop IPv6 addresses on the test interface in the sink_ns
+	echo "info: populating ${IPV6_NEXTHOP_ADDR_COUNT} IPv6 addresses on the ${SINK_TEST_IFACE} interface ..."
+	for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do
+		ip -n ${sink_ns} addr add ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" "${IP}")/${IPV6_NEXTHOP_ADDR_MASK} dev ${SINK_TEST_IFACE};
+	done
+
+	# Preparing list of nexthops
+	for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do
+		nexthop_ip_list=$nexthop_ip_list" nexthop via ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" $IP) dev ${SOURCE_TEST_IFACE} weight 1"
+	done
+}
+
+
+test_soft_lockup_during_routing_table_refresh() {
+	# Start num_of_iperf_servers iperf3 servers in the sink_ns namespace,
+	# each listening on ports starting at 5001 and incrementing
+	# sequentially. Since iperf3 instances may terminate unexpectedly, a
+	# while loop is used to automatically restart them in such cases.
+	echo "info: starting ${num_of_iperf_servers} iperf3 servers in the sink_ns namespace ..."
+	for i in $(seq 1 ${num_of_iperf_servers}); do
+		cmd="iperf3 --bind ${SINK_LOOPBACK_IP_ADDR} -s -p $(printf '5%03d' ${i}) --rcv-timeout 200 &>/dev/null"
+		ip netns exec ${sink_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null
+	done
+
+	# Wait for the iperf3 servers to be ready
+	for i in $(seq ${num_of_iperf_servers}); do
+		port=$(printf '5%03d' ${i});
+		wait_local_port_listen ${sink_ns} ${port} tcp
+	done
+
+	# Continuously refresh the routing table in the background within
+	# the source_ns namespace
+	ip netns exec ${source_ns} bash -c "
+		while \$(ip netns list | grep -q ${source_ns}); do
+			ip -6 route add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} ${nexthop_ip_list};
+			sleep ${ROUTING_TABLE_REFRESH_PERIOD};
+			ip -6 route delete ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK};
+		done &"
+
+	# Start num_of_iperf_servers iperf3 clients in the source_ns namespace,
+	# each sending TCP traffic on sequential ports starting at 5001.
+	# Since iperf3 instances may terminate unexpectedly (e.g., if the route
+	# to the server is deleted in the background during a route refresh), a
+	# while loop is used to automatically restart them in such cases.
+	echo "info: starting ${num_of_iperf_servers} iperf3 clients in the source_ns namespace ..."
+	for i in $(seq 1 ${num_of_iperf_servers}); do
+		cmd="iperf3 -c ${SINK_LOOPBACK_IP_ADDR} -p $(printf '5%03d' ${i}) --length 64 --bitrate ${IPERF3_BITRATE} -t 0 --connect-timeout 150 &>/dev/null"
+		ip netns exec ${source_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null
+	done
+
+	echo "info: IPv6 routing table is being updated at the rate of $(echo "1/${ROUTING_TABLE_REFRESH_PERIOD}" | bc)/s for ${TEST_DURATION} seconds ..."
+	echo "info: A kernel soft lockup, if detected, results in a kernel panic!"
+
+	wait
+}
+
+# Make sure 'iperf3' is installed, skip the test otherwise
+if [ ! -x "$(command -v "iperf3")" ]; then
+	echo "SKIP: 'iperf3' is not installed. Skipping the test."
+	exit ${ksft_skip}
+fi
+
+# Determine the number of cores on the machine
+num_of_iperf_servers=$(( $(nproc)/2 ))
+
+# Check if we are running on a multi-core machine, skip the test otherwise
+if [ "${num_of_iperf_servers}" -eq 0 ]; then
+	echo "SKIP: This test is not valid on a single core machine!"
+	exit ${ksft_skip}
+fi
+
+# Since the kernel soft lockup we're testing causes at least one core to enter
+# an infinite loop, destabilizing the host and likely affecting subsequent
+# tests, we trigger a kernel panic instead of reporting a failure and
+# continuing
+kernel_softlokup_panic_prev_val=$(sysctl -n kernel.softlockup_panic)
+sysctl -qw kernel.softlockup_panic=1
+
+handle_sigint() {
+	termination_signal="SIGINT"
+	cleanup
+	exit ${ksft_skip}
+}
+
+handle_sigalrm() {
+	termination_signal="SIGALRM"
+	cleanup
+	exit ${ksft_pass}
+}
+
+trap handle_sigint SIGINT
+trap handle_sigalrm SIGALRM
+
+(sleep ${TEST_DURATION} && kill -s SIGALRM $$)&
+
+setup_prepare
+test_soft_lockup_during_routing_table_refresh
-- 
cgit v1.2.3


From 75e3f12fa51b758f6b8d7684b65b4684386e7706 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 6 Nov 2024 14:47:10 +0530
Subject: selftests: hsr: Add test for VLAN

Add test for VLAN ping for HSR. The test adds vlan interfaces to the hsr
interface and then verifies if ping to them works.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20241106091710.3308519-5-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/hsr/config      |  1 +
 tools/testing/selftests/net/hsr/hsr_ping.sh | 98 +++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/hsr/config b/tools/testing/selftests/net/hsr/config
index 241542441c51..555a868743f0 100644
--- a/tools/testing/selftests/net/hsr/config
+++ b/tools/testing/selftests/net/hsr/config
@@ -3,3 +3,4 @@ CONFIG_NET_SCH_NETEM=m
 CONFIG_HSR=y
 CONFIG_VETH=y
 CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=m
diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh
index f5d207fc770a..5a65f4f836be 100755
--- a/tools/testing/selftests/net/hsr/hsr_ping.sh
+++ b/tools/testing/selftests/net/hsr/hsr_ping.sh
@@ -175,6 +175,100 @@ setup_hsr_interfaces()
 	ip -net "$ns3" link set hsr3 up
 }
 
+setup_vlan_interfaces() {
+	ip -net "$ns1" link add link hsr1 name hsr1.2 type vlan id 2
+	ip -net "$ns1" link add link hsr1 name hsr1.3 type vlan id 3
+	ip -net "$ns1" link add link hsr1 name hsr1.4 type vlan id 4
+	ip -net "$ns1" link add link hsr1 name hsr1.5 type vlan id 5
+
+	ip -net "$ns2" link add link hsr2 name hsr2.2 type vlan id 2
+	ip -net "$ns2" link add link hsr2 name hsr2.3 type vlan id 3
+	ip -net "$ns2" link add link hsr2 name hsr2.4 type vlan id 4
+	ip -net "$ns2" link add link hsr2 name hsr2.5 type vlan id 5
+
+	ip -net "$ns3" link add link hsr3 name hsr3.2 type vlan id 2
+	ip -net "$ns3" link add link hsr3 name hsr3.3 type vlan id 3
+	ip -net "$ns3" link add link hsr3 name hsr3.4 type vlan id 4
+	ip -net "$ns3" link add link hsr3 name hsr3.5 type vlan id 5
+
+	ip -net "$ns1" addr add 100.64.2.1/24 dev hsr1.2
+	ip -net "$ns1" addr add 100.64.3.1/24 dev hsr1.3
+	ip -net "$ns1" addr add 100.64.4.1/24 dev hsr1.4
+	ip -net "$ns1" addr add 100.64.5.1/24 dev hsr1.5
+
+	ip -net "$ns2" addr add 100.64.2.2/24 dev hsr2.2
+	ip -net "$ns2" addr add 100.64.3.2/24 dev hsr2.3
+	ip -net "$ns2" addr add 100.64.4.2/24 dev hsr2.4
+	ip -net "$ns2" addr add 100.64.5.2/24 dev hsr2.5
+
+	ip -net "$ns3" addr add 100.64.2.3/24 dev hsr3.2
+	ip -net "$ns3" addr add 100.64.3.3/24 dev hsr3.3
+	ip -net "$ns3" addr add 100.64.4.3/24 dev hsr3.4
+	ip -net "$ns3" addr add 100.64.5.3/24 dev hsr3.5
+
+	ip -net "$ns1" link set dev hsr1.2 up
+	ip -net "$ns1" link set dev hsr1.3 up
+	ip -net "$ns1" link set dev hsr1.4 up
+	ip -net "$ns1" link set dev hsr1.5 up
+
+	ip -net "$ns2" link set dev hsr2.2 up
+	ip -net "$ns2" link set dev hsr2.3 up
+	ip -net "$ns2" link set dev hsr2.4 up
+	ip -net "$ns2" link set dev hsr2.5 up
+
+	ip -net "$ns3" link set dev hsr3.2 up
+	ip -net "$ns3" link set dev hsr3.3 up
+	ip -net "$ns3" link set dev hsr3.4 up
+	ip -net "$ns3" link set dev hsr3.5 up
+
+}
+
+hsr_vlan_ping() {
+	do_ping "$ns1" 100.64.2.2
+	do_ping "$ns1" 100.64.3.2
+	do_ping "$ns1" 100.64.4.2
+	do_ping "$ns1" 100.64.5.2
+
+	do_ping "$ns1" 100.64.2.3
+	do_ping "$ns1" 100.64.3.3
+	do_ping "$ns1" 100.64.4.3
+	do_ping "$ns1" 100.64.5.3
+
+	do_ping "$ns2" 100.64.2.1
+	do_ping "$ns2" 100.64.3.1
+	do_ping "$ns2" 100.64.4.1
+	do_ping "$ns2" 100.64.5.1
+
+	do_ping "$ns2" 100.64.2.3
+	do_ping "$ns2" 100.64.3.3
+	do_ping "$ns2" 100.64.4.3
+	do_ping "$ns2" 100.64.5.3
+
+	do_ping "$ns3" 100.64.2.1
+	do_ping "$ns3" 100.64.3.1
+	do_ping "$ns3" 100.64.4.1
+	do_ping "$ns3" 100.64.5.1
+
+	do_ping "$ns3" 100.64.2.2
+	do_ping "$ns3" 100.64.3.2
+	do_ping "$ns3" 100.64.4.2
+	do_ping "$ns3" 100.64.5.2
+}
+
+run_vlan_tests() {
+	vlan_challenged_hsr1=$(ip net exec "$ns1" ethtool -k hsr1 | grep "vlan-challenged" | awk '{print $2}')
+	vlan_challenged_hsr2=$(ip net exec "$ns2" ethtool -k hsr2 | grep "vlan-challenged" | awk '{print $2}')
+	vlan_challenged_hsr3=$(ip net exec "$ns3" ethtool -k hsr3 | grep "vlan-challenged" | awk '{print $2}')
+
+	if [[ "$vlan_challenged_hsr1" = "off" || "$vlan_challenged_hsr2" = "off" || "$vlan_challenged_hsr3" = "off" ]]; then
+		echo "INFO: Running VLAN tests"
+		setup_vlan_interfaces
+		hsr_vlan_ping
+	else
+		echo "INFO: Not Running VLAN tests as the device does not support VLAN"
+	fi
+}
+
 check_prerequisites
 setup_ns ns1 ns2 ns3
 
@@ -183,9 +277,13 @@ trap cleanup_all_ns EXIT
 setup_hsr_interfaces 0
 do_complete_ping_test
 
+run_vlan_tests
+
 setup_ns ns1 ns2 ns3
 
 setup_hsr_interfaces 1
 do_complete_ping_test
 
+run_vlan_tests
+
 exit $ret
-- 
cgit v1.2.3


From 6891f0b523e1ef452523ba43d67ca2a654760e78 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:00 -0800
Subject: selftests: ncdevmem: Redirect all non-payload output to stderr

That should make it possible to do expected payload validation on
the caller side.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 61 +++++++++++++++++-----------------
 1 file changed, 30 insertions(+), 31 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 64d6805381c5..9245d3f158dd 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -88,7 +88,6 @@ void print_nonzero_bytes(void *ptr, size_t size)
 
 	for (i = 0; i < size; i++)
 		putchar(p[i]);
-	printf("\n");
 }
 
 void validate_buffer(void *line, size_t size)
@@ -120,7 +119,7 @@ void validate_buffer(void *line, size_t size)
 		char command[256];                                      \
 		memset(command, 0, sizeof(command));                    \
 		snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \
-		printf("Running: %s\n", command);                       \
+		fprintf(stderr, "Running: %s\n", command);                       \
 		system(command);                                        \
 	})
 
@@ -128,22 +127,22 @@ static int reset_flow_steering(void)
 {
 	int ret = 0;
 
-	ret = run_command("sudo ethtool -K %s ntuple off", ifname);
+	ret = run_command("sudo ethtool -K %s ntuple off >&2", ifname);
 	if (ret)
 		return ret;
 
-	return run_command("sudo ethtool -K %s ntuple on", ifname);
+	return run_command("sudo ethtool -K %s ntuple on >&2", ifname);
 }
 
 static int configure_headersplit(bool on)
 {
-	return run_command("sudo ethtool -G %s tcp-data-split %s", ifname,
+	return run_command("sudo ethtool -G %s tcp-data-split %s >&2", ifname,
 			   on ? "on" : "off");
 }
 
 static int configure_rss(void)
 {
-	return run_command("sudo ethtool -X %s equal %d", ifname, start_queue);
+	return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue);
 }
 
 static int configure_channels(unsigned int rx, unsigned int tx)
@@ -153,7 +152,7 @@ static int configure_channels(unsigned int rx, unsigned int tx)
 
 static int configure_flow_steering(void)
 {
-	return run_command("sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d",
+	return run_command("sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d >&2",
 			   ifname, client_ip, server_ip, port, port, start_queue);
 }
 
@@ -187,7 +186,7 @@ static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
 		goto err_close;
 	}
 
-	printf("got dmabuf id=%d\n", rsp->id);
+	fprintf(stderr, "got dmabuf id=%d\n", rsp->id);
 	dmabuf_id = rsp->id;
 
 	netdev_bind_rx_req_free(req);
@@ -314,8 +313,8 @@ int do_server(void)
 	if (ret)
 		error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
 
-	printf("binding to address %s:%d\n", server_ip,
-	       ntohs(server_sin.sin_port));
+	fprintf(stderr, "binding to address %s:%d\n", server_ip,
+		ntohs(server_sin.sin_port));
 
 	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
 	if (ret)
@@ -329,14 +328,14 @@ int do_server(void)
 
 	inet_ntop(server_sin.sin_family, &server_sin.sin_addr, buffer,
 		  sizeof(buffer));
-	printf("Waiting or connection on %s:%d\n", buffer,
-	       ntohs(server_sin.sin_port));
+	fprintf(stderr, "Waiting or connection on %s:%d\n", buffer,
+		ntohs(server_sin.sin_port));
 	client_fd = accept(socket_fd, &client_addr, &client_addr_len);
 
 	inet_ntop(client_addr.sin_family, &client_addr.sin_addr, buffer,
 		  sizeof(buffer));
-	printf("Got connection from %s:%d\n", buffer,
-	       ntohs(client_addr.sin_port));
+	fprintf(stderr, "Got connection from %s:%d\n", buffer,
+		ntohs(client_addr.sin_port));
 
 	while (1) {
 		struct iovec iov = { .iov_base = iobuf,
@@ -349,14 +348,13 @@ int do_server(void)
 		ssize_t ret;
 
 		is_devmem = false;
-		printf("\n\n");
 
 		msg.msg_iov = &iov;
 		msg.msg_iovlen = 1;
 		msg.msg_control = ctrl_data;
 		msg.msg_controllen = sizeof(ctrl_data);
 		ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM);
-		printf("recvmsg ret=%ld\n", ret);
+		fprintf(stderr, "recvmsg ret=%ld\n", ret);
 		if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK))
 			continue;
 		if (ret < 0) {
@@ -364,7 +362,7 @@ int do_server(void)
 			continue;
 		}
 		if (ret == 0) {
-			printf("client exited\n");
+			fprintf(stderr, "client exited\n");
 			goto cleanup;
 		}
 
@@ -373,7 +371,7 @@ int do_server(void)
 			if (cm->cmsg_level != SOL_SOCKET ||
 			    (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
 			     cm->cmsg_type != SCM_DEVMEM_LINEAR)) {
-				fprintf(stdout, "skipping non-devmem cmsg\n");
+				fprintf(stderr, "skipping non-devmem cmsg\n");
 				continue;
 			}
 
@@ -384,7 +382,7 @@ int do_server(void)
 				/* TODO: process data copied from skb's linear
 				 * buffer.
 				 */
-				fprintf(stdout,
+				fprintf(stderr,
 					"SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n",
 					dmabuf_cmsg->frag_size);
 
@@ -395,12 +393,13 @@ int do_server(void)
 			token.token_count = 1;
 
 			total_received += dmabuf_cmsg->frag_size;
-			printf("received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n",
-			       dmabuf_cmsg->frag_offset >> PAGE_SHIFT,
-			       dmabuf_cmsg->frag_offset % getpagesize(),
-			       dmabuf_cmsg->frag_offset, dmabuf_cmsg->frag_size,
-			       dmabuf_cmsg->frag_token, total_received,
-			       dmabuf_cmsg->dmabuf_id);
+			fprintf(stderr,
+				"received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n",
+				dmabuf_cmsg->frag_offset >> PAGE_SHIFT,
+				dmabuf_cmsg->frag_offset % getpagesize(),
+				dmabuf_cmsg->frag_offset,
+				dmabuf_cmsg->frag_size, dmabuf_cmsg->frag_token,
+				total_received, dmabuf_cmsg->dmabuf_id);
 
 			if (dmabuf_cmsg->dmabuf_id != dmabuf_id)
 				error(1, 0,
@@ -438,15 +437,15 @@ int do_server(void)
 		if (!is_devmem)
 			error(1, 0, "flow steering error\n");
 
-		printf("total_received=%lu\n", total_received);
+		fprintf(stderr, "total_received=%lu\n", total_received);
 	}
 
-	fprintf(stdout, "%s: ok\n", TEST_PREFIX);
+	fprintf(stderr, "%s: ok\n", TEST_PREFIX);
 
-	fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
 		page_aligned_frags, non_page_aligned_frags);
 
-	fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
 		page_aligned_frags, non_page_aligned_frags);
 
 cleanup:
@@ -551,7 +550,7 @@ int main(int argc, char *argv[])
 			ifname = optarg;
 			break;
 		case '?':
-			printf("unknown option: %c\n", optopt);
+			fprintf(stderr, "unknown option: %c\n", optopt);
 			break;
 		}
 	}
@@ -559,7 +558,7 @@ int main(int argc, char *argv[])
 	ifindex = if_nametoindex(ifname);
 
 	for (; optind < argc; optind++)
-		printf("extra arguments: %s\n", argv[optind]);
+		fprintf(stderr, "extra arguments: %s\n", argv[optind]);
 
 	run_devmem_tests();
 
-- 
cgit v1.2.3


From 8b9049af8066b4705d83bb7847ee3c960fc58d09 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:01 -0800
Subject: selftests: ncdevmem: Separate out dmabuf provider

So we can plug the other ones in the future if needed.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 203 +++++++++++++++++++--------------
 1 file changed, 119 insertions(+), 84 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 9245d3f158dd..3e7ef2eedd60 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -71,17 +71,101 @@ static char *ifname = "eth1";
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
 
-void print_bytes(void *ptr, size_t size)
+struct memory_buffer {
+	int fd;
+	size_t size;
+
+	int devfd;
+	int memfd;
+	char *buf_mem;
+};
+
+struct memory_provider {
+	struct memory_buffer *(*alloc)(size_t size);
+	void (*free)(struct memory_buffer *ctx);
+	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
+				   size_t off, int n);
+};
+
+static struct memory_buffer *udmabuf_alloc(size_t size)
 {
-	unsigned char *p = ptr;
-	int i;
+	struct udmabuf_create create;
+	struct memory_buffer *ctx;
+	int ret;
 
-	for (i = 0; i < size; i++)
-		printf("%02hhX ", p[i]);
-	printf("\n");
+	ctx = malloc(sizeof(*ctx));
+	if (!ctx)
+		error(1, ENOMEM, "malloc failed");
+
+	ctx->size = size;
+
+	ctx->devfd = open("/dev/udmabuf", O_RDWR);
+	if (ctx->devfd < 0)
+		error(1, errno,
+		      "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
+		      TEST_PREFIX);
+
+	ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
+	if (ctx->memfd < 0)
+		error(1, errno, "%s: [skip,no-memfd]\n", TEST_PREFIX);
+
+	ret = fcntl(ctx->memfd, F_ADD_SEALS, F_SEAL_SHRINK);
+	if (ret < 0)
+		error(1, errno, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+
+	ret = ftruncate(ctx->memfd, size);
+	if (ret == -1)
+		error(1, errno, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+
+	memset(&create, 0, sizeof(create));
+
+	create.memfd = ctx->memfd;
+	create.offset = 0;
+	create.size = size;
+	ctx->fd = ioctl(ctx->devfd, UDMABUF_CREATE, &create);
+	if (ctx->fd < 0)
+		error(1, errno, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX);
+
+	ctx->buf_mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED,
+			    ctx->fd, 0);
+	if (ctx->buf_mem == MAP_FAILED)
+		error(1, errno, "%s: [FAIL, map udmabuf]\n", TEST_PREFIX);
+
+	return ctx;
+}
+
+static void udmabuf_free(struct memory_buffer *ctx)
+{
+	munmap(ctx->buf_mem, ctx->size);
+	close(ctx->fd);
+	close(ctx->memfd);
+	close(ctx->devfd);
+	free(ctx);
 }
 
-void print_nonzero_bytes(void *ptr, size_t size)
+static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
+				       size_t off, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START;
+	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst, src->buf_mem + off, n);
+
+	sync.flags = DMA_BUF_SYNC_END;
+	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
+static struct memory_provider udmabuf_memory_provider = {
+	.alloc = udmabuf_alloc,
+	.free = udmabuf_free,
+	.memcpy_from_device = udmabuf_memcpy_from_device,
+};
+
+static struct memory_provider *provider = &udmabuf_memory_provider;
+
+static void print_nonzero_bytes(void *ptr, size_t size)
 {
 	unsigned char *p = ptr;
 	unsigned int i;
@@ -201,42 +285,7 @@ err_close:
 	return -1;
 }
 
-static void create_udmabuf(int *devfd, int *memfd, int *buf, size_t dmabuf_size)
-{
-	struct udmabuf_create create;
-	int ret;
-
-	*devfd = open("/dev/udmabuf", O_RDWR);
-	if (*devfd < 0) {
-		error(70, 0,
-		      "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
-		      TEST_PREFIX);
-	}
-
-	*memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
-	if (*memfd < 0)
-		error(70, 0, "%s: [skip,no-memfd]\n", TEST_PREFIX);
-
-	/* Required for udmabuf */
-	ret = fcntl(*memfd, F_ADD_SEALS, F_SEAL_SHRINK);
-	if (ret < 0)
-		error(73, 0, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
-
-	ret = ftruncate(*memfd, dmabuf_size);
-	if (ret == -1)
-		error(74, 0, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
-
-	memset(&create, 0, sizeof(create));
-
-	create.memfd = *memfd;
-	create.offset = 0;
-	create.size = dmabuf_size;
-	*buf = ioctl(*devfd, UDMABUF_CREATE, &create);
-	if (*buf < 0)
-		error(75, 0, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX);
-}
-
-int do_server(void)
+int do_server(struct memory_buffer *mem)
 {
 	char ctrl_data[sizeof(int) * 20000];
 	struct netdev_queue_id *queues;
@@ -244,23 +293,18 @@ int do_server(void)
 	struct sockaddr_in client_addr;
 	struct sockaddr_in server_sin;
 	size_t page_aligned_frags = 0;
-	int devfd, memfd, buf, ret;
 	size_t total_received = 0;
 	socklen_t client_addr_len;
 	bool is_devmem = false;
-	char *buf_mem = NULL;
+	char *tmp_mem = NULL;
 	struct ynl_sock *ys;
-	size_t dmabuf_size;
 	char iobuf[819200];
 	char buffer[256];
 	int socket_fd;
 	int client_fd;
 	size_t i = 0;
 	int opt = 1;
-
-	dmabuf_size = getpagesize() * NUM_PAGES;
-
-	create_udmabuf(&devfd, &memfd, &buf, dmabuf_size);
+	int ret;
 
 	if (reset_flow_steering())
 		error(1, 0, "Failed to reset flow steering\n");
@@ -284,13 +328,12 @@ int do_server(void)
 		queues[i].id = start_queue + i;
 	}
 
-	if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
 		error(1, 0, "Failed to bind\n");
 
-	buf_mem = mmap(NULL, dmabuf_size, PROT_READ | PROT_WRITE, MAP_SHARED,
-		       buf, 0);
-	if (buf_mem == MAP_FAILED)
-		error(1, 0, "mmap()");
+	tmp_mem = malloc(mem->size);
+	if (!tmp_mem)
+		error(1, ENOMEM, "malloc failed");
 
 	server_sin.sin_family = AF_INET;
 	server_sin.sin_port = htons(atoi(port));
@@ -341,7 +384,6 @@ int do_server(void)
 		struct iovec iov = { .iov_base = iobuf,
 				     .iov_len = sizeof(iobuf) };
 		struct dmabuf_cmsg *dmabuf_cmsg = NULL;
-		struct dma_buf_sync sync = { 0 };
 		struct cmsghdr *cm = NULL;
 		struct msghdr msg = { 0 };
 		struct dmabuf_token token;
@@ -410,22 +452,16 @@ int do_server(void)
 			else
 				page_aligned_frags++;
 
-			sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_START;
-			ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync);
+			provider->memcpy_from_device(tmp_mem, mem,
+						     dmabuf_cmsg->frag_offset,
+						     dmabuf_cmsg->frag_size);
 
 			if (do_validation)
-				validate_buffer(
-					((unsigned char *)buf_mem) +
-						dmabuf_cmsg->frag_offset,
-					dmabuf_cmsg->frag_size);
+				validate_buffer(tmp_mem,
+						dmabuf_cmsg->frag_size);
 			else
-				print_nonzero_bytes(
-					((unsigned char *)buf_mem) +
-						dmabuf_cmsg->frag_offset,
-					dmabuf_cmsg->frag_size);
-
-			sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_END;
-			ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync);
+				print_nonzero_bytes(tmp_mem,
+						    dmabuf_cmsg->frag_size);
 
 			ret = setsockopt(client_fd, SOL_SOCKET,
 					 SO_DEVMEM_DONTNEED, &token,
@@ -450,12 +486,9 @@ int do_server(void)
 
 cleanup:
 
-	munmap(buf_mem, dmabuf_size);
+	free(tmp_mem);
 	close(client_fd);
 	close(socket_fd);
-	close(buf);
-	close(memfd);
-	close(devfd);
 	ynl_sock_destroy(ys);
 
 	return 0;
@@ -464,14 +497,11 @@ cleanup:
 void run_devmem_tests(void)
 {
 	struct netdev_queue_id *queues;
-	int devfd, memfd, buf;
+	struct memory_buffer *mem;
 	struct ynl_sock *ys;
-	size_t dmabuf_size;
 	size_t i = 0;
 
-	dmabuf_size = getpagesize() * NUM_PAGES;
-
-	create_udmabuf(&devfd, &memfd, &buf, dmabuf_size);
+	mem = provider->alloc(getpagesize() * NUM_PAGES);
 
 	/* Configure RSS to divert all traffic from our devmem queues */
 	if (configure_rss())
@@ -482,7 +512,7 @@ void run_devmem_tests(void)
 	if (configure_headersplit(1))
 		error(1, 0, "Failed to configure header split\n");
 
-	if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
 		error(1, 0, "Binding empty queues array should have failed\n");
 
 	for (i = 0; i < num_queues; i++) {
@@ -495,7 +525,7 @@ void run_devmem_tests(void)
 	if (configure_headersplit(0))
 		error(1, 0, "Failed to configure header split\n");
 
-	if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
 		error(1, 0, "Configure dmabuf with header split off should have failed\n");
 
 	if (configure_headersplit(1))
@@ -508,7 +538,7 @@ void run_devmem_tests(void)
 		queues[i].id = start_queue + i;
 	}
 
-	if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
 		error(1, 0, "Failed to bind\n");
 
 	/* Deactivating a bound queue should not be legal */
@@ -517,11 +547,15 @@ void run_devmem_tests(void)
 
 	/* Closing the netlink socket does an implicit unbind */
 	ynl_sock_destroy(ys);
+
+	provider->free(mem);
 }
 
 int main(int argc, char *argv[])
 {
+	struct memory_buffer *mem;
 	int is_server = 0, opt;
+	int ret;
 
 	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) {
 		switch (opt) {
@@ -562,8 +596,9 @@ int main(int argc, char *argv[])
 
 	run_devmem_tests();
 
-	if (is_server)
-		return do_server();
+	mem = provider->alloc(getpagesize() * NUM_PAGES);
+	ret = is_server ? do_server(mem) : 1;
+	provider->free(mem);
 
-	return 0;
+	return ret;
 }
-- 
cgit v1.2.3


From bfccbaac1b45f9af7d76589d7e31ad921b50c0d7 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:02 -0800
Subject: selftests: ncdevmem: Unify error handling

There is a bunch of places where error() calls look out of place.
Use the same error(1, errno, ...) pattern everywhere.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-4-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 3e7ef2eedd60..4733d1a0aab5 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -339,33 +339,33 @@ int do_server(struct memory_buffer *mem)
 	server_sin.sin_port = htons(atoi(port));
 
 	ret = inet_pton(server_sin.sin_family, server_ip, &server_sin.sin_addr);
-	if (socket < 0)
-		error(79, 0, "%s: [FAIL, create socket]\n", TEST_PREFIX);
+	if (ret < 0)
+		error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
 
 	socket_fd = socket(server_sin.sin_family, SOCK_STREAM, 0);
-	if (socket < 0)
-		error(errno, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
+	if (socket_fd < 0)
+		error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
 
 	ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEPORT, &opt,
 			 sizeof(opt));
 	if (ret)
-		error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
+		error(1, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
 
 	ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEADDR, &opt,
 			 sizeof(opt));
 	if (ret)
-		error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
+		error(1, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
 
 	fprintf(stderr, "binding to address %s:%d\n", server_ip,
 		ntohs(server_sin.sin_port));
 
 	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
 	if (ret)
-		error(errno, errno, "%s: [FAIL, bind]\n", TEST_PREFIX);
+		error(1, errno, "%s: [FAIL, bind]\n", TEST_PREFIX);
 
 	ret = listen(socket_fd, 1);
 	if (ret)
-		error(errno, errno, "%s: [FAIL, listen]\n", TEST_PREFIX);
+		error(1, errno, "%s: [FAIL, listen]\n", TEST_PREFIX);
 
 	client_addr_len = sizeof(client_addr);
 
-- 
cgit v1.2.3


From 0ebd75f5f2392c2ada04c6e11447415911fe1506 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:03 -0800
Subject: selftests: ncdevmem: Make client_ip optional

Support 3-tuple filtering by making client_ip optional. When -c is
not passed, don't specify src-ip/src-port in the filter.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-5-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 4733d1a0aab5..faa9dce121c7 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -62,7 +62,7 @@
  */
 
 static char *server_ip = "192.168.1.4";
-static char *client_ip = "192.168.1.2";
+static char *client_ip;
 static char *port = "5201";
 static size_t do_validation;
 static int start_queue = 8;
@@ -236,8 +236,14 @@ static int configure_channels(unsigned int rx, unsigned int tx)
 
 static int configure_flow_steering(void)
 {
-	return run_command("sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d >&2",
-			   ifname, client_ip, server_ip, port, port, start_queue);
+	return run_command("sudo ethtool -N %s flow-type tcp4 %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
+			   ifname,
+			   client_ip ? "src-ip" : "",
+			   client_ip ?: "",
+			   server_ip,
+			   client_ip ? "src-port" : "",
+			   client_ip ? port : "",
+			   port, start_queue);
 }
 
 static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
-- 
cgit v1.2.3


From d3ca35c64d48daf3451851043cffe2bda3913648 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:04 -0800
Subject: selftests: ncdevmem: Remove default arguments

To make it clear what's required and what's not. Also, some of the
values don't seem like a good defaults; for example eth1.

Move the invocation comment to the top, add missing -s to the client
and cleanup the client invocation a bit to make more readable.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-6-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 61 ++++++++++++++++++++++------------
 1 file changed, 39 insertions(+), 22 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index faa9dce121c7..0feeca56c049 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -1,4 +1,31 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * tcpdevmem netcat. Works similarly to netcat but does device memory TCP
+ * instead of regular TCP. Uses udmabuf to mock a dmabuf provider.
+ *
+ * Usage:
+ *
+ *     On server:
+ *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201
+ *
+ *     On client:
+ *     echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201
+ *
+ * Test data validation:
+ *
+ *     On server:
+ *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7
+ *
+ *     On client:
+ *     yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
+ *             tr \\n \\0 | \
+ *             head -c 5G | \
+ *             nc <server IP> 5201 -p 5201
+ *
+ *
+ * Note this is compatible with regular netcat. i.e. the sender or receiver can
+ * be replaced with regular netcat to test the RX or TX path in isolation.
+ */
 #define _GNU_SOURCE
 #define __EXPORTED_HEADERS__
 
@@ -42,32 +69,13 @@
 #define MSG_SOCK_DEVMEM 0x2000000
 #endif
 
-/*
- * tcpdevmem netcat. Works similarly to netcat but does device memory TCP
- * instead of regular TCP. Uses udmabuf to mock a dmabuf provider.
- *
- * Usage:
- *
- *	On server:
- *	ncdevmem -s <server IP> -c <client IP> -f eth1 -l -p 5201 -v 7
- *
- *	On client:
- *	yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
- *		tr \\n \\0 | \
- *		head -c 5G | \
- *		nc <server IP> 5201 -p 5201
- *
- * Note this is compatible with regular netcat. i.e. the sender or receiver can
- * be replaced with regular netcat to test the RX or TX path in isolation.
- */
-
-static char *server_ip = "192.168.1.4";
+static char *server_ip;
 static char *client_ip;
-static char *port = "5201";
+static char *port;
 static size_t do_validation;
 static int start_queue = 8;
 static int num_queues = 8;
-static char *ifname = "eth1";
+static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
 
@@ -595,6 +603,15 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (!server_ip)
+		error(1, 0, "Missing -s argument\n");
+
+	if (!port)
+		error(1, 0, "Missing -p argument\n");
+
+	if (!ifname)
+		error(1, 0, "Missing -f argument\n");
+
 	ifindex = if_nametoindex(ifname);
 
 	for (; optind < argc; optind++)
-- 
cgit v1.2.3


From 933056357a8cf0c9b3fb2ecc4d2d8d142614f0a3 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:05 -0800
Subject: selftests: ncdevmem: Switch to AF_INET6

Use dualstack socket to support both v4 and v6. v4-mapped-v6 address
can be used to do v4.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-7-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 97 ++++++++++++++++++++++++----------
 1 file changed, 68 insertions(+), 29 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 0feeca56c049..645ef0bb63ec 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -242,13 +242,26 @@ static int configure_channels(unsigned int rx, unsigned int tx)
 	return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx);
 }
 
-static int configure_flow_steering(void)
+static int configure_flow_steering(struct sockaddr_in6 *server_sin)
 {
-	return run_command("sudo ethtool -N %s flow-type tcp4 %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
+	const char *type = "tcp6";
+	const char *server_addr;
+	char buf[40];
+
+	inet_ntop(AF_INET6, &server_sin->sin6_addr, buf, sizeof(buf));
+	server_addr = buf;
+
+	if (IN6_IS_ADDR_V4MAPPED(&server_sin->sin6_addr)) {
+		type = "tcp4";
+		server_addr = strrchr(server_addr, ':') + 1;
+	}
+
+	return run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
 			   ifname,
+			   type,
 			   client_ip ? "src-ip" : "",
 			   client_ip ?: "",
-			   server_ip,
+			   server_addr,
 			   client_ip ? "src-port" : "",
 			   client_ip ? port : "",
 			   port, start_queue);
@@ -299,13 +312,51 @@ err_close:
 	return -1;
 }
 
+static void enable_reuseaddr(int fd)
+{
+	int opt = 1;
+	int ret;
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+	if (ret)
+		error(1, errno, "%s: [FAIL, SO_REUSEPORT]\n", TEST_PREFIX);
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+	if (ret)
+		error(1, errno, "%s: [FAIL, SO_REUSEADDR]\n", TEST_PREFIX);
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
 int do_server(struct memory_buffer *mem)
 {
 	char ctrl_data[sizeof(int) * 20000];
 	struct netdev_queue_id *queues;
 	size_t non_page_aligned_frags = 0;
-	struct sockaddr_in client_addr;
-	struct sockaddr_in server_sin;
+	struct sockaddr_in6 client_addr;
+	struct sockaddr_in6 server_sin;
 	size_t page_aligned_frags = 0;
 	size_t total_received = 0;
 	socklen_t client_addr_len;
@@ -317,9 +368,12 @@ int do_server(struct memory_buffer *mem)
 	int socket_fd;
 	int client_fd;
 	size_t i = 0;
-	int opt = 1;
 	int ret;
 
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0)
+		error(1, 0, "parse server address");
+
 	if (reset_flow_steering())
 		error(1, 0, "Failed to reset flow steering\n");
 
@@ -328,7 +382,7 @@ int do_server(struct memory_buffer *mem)
 		error(1, 0, "Failed to configure rss\n");
 
 	/* Flow steer our devmem flows to start_queue */
-	if (configure_flow_steering())
+	if (configure_flow_steering(&server_sin))
 		error(1, 0, "Failed to configure flow steering\n");
 
 	sleep(1);
@@ -349,29 +403,14 @@ int do_server(struct memory_buffer *mem)
 	if (!tmp_mem)
 		error(1, ENOMEM, "malloc failed");
 
-	server_sin.sin_family = AF_INET;
-	server_sin.sin_port = htons(atoi(port));
-
-	ret = inet_pton(server_sin.sin_family, server_ip, &server_sin.sin_addr);
-	if (ret < 0)
-		error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
-
-	socket_fd = socket(server_sin.sin_family, SOCK_STREAM, 0);
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
 	if (socket_fd < 0)
 		error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
 
-	ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEPORT, &opt,
-			 sizeof(opt));
-	if (ret)
-		error(1, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
-
-	ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEADDR, &opt,
-			 sizeof(opt));
-	if (ret)
-		error(1, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
+	enable_reuseaddr(socket_fd);
 
 	fprintf(stderr, "binding to address %s:%d\n", server_ip,
-		ntohs(server_sin.sin_port));
+		ntohs(server_sin.sin6_port));
 
 	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
 	if (ret)
@@ -383,16 +422,16 @@ int do_server(struct memory_buffer *mem)
 
 	client_addr_len = sizeof(client_addr);
 
-	inet_ntop(server_sin.sin_family, &server_sin.sin_addr, buffer,
+	inet_ntop(AF_INET6, &server_sin.sin6_addr, buffer,
 		  sizeof(buffer));
 	fprintf(stderr, "Waiting or connection on %s:%d\n", buffer,
-		ntohs(server_sin.sin_port));
+		ntohs(server_sin.sin6_port));
 	client_fd = accept(socket_fd, &client_addr, &client_addr_len);
 
-	inet_ntop(client_addr.sin_family, &client_addr.sin_addr, buffer,
+	inet_ntop(AF_INET6, &client_addr.sin6_addr, buffer,
 		  sizeof(buffer));
 	fprintf(stderr, "Got connection from %s:%d\n", buffer,
-		ntohs(client_addr.sin_port));
+		ntohs(client_addr.sin6_port));
 
 	while (1) {
 		struct iovec iov = { .iov_base = iobuf,
-- 
cgit v1.2.3


From e3c09623a53b8d11ff9e3c0f435ce1e8f52134ba Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:06 -0800
Subject: selftests: ncdevmem: Properly reset flow steering

ntuple off/on might be not enough to do it on all NICs.
Add a bunch of shell crap to explicitly remove the rules.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-8-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 645ef0bb63ec..ad6de8e0e97b 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -217,13 +217,18 @@ void validate_buffer(void *line, size_t size)
 
 static int reset_flow_steering(void)
 {
-	int ret = 0;
-
-	ret = run_command("sudo ethtool -K %s ntuple off >&2", ifname);
-	if (ret)
-		return ret;
-
-	return run_command("sudo ethtool -K %s ntuple on >&2", ifname);
+	/* Depending on the NIC, toggling ntuple off and on might not
+	 * be allowed. Additionally, attempting to delete existing filters
+	 * will fail if no filters are present. Therefore, do not enforce
+	 * the exit status.
+	 */
+
+	run_command("sudo ethtool -K %s ntuple off >&2", ifname);
+	run_command("sudo ethtool -K %s ntuple on >&2", ifname);
+	run_command(
+		"sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2",
+		ifname, ifname);
+	return 0;
 }
 
 static int configure_headersplit(bool on)
-- 
cgit v1.2.3


From 798d822e5d34ffe3f25b66b2573928962a5d3c11 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:07 -0800
Subject: selftests: ncdevmem: Use YNL to enable TCP header split

In the next patch the hard-coded queue numbers are gonna be removed.
So introduce some initial support for ethtool YNL and use
it to enable header split.

Also, tcp-data-split requires latest ethtool which is unlikely
to be present in the distros right now.

(ideally, we should not shell out to ethtool at all).

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-9-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile   |  2 +-
 tools/testing/selftests/net/ncdevmem.c | 57 ++++++++++++++++++++++++++++++++--
 2 files changed, 56 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8c4db5199a42..61cce028f105 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -112,7 +112,7 @@ TEST_INCLUDES := forwarding/lib.sh
 include ../lib.mk
 
 # YNL build
-YNL_GENS := netdev
+YNL_GENS := ethtool netdev
 include ynl.mk
 
 $(OUTPUT)/epoll_busy_poll: LDLIBS += -lcap
diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index ad6de8e0e97b..9ca2da3a2f63 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -55,10 +55,12 @@
 #include <linux/netlink.h>
 #include <linux/genetlink.h>
 #include <linux/netdev.h>
+#include <linux/ethtool_netlink.h>
 #include <time.h>
 #include <net/if.h>
 
 #include "netdev-user.h"
+#include "ethtool-user.h"
 #include <ynl.h>
 
 #define PAGE_SHIFT 12
@@ -231,10 +233,58 @@ static int reset_flow_steering(void)
 	return 0;
 }
 
+static const char *tcp_data_split_str(int val)
+{
+	switch (val) {
+	case 0:
+		return "off";
+	case 1:
+		return "auto";
+	case 2:
+		return "on";
+	default:
+		return "?";
+	}
+}
+
 static int configure_headersplit(bool on)
 {
-	return run_command("sudo ethtool -G %s tcp-data-split %s >&2", ifname,
-			   on ? "on" : "off");
+	struct ethtool_rings_get_req *get_req;
+	struct ethtool_rings_get_rsp *get_rsp;
+	struct ethtool_rings_set_req *req;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int ret;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_rings_set_req_alloc();
+	ethtool_rings_set_req_set_header_dev_index(req, ifindex);
+	/* 0 - off, 1 - auto, 2 - on */
+	ethtool_rings_set_req_set_tcp_data_split(req, on ? 2 : 0);
+	ret = ethtool_rings_set(ys, req);
+	if (ret < 0)
+		fprintf(stderr, "YNL failed: %s\n", ys->err.msg);
+	ethtool_rings_set_req_free(req);
+
+	if (ret == 0) {
+		get_req = ethtool_rings_get_req_alloc();
+		ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+		get_rsp = ethtool_rings_get(ys, get_req);
+		ethtool_rings_get_req_free(get_req);
+		if (get_rsp)
+			fprintf(stderr, "TCP header split: %s\n",
+				tcp_data_split_str(get_rsp->tcp_data_split));
+		ethtool_rings_get_rsp_free(get_rsp);
+	}
+
+	ynl_sock_destroy(ys);
+
+	return ret;
 }
 
 static int configure_rss(void)
@@ -382,6 +432,9 @@ int do_server(struct memory_buffer *mem)
 	if (reset_flow_steering())
 		error(1, 0, "Failed to reset flow steering\n");
 
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to enable TCP header split\n");
+
 	/* Configure RSS to divert all traffic from our devmem queues */
 	if (configure_rss())
 		error(1, 0, "Failed to configure rss\n");
-- 
cgit v1.2.3


From d4ef05d211315395974fa846308c693ab2ea1ff2 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:08 -0800
Subject: selftests: ncdevmem: Remove hard-coded queue numbers

Use single last queue of the device and probe it dynamically.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-10-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 40 ++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 9ca2da3a2f63..1ea62c129ddc 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -75,8 +75,8 @@ static char *server_ip;
 static char *client_ip;
 static char *port;
 static size_t do_validation;
-static int start_queue = 8;
-static int num_queues = 8;
+static int start_queue = -1;
+static int num_queues = 1;
 static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
@@ -208,6 +208,33 @@ void validate_buffer(void *line, size_t size)
 	fprintf(stdout, "Validated buffer\n");
 }
 
+static int rxq_num(int ifindex)
+{
+	struct ethtool_channels_get_req *req;
+	struct ethtool_channels_get_rsp *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int num = -1;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_channels_get_req_alloc();
+	ethtool_channels_get_req_set_header_dev_index(req, ifindex);
+	rsp = ethtool_channels_get(ys, req);
+	if (rsp)
+		num = rsp->rx_count + rsp->combined_count;
+	ethtool_channels_get_req_free(req);
+	ethtool_channels_get_rsp_free(rsp);
+
+	ynl_sock_destroy(ys);
+
+	return num;
+}
+
 #define run_command(cmd, ...)                                           \
 	({                                                              \
 		char command[256];                                      \
@@ -711,6 +738,15 @@ int main(int argc, char *argv[])
 
 	ifindex = if_nametoindex(ifname);
 
+	if (start_queue < 0) {
+		start_queue = rxq_num(ifindex) - 1;
+
+		if (start_queue < 0)
+			error(1, 0, "couldn't detect number of queues\n");
+
+		fprintf(stderr, "using queues %d..%d\n", start_queue, start_queue + num_queues);
+	}
+
 	for (; optind < argc; optind++)
 		fprintf(stderr, "extra arguments: %s\n", argv[optind]);
 
-- 
cgit v1.2.3


From 77f870a000165f364082e06bfd8fd16d331219d8 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:09 -0800
Subject: selftests: ncdevmem: Run selftest when none of the -s or -c has been
 provided

This will be used as a 'probe' mode in the selftest to check whether
the device supports the devmem or not. Use hard-coded queue layout
(two last queues) and prevent user from passing custom -q and/or -t.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-11-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ncdevmem.c | 49 +++++++++++++++++++++++++++-------
 1 file changed, 39 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index 1ea62c129ddc..8e502a1f8f9b 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -76,7 +76,7 @@ static char *client_ip;
 static char *port;
 static size_t do_validation;
 static int start_queue = -1;
-static int num_queues = 1;
+static int num_queues = -1;
 static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
@@ -727,19 +727,38 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	if (!server_ip)
-		error(1, 0, "Missing -s argument\n");
-
-	if (!port)
-		error(1, 0, "Missing -p argument\n");
-
 	if (!ifname)
 		error(1, 0, "Missing -f argument\n");
 
 	ifindex = if_nametoindex(ifname);
 
-	if (start_queue < 0) {
-		start_queue = rxq_num(ifindex) - 1;
+	if (!server_ip && !client_ip) {
+		if (start_queue < 0 && num_queues < 0) {
+			num_queues = rxq_num(ifindex);
+			if (num_queues < 0)
+				error(1, 0, "couldn't detect number of queues\n");
+			if (num_queues < 2)
+				error(1, 0,
+				      "number of device queues is too low\n");
+			/* make sure can bind to multiple queues */
+			start_queue = num_queues / 2;
+			num_queues /= 2;
+		}
+
+		if (start_queue < 0 || num_queues < 0)
+			error(1, 0, "Both -t and -q are required\n");
+
+		run_devmem_tests();
+		return 0;
+	}
+
+	if (start_queue < 0 && num_queues < 0) {
+		num_queues = rxq_num(ifindex);
+		if (num_queues < 2)
+			error(1, 0, "number of device queues is too low\n");
+
+		num_queues = 1;
+		start_queue = rxq_num(ifindex) - num_queues;
 
 		if (start_queue < 0)
 			error(1, 0, "couldn't detect number of queues\n");
@@ -750,7 +769,17 @@ int main(int argc, char *argv[])
 	for (; optind < argc; optind++)
 		fprintf(stderr, "extra arguments: %s\n", argv[optind]);
 
-	run_devmem_tests();
+	if (start_queue < 0)
+		error(1, 0, "Missing -t argument\n");
+
+	if (num_queues < 0)
+		error(1, 0, "Missing -q argument\n");
+
+	if (!server_ip)
+		error(1, 0, "Missing -s argument\n");
+
+	if (!port)
+		error(1, 0, "Missing -p argument\n");
 
 	mem = provider->alloc(getpagesize() * NUM_PAGES);
 	ret = is_server ? do_server(mem) : 1;
-- 
cgit v1.2.3


From be43a6b2382983c89b59166ba2c32ec0f1092cfe Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:10 -0800
Subject: selftests: ncdevmem: Move ncdevmem under drivers/net/hw

This is where all the tests that depend on the HW functionality live in
and this is where the automated test is gonna be added in the next
patch.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20241107181211.3934153-12-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/.gitignore |   1 +
 tools/testing/selftests/drivers/net/hw/Makefile   |   8 +
 tools/testing/selftests/drivers/net/hw/ncdevmem.c | 789 ++++++++++++++++++++++
 tools/testing/selftests/net/.gitignore            |   1 -
 tools/testing/selftests/net/Makefile              |   8 -
 tools/testing/selftests/net/ncdevmem.c            | 789 ----------------------
 6 files changed, 798 insertions(+), 798 deletions(-)
 create mode 100644 tools/testing/selftests/drivers/net/hw/.gitignore
 create mode 100644 tools/testing/selftests/drivers/net/hw/ncdevmem.c
 delete mode 100644 tools/testing/selftests/net/ncdevmem.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore
new file mode 100644
index 000000000000..e9fe6ede681a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/.gitignore
@@ -0,0 +1 @@
+ncdevmem
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index c9f2f48fc30f..182348f4bd40 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -26,4 +26,12 @@ TEST_INCLUDES := \
 	../../../net/forwarding/tc_common.sh \
 	#
 
+# YNL files, must be before "include ..lib.mk"
+YNL_GEN_FILES := ncdevmem
+TEST_GEN_FILES += $(YNL_GEN_FILES)
+
 include ../../../lib.mk
+
+# YNL build
+YNL_GENS := ethtool netdev
+include ../../../net/ynl.mk
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
new file mode 100644
index 000000000000..8e502a1f8f9b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -0,0 +1,789 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tcpdevmem netcat. Works similarly to netcat but does device memory TCP
+ * instead of regular TCP. Uses udmabuf to mock a dmabuf provider.
+ *
+ * Usage:
+ *
+ *     On server:
+ *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201
+ *
+ *     On client:
+ *     echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201
+ *
+ * Test data validation:
+ *
+ *     On server:
+ *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7
+ *
+ *     On client:
+ *     yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
+ *             tr \\n \\0 | \
+ *             head -c 5G | \
+ *             nc <server IP> 5201 -p 5201
+ *
+ *
+ * Note this is compatible with regular netcat. i.e. the sender or receiver can
+ * be replaced with regular netcat to test the RX or TX path in isolation.
+ */
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <linux/uio.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#define __iovec_defined
+#include <fcntl.h>
+#include <malloc.h>
+#include <error.h>
+
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+
+#include <linux/memfd.h>
+#include <linux/dma-buf.h>
+#include <linux/udmabuf.h>
+#include <libmnl/libmnl.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+#include <linux/genetlink.h>
+#include <linux/netdev.h>
+#include <linux/ethtool_netlink.h>
+#include <time.h>
+#include <net/if.h>
+
+#include "netdev-user.h"
+#include "ethtool-user.h"
+#include <ynl.h>
+
+#define PAGE_SHIFT 12
+#define TEST_PREFIX "ncdevmem"
+#define NUM_PAGES 16000
+
+#ifndef MSG_SOCK_DEVMEM
+#define MSG_SOCK_DEVMEM 0x2000000
+#endif
+
+static char *server_ip;
+static char *client_ip;
+static char *port;
+static size_t do_validation;
+static int start_queue = -1;
+static int num_queues = -1;
+static char *ifname;
+static unsigned int ifindex;
+static unsigned int dmabuf_id;
+
+struct memory_buffer {
+	int fd;
+	size_t size;
+
+	int devfd;
+	int memfd;
+	char *buf_mem;
+};
+
+struct memory_provider {
+	struct memory_buffer *(*alloc)(size_t size);
+	void (*free)(struct memory_buffer *ctx);
+	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
+				   size_t off, int n);
+};
+
+static struct memory_buffer *udmabuf_alloc(size_t size)
+{
+	struct udmabuf_create create;
+	struct memory_buffer *ctx;
+	int ret;
+
+	ctx = malloc(sizeof(*ctx));
+	if (!ctx)
+		error(1, ENOMEM, "malloc failed");
+
+	ctx->size = size;
+
+	ctx->devfd = open("/dev/udmabuf", O_RDWR);
+	if (ctx->devfd < 0)
+		error(1, errno,
+		      "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
+		      TEST_PREFIX);
+
+	ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
+	if (ctx->memfd < 0)
+		error(1, errno, "%s: [skip,no-memfd]\n", TEST_PREFIX);
+
+	ret = fcntl(ctx->memfd, F_ADD_SEALS, F_SEAL_SHRINK);
+	if (ret < 0)
+		error(1, errno, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+
+	ret = ftruncate(ctx->memfd, size);
+	if (ret == -1)
+		error(1, errno, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+
+	memset(&create, 0, sizeof(create));
+
+	create.memfd = ctx->memfd;
+	create.offset = 0;
+	create.size = size;
+	ctx->fd = ioctl(ctx->devfd, UDMABUF_CREATE, &create);
+	if (ctx->fd < 0)
+		error(1, errno, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX);
+
+	ctx->buf_mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED,
+			    ctx->fd, 0);
+	if (ctx->buf_mem == MAP_FAILED)
+		error(1, errno, "%s: [FAIL, map udmabuf]\n", TEST_PREFIX);
+
+	return ctx;
+}
+
+static void udmabuf_free(struct memory_buffer *ctx)
+{
+	munmap(ctx->buf_mem, ctx->size);
+	close(ctx->fd);
+	close(ctx->memfd);
+	close(ctx->devfd);
+	free(ctx);
+}
+
+static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
+				       size_t off, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START;
+	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst, src->buf_mem + off, n);
+
+	sync.flags = DMA_BUF_SYNC_END;
+	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
+static struct memory_provider udmabuf_memory_provider = {
+	.alloc = udmabuf_alloc,
+	.free = udmabuf_free,
+	.memcpy_from_device = udmabuf_memcpy_from_device,
+};
+
+static struct memory_provider *provider = &udmabuf_memory_provider;
+
+static void print_nonzero_bytes(void *ptr, size_t size)
+{
+	unsigned char *p = ptr;
+	unsigned int i;
+
+	for (i = 0; i < size; i++)
+		putchar(p[i]);
+}
+
+void validate_buffer(void *line, size_t size)
+{
+	static unsigned char seed = 1;
+	unsigned char *ptr = line;
+	int errors = 0;
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		if (ptr[i] != seed) {
+			fprintf(stderr,
+				"Failed validation: expected=%u, actual=%u, index=%lu\n",
+				seed, ptr[i], i);
+			errors++;
+			if (errors > 20)
+				error(1, 0, "validation failed.");
+		}
+		seed++;
+		if (seed == do_validation)
+			seed = 0;
+	}
+
+	fprintf(stdout, "Validated buffer\n");
+}
+
+static int rxq_num(int ifindex)
+{
+	struct ethtool_channels_get_req *req;
+	struct ethtool_channels_get_rsp *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int num = -1;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_channels_get_req_alloc();
+	ethtool_channels_get_req_set_header_dev_index(req, ifindex);
+	rsp = ethtool_channels_get(ys, req);
+	if (rsp)
+		num = rsp->rx_count + rsp->combined_count;
+	ethtool_channels_get_req_free(req);
+	ethtool_channels_get_rsp_free(rsp);
+
+	ynl_sock_destroy(ys);
+
+	return num;
+}
+
+#define run_command(cmd, ...)                                           \
+	({                                                              \
+		char command[256];                                      \
+		memset(command, 0, sizeof(command));                    \
+		snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \
+		fprintf(stderr, "Running: %s\n", command);                       \
+		system(command);                                        \
+	})
+
+static int reset_flow_steering(void)
+{
+	/* Depending on the NIC, toggling ntuple off and on might not
+	 * be allowed. Additionally, attempting to delete existing filters
+	 * will fail if no filters are present. Therefore, do not enforce
+	 * the exit status.
+	 */
+
+	run_command("sudo ethtool -K %s ntuple off >&2", ifname);
+	run_command("sudo ethtool -K %s ntuple on >&2", ifname);
+	run_command(
+		"sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2",
+		ifname, ifname);
+	return 0;
+}
+
+static const char *tcp_data_split_str(int val)
+{
+	switch (val) {
+	case 0:
+		return "off";
+	case 1:
+		return "auto";
+	case 2:
+		return "on";
+	default:
+		return "?";
+	}
+}
+
+static int configure_headersplit(bool on)
+{
+	struct ethtool_rings_get_req *get_req;
+	struct ethtool_rings_get_rsp *get_rsp;
+	struct ethtool_rings_set_req *req;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int ret;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_rings_set_req_alloc();
+	ethtool_rings_set_req_set_header_dev_index(req, ifindex);
+	/* 0 - off, 1 - auto, 2 - on */
+	ethtool_rings_set_req_set_tcp_data_split(req, on ? 2 : 0);
+	ret = ethtool_rings_set(ys, req);
+	if (ret < 0)
+		fprintf(stderr, "YNL failed: %s\n", ys->err.msg);
+	ethtool_rings_set_req_free(req);
+
+	if (ret == 0) {
+		get_req = ethtool_rings_get_req_alloc();
+		ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+		get_rsp = ethtool_rings_get(ys, get_req);
+		ethtool_rings_get_req_free(get_req);
+		if (get_rsp)
+			fprintf(stderr, "TCP header split: %s\n",
+				tcp_data_split_str(get_rsp->tcp_data_split));
+		ethtool_rings_get_rsp_free(get_rsp);
+	}
+
+	ynl_sock_destroy(ys);
+
+	return ret;
+}
+
+static int configure_rss(void)
+{
+	return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue);
+}
+
+static int configure_channels(unsigned int rx, unsigned int tx)
+{
+	return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx);
+}
+
+static int configure_flow_steering(struct sockaddr_in6 *server_sin)
+{
+	const char *type = "tcp6";
+	const char *server_addr;
+	char buf[40];
+
+	inet_ntop(AF_INET6, &server_sin->sin6_addr, buf, sizeof(buf));
+	server_addr = buf;
+
+	if (IN6_IS_ADDR_V4MAPPED(&server_sin->sin6_addr)) {
+		type = "tcp4";
+		server_addr = strrchr(server_addr, ':') + 1;
+	}
+
+	return run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
+			   ifname,
+			   type,
+			   client_ip ? "src-ip" : "",
+			   client_ip ?: "",
+			   server_addr,
+			   client_ip ? "src-port" : "",
+			   client_ip ? port : "",
+			   port, start_queue);
+}
+
+static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct netdev_queue_id *queues,
+			 unsigned int n_queue_index, struct ynl_sock **ys)
+{
+	struct netdev_bind_rx_req *req = NULL;
+	struct netdev_bind_rx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_rx_req_alloc();
+	netdev_bind_rx_req_set_ifindex(req, ifindex);
+	netdev_bind_rx_req_set_fd(req, dmabuf_fd);
+	__netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
+
+	rsp = netdev_bind_rx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_rx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	fprintf(stderr, "got dmabuf id=%d\n", rsp->id);
+	dmabuf_id = rsp->id;
+
+	netdev_bind_rx_req_free(req);
+	netdev_bind_rx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_rx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
+static void enable_reuseaddr(int fd)
+{
+	int opt = 1;
+	int ret;
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+	if (ret)
+		error(1, errno, "%s: [FAIL, SO_REUSEPORT]\n", TEST_PREFIX);
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+	if (ret)
+		error(1, errno, "%s: [FAIL, SO_REUSEADDR]\n", TEST_PREFIX);
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+int do_server(struct memory_buffer *mem)
+{
+	char ctrl_data[sizeof(int) * 20000];
+	struct netdev_queue_id *queues;
+	size_t non_page_aligned_frags = 0;
+	struct sockaddr_in6 client_addr;
+	struct sockaddr_in6 server_sin;
+	size_t page_aligned_frags = 0;
+	size_t total_received = 0;
+	socklen_t client_addr_len;
+	bool is_devmem = false;
+	char *tmp_mem = NULL;
+	struct ynl_sock *ys;
+	char iobuf[819200];
+	char buffer[256];
+	int socket_fd;
+	int client_fd;
+	size_t i = 0;
+	int ret;
+
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0)
+		error(1, 0, "parse server address");
+
+	if (reset_flow_steering())
+		error(1, 0, "Failed to reset flow steering\n");
+
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to enable TCP header split\n");
+
+	/* Configure RSS to divert all traffic from our devmem queues */
+	if (configure_rss())
+		error(1, 0, "Failed to configure rss\n");
+
+	/* Flow steer our devmem flows to start_queue */
+	if (configure_flow_steering(&server_sin))
+		error(1, 0, "Failed to configure flow steering\n");
+
+	sleep(1);
+
+	queues = malloc(sizeof(*queues) * num_queues);
+
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	tmp_mem = malloc(mem->size);
+	if (!tmp_mem)
+		error(1, ENOMEM, "malloc failed");
+
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (socket_fd < 0)
+		error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
+
+	enable_reuseaddr(socket_fd);
+
+	fprintf(stderr, "binding to address %s:%d\n", server_ip,
+		ntohs(server_sin.sin6_port));
+
+	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret)
+		error(1, errno, "%s: [FAIL, bind]\n", TEST_PREFIX);
+
+	ret = listen(socket_fd, 1);
+	if (ret)
+		error(1, errno, "%s: [FAIL, listen]\n", TEST_PREFIX);
+
+	client_addr_len = sizeof(client_addr);
+
+	inet_ntop(AF_INET6, &server_sin.sin6_addr, buffer,
+		  sizeof(buffer));
+	fprintf(stderr, "Waiting or connection on %s:%d\n", buffer,
+		ntohs(server_sin.sin6_port));
+	client_fd = accept(socket_fd, &client_addr, &client_addr_len);
+
+	inet_ntop(AF_INET6, &client_addr.sin6_addr, buffer,
+		  sizeof(buffer));
+	fprintf(stderr, "Got connection from %s:%d\n", buffer,
+		ntohs(client_addr.sin6_port));
+
+	while (1) {
+		struct iovec iov = { .iov_base = iobuf,
+				     .iov_len = sizeof(iobuf) };
+		struct dmabuf_cmsg *dmabuf_cmsg = NULL;
+		struct cmsghdr *cm = NULL;
+		struct msghdr msg = { 0 };
+		struct dmabuf_token token;
+		ssize_t ret;
+
+		is_devmem = false;
+
+		msg.msg_iov = &iov;
+		msg.msg_iovlen = 1;
+		msg.msg_control = ctrl_data;
+		msg.msg_controllen = sizeof(ctrl_data);
+		ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM);
+		fprintf(stderr, "recvmsg ret=%ld\n", ret);
+		if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK))
+			continue;
+		if (ret < 0) {
+			perror("recvmsg");
+			continue;
+		}
+		if (ret == 0) {
+			fprintf(stderr, "client exited\n");
+			goto cleanup;
+		}
+
+		i++;
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_SOCKET ||
+			    (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
+			     cm->cmsg_type != SCM_DEVMEM_LINEAR)) {
+				fprintf(stderr, "skipping non-devmem cmsg\n");
+				continue;
+			}
+
+			dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm);
+			is_devmem = true;
+
+			if (cm->cmsg_type == SCM_DEVMEM_LINEAR) {
+				/* TODO: process data copied from skb's linear
+				 * buffer.
+				 */
+				fprintf(stderr,
+					"SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n",
+					dmabuf_cmsg->frag_size);
+
+				continue;
+			}
+
+			token.token_start = dmabuf_cmsg->frag_token;
+			token.token_count = 1;
+
+			total_received += dmabuf_cmsg->frag_size;
+			fprintf(stderr,
+				"received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n",
+				dmabuf_cmsg->frag_offset >> PAGE_SHIFT,
+				dmabuf_cmsg->frag_offset % getpagesize(),
+				dmabuf_cmsg->frag_offset,
+				dmabuf_cmsg->frag_size, dmabuf_cmsg->frag_token,
+				total_received, dmabuf_cmsg->dmabuf_id);
+
+			if (dmabuf_cmsg->dmabuf_id != dmabuf_id)
+				error(1, 0,
+				      "received on wrong dmabuf_id: flow steering error\n");
+
+			if (dmabuf_cmsg->frag_size % getpagesize())
+				non_page_aligned_frags++;
+			else
+				page_aligned_frags++;
+
+			provider->memcpy_from_device(tmp_mem, mem,
+						     dmabuf_cmsg->frag_offset,
+						     dmabuf_cmsg->frag_size);
+
+			if (do_validation)
+				validate_buffer(tmp_mem,
+						dmabuf_cmsg->frag_size);
+			else
+				print_nonzero_bytes(tmp_mem,
+						    dmabuf_cmsg->frag_size);
+
+			ret = setsockopt(client_fd, SOL_SOCKET,
+					 SO_DEVMEM_DONTNEED, &token,
+					 sizeof(token));
+			if (ret != 1)
+				error(1, 0,
+				      "SO_DEVMEM_DONTNEED not enough tokens");
+		}
+		if (!is_devmem)
+			error(1, 0, "flow steering error\n");
+
+		fprintf(stderr, "total_received=%lu\n", total_received);
+	}
+
+	fprintf(stderr, "%s: ok\n", TEST_PREFIX);
+
+	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+		page_aligned_frags, non_page_aligned_frags);
+
+	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+		page_aligned_frags, non_page_aligned_frags);
+
+cleanup:
+
+	free(tmp_mem);
+	close(client_fd);
+	close(socket_fd);
+	ynl_sock_destroy(ys);
+
+	return 0;
+}
+
+void run_devmem_tests(void)
+{
+	struct netdev_queue_id *queues;
+	struct memory_buffer *mem;
+	struct ynl_sock *ys;
+	size_t i = 0;
+
+	mem = provider->alloc(getpagesize() * NUM_PAGES);
+
+	/* Configure RSS to divert all traffic from our devmem queues */
+	if (configure_rss())
+		error(1, 0, "rss error\n");
+
+	queues = calloc(num_queues, sizeof(*queues));
+
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to configure header split\n");
+
+	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+		error(1, 0, "Binding empty queues array should have failed\n");
+
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	if (configure_headersplit(0))
+		error(1, 0, "Failed to configure header split\n");
+
+	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+		error(1, 0, "Configure dmabuf with header split off should have failed\n");
+
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to configure header split\n");
+
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	/* Deactivating a bound queue should not be legal */
+	if (!configure_channels(num_queues, num_queues - 1))
+		error(1, 0, "Deactivating a bound queue should be illegal.\n");
+
+	/* Closing the netlink socket does an implicit unbind */
+	ynl_sock_destroy(ys);
+
+	provider->free(mem);
+}
+
+int main(int argc, char *argv[])
+{
+	struct memory_buffer *mem;
+	int is_server = 0, opt;
+	int ret;
+
+	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) {
+		switch (opt) {
+		case 'l':
+			is_server = 1;
+			break;
+		case 's':
+			server_ip = optarg;
+			break;
+		case 'c':
+			client_ip = optarg;
+			break;
+		case 'p':
+			port = optarg;
+			break;
+		case 'v':
+			do_validation = atoll(optarg);
+			break;
+		case 'q':
+			num_queues = atoi(optarg);
+			break;
+		case 't':
+			start_queue = atoi(optarg);
+			break;
+		case 'f':
+			ifname = optarg;
+			break;
+		case '?':
+			fprintf(stderr, "unknown option: %c\n", optopt);
+			break;
+		}
+	}
+
+	if (!ifname)
+		error(1, 0, "Missing -f argument\n");
+
+	ifindex = if_nametoindex(ifname);
+
+	if (!server_ip && !client_ip) {
+		if (start_queue < 0 && num_queues < 0) {
+			num_queues = rxq_num(ifindex);
+			if (num_queues < 0)
+				error(1, 0, "couldn't detect number of queues\n");
+			if (num_queues < 2)
+				error(1, 0,
+				      "number of device queues is too low\n");
+			/* make sure can bind to multiple queues */
+			start_queue = num_queues / 2;
+			num_queues /= 2;
+		}
+
+		if (start_queue < 0 || num_queues < 0)
+			error(1, 0, "Both -t and -q are required\n");
+
+		run_devmem_tests();
+		return 0;
+	}
+
+	if (start_queue < 0 && num_queues < 0) {
+		num_queues = rxq_num(ifindex);
+		if (num_queues < 2)
+			error(1, 0, "number of device queues is too low\n");
+
+		num_queues = 1;
+		start_queue = rxq_num(ifindex) - num_queues;
+
+		if (start_queue < 0)
+			error(1, 0, "couldn't detect number of queues\n");
+
+		fprintf(stderr, "using queues %d..%d\n", start_queue, start_queue + num_queues);
+	}
+
+	for (; optind < argc; optind++)
+		fprintf(stderr, "extra arguments: %s\n", argv[optind]);
+
+	if (start_queue < 0)
+		error(1, 0, "Missing -t argument\n");
+
+	if (num_queues < 0)
+		error(1, 0, "Missing -q argument\n");
+
+	if (!server_ip)
+		error(1, 0, "Missing -s argument\n");
+
+	if (!port)
+		error(1, 0, "Missing -p argument\n");
+
+	mem = provider->alloc(getpagesize() * NUM_PAGES);
+	ret = is_server ? do_server(mem) : 1;
+	provider->free(mem);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 217d8b7a7365..a78debbd1fe7 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -18,7 +18,6 @@ ipv6_flowlabel_mgr
 log.txt
 msg_oob
 msg_zerocopy
-ncdevmem
 nettest
 psock_fanout
 psock_snd
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 61cce028f105..9322b904ad00 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -98,10 +98,6 @@ TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
 TEST_PROGS += ipv6_route_update_soft_lockup.sh
 
-# YNL files, must be before "include ..lib.mk"
-YNL_GEN_FILES := ncdevmem
-TEST_GEN_FILES += $(YNL_GEN_FILES)
-
 TEST_FILES := settings
 TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
 
@@ -111,10 +107,6 @@ TEST_INCLUDES := forwarding/lib.sh
 
 include ../lib.mk
 
-# YNL build
-YNL_GENS := ethtool netdev
-include ynl.mk
-
 $(OUTPUT)/epoll_busy_poll: LDLIBS += -lcap
 $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto
diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
deleted file mode 100644
index 8e502a1f8f9b..000000000000
--- a/tools/testing/selftests/net/ncdevmem.c
+++ /dev/null
@@ -1,789 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * tcpdevmem netcat. Works similarly to netcat but does device memory TCP
- * instead of regular TCP. Uses udmabuf to mock a dmabuf provider.
- *
- * Usage:
- *
- *     On server:
- *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201
- *
- *     On client:
- *     echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201
- *
- * Test data validation:
- *
- *     On server:
- *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7
- *
- *     On client:
- *     yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
- *             tr \\n \\0 | \
- *             head -c 5G | \
- *             nc <server IP> 5201 -p 5201
- *
- *
- * Note this is compatible with regular netcat. i.e. the sender or receiver can
- * be replaced with regular netcat to test the RX or TX path in isolation.
- */
-#define _GNU_SOURCE
-#define __EXPORTED_HEADERS__
-
-#include <linux/uio.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <stdbool.h>
-#include <string.h>
-#include <errno.h>
-#define __iovec_defined
-#include <fcntl.h>
-#include <malloc.h>
-#include <error.h>
-
-#include <arpa/inet.h>
-#include <sys/socket.h>
-#include <sys/mman.h>
-#include <sys/ioctl.h>
-#include <sys/syscall.h>
-
-#include <linux/memfd.h>
-#include <linux/dma-buf.h>
-#include <linux/udmabuf.h>
-#include <libmnl/libmnl.h>
-#include <linux/types.h>
-#include <linux/netlink.h>
-#include <linux/genetlink.h>
-#include <linux/netdev.h>
-#include <linux/ethtool_netlink.h>
-#include <time.h>
-#include <net/if.h>
-
-#include "netdev-user.h"
-#include "ethtool-user.h"
-#include <ynl.h>
-
-#define PAGE_SHIFT 12
-#define TEST_PREFIX "ncdevmem"
-#define NUM_PAGES 16000
-
-#ifndef MSG_SOCK_DEVMEM
-#define MSG_SOCK_DEVMEM 0x2000000
-#endif
-
-static char *server_ip;
-static char *client_ip;
-static char *port;
-static size_t do_validation;
-static int start_queue = -1;
-static int num_queues = -1;
-static char *ifname;
-static unsigned int ifindex;
-static unsigned int dmabuf_id;
-
-struct memory_buffer {
-	int fd;
-	size_t size;
-
-	int devfd;
-	int memfd;
-	char *buf_mem;
-};
-
-struct memory_provider {
-	struct memory_buffer *(*alloc)(size_t size);
-	void (*free)(struct memory_buffer *ctx);
-	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
-				   size_t off, int n);
-};
-
-static struct memory_buffer *udmabuf_alloc(size_t size)
-{
-	struct udmabuf_create create;
-	struct memory_buffer *ctx;
-	int ret;
-
-	ctx = malloc(sizeof(*ctx));
-	if (!ctx)
-		error(1, ENOMEM, "malloc failed");
-
-	ctx->size = size;
-
-	ctx->devfd = open("/dev/udmabuf", O_RDWR);
-	if (ctx->devfd < 0)
-		error(1, errno,
-		      "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
-		      TEST_PREFIX);
-
-	ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
-	if (ctx->memfd < 0)
-		error(1, errno, "%s: [skip,no-memfd]\n", TEST_PREFIX);
-
-	ret = fcntl(ctx->memfd, F_ADD_SEALS, F_SEAL_SHRINK);
-	if (ret < 0)
-		error(1, errno, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
-
-	ret = ftruncate(ctx->memfd, size);
-	if (ret == -1)
-		error(1, errno, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
-
-	memset(&create, 0, sizeof(create));
-
-	create.memfd = ctx->memfd;
-	create.offset = 0;
-	create.size = size;
-	ctx->fd = ioctl(ctx->devfd, UDMABUF_CREATE, &create);
-	if (ctx->fd < 0)
-		error(1, errno, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX);
-
-	ctx->buf_mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED,
-			    ctx->fd, 0);
-	if (ctx->buf_mem == MAP_FAILED)
-		error(1, errno, "%s: [FAIL, map udmabuf]\n", TEST_PREFIX);
-
-	return ctx;
-}
-
-static void udmabuf_free(struct memory_buffer *ctx)
-{
-	munmap(ctx->buf_mem, ctx->size);
-	close(ctx->fd);
-	close(ctx->memfd);
-	close(ctx->devfd);
-	free(ctx);
-}
-
-static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
-				       size_t off, int n)
-{
-	struct dma_buf_sync sync = {};
-
-	sync.flags = DMA_BUF_SYNC_START;
-	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
-
-	memcpy(dst, src->buf_mem + off, n);
-
-	sync.flags = DMA_BUF_SYNC_END;
-	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
-}
-
-static struct memory_provider udmabuf_memory_provider = {
-	.alloc = udmabuf_alloc,
-	.free = udmabuf_free,
-	.memcpy_from_device = udmabuf_memcpy_from_device,
-};
-
-static struct memory_provider *provider = &udmabuf_memory_provider;
-
-static void print_nonzero_bytes(void *ptr, size_t size)
-{
-	unsigned char *p = ptr;
-	unsigned int i;
-
-	for (i = 0; i < size; i++)
-		putchar(p[i]);
-}
-
-void validate_buffer(void *line, size_t size)
-{
-	static unsigned char seed = 1;
-	unsigned char *ptr = line;
-	int errors = 0;
-	size_t i;
-
-	for (i = 0; i < size; i++) {
-		if (ptr[i] != seed) {
-			fprintf(stderr,
-				"Failed validation: expected=%u, actual=%u, index=%lu\n",
-				seed, ptr[i], i);
-			errors++;
-			if (errors > 20)
-				error(1, 0, "validation failed.");
-		}
-		seed++;
-		if (seed == do_validation)
-			seed = 0;
-	}
-
-	fprintf(stdout, "Validated buffer\n");
-}
-
-static int rxq_num(int ifindex)
-{
-	struct ethtool_channels_get_req *req;
-	struct ethtool_channels_get_rsp *rsp;
-	struct ynl_error yerr;
-	struct ynl_sock *ys;
-	int num = -1;
-
-	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
-	if (!ys) {
-		fprintf(stderr, "YNL: %s\n", yerr.msg);
-		return -1;
-	}
-
-	req = ethtool_channels_get_req_alloc();
-	ethtool_channels_get_req_set_header_dev_index(req, ifindex);
-	rsp = ethtool_channels_get(ys, req);
-	if (rsp)
-		num = rsp->rx_count + rsp->combined_count;
-	ethtool_channels_get_req_free(req);
-	ethtool_channels_get_rsp_free(rsp);
-
-	ynl_sock_destroy(ys);
-
-	return num;
-}
-
-#define run_command(cmd, ...)                                           \
-	({                                                              \
-		char command[256];                                      \
-		memset(command, 0, sizeof(command));                    \
-		snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \
-		fprintf(stderr, "Running: %s\n", command);                       \
-		system(command);                                        \
-	})
-
-static int reset_flow_steering(void)
-{
-	/* Depending on the NIC, toggling ntuple off and on might not
-	 * be allowed. Additionally, attempting to delete existing filters
-	 * will fail if no filters are present. Therefore, do not enforce
-	 * the exit status.
-	 */
-
-	run_command("sudo ethtool -K %s ntuple off >&2", ifname);
-	run_command("sudo ethtool -K %s ntuple on >&2", ifname);
-	run_command(
-		"sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2",
-		ifname, ifname);
-	return 0;
-}
-
-static const char *tcp_data_split_str(int val)
-{
-	switch (val) {
-	case 0:
-		return "off";
-	case 1:
-		return "auto";
-	case 2:
-		return "on";
-	default:
-		return "?";
-	}
-}
-
-static int configure_headersplit(bool on)
-{
-	struct ethtool_rings_get_req *get_req;
-	struct ethtool_rings_get_rsp *get_rsp;
-	struct ethtool_rings_set_req *req;
-	struct ynl_error yerr;
-	struct ynl_sock *ys;
-	int ret;
-
-	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
-	if (!ys) {
-		fprintf(stderr, "YNL: %s\n", yerr.msg);
-		return -1;
-	}
-
-	req = ethtool_rings_set_req_alloc();
-	ethtool_rings_set_req_set_header_dev_index(req, ifindex);
-	/* 0 - off, 1 - auto, 2 - on */
-	ethtool_rings_set_req_set_tcp_data_split(req, on ? 2 : 0);
-	ret = ethtool_rings_set(ys, req);
-	if (ret < 0)
-		fprintf(stderr, "YNL failed: %s\n", ys->err.msg);
-	ethtool_rings_set_req_free(req);
-
-	if (ret == 0) {
-		get_req = ethtool_rings_get_req_alloc();
-		ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
-		get_rsp = ethtool_rings_get(ys, get_req);
-		ethtool_rings_get_req_free(get_req);
-		if (get_rsp)
-			fprintf(stderr, "TCP header split: %s\n",
-				tcp_data_split_str(get_rsp->tcp_data_split));
-		ethtool_rings_get_rsp_free(get_rsp);
-	}
-
-	ynl_sock_destroy(ys);
-
-	return ret;
-}
-
-static int configure_rss(void)
-{
-	return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue);
-}
-
-static int configure_channels(unsigned int rx, unsigned int tx)
-{
-	return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx);
-}
-
-static int configure_flow_steering(struct sockaddr_in6 *server_sin)
-{
-	const char *type = "tcp6";
-	const char *server_addr;
-	char buf[40];
-
-	inet_ntop(AF_INET6, &server_sin->sin6_addr, buf, sizeof(buf));
-	server_addr = buf;
-
-	if (IN6_IS_ADDR_V4MAPPED(&server_sin->sin6_addr)) {
-		type = "tcp4";
-		server_addr = strrchr(server_addr, ':') + 1;
-	}
-
-	return run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
-			   ifname,
-			   type,
-			   client_ip ? "src-ip" : "",
-			   client_ip ?: "",
-			   server_addr,
-			   client_ip ? "src-port" : "",
-			   client_ip ? port : "",
-			   port, start_queue);
-}
-
-static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
-			 struct netdev_queue_id *queues,
-			 unsigned int n_queue_index, struct ynl_sock **ys)
-{
-	struct netdev_bind_rx_req *req = NULL;
-	struct netdev_bind_rx_rsp *rsp = NULL;
-	struct ynl_error yerr;
-
-	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
-	if (!*ys) {
-		fprintf(stderr, "YNL: %s\n", yerr.msg);
-		return -1;
-	}
-
-	req = netdev_bind_rx_req_alloc();
-	netdev_bind_rx_req_set_ifindex(req, ifindex);
-	netdev_bind_rx_req_set_fd(req, dmabuf_fd);
-	__netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
-
-	rsp = netdev_bind_rx(*ys, req);
-	if (!rsp) {
-		perror("netdev_bind_rx");
-		goto err_close;
-	}
-
-	if (!rsp->_present.id) {
-		perror("id not present");
-		goto err_close;
-	}
-
-	fprintf(stderr, "got dmabuf id=%d\n", rsp->id);
-	dmabuf_id = rsp->id;
-
-	netdev_bind_rx_req_free(req);
-	netdev_bind_rx_rsp_free(rsp);
-
-	return 0;
-
-err_close:
-	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
-	netdev_bind_rx_req_free(req);
-	ynl_sock_destroy(*ys);
-	return -1;
-}
-
-static void enable_reuseaddr(int fd)
-{
-	int opt = 1;
-	int ret;
-
-	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
-	if (ret)
-		error(1, errno, "%s: [FAIL, SO_REUSEPORT]\n", TEST_PREFIX);
-
-	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
-	if (ret)
-		error(1, errno, "%s: [FAIL, SO_REUSEADDR]\n", TEST_PREFIX);
-}
-
-static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
-{
-	int ret;
-
-	sin6->sin6_family = AF_INET6;
-	sin6->sin6_port = htons(port);
-
-	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
-	if (ret != 1) {
-		/* fallback to plain IPv4 */
-		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
-		if (ret != 1)
-			return -1;
-
-		/* add ::ffff prefix */
-		sin6->sin6_addr.s6_addr32[0] = 0;
-		sin6->sin6_addr.s6_addr32[1] = 0;
-		sin6->sin6_addr.s6_addr16[4] = 0;
-		sin6->sin6_addr.s6_addr16[5] = 0xffff;
-	}
-
-	return 0;
-}
-
-int do_server(struct memory_buffer *mem)
-{
-	char ctrl_data[sizeof(int) * 20000];
-	struct netdev_queue_id *queues;
-	size_t non_page_aligned_frags = 0;
-	struct sockaddr_in6 client_addr;
-	struct sockaddr_in6 server_sin;
-	size_t page_aligned_frags = 0;
-	size_t total_received = 0;
-	socklen_t client_addr_len;
-	bool is_devmem = false;
-	char *tmp_mem = NULL;
-	struct ynl_sock *ys;
-	char iobuf[819200];
-	char buffer[256];
-	int socket_fd;
-	int client_fd;
-	size_t i = 0;
-	int ret;
-
-	ret = parse_address(server_ip, atoi(port), &server_sin);
-	if (ret < 0)
-		error(1, 0, "parse server address");
-
-	if (reset_flow_steering())
-		error(1, 0, "Failed to reset flow steering\n");
-
-	if (configure_headersplit(1))
-		error(1, 0, "Failed to enable TCP header split\n");
-
-	/* Configure RSS to divert all traffic from our devmem queues */
-	if (configure_rss())
-		error(1, 0, "Failed to configure rss\n");
-
-	/* Flow steer our devmem flows to start_queue */
-	if (configure_flow_steering(&server_sin))
-		error(1, 0, "Failed to configure flow steering\n");
-
-	sleep(1);
-
-	queues = malloc(sizeof(*queues) * num_queues);
-
-	for (i = 0; i < num_queues; i++) {
-		queues[i]._present.type = 1;
-		queues[i]._present.id = 1;
-		queues[i].type = NETDEV_QUEUE_TYPE_RX;
-		queues[i].id = start_queue + i;
-	}
-
-	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
-		error(1, 0, "Failed to bind\n");
-
-	tmp_mem = malloc(mem->size);
-	if (!tmp_mem)
-		error(1, ENOMEM, "malloc failed");
-
-	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (socket_fd < 0)
-		error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
-
-	enable_reuseaddr(socket_fd);
-
-	fprintf(stderr, "binding to address %s:%d\n", server_ip,
-		ntohs(server_sin.sin6_port));
-
-	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
-	if (ret)
-		error(1, errno, "%s: [FAIL, bind]\n", TEST_PREFIX);
-
-	ret = listen(socket_fd, 1);
-	if (ret)
-		error(1, errno, "%s: [FAIL, listen]\n", TEST_PREFIX);
-
-	client_addr_len = sizeof(client_addr);
-
-	inet_ntop(AF_INET6, &server_sin.sin6_addr, buffer,
-		  sizeof(buffer));
-	fprintf(stderr, "Waiting or connection on %s:%d\n", buffer,
-		ntohs(server_sin.sin6_port));
-	client_fd = accept(socket_fd, &client_addr, &client_addr_len);
-
-	inet_ntop(AF_INET6, &client_addr.sin6_addr, buffer,
-		  sizeof(buffer));
-	fprintf(stderr, "Got connection from %s:%d\n", buffer,
-		ntohs(client_addr.sin6_port));
-
-	while (1) {
-		struct iovec iov = { .iov_base = iobuf,
-				     .iov_len = sizeof(iobuf) };
-		struct dmabuf_cmsg *dmabuf_cmsg = NULL;
-		struct cmsghdr *cm = NULL;
-		struct msghdr msg = { 0 };
-		struct dmabuf_token token;
-		ssize_t ret;
-
-		is_devmem = false;
-
-		msg.msg_iov = &iov;
-		msg.msg_iovlen = 1;
-		msg.msg_control = ctrl_data;
-		msg.msg_controllen = sizeof(ctrl_data);
-		ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM);
-		fprintf(stderr, "recvmsg ret=%ld\n", ret);
-		if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK))
-			continue;
-		if (ret < 0) {
-			perror("recvmsg");
-			continue;
-		}
-		if (ret == 0) {
-			fprintf(stderr, "client exited\n");
-			goto cleanup;
-		}
-
-		i++;
-		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
-			if (cm->cmsg_level != SOL_SOCKET ||
-			    (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
-			     cm->cmsg_type != SCM_DEVMEM_LINEAR)) {
-				fprintf(stderr, "skipping non-devmem cmsg\n");
-				continue;
-			}
-
-			dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm);
-			is_devmem = true;
-
-			if (cm->cmsg_type == SCM_DEVMEM_LINEAR) {
-				/* TODO: process data copied from skb's linear
-				 * buffer.
-				 */
-				fprintf(stderr,
-					"SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n",
-					dmabuf_cmsg->frag_size);
-
-				continue;
-			}
-
-			token.token_start = dmabuf_cmsg->frag_token;
-			token.token_count = 1;
-
-			total_received += dmabuf_cmsg->frag_size;
-			fprintf(stderr,
-				"received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n",
-				dmabuf_cmsg->frag_offset >> PAGE_SHIFT,
-				dmabuf_cmsg->frag_offset % getpagesize(),
-				dmabuf_cmsg->frag_offset,
-				dmabuf_cmsg->frag_size, dmabuf_cmsg->frag_token,
-				total_received, dmabuf_cmsg->dmabuf_id);
-
-			if (dmabuf_cmsg->dmabuf_id != dmabuf_id)
-				error(1, 0,
-				      "received on wrong dmabuf_id: flow steering error\n");
-
-			if (dmabuf_cmsg->frag_size % getpagesize())
-				non_page_aligned_frags++;
-			else
-				page_aligned_frags++;
-
-			provider->memcpy_from_device(tmp_mem, mem,
-						     dmabuf_cmsg->frag_offset,
-						     dmabuf_cmsg->frag_size);
-
-			if (do_validation)
-				validate_buffer(tmp_mem,
-						dmabuf_cmsg->frag_size);
-			else
-				print_nonzero_bytes(tmp_mem,
-						    dmabuf_cmsg->frag_size);
-
-			ret = setsockopt(client_fd, SOL_SOCKET,
-					 SO_DEVMEM_DONTNEED, &token,
-					 sizeof(token));
-			if (ret != 1)
-				error(1, 0,
-				      "SO_DEVMEM_DONTNEED not enough tokens");
-		}
-		if (!is_devmem)
-			error(1, 0, "flow steering error\n");
-
-		fprintf(stderr, "total_received=%lu\n", total_received);
-	}
-
-	fprintf(stderr, "%s: ok\n", TEST_PREFIX);
-
-	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
-		page_aligned_frags, non_page_aligned_frags);
-
-	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
-		page_aligned_frags, non_page_aligned_frags);
-
-cleanup:
-
-	free(tmp_mem);
-	close(client_fd);
-	close(socket_fd);
-	ynl_sock_destroy(ys);
-
-	return 0;
-}
-
-void run_devmem_tests(void)
-{
-	struct netdev_queue_id *queues;
-	struct memory_buffer *mem;
-	struct ynl_sock *ys;
-	size_t i = 0;
-
-	mem = provider->alloc(getpagesize() * NUM_PAGES);
-
-	/* Configure RSS to divert all traffic from our devmem queues */
-	if (configure_rss())
-		error(1, 0, "rss error\n");
-
-	queues = calloc(num_queues, sizeof(*queues));
-
-	if (configure_headersplit(1))
-		error(1, 0, "Failed to configure header split\n");
-
-	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
-		error(1, 0, "Binding empty queues array should have failed\n");
-
-	for (i = 0; i < num_queues; i++) {
-		queues[i]._present.type = 1;
-		queues[i]._present.id = 1;
-		queues[i].type = NETDEV_QUEUE_TYPE_RX;
-		queues[i].id = start_queue + i;
-	}
-
-	if (configure_headersplit(0))
-		error(1, 0, "Failed to configure header split\n");
-
-	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
-		error(1, 0, "Configure dmabuf with header split off should have failed\n");
-
-	if (configure_headersplit(1))
-		error(1, 0, "Failed to configure header split\n");
-
-	for (i = 0; i < num_queues; i++) {
-		queues[i]._present.type = 1;
-		queues[i]._present.id = 1;
-		queues[i].type = NETDEV_QUEUE_TYPE_RX;
-		queues[i].id = start_queue + i;
-	}
-
-	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
-		error(1, 0, "Failed to bind\n");
-
-	/* Deactivating a bound queue should not be legal */
-	if (!configure_channels(num_queues, num_queues - 1))
-		error(1, 0, "Deactivating a bound queue should be illegal.\n");
-
-	/* Closing the netlink socket does an implicit unbind */
-	ynl_sock_destroy(ys);
-
-	provider->free(mem);
-}
-
-int main(int argc, char *argv[])
-{
-	struct memory_buffer *mem;
-	int is_server = 0, opt;
-	int ret;
-
-	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) {
-		switch (opt) {
-		case 'l':
-			is_server = 1;
-			break;
-		case 's':
-			server_ip = optarg;
-			break;
-		case 'c':
-			client_ip = optarg;
-			break;
-		case 'p':
-			port = optarg;
-			break;
-		case 'v':
-			do_validation = atoll(optarg);
-			break;
-		case 'q':
-			num_queues = atoi(optarg);
-			break;
-		case 't':
-			start_queue = atoi(optarg);
-			break;
-		case 'f':
-			ifname = optarg;
-			break;
-		case '?':
-			fprintf(stderr, "unknown option: %c\n", optopt);
-			break;
-		}
-	}
-
-	if (!ifname)
-		error(1, 0, "Missing -f argument\n");
-
-	ifindex = if_nametoindex(ifname);
-
-	if (!server_ip && !client_ip) {
-		if (start_queue < 0 && num_queues < 0) {
-			num_queues = rxq_num(ifindex);
-			if (num_queues < 0)
-				error(1, 0, "couldn't detect number of queues\n");
-			if (num_queues < 2)
-				error(1, 0,
-				      "number of device queues is too low\n");
-			/* make sure can bind to multiple queues */
-			start_queue = num_queues / 2;
-			num_queues /= 2;
-		}
-
-		if (start_queue < 0 || num_queues < 0)
-			error(1, 0, "Both -t and -q are required\n");
-
-		run_devmem_tests();
-		return 0;
-	}
-
-	if (start_queue < 0 && num_queues < 0) {
-		num_queues = rxq_num(ifindex);
-		if (num_queues < 2)
-			error(1, 0, "number of device queues is too low\n");
-
-		num_queues = 1;
-		start_queue = rxq_num(ifindex) - num_queues;
-
-		if (start_queue < 0)
-			error(1, 0, "couldn't detect number of queues\n");
-
-		fprintf(stderr, "using queues %d..%d\n", start_queue, start_queue + num_queues);
-	}
-
-	for (; optind < argc; optind++)
-		fprintf(stderr, "extra arguments: %s\n", argv[optind]);
-
-	if (start_queue < 0)
-		error(1, 0, "Missing -t argument\n");
-
-	if (num_queues < 0)
-		error(1, 0, "Missing -q argument\n");
-
-	if (!server_ip)
-		error(1, 0, "Missing -s argument\n");
-
-	if (!port)
-		error(1, 0, "Missing -p argument\n");
-
-	mem = provider->alloc(getpagesize() * NUM_PAGES);
-	ret = is_server ? do_server(mem) : 1;
-	provider->free(mem);
-
-	return ret;
-}
-- 
cgit v1.2.3


From 80230864b7b0fd9b54b294ab08a28f01d4193aa2 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 7 Nov 2024 10:12:11 -0800
Subject: selftests: ncdevmem: Add automated test

Only RX side for now and small message to test the setup.
In the future, we can extend it to TX side and to testing
both sides with a couple of megs of data.

  make \
  	-C tools/testing/selftests \
  	TARGETS="drivers/hw/net" \
  	install INSTALL_PATH=~/tmp/ksft

  scp ~/tmp/ksft ${HOST}:
  scp ~/tmp/ksft ${PEER}:

  cfg+="NETIF=${DEV}\n"
  cfg+="LOCAL_V6=${HOST_IP}\n"
  cfg+="REMOTE_V6=${PEER_IP}\n"
  cfg+="REMOTE_TYPE=ssh\n"
  cfg+="REMOTE_ARGS=root@${PEER}\n"

  echo -e "$cfg" | ssh root@${HOST} "cat > ksft/drivers/net/net.config"
  ssh root@${HOST} "cd ksft && ./run_kselftest.sh -t drivers/net:devmem.py"

Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20241107181211.3934153-13-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/Makefile  |  1 +
 tools/testing/selftests/drivers/net/hw/devmem.py | 45 ++++++++++++++++++++++++
 2 files changed, 46 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/hw/devmem.py

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 182348f4bd40..1c6a77480923 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -3,6 +3,7 @@
 TEST_PROGS = \
 	csum.py \
 	devlink_port_split.py \
+	devmem.py \
 	ethtool.sh \
 	ethtool_extended_state.sh \
 	ethtool_mm.sh \
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
new file mode 100755
index 000000000000..1223f0f5c10c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, KsftSkipEx
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, cmd, rand_port, wait_port_listen
+from lib.py import ksft_disruptive
+
+
+def require_devmem(cfg):
+    if not hasattr(cfg, "_devmem_probed"):
+        port = rand_port()
+        probe_command = f"./ncdevmem -f {cfg.ifname}"
+        cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
+        cfg._devmem_probed = True
+
+    if not cfg._devmem_supported:
+        raise KsftSkipEx("Test requires devmem support")
+
+
+@ksft_disruptive
+def check_rx(cfg) -> None:
+    cfg.require_v6()
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.v6} -p {port}"
+
+    with bkg(listen_cmd) as socat:
+        wait_port_listen(port)
+        cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.v6}]:{port}", host=cfg.remote, shell=True)
+
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run([check_rx],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
-- 
cgit v1.2.3


From 347fcdc414f98998df1c5969e4612e4da67d6852 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Sat, 9 Nov 2024 05:02:35 +0000
Subject: selftests: net: Add busy_poll_test

Add an epoll busy poll test using netdevsim.

This test is comprised of:
  - busy_poller (via busy_poller.c)
  - busy_poll_test.sh which loads netdevsim, sets up network namespaces,
    and runs busy_poller to receive data and socat to send data.

The selftest tests two different scenarios:
  - busy poll (the pre-existing version in the kernel)
  - busy poll with suspend enabled (what this series adds)

The data transmit is a 1MiB temporary file generated from /dev/urandom
and the test is considered passing if the md5sum of the input file to
socat matches the md5sum of the output file from busy_poller.

netdevsim was chosen instead of veth due to netdevsim's support for
netdev-genl.

For now, this test uses the functionality that netdevsim provides. In the
future, perhaps netdevsim can be extended to emulate device IRQs to more
thoroughly test all pre-existing kernel options (like defer_hard_irqs)
and suspend.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Co-developed-by: Martin Karsten <mkarsten@uwaterloo.ca>
Signed-off-by: Martin Karsten <mkarsten@uwaterloo.ca>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20241109050245.191288-6-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/.gitignore        |   1 +
 tools/testing/selftests/net/Makefile          |   9 +
 tools/testing/selftests/net/busy_poll_test.sh | 165 ++++++++++++
 tools/testing/selftests/net/busy_poller.c     | 346 ++++++++++++++++++++++++++
 4 files changed, 521 insertions(+)
 create mode 100755 tools/testing/selftests/net/busy_poll_test.sh
 create mode 100644 tools/testing/selftests/net/busy_poller.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index a78debbd1fe7..48973e78d46b 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -2,6 +2,7 @@
 bind_bhash
 bind_timewait
 bind_wildcard
+busy_poller
 cmsg_sender
 diag_uid
 epoll_busy_poll
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 9322b904ad00..2b2a5ec7fa6a 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -97,6 +97,11 @@ TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
 TEST_PROGS += ipv6_route_update_soft_lockup.sh
+TEST_PROGS += busy_poll_test.sh
+
+# YNL files, must be before "include ..lib.mk"
+YNL_GEN_FILES := busy_poller
+TEST_GEN_FILES += $(YNL_GEN_FILES)
 
 TEST_FILES := settings
 TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
@@ -107,6 +112,10 @@ TEST_INCLUDES := forwarding/lib.sh
 
 include ../lib.mk
 
+# YNL build
+YNL_GENS := netdev
+include ynl.mk
+
 $(OUTPUT)/epoll_busy_poll: LDLIBS += -lcap
 $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto
diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh
new file mode 100755
index 000000000000..7db292ec4884
--- /dev/null
+++ b/tools/testing/selftests/net/busy_poll_test.sh
@@ -0,0 +1,165 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source net_helper.sh
+
+NSIM_SV_ID=$((256 + RANDOM % 256))
+NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
+NSIM_CL_ID=$((512 + RANDOM % 256))
+NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device
+NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device
+
+SERVER_IP=192.168.1.1
+CLIENT_IP=192.168.1.2
+SERVER_PORT=48675
+
+# busy poll config
+MAX_EVENTS=8
+BUSY_POLL_USECS=0
+BUSY_POLL_BUDGET=16
+PREFER_BUSY_POLL=1
+
+# IRQ deferral config
+NAPI_DEFER_HARD_IRQS=100
+GRO_FLUSH_TIMEOUT=50000
+SUSPEND_TIMEOUT=20000000
+
+setup_ns()
+{
+	set -e
+	ip netns add nssv
+	ip netns add nscl
+
+	NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_SV_SYS/net -exec basename {} \;)
+	NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_CL_SYS/net -exec basename {} \;)
+
+	# ensure the server has 1 queue
+	ethtool -L $NSIM_SV_NAME combined 1 2>/dev/null
+
+	ip link set $NSIM_SV_NAME netns nssv
+	ip link set $NSIM_CL_NAME netns nscl
+
+	ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME
+	ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME
+
+	ip netns exec nssv ip link set dev $NSIM_SV_NAME up
+	ip netns exec nscl ip link set dev $NSIM_CL_NAME up
+
+	set +e
+}
+
+cleanup_ns()
+{
+	ip netns del nscl
+	ip netns del nssv
+}
+
+test_busypoll()
+{
+	suspend_value=${1:-0}
+	tmp_file=$(mktemp)
+	out_file=$(mktemp)
+
+	# fill a test file with random data
+	dd if=/dev/urandom of=${tmp_file} bs=1M count=1 2> /dev/null
+
+	timeout -k 1s 30s ip netns exec nssv ./busy_poller         \
+					     -p${SERVER_PORT}      \
+					     -b${SERVER_IP}        \
+					     -m${MAX_EVENTS}       \
+					     -u${BUSY_POLL_USECS}  \
+					     -P${PREFER_BUSY_POLL} \
+					     -g${BUSY_POLL_BUDGET} \
+					     -i${NSIM_SV_IFIDX}    \
+					     -s${suspend_value}    \
+					     -o${out_file}&
+
+	wait_local_port_listen nssv ${SERVER_PORT} tcp
+
+	ip netns exec nscl socat -u $tmp_file TCP:${SERVER_IP}:${SERVER_PORT}
+
+	wait
+
+	tmp_file_md5sum=$(md5sum $tmp_file | cut -f1 -d' ')
+	out_file_md5sum=$(md5sum $out_file | cut -f1 -d' ')
+
+	if [ "$tmp_file_md5sum" = "$out_file_md5sum" ]; then
+		res=0
+	else
+		echo "md5sum mismatch"
+		echo "input file md5sum: ${tmp_file_md5sum}";
+		echo "output file md5sum: ${out_file_md5sum}";
+		res=1
+	fi
+
+	rm $out_file $tmp_file
+
+	return $res
+}
+
+test_busypoll_with_suspend()
+{
+	test_busypoll ${SUSPEND_TIMEOUT}
+
+	return $?
+}
+
+###
+### Code start
+###
+
+modprobe netdevsim
+
+# linking
+
+echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+
+setup_ns
+
+NSIM_SV_FD=$((256 + RANDOM % 256))
+exec {NSIM_SV_FD}</var/run/netns/nssv
+NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex)
+
+NSIM_CL_FD=$((256 + RANDOM % 256))
+exec {NSIM_CL_FD}</var/run/netns/nscl
+NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex)
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \
+     $NSIM_DEV_SYS_LINK
+
+if [ $? -ne 0 ]; then
+	echo "linking netdevsim1 with netdevsim2 should succeed"
+	cleanup_ns
+	exit 1
+fi
+
+test_busypoll
+if [ $? -ne 0 ]; then
+	echo "test_busypoll failed"
+	cleanup_ns
+	exit 1
+fi
+
+test_busypoll_with_suspend
+if [ $? -ne 0 ]; then
+	echo "test_busypoll_with_suspend failed"
+	cleanup_ns
+	exit 1
+fi
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK
+
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL
+
+cleanup_ns
+
+modprobe -r netdevsim
+
+exit 0
diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c
new file mode 100644
index 000000000000..99b0e8c17fca
--- /dev/null
+++ b/tools/testing/selftests/net/busy_poller.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <ynl.h>
+
+#include <arpa/inet.h>
+#include <netinet/in.h>
+
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include <linux/genetlink.h>
+#include <linux/netlink.h>
+
+#include "netdev-user.h"
+
+/* The below ifdef blob is required because:
+ *
+ * - sys/epoll.h does not (yet) have the ioctl definitions included. So,
+ *   systems with older glibcs will not have them available. However,
+ *   sys/epoll.h does include the type definition for epoll_data, which is
+ *   needed by the user program (e.g. epoll_event.data.fd)
+ *
+ * - linux/eventpoll.h does not define the epoll_data type, it is simply an
+ *   opaque __u64. It does, however, include the ioctl definition.
+ *
+ * Including both headers is impossible (types would be redefined), so I've
+ * opted instead to take sys/epoll.h, and include the blob below.
+ *
+ * Someday, when glibc is globally up to date, the blob below can be removed.
+ */
+#if !defined(EPOLL_IOC_TYPE)
+struct epoll_params {
+	uint32_t busy_poll_usecs;
+	uint16_t busy_poll_budget;
+	uint8_t prefer_busy_poll;
+
+	/* pad the struct to a multiple of 64bits */
+	uint8_t __pad;
+};
+
+#define EPOLL_IOC_TYPE 0x8A
+#define EPIOCSPARAMS _IOW(EPOLL_IOC_TYPE, 0x01, struct epoll_params)
+#define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params)
+#endif
+
+static uint32_t cfg_port = 8000;
+static struct in_addr cfg_bind_addr = { .s_addr = INADDR_ANY };
+static char *cfg_outfile;
+static int cfg_max_events = 8;
+static int cfg_ifindex;
+
+/* busy poll params */
+static uint32_t cfg_busy_poll_usecs;
+static uint32_t cfg_busy_poll_budget;
+static uint32_t cfg_prefer_busy_poll;
+
+/* IRQ params */
+static uint32_t cfg_defer_hard_irqs;
+static uint64_t cfg_gro_flush_timeout;
+static uint64_t cfg_irq_suspend_timeout;
+
+static void usage(const char *filepath)
+{
+	error(1, 0,
+	      "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -i<ifindex>",
+	      filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int ret;
+	int c;
+
+	if (argc <= 1)
+		usage(argv[0]);
+
+	while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) {
+		switch (c) {
+		case 'u':
+			cfg_busy_poll_usecs = strtoul(optarg, NULL, 0);
+			if (cfg_busy_poll_usecs == ULONG_MAX ||
+			    cfg_busy_poll_usecs > UINT32_MAX)
+				error(1, ERANGE, "busy_poll_usecs too large");
+			break;
+		case 'P':
+			cfg_prefer_busy_poll = strtoul(optarg, NULL, 0);
+			if (cfg_prefer_busy_poll == ULONG_MAX ||
+			    cfg_prefer_busy_poll > 1)
+				error(1, ERANGE,
+				      "prefer busy poll should be 0 or 1");
+			break;
+		case 'g':
+			cfg_busy_poll_budget = strtoul(optarg, NULL, 0);
+			if (cfg_busy_poll_budget == ULONG_MAX ||
+			    cfg_busy_poll_budget > UINT16_MAX)
+				error(1, ERANGE,
+				      "busy poll budget must be [0, UINT16_MAX]");
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			if (cfg_port > UINT16_MAX)
+				error(1, ERANGE, "port must be <= 65535");
+			break;
+		case 'b':
+			ret = inet_aton(optarg, &cfg_bind_addr);
+			if (ret == 0)
+				error(1, errno,
+				      "bind address %s invalid", optarg);
+			break;
+		case 'o':
+			cfg_outfile = strdup(optarg);
+			if (!cfg_outfile)
+				error(1, 0, "outfile invalid");
+			break;
+		case 'm':
+			cfg_max_events = strtol(optarg, NULL, 0);
+
+			if (cfg_max_events == LONG_MIN ||
+			    cfg_max_events == LONG_MAX ||
+			    cfg_max_events <= 0)
+				error(1, ERANGE,
+				      "max events must be > 0 and < LONG_MAX");
+			break;
+		case 'd':
+			cfg_defer_hard_irqs = strtoul(optarg, NULL, 0);
+
+			if (cfg_defer_hard_irqs == ULONG_MAX ||
+			    cfg_defer_hard_irqs > INT32_MAX)
+				error(1, ERANGE,
+				      "defer_hard_irqs must be <= INT32_MAX");
+			break;
+		case 'r':
+			cfg_gro_flush_timeout = strtoull(optarg, NULL, 0);
+
+			if (cfg_gro_flush_timeout == ULLONG_MAX)
+				error(1, ERANGE,
+				      "gro_flush_timeout must be < ULLONG_MAX");
+			break;
+		case 's':
+			cfg_irq_suspend_timeout = strtoull(optarg, NULL, 0);
+
+			if (cfg_irq_suspend_timeout == ULLONG_MAX)
+				error(1, ERANGE,
+				      "irq_suspend_timeout must be < ULLONG_MAX");
+			break;
+		case 'i':
+			cfg_ifindex = strtoul(optarg, NULL, 0);
+			if (cfg_ifindex == ULONG_MAX)
+				error(1, ERANGE,
+				      "ifindex must be < ULONG_MAX");
+			break;
+		}
+	}
+
+	if (!cfg_ifindex)
+		usage(argv[0]);
+
+	if (optind != argc)
+		usage(argv[0]);
+}
+
+static void epoll_ctl_add(int epfd, int fd, uint32_t events)
+{
+	struct epoll_event ev;
+
+	ev.events = events;
+	ev.data.fd = fd;
+	if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &ev) == -1)
+		error(1, errno, "epoll_ctl add fd: %d", fd);
+}
+
+static void setnonblock(int sockfd)
+{
+	int flags;
+
+	flags = fcntl(sockfd, F_GETFL, 0);
+
+	if (fcntl(sockfd, F_SETFL, flags | O_NONBLOCK) == -1)
+		error(1, errno, "unable to set socket to nonblocking mode");
+}
+
+static void write_chunk(int fd, char *buf, ssize_t buflen)
+{
+	ssize_t remaining = buflen;
+	char *buf_offset = buf;
+	ssize_t writelen = 0;
+	ssize_t write_result;
+
+	while (writelen < buflen) {
+		write_result = write(fd, buf_offset, remaining);
+		if (write_result == -1)
+			error(1, errno, "unable to write data to outfile");
+
+		writelen += write_result;
+		remaining -= write_result;
+		buf_offset += write_result;
+	}
+}
+
+static void setup_queue(void)
+{
+	struct netdev_napi_get_list *napi_list = NULL;
+	struct netdev_napi_get_req_dump *req = NULL;
+	struct netdev_napi_set_req *set_req = NULL;
+	struct ynl_sock *ys;
+	struct ynl_error yerr;
+	uint32_t napi_id;
+
+	ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!ys)
+		error(1, 0, "YNL: %s", yerr.msg);
+
+	req = netdev_napi_get_req_dump_alloc();
+	netdev_napi_get_req_dump_set_ifindex(req, cfg_ifindex);
+	napi_list = netdev_napi_get_dump(ys, req);
+
+	/* assume there is 1 NAPI configured and take the first */
+	if (napi_list->obj._present.id)
+		napi_id = napi_list->obj.id;
+	else
+		error(1, 0, "napi ID not present?");
+
+	set_req = netdev_napi_set_req_alloc();
+	netdev_napi_set_req_set_id(set_req, napi_id);
+	netdev_napi_set_req_set_defer_hard_irqs(set_req, cfg_defer_hard_irqs);
+	netdev_napi_set_req_set_gro_flush_timeout(set_req,
+						  cfg_gro_flush_timeout);
+	netdev_napi_set_req_set_irq_suspend_timeout(set_req,
+						    cfg_irq_suspend_timeout);
+
+	if (netdev_napi_set(ys, set_req))
+		error(1, 0, "can't set NAPI params: %s\n", yerr.msg);
+
+	netdev_napi_get_list_free(napi_list);
+	netdev_napi_get_req_dump_free(req);
+	netdev_napi_set_req_free(set_req);
+	ynl_sock_destroy(ys);
+}
+
+static void run_poller(void)
+{
+	struct epoll_event events[cfg_max_events];
+	struct epoll_params epoll_params = {0};
+	struct sockaddr_in server_addr;
+	int i, epfd, nfds;
+	ssize_t readlen;
+	int outfile_fd;
+	char buf[1024];
+	int sockfd;
+	int conn;
+	int val;
+
+	outfile_fd = open(cfg_outfile, O_WRONLY | O_CREAT, 0644);
+	if (outfile_fd == -1)
+		error(1, errno, "unable to open outfile: %s", cfg_outfile);
+
+	sockfd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+	if (sockfd == -1)
+		error(1, errno, "unable to create listen socket");
+
+	server_addr.sin_family = AF_INET;
+	server_addr.sin_port = htons(cfg_port);
+	server_addr.sin_addr = cfg_bind_addr;
+
+	/* these values are range checked during parse_opts, so casting is safe
+	 * here
+	 */
+	epoll_params.busy_poll_usecs = cfg_busy_poll_usecs;
+	epoll_params.busy_poll_budget = (uint16_t)cfg_busy_poll_budget;
+	epoll_params.prefer_busy_poll = (uint8_t)cfg_prefer_busy_poll;
+	epoll_params.__pad = 0;
+
+	val = 1;
+	if (setsockopt(sockfd, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val)))
+		error(1, errno, "poller setsockopt reuseaddr");
+
+	setnonblock(sockfd);
+
+	if (bind(sockfd, (struct sockaddr *)&server_addr,
+		 sizeof(struct sockaddr_in)))
+		error(0, errno, "poller bind to port: %d\n", cfg_port);
+
+	if (listen(sockfd, 1))
+		error(1, errno, "poller listen");
+
+	epfd = epoll_create1(0);
+	if (ioctl(epfd, EPIOCSPARAMS, &epoll_params) == -1)
+		error(1, errno, "unable to set busy poll params");
+
+	epoll_ctl_add(epfd, sockfd, EPOLLIN | EPOLLOUT | EPOLLET);
+
+	for (;;) {
+		nfds = epoll_wait(epfd, events, cfg_max_events, -1);
+		for (i = 0; i < nfds; i++) {
+			if (events[i].data.fd == sockfd) {
+				conn = accept(sockfd, NULL, NULL);
+				if (conn == -1)
+					error(1, errno,
+					      "accepting incoming connection failed");
+
+				setnonblock(conn);
+				epoll_ctl_add(epfd, conn,
+					      EPOLLIN | EPOLLET | EPOLLRDHUP |
+					      EPOLLHUP);
+			} else if (events[i].events & EPOLLIN) {
+				for (;;) {
+					readlen = read(events[i].data.fd, buf,
+						       sizeof(buf));
+					if (readlen > 0)
+						write_chunk(outfile_fd, buf,
+							    readlen);
+					else
+						break;
+				}
+			} else {
+				/* spurious event ? */
+			}
+			if (events[i].events & (EPOLLRDHUP | EPOLLHUP)) {
+				epoll_ctl(epfd, EPOLL_CTL_DEL,
+					  events[i].data.fd, NULL);
+				close(events[i].data.fd);
+				close(outfile_fd);
+				return;
+			}
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	parse_opts(argc, argv);
+	setup_queue();
+	run_poller();
+	return 0;
+}
-- 
cgit v1.2.3


From 43271bb5bf67e78def9c2898040505e7cb5935f3 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 8 Nov 2024 06:59:25 -0800
Subject: net: netconsole: selftests: Check if netdevsim is available

The netconsole selftest relies on the availability of the netdevsim module.
To ensure the test can run correctly, we need to check if the netdevsim
module is either loaded or built-in before proceeding.

Update the netconsole selftest to check for the existence of
the /sys/bus/netdevsim/new_device file before running the test. If the
file is not found, the test is skipped with an explanation that the
CONFIG_NETDEVSIM kernel config option may not be enabled.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20241108-netcon_selftest_deps-v1-1-1789cbf3adcd@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/netcons_basic.sh | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh
index 182eb1a97e59..b175f4d966e5 100755
--- a/tools/testing/selftests/drivers/net/netcons_basic.sh
+++ b/tools/testing/selftests/drivers/net/netcons_basic.sh
@@ -39,6 +39,7 @@ NAMESPACE=""
 # IDs for netdevsim
 NSIM_DEV_1_ID=$((256 + RANDOM % 256))
 NSIM_DEV_2_ID=$((512 + RANDOM % 256))
+NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device"
 
 # Used to create and delete namespaces
 source "${SCRIPTDIR}"/../../net/lib.sh
@@ -46,7 +47,6 @@ source "${SCRIPTDIR}"/../../net/net_helper.sh
 
 # Create netdevsim interfaces
 create_ifaces() {
-	local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
 
 	echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW"
 	echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW"
@@ -212,6 +212,11 @@ function check_for_dependencies() {
 		exit "${ksft_skip}"
 	fi
 
+	if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then
+		echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
 	if [ ! -d "${NETCONS_CONFIGFS}" ]; then
 		echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2
 		exit "${ksft_skip}"
-- 
cgit v1.2.3


From 7d3f3b4367f315a61fc615e3138f3d320da8c466 Mon Sep 17 00:00:00 2001
From: Vladimir Vdovin <deliran@verdict.gg>
Date: Fri, 8 Nov 2024 09:34:24 +0000
Subject: net: ipv4: Cache pmtu for all packet paths if multipath enabled

Check number of paths by fib_info_num_path(),
and update_or_create_fnhe() for every path.
Problem is that pmtu is cached only for the oif
that has received icmp message "need to frag",
other oifs will still try to use "default" iface mtu.

An example topology showing the problem:

                    |  host1
                +---------+
                |  dummy0 | 10.179.20.18/32  mtu9000
                +---------+
        +-----------+----------------+
    +---------+                     +---------+
    | ens17f0 |  10.179.2.141/31    | ens17f1 |  10.179.2.13/31
    +---------+                     +---------+
        |    (all here have mtu 9000)    |
    +------+                         +------+
    | ro1  |  10.179.2.140/31        | ro2  |  10.179.2.12/31
    +------+                         +------+
        |                                |
---------+------------+-------------------+------
                        |
                    +-----+
                    | ro3 | 10.10.10.10  mtu1500
                    +-----+
                        |
    ========================================
                some networks
    ========================================
                        |
                    +-----+
                    | eth0| 10.10.30.30  mtu9000
                    +-----+
                        |  host2

host1 have enabled multipath and
sysctl net.ipv4.fib_multipath_hash_policy = 1:

default proto static src 10.179.20.18
        nexthop via 10.179.2.12 dev ens17f1 weight 1
        nexthop via 10.179.2.140 dev ens17f0 weight 1

When host1 tries to do pmtud from 10.179.20.18/32 to host2,
host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500.
And host1 caches it in nexthop exceptions cache.

Problem is that it is cached only for the iface that has received icmp,
and there is no way that ro3 will send icmp msg to host1 via another path.

Host1 now have this routes to host2:

ip r g 10.10.30.30 sport 30000 dport 443
10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0
    cache expires 521sec mtu 1500

ip r g 10.10.30.30 sport 30033 dport 443
10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0
    cache

So when host1 tries again to reach host2 with mtu>1500,
if packet flow is lucky enough to be hashed with oif=ens17f1 its ok,
if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1,
until lucky day when ro3 will send it through another flow to ens17f0.

Signed-off-by: Vladimir Vdovin <deliran@verdict.gg>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20241108093427.317942-1-deliran@verdict.gg
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c                    |  13 +++++
 tools/testing/selftests/net/pmtu.sh | 112 ++++++++++++++++++++++++++++++------
 2 files changed, 108 insertions(+), 17 deletions(-)

(limited to 'tools/testing')

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4c5e773002fe..ccdbe9c70132 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		struct fib_nh_common *nhc;
 
 		fib_select_path(net, &res, fl4, NULL);
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+		if (fib_info_num_path(res.fi) > 1) {
+			int nhsel;
+
+			for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) {
+				nhc = fib_info_nhc(res.fi, nhsel);
+				update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
+						      jiffies + net->ipv4.ip_rt_mtu_expires);
+			}
+			rcu_read_unlock();
+			return;
+		}
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
 		nhc = FIB_RES_NHC(res);
 		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + net->ipv4.ip_rt_mtu_expires);
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 6c651c880fe8..66be7699c72c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -197,6 +197,12 @@
 #
 # - pmtu_ipv6_route_change
 #	Same as above but with IPv6
+#
+# - pmtu_ipv4_mp_exceptions
+#	Use the same topology as in pmtu_ipv4, but add routeable addresses
+#	on host A and B on lo reachable via both routers. Host A and B
+#	addresses have multipath routes to each other, b_r1 mtu = 1500.
+#	Check that PMTU exceptions are created for both paths.
 
 source lib.sh
 source net_helper.sh
@@ -266,7 +272,8 @@ tests="
 	list_flush_ipv4_exception	ipv4: list and flush cached exceptions	1
 	list_flush_ipv6_exception	ipv6: list and flush cached exceptions	1
 	pmtu_ipv4_route_change		ipv4: PMTU exception w/route replace	1
-	pmtu_ipv6_route_change		ipv6: PMTU exception w/route replace	1"
+	pmtu_ipv6_route_change		ipv6: PMTU exception w/route replace	1
+	pmtu_ipv4_mp_exceptions		ipv4: PMTU multipath nh exceptions	1"
 
 # Addressing and routing for tests with routers: four network segments, with
 # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
@@ -343,6 +350,9 @@ tunnel6_a_addr="fd00:2::a"
 tunnel6_b_addr="fd00:2::b"
 tunnel6_mask="64"
 
+host4_a_addr="192.168.99.99"
+host4_b_addr="192.168.88.88"
+
 dummy6_0_prefix="fc00:1000::"
 dummy6_1_prefix="fc00:1001::"
 dummy6_mask="64"
@@ -984,6 +994,52 @@ setup_ovs_bridge() {
 	run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2
 }
 
+setup_multipath_new() {
+	# Set up host A with multipath routes to host B host4_b_addr
+	run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo
+	run_cmd ${ns_a} ip nexthop add id 401 via ${prefix4}.${a_r1}.2 dev veth_A-R1
+	run_cmd ${ns_a} ip nexthop add id 402 via ${prefix4}.${a_r2}.2 dev veth_A-R2
+	run_cmd ${ns_a} ip nexthop add id 403 group 401/402
+	run_cmd ${ns_a} ip route add ${host4_b_addr} src ${host4_a_addr} nhid 403
+
+	# Set up host B with multipath routes to host A host4_a_addr
+	run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo
+	run_cmd ${ns_b} ip nexthop add id 401 via ${prefix4}.${b_r1}.2 dev veth_B-R1
+	run_cmd ${ns_b} ip nexthop add id 402 via ${prefix4}.${b_r2}.2 dev veth_B-R2
+	run_cmd ${ns_b} ip nexthop add id 403 group 401/402
+	run_cmd ${ns_b} ip route add ${host4_a_addr} src ${host4_b_addr} nhid 403
+}
+
+setup_multipath_old() {
+	# Set up host A with multipath routes to host B host4_b_addr
+	run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo
+	run_cmd ${ns_a} ip route add ${host4_b_addr} \
+			src ${host4_a_addr} \
+			nexthop via ${prefix4}.${a_r1}.2 weight 1 \
+			nexthop via ${prefix4}.${a_r2}.2 weight 1
+
+	# Set up host B with multipath routes to host A host4_a_addr
+	run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo
+	run_cmd ${ns_b} ip route add ${host4_a_addr} \
+			src ${host4_b_addr} \
+			nexthop via ${prefix4}.${b_r1}.2 weight 1 \
+			nexthop via ${prefix4}.${b_r2}.2 weight 1
+}
+
+setup_multipath() {
+	if [ "$USE_NH" = "yes" ]; then
+		setup_multipath_new
+	else
+		setup_multipath_old
+	fi
+
+	# Set up routers with routes to dummies
+	run_cmd ${ns_r1} ip route add ${host4_a_addr} via ${prefix4}.${a_r1}.1
+	run_cmd ${ns_r2} ip route add ${host4_a_addr} via ${prefix4}.${a_r2}.1
+	run_cmd ${ns_r1} ip route add ${host4_b_addr} via ${prefix4}.${b_r1}.1
+	run_cmd ${ns_r2} ip route add ${host4_b_addr} via ${prefix4}.${b_r2}.1
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -1076,23 +1132,15 @@ link_get_mtu() {
 }
 
 route_get_dst_exception() {
-	ns_cmd="${1}"
-	dst="${2}"
-	dsfield="${3}"
+	ns_cmd="${1}"; shift
 
-	if [ -z "${dsfield}" ]; then
-		dsfield=0
-	fi
-
-	${ns_cmd} ip route get "${dst}" dsfield "${dsfield}"
+	${ns_cmd} ip route get "$@"
 }
 
 route_get_dst_pmtu_from_exception() {
-	ns_cmd="${1}"
-	dst="${2}"
-	dsfield="${3}"
+	ns_cmd="${1}"; shift
 
-	mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")"
+	mtu_parse "$(route_get_dst_exception "${ns_cmd}" "$@")"
 }
 
 check_pmtu_value() {
@@ -1235,10 +1283,10 @@ test_pmtu_ipv4_dscp_icmp_exception() {
 	run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}"
 
 	# Check that exceptions have been created with the correct PMTU
-	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")"
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")"
 	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
 
-	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")"
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")"
 	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
 }
 
@@ -1285,9 +1333,9 @@ test_pmtu_ipv4_dscp_udp_exception() {
 		UDP:"${dst2}":50000,tos="${dsfield}"
 
 	# Check that exceptions have been created with the correct PMTU
-	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")"
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")"
 	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
-	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")"
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")"
 	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
 }
 
@@ -2329,6 +2377,36 @@ test_pmtu_ipv6_route_change() {
 	test_pmtu_ipvX_route_change 6
 }
 
+test_pmtu_ipv4_mp_exceptions() {
+	setup namespaces routing multipath || return $ksft_skip
+
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1500
+	mtu "${ns_b}"  veth_B-R1 1500
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Ping and expect two nexthop exceptions for two routes
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -c 1 -s 1800 "${host4_b_addr}"
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_a_R1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R1)"
+	pmtu_a_R2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R2)"
+
+	check_pmtu_value "1500" "${pmtu_a_R1}" "exceeding MTU (veth_A-R1)" || return 1
+	check_pmtu_value "1500" "${pmtu_a_R2}" "exceeding MTU (veth_A-R2)" || return 1
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
-- 
cgit v1.2.3


From df6cb25f07794b39e7993938ee3ca6749a88f300 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Wed, 30 Oct 2024 09:00:02 +0800
Subject: selftests: netfilter: Add missing gitignore file

Compiled binary files should be added to .gitignore
'git status' complains:
   Untracked files:
   (use "git add <file>..." to include in what will be committed)
         net/netfilter/conntrack_reverse_clash

Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/net/netfilter/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/netfilter/.gitignore b/tools/testing/selftests/net/netfilter/.gitignore
index 0a64d6d0e29a..64c4f8d9aa6c 100644
--- a/tools/testing/selftests/net/netfilter/.gitignore
+++ b/tools/testing/selftests/net/netfilter/.gitignore
@@ -2,5 +2,6 @@
 audit_logread
 connect_close
 conntrack_dump_flush
+conntrack_reverse_clash
 sctp_collision
 nf_queue
-- 
cgit v1.2.3


From 041bd1e4f2d82859690cd8b41c35f0f9404c3770 Mon Sep 17 00:00:00 2001
From: guanjing <guanjing@cmss.chinamobile.com>
Date: Fri, 8 Nov 2024 16:13:58 +0800
Subject: selftests: netfilter: Fix missing return values in
 conntrack_dump_flush

Fix the bug of some functions were missing return values.

Fixes: eff3c558bb7e ("netfilter: ctnetlink: support filtering by zone")
Signed-off-by: Guan Jing <guanjing@cmss.chinamobile.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/net/netfilter/conntrack_dump_flush.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c
index 254ff03297f0..5f827e10717d 100644
--- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c
+++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c
@@ -43,6 +43,8 @@ static int build_cta_tuple_v4(struct nlmsghdr *nlh, int type,
 	mnl_attr_nest_end(nlh, nest_proto);
 
 	mnl_attr_nest_end(nlh, nest);
+
+	return 0;
 }
 
 static int build_cta_tuple_v6(struct nlmsghdr *nlh, int type,
@@ -71,6 +73,8 @@ static int build_cta_tuple_v6(struct nlmsghdr *nlh, int type,
 	mnl_attr_nest_end(nlh, nest_proto);
 
 	mnl_attr_nest_end(nlh, nest);
+
+	return 0;
 }
 
 static int build_cta_proto(struct nlmsghdr *nlh)
@@ -90,6 +94,8 @@ static int build_cta_proto(struct nlmsghdr *nlh)
 	mnl_attr_nest_end(nlh, nest_proto);
 
 	mnl_attr_nest_end(nlh, nest);
+
+	return 0;
 }
 
 static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh,
-- 
cgit v1.2.3


From b2d5b4c468568b60916bdd5e7c10ab11b09bd164 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Wed, 13 Nov 2024 12:13:11 +0000
Subject: selftest: include dst-ip in ethtool ntuple rules

sfc hardware does not support filters with only ipproto + dst-port;
 adding dst-ip to the flow spec allows the rss_ctx test to be run on
 these devices.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://patch.msgid.link/8e5d23c8f21310c23c080cc7bcd31b76f8fd3096.1731499022.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 29995586993c..fb61dae20fd8 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -215,7 +215,7 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True):
         defer(ethtool, f"-X {cfg.ifname} default")
     else:
         other_key = 'noise'
-        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}"
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id}"
         ntuple = ethtool_create(cfg, "-N", flow)
         defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
 
@@ -429,7 +429,7 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
         ksft_eq(max(data['rss-indirection-table']), 2 + i * 2 + 1, "Unexpected context cfg: " + str(data))
 
         ports.append(rand_port())
-        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id}"
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {ports[i]} context {ctx_id}"
         ntuple = ethtool_create(cfg, "-N", flow)
         defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
 
@@ -516,7 +516,7 @@ def test_rss_context_out_of_order(cfg, ctx_cnt=4):
         ctx.append(defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete"))
 
         ports.append(rand_port())
-        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id}"
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {ports[i]} context {ctx_id}"
         ntuple_id = ethtool_create(cfg, "-N", flow)
         ntuple.append(defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}"))
 
@@ -569,7 +569,7 @@ def test_rss_context_overlap(cfg, other_ctx=0):
 
     port = rand_port()
     if other_ctx:
-        flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {other_ctx}"
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {other_ctx}"
         ntuple_id = ethtool_create(cfg, "-N", flow)
         ntuple = defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
 
@@ -587,7 +587,7 @@ def test_rss_context_overlap(cfg, other_ctx=0):
     # Now create a rule for context 1 and make sure traffic goes to a subset
     if other_ctx:
         ntuple.exec()
-    flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}"
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id}"
     ntuple_id = ethtool_create(cfg, "-N", flow)
     defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
 
@@ -620,7 +620,7 @@ def test_delete_rss_context_busy(cfg):
 
     # utilize context from ntuple filter
     port = rand_port()
-    flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}"
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id}"
     ntuple_id = ethtool_create(cfg, "-N", flow)
     defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
 
-- 
cgit v1.2.3


From e9e8abfec214b6a47f6c21d533c43c7f3c1f8887 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Wed, 13 Nov 2024 12:13:12 +0000
Subject: selftest: validate RSS+ntuple filters with nonzero ring_cookie

Test creates an ntuple filter with 'action 2' and an RSS context whose
 indirection table has entries 0 and 1.  Resulting traffic should go to
 queues 2 and 3; verify that it never hits queues 0 and 1.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/114afdf4d2867f72ed27751e8e08fe8b128a8529.1731499022.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 41 ++++++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index fb61dae20fd8..8f62dc29bd26 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -633,6 +633,45 @@ def test_delete_rss_context_busy(cfg):
         pass
 
 
+def test_rss_ntuple_addition(cfg):
+    """
+    Test that the queue offset (ring_cookie) of an ntuple rule is added
+    to the queue number read from the indirection table.
+    """
+
+    require_ntuple(cfg)
+
+    queue_cnt = len(_get_rx_cnts(cfg))
+    if queue_cnt < 4:
+        try:
+            ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+            ethtool(f"-L {cfg.ifname} combined 4")
+            defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    # Use queue 0 for normal traffic
+    ethtool(f"-X {cfg.ifname} equal 1")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    # create additional rss context
+    ctx_id = ethtool_create(cfg, "-X", "context new equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    # utilize context from ntuple filter
+    port = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id} action 2"
+    try:
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+    except CmdExitFailure:
+        raise KsftSkipEx("Ntuple filter with RSS and nonzero action not supported")
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    _send_traffic_check(cfg, port, f"context {ctx_id}", { 'target': (2, 3),
+                                                          'empty' : (1,),
+                                                          'noise' : (0,) })
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         cfg.ethnl = EthtoolFamily()
@@ -644,7 +683,7 @@ def main() -> None:
                   test_rss_context_dump, test_rss_context_queue_reconfigure,
                   test_rss_context_overlap, test_rss_context_overlap2,
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
-                  test_delete_rss_context_busy],
+                  test_delete_rss_context_busy, test_rss_ntuple_addition],
                  args=(cfg, ))
     ksft_exit()
 
-- 
cgit v1.2.3


From 29a4bc1fe961caea52a5b945be2b4267b02002d7 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Wed, 13 Nov 2024 12:13:13 +0000
Subject: selftest: extend test_rss_context_queue_reconfigure for action
 addition

The combination of ntuple action (ring_cookie) and RSS context can
 cause an ntuple rule to target a higher queue than appears in any
 RSS indirection table or directly in the ntuple rule, since the two
 numbers are added together.  Verify the logic that prevents reducing
 the queue count in this case.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/58276b800ab78c0a79c1918046ccae7fe45ba802.1731499022.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 26 +++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 8f62dc29bd26..0b49ce7ae678 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -238,6 +238,32 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True):
     else:
         raise Exception(f"Driver didn't prevent us from deactivating a used queue (context {ctx_id})")
 
+    if not main_ctx:
+        ethtool(f"-L {cfg.ifname} combined 4")
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id} action 1"
+        try:
+            # this targets queue 4, which doesn't exist
+            ntuple2 = ethtool_create(cfg, "-N", flow)
+        except CmdExitFailure:
+            pass
+        else:
+            raise Exception(f"Driver didn't prevent us from targeting a nonexistent queue (context {ctx_id})")
+        # change the table to target queues 0 and 2
+        ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0")
+        # ntuple rule therefore targets queues 1 and 3
+        ntuple2 = ethtool_create(cfg, "-N", flow)
+        # should replace existing filter
+        ksft_eq(ntuple, ntuple2)
+        _send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3),
+                                                  'noise' : (0, 2) })
+        # Setting queue count to 3 should fail, queue 3 is used
+        try:
+            ethtool(f"-L {cfg.ifname} combined 3")
+        except CmdExitFailure:
+            pass
+        else:
+            raise Exception(f"Driver didn't prevent us from deactivating a used queue (context {ctx_id})")
+
 
 def test_rss_resize(cfg):
     """Test resizing of the RSS table.
-- 
cgit v1.2.3


From b219bcfcc92e9bd50c6277ac68cb75f64b403e5e Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 14 Nov 2024 15:09:55 +0100
Subject: selftests: net: lib: Move logging from forwarding/lib.sh here

Many net selftests invent their own logging helpers. These really should be
in a library sourced by these tests. Currently forwarding/lib.sh has a
suite of perfectly fine logging helpers, but sourcing a forwarding/ library
from a higher-level directory smells of layering violation. In this patch,
move the logging helpers to net/lib.sh so that every net test can use them.

Together with the logging helpers, it's also necessary to move
pause_on_fail(), and EXIT_STATUS and RET.

Existing lib.sh users might be using these same names for their functions
or variables. However lib.sh is always sourced near the top of the
file (checked), and whatever new definitions will simply override the ones
provided by lib.sh.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://patch.msgid.link/edd3785a3bd72ffbe1409300989e993ee50ae98b.1731589511.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/lib.sh | 113 -------------------------
 tools/testing/selftests/net/lib.sh            | 115 ++++++++++++++++++++++++++
 2 files changed, 115 insertions(+), 113 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 89c25f72b10c..41dd14c42c48 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -48,7 +48,6 @@ declare -A NETIFS=(
 : "${WAIT_TIME:=5}"
 
 # Whether to pause on, respectively, after a failure and before cleanup.
-: "${PAUSE_ON_FAIL:=no}"
 : "${PAUSE_ON_CLEANUP:=no}"
 
 # Whether to create virtual interfaces, and what netdevice type they should be.
@@ -446,22 +445,6 @@ done
 ##############################################################################
 # Helpers
 
-# Exit status to return at the end. Set in case one of the tests fails.
-EXIT_STATUS=0
-# Per-test return value. Clear at the beginning of each test.
-RET=0
-
-ret_set_ksft_status()
-{
-	local ksft_status=$1; shift
-	local msg=$1; shift
-
-	RET=$(ksft_status_merge $RET $ksft_status)
-	if (( $? )); then
-		retmsg=$msg
-	fi
-}
-
 # Whether FAILs should be interpreted as XFAILs. Internal.
 FAIL_TO_XFAIL=
 
@@ -535,102 +518,6 @@ xfail_on_veth()
 	fi
 }
 
-log_test_result()
-{
-	local test_name=$1; shift
-	local opt_str=$1; shift
-	local result=$1; shift
-	local retmsg=$1; shift
-
-	printf "TEST: %-60s  [%s]\n" "$test_name $opt_str" "$result"
-	if [[ $retmsg ]]; then
-		printf "\t%s\n" "$retmsg"
-	fi
-}
-
-pause_on_fail()
-{
-	if [[ $PAUSE_ON_FAIL == yes ]]; then
-		echo "Hit enter to continue, 'q' to quit"
-		read a
-		[[ $a == q ]] && exit 1
-	fi
-}
-
-handle_test_result_pass()
-{
-	local test_name=$1; shift
-	local opt_str=$1; shift
-
-	log_test_result "$test_name" "$opt_str" " OK "
-}
-
-handle_test_result_fail()
-{
-	local test_name=$1; shift
-	local opt_str=$1; shift
-
-	log_test_result "$test_name" "$opt_str" FAIL "$retmsg"
-	pause_on_fail
-}
-
-handle_test_result_xfail()
-{
-	local test_name=$1; shift
-	local opt_str=$1; shift
-
-	log_test_result "$test_name" "$opt_str" XFAIL "$retmsg"
-	pause_on_fail
-}
-
-handle_test_result_skip()
-{
-	local test_name=$1; shift
-	local opt_str=$1; shift
-
-	log_test_result "$test_name" "$opt_str" SKIP "$retmsg"
-}
-
-log_test()
-{
-	local test_name=$1
-	local opt_str=$2
-
-	if [[ $# -eq 2 ]]; then
-		opt_str="($opt_str)"
-	fi
-
-	if ((RET == ksft_pass)); then
-		handle_test_result_pass "$test_name" "$opt_str"
-	elif ((RET == ksft_xfail)); then
-		handle_test_result_xfail "$test_name" "$opt_str"
-	elif ((RET == ksft_skip)); then
-		handle_test_result_skip "$test_name" "$opt_str"
-	else
-		handle_test_result_fail "$test_name" "$opt_str"
-	fi
-
-	EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET)
-	return $RET
-}
-
-log_test_skip()
-{
-	RET=$ksft_skip retmsg= log_test "$@"
-}
-
-log_test_xfail()
-{
-	RET=$ksft_xfail retmsg= log_test "$@"
-}
-
-log_info()
-{
-	local msg=$1
-
-	echo "INFO: $msg"
-}
-
 not()
 {
 	"$@"
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index c8991cc6bf28..691318b1ec55 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -9,6 +9,9 @@ source "$net_dir/lib/sh/defer.sh"
 
 : "${WAIT_TIMEOUT:=20}"
 
+# Whether to pause on after a failure.
+: "${PAUSE_ON_FAIL:=no}"
+
 BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
 
 # Kselftest framework constants.
@@ -20,6 +23,11 @@ ksft_skip=4
 # namespace list created by setup_ns
 NS_LIST=()
 
+# Exit status to return at the end. Set in case one of the tests fails.
+EXIT_STATUS=0
+# Per-test return value. Clear at the beginning of each test.
+RET=0
+
 ##############################################################################
 # Helpers
 
@@ -236,3 +244,110 @@ tc_rule_handle_stats_get()
 	    | jq ".[] | select(.options.handle == $handle) | \
 		  .options.actions[0].stats$selector"
 }
+
+ret_set_ksft_status()
+{
+	local ksft_status=$1; shift
+	local msg=$1; shift
+
+	RET=$(ksft_status_merge $RET $ksft_status)
+	if (( $? )); then
+		retmsg=$msg
+	fi
+}
+
+log_test_result()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+	local result=$1; shift
+	local retmsg=$1; shift
+
+	printf "TEST: %-60s  [%s]\n" "$test_name $opt_str" "$result"
+	if [[ $retmsg ]]; then
+		printf "\t%s\n" "$retmsg"
+	fi
+}
+
+pause_on_fail()
+{
+	if [[ $PAUSE_ON_FAIL == yes ]]; then
+		echo "Hit enter to continue, 'q' to quit"
+		read a
+		[[ $a == q ]] && exit 1
+	fi
+}
+
+handle_test_result_pass()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" " OK "
+}
+
+handle_test_result_fail()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" FAIL "$retmsg"
+	pause_on_fail
+}
+
+handle_test_result_xfail()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" XFAIL "$retmsg"
+	pause_on_fail
+}
+
+handle_test_result_skip()
+{
+	local test_name=$1; shift
+	local opt_str=$1; shift
+
+	log_test_result "$test_name" "$opt_str" SKIP "$retmsg"
+}
+
+log_test()
+{
+	local test_name=$1
+	local opt_str=$2
+
+	if [[ $# -eq 2 ]]; then
+		opt_str="($opt_str)"
+	fi
+
+	if ((RET == ksft_pass)); then
+		handle_test_result_pass "$test_name" "$opt_str"
+	elif ((RET == ksft_xfail)); then
+		handle_test_result_xfail "$test_name" "$opt_str"
+	elif ((RET == ksft_skip)); then
+		handle_test_result_skip "$test_name" "$opt_str"
+	else
+		handle_test_result_fail "$test_name" "$opt_str"
+	fi
+
+	EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET)
+	return $RET
+}
+
+log_test_skip()
+{
+	RET=$ksft_skip retmsg= log_test "$@"
+}
+
+log_test_xfail()
+{
+	RET=$ksft_xfail retmsg= log_test "$@"
+}
+
+log_info()
+{
+	local msg=$1
+
+	echo "INFO: $msg"
+}
-- 
cgit v1.2.3


From 601d9d70a40a8ccf93f41a153dd4c9aa1db60d57 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 14 Nov 2024 15:09:56 +0100
Subject: selftests: net: lib: Move tests_run from forwarding/lib.sh here

It would be good to use the same mechanism for scheduling and dispatching
general net tests as the many forwarding tests already use. To that end,
move the logging helpers to net/lib.sh so that every net test can use them.

Existing lib.sh users might be using the name themselves. However lib.sh is
always sourced near the top of the file (checked), and whatever new
definition will simply override the one provided by lib.sh.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://patch.msgid.link/a6fc083486493425b2c61185c327845b6ce3233a.1731589511.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/lib.sh | 10 ----------
 tools/testing/selftests/net/lib.sh            | 10 ++++++++++
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 41dd14c42c48..d28dbf27c1f0 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1285,16 +1285,6 @@ matchall_sink_create()
 	   action drop
 }
 
-tests_run()
-{
-	local current_test
-
-	for current_test in ${TESTS:-$ALL_TESTS}; do
-		in_defer_scope \
-			$current_test
-	done
-}
-
 cleanup()
 {
 	pre_cleanup
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 691318b1ec55..4f52b8e48a3a 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -351,3 +351,13 @@ log_info()
 
 	echo "INFO: $msg"
 }
+
+tests_run()
+{
+	local current_test
+
+	for current_test in ${TESTS:-$ALL_TESTS}; do
+		in_defer_scope \
+			$current_test
+	done
+}
-- 
cgit v1.2.3


From af76b4431818cf7a73cf0ec19465ad3b01cdb159 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 14 Nov 2024 15:09:57 +0100
Subject: selftests: net: lib: Move checks from forwarding/lib.sh here

For logging to be useful, something has to set RET and retmsg by calling
ret_set_ksft_status(). There is a suite of functions to that end in
forwarding/lib: check_err, check_fail et.al. Move them to net/lib.sh so
that every net test can use them.

Existing lib.sh users might be using these same names for their functions.
However lib.sh is always sourced near the top of the file (checked), and
whatever new definitions will simply override the ones provided by lib.sh.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://patch.msgid.link/f488a00dc85b8e0c1f3c71476b32b21b5189a847.1731589511.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/lib.sh | 73 ---------------------------
 tools/testing/selftests/net/lib.sh            | 73 +++++++++++++++++++++++++++
 2 files changed, 73 insertions(+), 73 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index d28dbf27c1f0..8625e3c99f55 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -445,79 +445,6 @@ done
 ##############################################################################
 # Helpers
 
-# Whether FAILs should be interpreted as XFAILs. Internal.
-FAIL_TO_XFAIL=
-
-check_err()
-{
-	local err=$1
-	local msg=$2
-
-	if ((err)); then
-		if [[ $FAIL_TO_XFAIL = yes ]]; then
-			ret_set_ksft_status $ksft_xfail "$msg"
-		else
-			ret_set_ksft_status $ksft_fail "$msg"
-		fi
-	fi
-}
-
-check_fail()
-{
-	local err=$1
-	local msg=$2
-
-	check_err $((!err)) "$msg"
-}
-
-check_err_fail()
-{
-	local should_fail=$1; shift
-	local err=$1; shift
-	local what=$1; shift
-
-	if ((should_fail)); then
-		check_fail $err "$what succeeded, but should have failed"
-	else
-		check_err $err "$what failed"
-	fi
-}
-
-xfail()
-{
-	FAIL_TO_XFAIL=yes "$@"
-}
-
-xfail_on_slow()
-{
-	if [[ $KSFT_MACHINE_SLOW = yes ]]; then
-		FAIL_TO_XFAIL=yes "$@"
-	else
-		"$@"
-	fi
-}
-
-omit_on_slow()
-{
-	if [[ $KSFT_MACHINE_SLOW != yes ]]; then
-		"$@"
-	fi
-}
-
-xfail_on_veth()
-{
-	local dev=$1; shift
-	local kind
-
-	kind=$(ip -j -d link show dev $dev |
-			jq -r '.[].linkinfo.info_kind')
-	if [[ $kind = veth ]]; then
-		FAIL_TO_XFAIL=yes "$@"
-	else
-		"$@"
-	fi
-}
-
 not()
 {
 	"$@"
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 4f52b8e48a3a..6bcf5d13879d 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -361,3 +361,76 @@ tests_run()
 			$current_test
 	done
 }
+
+# Whether FAILs should be interpreted as XFAILs. Internal.
+FAIL_TO_XFAIL=
+
+check_err()
+{
+	local err=$1
+	local msg=$2
+
+	if ((err)); then
+		if [[ $FAIL_TO_XFAIL = yes ]]; then
+			ret_set_ksft_status $ksft_xfail "$msg"
+		else
+			ret_set_ksft_status $ksft_fail "$msg"
+		fi
+	fi
+}
+
+check_fail()
+{
+	local err=$1
+	local msg=$2
+
+	check_err $((!err)) "$msg"
+}
+
+check_err_fail()
+{
+	local should_fail=$1; shift
+	local err=$1; shift
+	local what=$1; shift
+
+	if ((should_fail)); then
+		check_fail $err "$what succeeded, but should have failed"
+	else
+		check_err $err "$what failed"
+	fi
+}
+
+xfail()
+{
+	FAIL_TO_XFAIL=yes "$@"
+}
+
+xfail_on_slow()
+{
+	if [[ $KSFT_MACHINE_SLOW = yes ]]; then
+		FAIL_TO_XFAIL=yes "$@"
+	else
+		"$@"
+	fi
+}
+
+omit_on_slow()
+{
+	if [[ $KSFT_MACHINE_SLOW != yes ]]; then
+		"$@"
+	fi
+}
+
+xfail_on_veth()
+{
+	local dev=$1; shift
+	local kind
+
+	kind=$(ip -j -d link show dev $dev |
+			jq -r '.[].linkinfo.info_kind')
+	if [[ $kind = veth ]]; then
+		FAIL_TO_XFAIL=yes "$@"
+	else
+		"$@"
+	fi
+}
-- 
cgit v1.2.3


From 46f6569cf0754e27816403c3701c7070ff281ad0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 14 Nov 2024 15:09:58 +0100
Subject: selftests: net: lib: Add kill_process

A number of selftests run processes in the background and need to kill them
afterwards. Instead for everyone to open-code the kill / wait / redirect
mantra, add a helper in net/lib.sh. Convert existing open-code sites.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Link: https://patch.msgid.link/a9db102067d741c118f0bd93b10c75e2a34665ea.1731589511.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh    |  2 +-
 .../selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh     |  4 ++--
 .../drivers/net/mlxsw/devlink_trap_l3_exceptions.sh          | 12 ++++++------
 .../selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh  |  4 ++--
 .../selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh |  4 ++--
 .../selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh |  4 ++--
 .../drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh      |  4 ++--
 tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh       |  4 ++--
 .../selftests/drivers/net/netdevsim/fib_notifications.sh     |  6 +++---
 tools/testing/selftests/net/drop_monitor_tests.sh            |  2 +-
 tools/testing/selftests/net/fib_tests.sh                     |  8 ++++----
 tools/testing/selftests/net/forwarding/devlink_lib.sh        |  2 +-
 tools/testing/selftests/net/forwarding/lib.sh                |  3 +--
 tools/testing/selftests/net/forwarding/tc_police.sh          |  8 ++++----
 tools/testing/selftests/net/lib.sh                           |  8 ++++++++
 15 files changed, 41 insertions(+), 34 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
index 89b55e946eed..36055279ba92 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
@@ -116,7 +116,7 @@ dev_del_test()
 
 	log_test "Device delete"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index 160891dcb4bc..db5806d189bb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -595,7 +595,7 @@ irif_disabled_test()
 
 	log_test "Ingress RIF disabled"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	ip link set dev $rp1 nomaster
 	__addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
 	ip link del dev br0 type bridge
@@ -645,7 +645,7 @@ erif_disabled_test()
 
 	log_test "Egress RIF disabled"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	__addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
 	ip link del dev br0 type bridge
 	devlink_trap_action_set $trap_name "drop"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
index 190c1b6b5365..5d6d88b600f0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
@@ -202,7 +202,7 @@ mtu_value_is_too_small_test()
 
 	mtu_restore $rp2
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower
 }
 
@@ -235,7 +235,7 @@ __ttl_value_is_too_small_test()
 
 	log_test "TTL value is too small: TTL=$ttl_val"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower
 }
 
@@ -299,7 +299,7 @@ __mc_reverse_path_forwarding_test()
 
 	log_test "Multicast reverse path forwarding: $desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower
 }
 
@@ -347,7 +347,7 @@ __reject_route_test()
 
 	log_test "Reject route: $desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	ip route del unreachable $unreachable
 	tc filter del dev $h1 ingress protocol $proto pref 1 handle 101 flower
 }
@@ -542,7 +542,7 @@ ipv4_lpm_miss_test()
 
 	log_test "LPM miss: IPv4"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	vrf_without_routes_destroy
 }
 
@@ -569,7 +569,7 @@ ipv6_lpm_miss_test()
 
 	log_test "LPM miss: IPv6"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	vrf_without_routes_destroy
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
index e9a82cae8c9a..4ac1dae92d0f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -176,7 +176,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
@@ -207,7 +207,7 @@ no_matching_tunnel_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh
index 878125041fc3..fce885184404 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh
@@ -176,7 +176,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
@@ -207,7 +207,7 @@ no_matching_tunnel_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
index 5f6eb965cfd1..7aca8e5922cf 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
@@ -183,7 +183,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
@@ -253,7 +253,7 @@ corrupted_packet_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh
index f6c16cbb6cf7..4599c331240b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh
@@ -188,7 +188,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
@@ -262,7 +262,7 @@ corrupted_packet_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 83a0210e7544..bc7ea2df49fb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -218,7 +218,7 @@ psample_capture_start()
 
 psample_capture_stop()
 {
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 }
 
 __tc_sample_rate_test()
@@ -499,7 +499,7 @@ tc_sample_md_out_tc_occ_test()
 	backlog=$(tc -j -p -s qdisc show dev $rp2 | jq '.[0]["backlog"]')
 
 	# Kill mausezahn.
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 
 	psample_capture_stop
 
diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh
index 8d91191a098c..9896580c3d85 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh
@@ -94,7 +94,7 @@ route_addition_check()
 	sleep 1
 	$IP route add $route dev dummy1
 	sleep 1
-	kill %% && wait %% &> /dev/null
+	kill_process %%
 
 	route_notify_check $outfile $expected_num_notifications $offload_failed
 	rm -f $outfile
@@ -148,7 +148,7 @@ route_deletion_check()
 	sleep 1
 	$IP route del $route dev dummy1
 	sleep 1
-	kill %% && wait %% &> /dev/null
+	kill_process %%
 
 	route_notify_check $outfile $expected_num_notifications
 	rm -f $outfile
@@ -191,7 +191,7 @@ route_replacement_check()
 	sleep 1
 	$IP route replace $route dev dummy2
 	sleep 1
-	kill %% && wait %% &> /dev/null
+	kill_process %%
 
 	route_notify_check $outfile $expected_num_notifications
 	rm -f $outfile
diff --git a/tools/testing/selftests/net/drop_monitor_tests.sh b/tools/testing/selftests/net/drop_monitor_tests.sh
index 7c4818c971fc..507d0a82f5f0 100755
--- a/tools/testing/selftests/net/drop_monitor_tests.sh
+++ b/tools/testing/selftests/net/drop_monitor_tests.sh
@@ -77,7 +77,7 @@ sw_drops_test()
 
 	rm ${dir}/packets.pcap
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 	timeout 5 dwdump -o sw -w ${dir}/packets.pcap
 	(( $(tshark -r ${dir}/packets.pcap \
 		-Y 'ip.dst == 192.0.2.10' 2> /dev/null | wc -l) == 0))
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 5f3c28fc8624..3ea6f886a210 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -689,7 +689,7 @@ fib6_notify_test()
 
 	log_test $ret 0 "ipv6 route add notify"
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 
 	#rm errors.txt
 
@@ -736,7 +736,7 @@ fib_notify_test()
 
 	log_test $ret 0 "ipv4 route add notify"
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 
 	rm  errors.txt
 
@@ -2328,7 +2328,7 @@ ipv4_mangle_test()
 	$IP route del table 123 172.16.101.0/24 dev veth1
 	$IP rule del pref 100
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 	rm $tmp_file
 
 	route_cleanup
@@ -2386,7 +2386,7 @@ ipv6_mangle_test()
 	$IP -6 route del table 123 2001:db8:101::/64 dev veth1
 	$IP -6 rule del pref 100
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 	rm $tmp_file
 
 	route_cleanup
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 62a05bca1e82..18afa89ebbcc 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -501,7 +501,7 @@ devlink_trap_drop_cleanup()
 	local pref=$1; shift
 	local handle=$1; shift
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower
 }
 
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 8625e3c99f55..7337f398f9cc 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1574,8 +1574,7 @@ stop_traffic()
 {
 	local pid=${1-%%}; shift
 
-	# Suppress noise from killing mausezahn.
-	{ kill $pid && wait $pid; } 2>/dev/null
+	kill_process "$pid"
 }
 
 declare -A cappid
diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh
index 5103f64a71d6..509fdedfcfa1 100755
--- a/tools/testing/selftests/net/forwarding/tc_police.sh
+++ b/tools/testing/selftests/net/forwarding/tc_police.sh
@@ -148,7 +148,7 @@ police_common_test()
 
 	log_test "$test_name"
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
 }
 
@@ -198,7 +198,7 @@ police_shared_common_test()
 
 	log_test "$test_name"
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 }
 
 police_shared_test()
@@ -278,7 +278,7 @@ police_mirror_common_test()
 
 	log_test "$test_name"
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 	tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower
 	tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower
 	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
@@ -320,7 +320,7 @@ police_pps_common_test()
 
 	log_test "$test_name"
 
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 6bcf5d13879d..24f63e45735d 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -434,3 +434,11 @@ xfail_on_veth()
 		"$@"
 	fi
 }
+
+kill_process()
+{
+	local pid=$1; shift
+
+	# Suppress noise from killing the process.
+	{ kill $pid && wait $pid; } 2>/dev/null
+}
-- 
cgit v1.2.3


From 15880bec9bc32ddc8f70f8c551745c2344233372 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 14 Nov 2024 15:09:59 +0100
Subject: selftests: net: fdb_notify: Add a test for FDB notifications

Check that only one notification is produced for various FDB edit
operations.

Regarding the ip_link_add() and ip_link_master() helpers. This pattern of
action plus corresponding defer is bound to come up often, and a dedicated
vocabulary to capture it will be handy. tunnel_create() and vlan_create()
from forwarding/lib.sh are somewhat opaque and perhaps too kitchen-sinky,
so I tried to go in the opposite direction with these ones, and wrapped
only the bare minimum to schedule a corresponding cleanup.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Amit Cohen <amcohen@nvidia.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://patch.msgid.link/910c5880ae6d3b558d6889cbdba2be690c2615c6.1731589511.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile      |  2 +-
 tools/testing/selftests/net/fdb_notify.sh | 96 +++++++++++++++++++++++++++++++
 tools/testing/selftests/net/lib.sh        | 17 ++++++
 3 files changed, 114 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/fdb_notify.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index d323898c466c..3d487b03c4a0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -93,7 +93,7 @@ TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
-TEST_PROGS += fdb_flush.sh
+TEST_PROGS += fdb_flush.sh fdb_notify.sh
 TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh
new file mode 100755
index 000000000000..c03151e7791c
--- /dev/null
+++ b/tools/testing/selftests/net/fdb_notify.sh
@@ -0,0 +1,96 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+ALL_TESTS="
+	test_dup_bridge
+	test_dup_vxlan_self
+	test_dup_vxlan_master
+	test_dup_macvlan_self
+	test_dup_macvlan_master
+"
+
+do_test_dup()
+{
+	local op=$1; shift
+	local what=$1; shift
+	local tmpf
+
+	RET=0
+
+	tmpf=$(mktemp)
+	defer rm "$tmpf"
+
+	defer_scope_push
+		bridge monitor fdb &> "$tmpf" &
+		defer kill_process $!
+
+		sleep 0.5
+		bridge fdb "$op" 00:11:22:33:44:55 vlan 1 "$@"
+		sleep 0.5
+	defer_scope_pop
+
+	local count=$(grep -c -e 00:11:22:33:44:55 $tmpf)
+	((count == 1))
+	check_err $? "Got $count notifications, expected 1"
+
+	log_test "$what $op: Duplicate notifications"
+}
+
+test_dup_bridge()
+{
+	ip_link_add br up type bridge vlan_filtering 1
+	do_test_dup add "bridge" dev br self
+	do_test_dup del "bridge" dev br self
+}
+
+test_dup_vxlan_self()
+{
+	ip_link_add br up type bridge vlan_filtering 1
+	ip_link_add vx up type vxlan id 2000 dstport 4789
+	ip_link_master vx br
+
+	do_test_dup add "vxlan" dev vx self dst 192.0.2.1
+	do_test_dup del "vxlan" dev vx self dst 192.0.2.1
+}
+
+test_dup_vxlan_master()
+{
+	ip_link_add br up type bridge vlan_filtering 1
+	ip_link_add vx up type vxlan id 2000 dstport 4789
+	ip_link_master vx br
+
+	do_test_dup add "vxlan master" dev vx master
+	do_test_dup del "vxlan master" dev vx master
+}
+
+test_dup_macvlan_self()
+{
+	ip_link_add dd up type dummy
+	ip_link_add mv up link dd type macvlan mode passthru
+
+	do_test_dup add "macvlan self" dev mv self
+	do_test_dup del "macvlan self" dev mv self
+}
+
+test_dup_macvlan_master()
+{
+	ip_link_add br up type bridge vlan_filtering 1
+	ip_link_add dd up type dummy
+	ip_link_add mv up link dd type macvlan mode passthru
+	ip_link_master mv br
+
+	do_test_dup add "macvlan master" dev mv self
+	do_test_dup del "macvlan master" dev mv self
+}
+
+cleanup()
+{
+	defer_scopes_cleanup
+}
+
+trap cleanup EXIT
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 24f63e45735d..8994fec1c38f 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -442,3 +442,20 @@ kill_process()
 	# Suppress noise from killing the process.
 	{ kill $pid && wait $pid; } 2>/dev/null
 }
+
+ip_link_add()
+{
+	local name=$1; shift
+
+	ip link add name "$name" "$@"
+	defer ip link del dev "$name"
+}
+
+ip_link_master()
+{
+	local member=$1; shift
+	local master=$1; shift
+
+	ip link set dev "$member" master "$master"
+	defer ip link set dev "$member" nomaster
+}
-- 
cgit v1.2.3


From 357c52ff860b3d047de5d2c605c46dd9a8448821 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 14 Nov 2024 16:32:48 -0800
Subject: selftests: net: netlink-dumps: validation checks

The sanity checks are going to get silently cast to unsigned
and always pass. Cast the sizeof to signed size.

Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20241115003248.733862-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netlink-dumps.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c
index 7ee6dcd334df..84e29b7dffb6 100644
--- a/tools/testing/selftests/net/netlink-dumps.c
+++ b/tools/testing/selftests/net/netlink-dumps.c
@@ -56,10 +56,10 @@ TEST(test_sanity)
 	ASSERT_EQ(n, sizeof(dump_policies));
 
 	n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT);
-	ASSERT_GE(n, sizeof(struct nlmsghdr));
+	ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr));
 
 	n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT);
-	ASSERT_GE(n, sizeof(struct nlmsghdr));
+	ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr));
 
 	close(netlink_sock);
 }
-- 
cgit v1.2.3


From 920efe3e13f7eb5711d4ad8ecc0cced16b1a84cf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 15 Nov 2024 12:12:36 -0800
Subject: selftests: net: add more info to error in bpf_offload

bpf_offload caught a spurious warning in TC recently, but the error
message did not provide enough information to know what the problem
is:

  FAIL: Found 'netdevsim' in command output, leaky extack?

Add the extack to the output:

  FAIL: Unexpected command output, leaky extack? ('netdevsim', 'Warning: Filter with specified priority/protocol not found.')

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/bpf_offload.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py
index 3efe44f6e92a..d10f420e4ef6 100755
--- a/tools/testing/selftests/net/bpf_offload.py
+++ b/tools/testing/selftests/net/bpf_offload.py
@@ -594,8 +594,9 @@ def check_extack_nsim(output, reference, args):
     check_extack(output, "netdevsim: " + reference, args)
 
 def check_no_extack(res, needle):
-    fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
-         "Found '%s' in command output, leaky extack?" % (needle))
+    haystack = (res[1] + res[2]).strip()
+    fail(haystack.count(needle) or haystack.count("Warning:"),
+         "Unexpected command output, leaky extack? ('%s', '%s')" % (needle, haystack))
 
 def check_verifier_log(output, reference):
     lines = output.split("\n")
-- 
cgit v1.2.3


From 0290abc9860917f1ee8b58309c2bbd740a39ee8e Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 17 Nov 2024 22:20:29 +0100
Subject: wireguard: selftests: load nf_conntrack if not present

Some distros may not load nf_conntrack by default, which will cause
subsequent nf_conntrack sets to fail. Load this module if it is not
already loaded.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
[ Jason: add [[ -e ... ]] check so this works in the qemu harness. ]
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Link: https://patch.msgid.link/20241117212030.629159-4-Jason@zx2c4.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/wireguard/netns.sh | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 405ff262ca93..55500f901fbc 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -332,6 +332,7 @@ waitiface $netns1 vethc
 waitiface $netns2 veths
 
 n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
+[[ -e /proc/sys/net/netfilter/nf_conntrack_udp_timeout ]] || modprobe nf_conntrack
 n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout'
 n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream'
 n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1
-- 
cgit v1.2.3


From 0c4d5cb9a1c3583b61df199a51eccebe759e3c18 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <mrpre@163.com>
Date: Mon, 18 Nov 2024 11:09:10 +0800
Subject: selftests/bpf: Add some tests with sockmap SK_PASS

Add a new tests in sockmap_basic.c to test SK_PASS for sockmap

Signed-off-by: Jiayuan Chen <mrpre@163.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20241118030910.36230-3-mrpre@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/bpf/prog_tests/sockmap_basic.c       | 54 ++++++++++++++++++++++
 1 file changed, 54 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 82bfb266741c..a2041f8e32eb 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -501,6 +501,58 @@ out:
 	test_sockmap_pass_prog__destroy(skel);
 }
 
+static void test_sockmap_stream_pass(void)
+{
+	int zero = 0, sent, recvd;
+	int verdict, parser;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_pass_prog *pass = NULL;
+	char snd[256] = "0123456789";
+	char rcv[256] = "0";
+
+	pass = test_sockmap_pass_prog__open_and_load();
+	verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
+	parser = bpf_program__fd(pass->progs.prog_skb_parser);
+	map = bpf_map__fd(pass->maps.sock_map_rx);
+
+	err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
+		goto out;
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+		goto out;
+
+	err = create_pair(AF_INET, SOCK_STREAM, &c, &p);
+	if (err)
+		goto out;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+		goto out_close;
+
+	/*
+	 * as 'prog_skb_parser' return the original skb len and
+	 * 'prog_skb_verdict' return SK_PASS, the kernel will just
+	 * pass it through to original socket 'p'
+	 */
+	sent = xsend(c, snd, sizeof(snd), 0);
+	ASSERT_EQ(sent, sizeof(snd), "xsend(c)");
+
+	recvd = recv_timeout(p, rcv, sizeof(rcv), SOCK_NONBLOCK,
+			     IO_TIMEOUT_SEC);
+	ASSERT_EQ(recvd, sizeof(rcv), "recv_timeout(p)");
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_pass_prog__destroy(pass);
+}
+
 static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 {
 	int err, map, verdict, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
@@ -923,6 +975,8 @@ void test_sockmap_basic(void)
 		test_sockmap_progs_query(BPF_SK_SKB_VERDICT);
 	if (test__start_subtest("sockmap skb_verdict shutdown"))
 		test_sockmap_skb_verdict_shutdown();
+	if (test__start_subtest("sockmap stream parser and verdict pass"))
+		test_sockmap_stream_pass();
 	if (test__start_subtest("sockmap skb_verdict fionread"))
 		test_sockmap_skb_verdict_fionread(true);
 	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
-- 
cgit v1.2.3


From 6116075e18f79698419f2606d9cb34d23198f7e3 Mon Sep 17 00:00:00 2001
From: Mohan Prasad J <mohan.prasad@microchip.com>
Date: Fri, 15 Nov 2024 00:55:18 +0530
Subject: selftests: nic_link_layer: Add link layer selftest for NIC driver

Add selftest file for the link layer tests of a NIC driver.
Test for auto-negotiation is added.
Add LinkConfig class for changing link layer configs.
Selftest makes use of ksft modules and ethtool.
Include selftest file in the Makefile.

Signed-off-by: Mohan Prasad J <mohan.prasad@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/hw/Makefile    |   1 +
 .../selftests/drivers/net/hw/lib/py/__init__.py    |   1 +
 .../selftests/drivers/net/hw/lib/py/linkconfig.py  | 222 +++++++++++++++++++++
 .../selftests/drivers/net/hw/nic_link_layer.py     |  91 +++++++++
 4 files changed, 315 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
 create mode 100644 tools/testing/selftests/drivers/net/hw/nic_link_layer.py

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 1c6a77480923..a87f1f17a10a 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -11,6 +11,7 @@ TEST_PROGS = \
 	hw_stats_l3.sh \
 	hw_stats_l3_gre.sh \
 	loopback.sh \
+	nic_link_layer.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
 	#
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
index b582885786f5..399789a9676a 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -9,6 +9,7 @@ try:
     sys.path.append(KSFT_DIR.as_posix())
     from net.lib.py import *
     from drivers.net.lib.py import *
+    from .linkconfig import LinkConfig
 except ModuleNotFoundError as e:
     ksft_pr("Failed importing `net` library from kernel sources")
     ksft_pr(str(e))
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
new file mode 100644
index 000000000000..db84000fc75b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
@@ -0,0 +1,222 @@
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import cmd, ethtool, ip
+from lib.py import ksft_pr, ksft_eq, KsftSkipEx
+from typing import Optional
+import re
+import time
+import json
+
+#The LinkConfig class is implemented to handle the link layer configurations.
+#Required minimum ethtool version is 6.10
+
+class LinkConfig:
+    """Class for handling the link layer configurations"""
+    def __init__(self, cfg: object) -> None:
+        self.cfg = cfg
+        self.partner_netif = self.get_partner_netif_name()
+
+        """Get the initial link configuration of local interface"""
+        self.common_link_modes = self.get_common_link_modes()
+
+    def get_partner_netif_name(self) -> Optional[str]:
+        partner_netif = None
+        try:
+            if not self.verify_link_up():
+                return None
+            """Get partner interface name"""
+            partner_json_output = ip("addr show", json=True, host=self.cfg.remote)
+            for interface in partner_json_output:
+                for addr in interface.get('addr_info', []):
+                    if addr.get('local') == self.cfg.remote_addr:
+                        partner_netif = interface['ifname']
+                        ksft_pr(f"Partner Interface name: {partner_netif}")
+            if partner_netif is None:
+                ksft_pr("Unable to get the partner interface name")
+        except Exception as e:
+            print(f"Unexpected error occurred while getting partner interface name: {e}")
+        self.partner_netif = partner_netif
+        return partner_netif
+
+    def verify_link_up(self) -> bool:
+        """Verify whether the local interface link is up"""
+        with open(f"/sys/class/net/{self.cfg.ifname}/operstate", "r") as fp:
+            link_state = fp.read().strip()
+
+        if link_state == "down":
+            ksft_pr(f"Link state of interface {self.cfg.ifname} is DOWN")
+            return False
+        else:
+            return True
+
+    def reset_interface(self, local: bool = True, remote: bool = True) -> bool:
+        ksft_pr("Resetting interfaces in local and remote")
+        if remote:
+            if self.verify_link_up():
+                if self.partner_netif is not None:
+                    ifname = self.partner_netif
+                    link_up_cmd = f"ip link set up {ifname}"
+                    link_down_cmd = f"ip link set down {ifname}"
+                    reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
+                    try:
+                        cmd(reset_cmd, host=self.cfg.remote)
+                    except Exception as e:
+                        ksft_pr(f"Unexpected error occurred while resetting remote: {e}")
+                else:
+                    ksft_pr("Partner interface not available")
+        if local:
+            ifname = self.cfg.ifname
+            link_up_cmd = f"ip link set up {ifname}"
+            link_down_cmd = f"ip link set down {ifname}"
+            reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
+            try:
+                cmd(reset_cmd)
+            except Exception as e:
+                ksft_pr(f"Unexpected error occurred while resetting local: {e}")
+        time.sleep(10)
+        if self.verify_link_up() and self.get_ethtool_field("link-detected"):
+            ksft_pr("Local and remote interfaces reset to original state")
+            return True
+        else:
+            ksft_pr("Error occurred after resetting interfaces. Link is DOWN.")
+            return False
+
+    def set_speed_and_duplex(self, speed: str, duplex: str, autoneg: bool = True) -> bool:
+        """Set the speed and duplex state for the interface"""
+        autoneg_state = "on" if autoneg is True else "off"
+        process = None
+        try:
+            process = ethtool(f"--change {self.cfg.ifname} speed {speed} duplex {duplex} autoneg {autoneg_state}")
+        except Exception as e:
+            ksft_pr(f"Unexpected error occurred while setting speed/duplex: {e}")
+        if process is None or process.ret != 0:
+            return False
+        else:
+            ksft_pr(f"Speed: {speed} Mbps, Duplex: {duplex} set for Interface: {self.cfg.ifname}")
+            return True
+
+    def verify_speed_and_duplex(self, expected_speed: str, expected_duplex: str) -> bool:
+        if not self.verify_link_up():
+            return False
+        """Verifying the speed and duplex state for the interface"""
+        with open(f"/sys/class/net/{self.cfg.ifname}/speed", "r") as fp:
+            actual_speed = fp.read().strip()
+        with open(f"/sys/class/net/{self.cfg.ifname}/duplex", "r") as fp:
+            actual_duplex = fp.read().strip()
+
+        ksft_eq(actual_speed, expected_speed)
+        ksft_eq(actual_duplex, expected_duplex)
+        return True
+
+    def set_autonegotiation_state(self, state: str, remote: bool = False) -> bool:
+        common_link_modes = self.common_link_modes
+        speeds, duplex_modes = self.get_speed_duplex_values(self.common_link_modes)
+        speed = speeds[0]
+        duplex = duplex_modes[0]
+        if not speed or not duplex:
+            ksft_pr("No speed or duplex modes found")
+            return False
+
+        speed_duplex_cmd = f"speed {speed} duplex {duplex}" if state == "off" else ""
+        if remote:
+            if not self.verify_link_up():
+                return False
+            """Set the autonegotiation state for the partner"""
+            command = f"-s {self.partner_netif} {speed_duplex_cmd} autoneg {state}"
+            partner_autoneg_change = None
+            """Set autonegotiation state for interface in remote pc"""
+            try:
+                partner_autoneg_change = ethtool(command, host=self.cfg.remote)
+            except Exception as e:
+                ksft_pr(f"Unexpected error occurred while changing auto-neg in remote: {e}")
+            if partner_autoneg_change is None or partner_autoneg_change.ret != 0:
+                ksft_pr(f"Not able to set autoneg parameter for interface {self.partner_netif}.")
+                return False
+            ksft_pr(f"Autoneg set as {state} for {self.partner_netif}")
+        else:
+            """Set the autonegotiation state for the interface"""
+            try:
+                process = ethtool(f"-s {self.cfg.ifname} {speed_duplex_cmd} autoneg {state}")
+                if process.ret != 0:
+                    ksft_pr(f"Not able to set autoneg parameter for interface {self.cfg.ifname}")
+                    return False
+            except Exception as e:
+                ksft_pr(f"Unexpected error occurred while changing auto-neg in local: {e}")
+                return False
+            ksft_pr(f"Autoneg set as {state} for {self.cfg.ifname}")
+        return True
+
+    def check_autoneg_supported(self, remote: bool = False) -> bool:
+        if not remote:
+            local_autoneg = self.get_ethtool_field("supports-auto-negotiation")
+            if local_autoneg is None:
+                ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.cfg.ifname}")
+            """Return autoneg status of the local interface"""
+            return local_autoneg
+        else:
+            if not self.verify_link_up():
+                raise KsftSkipEx("Link is DOWN")
+            """Check remote auto-negotiation support status"""
+            partner_autoneg = False
+            if self.partner_netif is not None:
+                partner_autoneg = self.get_ethtool_field("supports-auto-negotiation", remote=True)
+                if partner_autoneg is None:
+                    ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.partner_netif}")
+            return partner_autoneg
+
+    def get_common_link_modes(self) -> set[str]:
+        common_link_modes = []
+        """Populate common link modes"""
+        link_modes = self.get_ethtool_field("supported-link-modes")
+        partner_link_modes = self.get_ethtool_field("link-partner-advertised-link-modes")
+        if link_modes is None:
+            raise KsftSkipEx(f"Link modes not available for {self.cfg.ifname}")
+        if partner_link_modes is None:
+            raise KsftSkipEx(f"Partner link modes not available for {self.cfg.ifname}")
+        common_link_modes = set(link_modes) and set(partner_link_modes)
+        return common_link_modes
+
+    def get_speed_duplex_values(self, link_modes: list[str]) -> tuple[list[str], list[str]]:
+        speed = []
+        duplex = []
+        """Check the link modes"""
+        for data in link_modes:
+            parts = data.split('/')
+            speed_value = re.match(r'\d+', parts[0])
+            if speed_value:
+                speed.append(speed_value.group())
+            else:
+                ksft_pr(f"No speed value found for interface {self.ifname}")
+                return None, None
+            duplex.append(parts[1].lower())
+        return speed, duplex
+
+    def get_ethtool_field(self, field: str, remote: bool = False) -> Optional[str]:
+        process = None
+        if not remote:
+            """Get the ethtool field value for the local interface"""
+            try:
+                process = ethtool(self.cfg.ifname, json=True)
+            except Exception as e:
+                ksft_pr("Required minimum ethtool version is 6.10")
+                ksft_pr(f"Unexpected error occurred while getting ethtool field in local: {e}")
+                return None
+        else:
+            if not self.verify_link_up():
+                return None
+            """Get the ethtool field value for the remote interface"""
+            self.cfg.require_cmd("ethtool", remote=True)
+            if self.partner_netif is None:
+                ksft_pr(f"Partner interface name is unavailable.")
+                return None
+            try:
+                process = ethtool(self.partner_netif, json=True, host=self.cfg.remote)
+            except Exception as e:
+                ksft_pr("Required minimum ethtool version is 6.10")
+                ksft_pr(f"Unexpected error occurred while getting ethtool field in remote: {e}")
+                return None
+        json_data = process[0]
+        """Check if the field exist in the json data"""
+        if field not in json_data:
+            raise KsftSkipEx(f"Field {field} does not exist in the output of interface {json_data["ifname"]}")
+        return json_data[field]
diff --git a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
new file mode 100644
index 000000000000..d8cc12e84a40
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
@@ -0,0 +1,91 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+#Introduction:
+#This file has basic link layer tests for generic NIC drivers.
+#The test comprises of auto-negotiation, speed and duplex checks.
+#
+#Setup:
+#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
+#
+#        DUT PC                                              Partner PC
+#┌───────────────────────┐                         ┌──────────────────────────┐
+#│                       │                         │                          │
+#│                       │                         │                          │
+#│           ┌───────────┐                         │                          │
+#│           │DUT NIC    │         Eth             │                          │
+#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
+#│           └───────────┘                         │                          │
+#│                       │                         │                          │
+#│                       │                         │                          │
+#└───────────────────────┘                         └──────────────────────────┘
+#
+#Configurations:
+#Required minimum ethtool version is 6.10 (supports json)
+#Default values:
+#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
+
+import time
+import argparse
+from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_eq
+from lib.py import KsftFailEx, KsftSkipEx
+from lib.py import NetDrvEpEnv
+from lib.py import LinkConfig
+
+def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
+    if link_config.partner_netif is None:
+        KsftSkipEx("Partner interface is not available")
+    if not link_config.check_autoneg_supported() or not link_config.check_autoneg_supported(remote=True):
+        KsftSkipEx(f"Auto-negotiation not supported for interface {cfg.ifname} or {link_config.partner_netif}")
+    if not link_config.verify_link_up():
+        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
+
+def verify_autonegotiation(cfg: object, expected_state: str, link_config: LinkConfig) -> None:
+    if not link_config.verify_link_up():
+        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
+    """Verifying the autonegotiation state in partner"""
+    partner_autoneg_output = link_config.get_ethtool_field("auto-negotiation", remote=True)
+    if partner_autoneg_output is None:
+        KsftSkipEx(f"Auto-negotiation state not available for interface {link_config.partner_netif}")
+    partner_autoneg_state = "on" if partner_autoneg_output is True else "off"
+
+    ksft_eq(partner_autoneg_state, expected_state)
+
+    """Verifying the autonegotiation state of local"""
+    autoneg_output = link_config.get_ethtool_field("auto-negotiation")
+    if autoneg_output is None:
+        KsftSkipEx(f"Auto-negotiation state not available for interface {cfg.ifname}")
+    actual_state = "on" if autoneg_output is True else "off"
+
+    ksft_eq(actual_state, expected_state)
+
+    """Verifying the link establishment"""
+    link_available = link_config.get_ethtool_field("link-detected")
+    if link_available is None:
+        KsftSkipEx(f"Link status not available for interface {cfg.ifname}")
+    if link_available != True:
+        raise KsftSkipEx("Link not established at interface {cfg.ifname} after changing auto-negotiation")
+
+def test_autonegotiation(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
+    _pre_test_checks(cfg, link_config)
+    for state in ["off", "on"]:
+        if not link_config.set_autonegotiation_state(state, remote=True):
+            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {link_config.partner_netif}")
+        if not link_config.set_autonegotiation_state(state):
+            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {cfg.ifname}")
+        time.sleep(time_delay)
+        verify_autonegotiation(cfg, state, link_config)
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Run basic link layer tests for NIC driver")
+    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
+    args = parser.parse_args()
+    time_delay = args.time_delay
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        link_config = LinkConfig(cfg)
+        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, time_delay,))
+        link_config.reset_interface()
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
-- 
cgit v1.2.3


From c087dc54394b3f8a2950007fb17a8937a38fe73a Mon Sep 17 00:00:00 2001
From: Mohan Prasad J <mohan.prasad@microchip.com>
Date: Fri, 15 Nov 2024 00:55:19 +0530
Subject: selftests: nic_link_layer: Add selftest case for speed and duplex
 states

Add selftest case for testing the speed and duplex state of
local NIC driver and the partner based on the supported
link modes obtained from the ethtool. Speed and duplex states
are varied and verified using ethtool.

Signed-off-by: Mohan Prasad J <mohan.prasad@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/hw/nic_link_layer.py     | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
index d8cc12e84a40..efd921180532 100644
--- a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
+++ b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
@@ -76,6 +76,28 @@ def test_autonegotiation(cfg: object, link_config: LinkConfig, time_delay: int)
         time.sleep(time_delay)
         verify_autonegotiation(cfg, state, link_config)
 
+def test_network_speed(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
+    _pre_test_checks(cfg, link_config)
+    common_link_modes = link_config.common_link_modes
+    if not common_link_modes:
+        KsftSkipEx("No common link modes exist")
+    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
+
+    if speeds and duplex_modes and len(speeds) == len(duplex_modes):
+        for idx in range(len(speeds)):
+            speed = speeds[idx]
+            duplex = duplex_modes[idx]
+            if not link_config.set_speed_and_duplex(speed, duplex):
+                raise KsftFailEx(f"Unable to set speed and duplex parameters for {cfg.ifname}")
+            time.sleep(time_delay)
+            if not link_config.verify_speed_and_duplex(speed, duplex):
+                raise KsftSkipEx(f"Error occurred while verifying speed and duplex states for interface {cfg.ifname}")
+    else:
+        if not speeds or not duplex_modes:
+            KsftSkipEx(f"No supported speeds or duplex modes found for interface {cfg.ifname}")
+        else:
+            KsftSkipEx("Mismatch in the number of speeds and duplex modes")
+
 def main() -> None:
     parser = argparse.ArgumentParser(description="Run basic link layer tests for NIC driver")
     parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-- 
cgit v1.2.3


From fbbf93556f0c1ad9b53fd1ec8fd2e67b2debb740 Mon Sep 17 00:00:00 2001
From: Mohan Prasad J <mohan.prasad@microchip.com>
Date: Fri, 15 Nov 2024 00:55:20 +0530
Subject: selftests: nic_performance: Add selftest for performance of NIC
 driver

Add selftest case to check the send and receive throughput.
Supported link modes between local NIC driver and partner
are varied. Then send and receive throughput is captured
and verified. Test uses iperf3 tool.
Add iperf3 server/client function in GenerateTraffic class.

Signed-off-by: Mohan Prasad J <mohan.prasad@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/hw/Makefile    |   1 +
 .../selftests/drivers/net/hw/nic_performance.py    | 137 +++++++++++++++++++++
 tools/testing/selftests/drivers/net/lib/py/load.py |  20 ++-
 3 files changed, 157 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/drivers/net/hw/nic_performance.py

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index a87f1f17a10a..21ba64ce1e34 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -12,6 +12,7 @@ TEST_PROGS = \
 	hw_stats_l3_gre.sh \
 	loopback.sh \
 	nic_link_layer.py \
+	nic_performance.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
 	#
diff --git a/tools/testing/selftests/drivers/net/hw/nic_performance.py b/tools/testing/selftests/drivers/net/hw/nic_performance.py
new file mode 100644
index 000000000000..201403b76ea3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/nic_performance.py
@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+#Introduction:
+#This file has basic performance test for generic NIC drivers.
+#The test comprises of throughput check for TCP and UDP streams.
+#
+#Setup:
+#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
+#
+#        DUT PC                                              Partner PC
+#┌───────────────────────┐                         ┌──────────────────────────┐
+#│                       │                         │                          │
+#│                       │                         │                          │
+#│           ┌───────────┐                         │                          │
+#│           │DUT NIC    │         Eth             │                          │
+#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
+#│           └───────────┘                         │                          │
+#│                       │                         │                          │
+#│                       │                         │                          │
+#└───────────────────────┘                         └──────────────────────────┘
+#
+#Configurations:
+#To prevent interruptions, Add ethtool, ip to the sudoers list in remote PC and get the ssh key from remote.
+#Required minimum ethtool version is 6.10
+#Change the below configuration based on your hw needs.
+# """Default values"""
+#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
+#test_duration = 10  #performance test duration for the throughput check, in seconds.
+#send_throughput_threshold = 80 #percentage of send throughput required to pass the check
+#receive_throughput_threshold = 50 #percentage of receive throughput required to pass the check
+
+import time
+import json
+import argparse
+from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_true
+from lib.py import KsftFailEx, KsftSkipEx, GenerateTraffic
+from lib.py import NetDrvEpEnv, bkg, wait_port_listen
+from lib.py import cmd
+from lib.py import LinkConfig
+
+class TestConfig:
+    def __init__(self, time_delay: int, test_duration: int, send_throughput_threshold: int, receive_throughput_threshold: int) -> None:
+        self.time_delay = time_delay
+        self.test_duration = test_duration
+        self.send_throughput_threshold = send_throughput_threshold
+        self.receive_throughput_threshold = receive_throughput_threshold
+
+def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
+    if not link_config.verify_link_up():
+        KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
+    common_link_modes = link_config.common_link_modes
+    if common_link_modes is None:
+        KsftSkipEx("No common link modes found")
+    if link_config.partner_netif == None:
+        KsftSkipEx("Partner interface is not available")
+    if link_config.check_autoneg_supported():
+        KsftSkipEx("Auto-negotiation not supported by local")
+    if link_config.check_autoneg_supported(remote=True):
+        KsftSkipEx("Auto-negotiation not supported by remote")
+    cfg.require_cmd("iperf3", remote=True)
+
+def check_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, protocol: str, traffic: GenerateTraffic) -> None:
+    common_link_modes = link_config.common_link_modes
+    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
+    """Test duration in seconds"""
+    duration = test_config.test_duration
+
+    ksft_pr(f"{protocol} test")
+    test_type = "-u" if protocol == "UDP" else ""
+
+    send_throughput = []
+    receive_throughput = []
+    for idx in range(0, len(speeds)):
+        if link_config.set_speed_and_duplex(speeds[idx], duplex_modes[idx]) == False:
+            raise KsftFailEx(f"Not able to set speed and duplex parameters for {cfg.ifname}")
+        time.sleep(test_config.time_delay)
+        if not link_config.verify_link_up():
+            raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
+
+        send_command=f"{test_type} -b 0 -t {duration} --json"
+        receive_command=f"{test_type} -b 0 -t {duration} --reverse --json"
+
+        send_result = traffic.run_remote_test(cfg, command=send_command)
+        if send_result.ret != 0:
+            raise KsftSkipEx("Error occurred during data transmit: {send_result.stdout}")
+
+        send_output = send_result.stdout
+        send_data = json.loads(send_output)
+
+        """Convert throughput to Mbps"""
+        send_throughput.append(round(send_data['end']['sum_sent']['bits_per_second'] / 1e6, 2))
+        ksft_pr(f"{protocol}: Send throughput: {send_throughput[idx]} Mbps")
+
+        receive_result = traffic.run_remote_test(cfg, command=receive_command)
+        if receive_result.ret != 0:
+            raise KsftSkipEx("Error occurred during data receive: {receive_result.stdout}")
+
+        receive_output = receive_result.stdout
+        receive_data = json.loads(receive_output)
+
+        """Convert throughput to Mbps"""
+        receive_throughput.append(round(receive_data['end']['sum_received']['bits_per_second'] / 1e6, 2))
+        ksft_pr(f"{protocol}: Receive throughput: {receive_throughput[idx]} Mbps")
+
+    """Check whether throughput is not below the threshold (default values set at start)"""
+    for idx in range(0, len(speeds)):
+        send_threshold = float(speeds[idx]) * float(test_config.send_throughput_threshold / 100)
+        receive_threshold = float(speeds[idx]) * float(test_config.receive_throughput_threshold / 100)
+        ksft_true(send_throughput[idx] >= send_threshold, f"{protocol}: Send throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
+        ksft_true(receive_throughput[idx] >= receive_threshold, f"{protocol}: Receive throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
+
+def test_tcp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
+    _pre_test_checks(cfg, link_config)
+    check_throughput(cfg, link_config, test_config, 'TCP', traffic)
+
+def test_udp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
+    _pre_test_checks(cfg, link_config)
+    check_throughput(cfg, link_config, test_config, 'UDP', traffic)
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Run basic performance test for NIC driver")
+    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
+    parser.add_argument('--test-duration', type=int, default=10, help='Performance test duration for the throughput check, in seconds. Default is 10 seconds.')
+    parser.add_argument('--stt', type=int, default=80, help='Send throughput Threshold: Percentage of send throughput upon actual throughput required to pass the throughput check (in percentage). Default is 80.')
+    parser.add_argument('--rtt', type=int, default=50, help='Receive throughput Threshold: Percentage of receive throughput upon actual throughput required to pass the throughput check (in percentage). Default is 50.')
+    args=parser.parse_args()
+    test_config = TestConfig(args.time_delay, args.test_duration, args.stt, args.rtt)
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        traffic = GenerateTraffic(cfg)
+        link_config = LinkConfig(cfg)
+        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, test_config, traffic,  ))
+        link_config.reset_interface()
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index d9c10613ae67..da5af2c680fa 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -2,7 +2,7 @@
 
 import time
 
-from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
+from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen, bkg
 
 class GenerateTraffic:
     def __init__(self, env, port=None):
@@ -23,6 +23,24 @@ class GenerateTraffic:
             self.stop(verbose=True)
             raise Exception("iperf3 traffic did not ramp up")
 
+    def run_remote_test(self, env: object, port=None, command=None):
+        if port is None:
+            port = rand_port()
+        try:
+            server_cmd = f"iperf3 -s 1 -p {port} --one-off"
+            with bkg(server_cmd, host=env.remote):
+                #iperf3 opens TCP connection as default in server
+                #-u to be specified in client command for UDP
+                wait_port_listen(port, host=env.remote)
+        except Exception as e:
+            raise Exception(f"Unexpected error occurred while running server command: {e}")
+        try:
+            client_cmd = f"iperf3 -c {env.remote_addr} -p {port} {command}"
+            proc = cmd(client_cmd)
+            return proc
+        except Exception as e:
+            raise Exception(f"Unexpected error occurred while running client command: {e}")
+
     def _wait_pkts(self, pkt_cnt=None, pps=None):
         """
         Wait until we've seen pkt_cnt or until traffic ramps up to pps.
-- 
cgit v1.2.3


From 96ed62ea02984f14b6d4f2e4aed327d803875b7a Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 19 Nov 2024 11:30:11 +0800
Subject: mm: page_frag: fix a compile error when kernel is not compiled

page_frag test module is an out of tree module, but built
using KDIR as the main kernel tree, the mm test suite is
just getting skipped if newly added page_frag test module
fails to compile due to kernel not yet compiled.

Fix the above problem by ensuring both kernel is built first
and a newer kernel which has page_frag_cache.h is used.

CC: Andrew Morton <akpm@linux-foundation.org>
CC: Alexander Duyck <alexanderduyck@fb.com>
CC: Linux-MM <linux-mm@kvack.org>
Fixes: 7fef0dec415c ("mm: page_frag: add a test module for page_frag")
Fixes: 65941f10caf2 ("mm: move the page fragment allocator from page_alloc into its own file")
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20241119033012.257525-1-linyunsheng@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/mm/Makefile           | 18 ++++++++++++++++++
 tools/testing/selftests/mm/page_frag/Makefile |  2 +-
 2 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index acec529baaca..04e04733fc8a 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -36,7 +36,16 @@ MAKEFLAGS += --no-builtin-rules
 CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS = -lrt -lpthread -lm
 
+KDIR ?= /lib/modules/$(shell uname -r)/build
+ifneq (,$(wildcard $(KDIR)/Module.symvers))
+ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h))
 TEST_GEN_MODS_DIR := page_frag
+else
+PAGE_FRAG_WARNING = "missing page_frag_cache.h, please use a newer kernel"
+endif
+else
+PAGE_FRAG_WARNING = "missing Module.symvers, please have the kernel built first"
+endif
 
 TEST_GEN_FILES = cow
 TEST_GEN_FILES += compaction_test
@@ -214,3 +223,12 @@ warn_missing_liburing:
 	echo "Warning: missing liburing support. Some tests will be skipped." ; \
 	echo
 endif
+
+ifneq ($(PAGE_FRAG_WARNING),)
+all: warn_missing_page_frag
+
+warn_missing_page_frag:
+	@echo ; \
+	echo "Warning: $(PAGE_FRAG_WARNING). page_frag test will be skipped." ; \
+	echo
+endif
diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile
index 58dda74d50a3..8c8bb39ffa28 100644
--- a/tools/testing/selftests/mm/page_frag/Makefile
+++ b/tools/testing/selftests/mm/page_frag/Makefile
@@ -1,5 +1,5 @@
 PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
-KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..)
+KDIR ?= /lib/modules/$(shell uname -r)/build
 
 ifeq ($(V),1)
 Q =
-- 
cgit v1.2.3