On Mon, Jul 28, 2025 at 09:43:45AM +0000, Mahe Tardy wrote:
> This test opens a server and client, attach a cgroup_skb program on
> egress and calls the icmp_send_unreach function from the client egress
> so that an ICMP unreach control message is sent back to the client.
> It then fetches the message from the error queue to confirm the correct
> ICMP unreach code has been sent.
>
> Note that the BPF program returns SK_PASS to let the connection being
> established to finish the test cases quicker. Otherwise, you have to
> wait for the TCP three-way handshake to timeout in the kernel and
> retrieve the errno translated from the unreach code set by the ICMP
> control message.
>
> Signed-off-by: Mahe Tardy <mahe.tardy@xxxxxxxxx>
> ---
> .../bpf/prog_tests/icmp_send_unreach_kfunc.c | 99 +++++++++++++++++++
> .../selftests/bpf/progs/icmp_send_unreach.c | 36 +++++++
> 2 files changed, 135 insertions(+)
> create mode 100644 tools/testing/selftests/bpf/prog_tests/icmp_send_unreach_kfunc.c
> create mode 100644 tools/testing/selftests/bpf/progs/icmp_send_unreach.c
>
> diff --git a/tools/testing/selftests/bpf/prog_tests/icmp_send_unreach_kfunc.c b/tools/testing/selftests/bpf/prog_tests/icmp_send_unreach_kfunc.c
> new file mode 100644
> index 000000000000..414c1ed8ced3
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/prog_tests/icmp_send_unreach_kfunc.c
> @@ -0,0 +1,99 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <test_progs.h>
> +#include <network_helpers.h>
> +#include <linux/errqueue.h>
> +#include "icmp_send_unreach.skel.h"
> +
> +#define TIMEOUT_MS 1000
> +#define SRV_PORT 54321
> +
> +#define ICMP_DEST_UNREACH 3
> +
> +#define ICMP_FRAG_NEEDED 4
> +#define NR_ICMP_UNREACH 15
small nit: Any reason why ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, and
NR_ICMP_UNREACH are redefined here? I think you should just be able to
#include <linux/icmp.h> this at the top to avoid redefining these.
> +
> +static void read_icmp_errqueue(int sockfd, int expected_code)
> +{
> + ssize_t n;
> + struct sock_extended_err *sock_err;
> + struct cmsghdr *cm;
> + char ctrl_buf[512];
> + struct msghdr msg = {
> + .msg_control = ctrl_buf,
> + .msg_controllen = sizeof(ctrl_buf),
> + };
> +
> + n = recvmsg(sockfd, &msg, MSG_ERRQUEUE);
> + if (!ASSERT_GE(n, 0, "recvmsg_errqueue"))
> + return;
> +
> + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
> + if (!ASSERT_EQ(cm->cmsg_level, IPPROTO_IP, "cmsg_type") ||
> + !ASSERT_EQ(cm->cmsg_type, IP_RECVERR, "cmsg_level"))
> + continue;
> +
> + sock_err = (struct sock_extended_err *)CMSG_DATA(cm);
> +
> + if (!ASSERT_EQ(sock_err->ee_origin, SO_EE_ORIGIN_ICMP,
> + "sock_err_origin_icmp"))
> + return;
> + if (!ASSERT_EQ(sock_err->ee_type, ICMP_DEST_UNREACH,
> + "sock_err_type_dest_unreach"))
> + return;
> + ASSERT_EQ(sock_err->ee_code, expected_code, "sock_err_code");
> + }
> +}
> +
> +void test_icmp_send_unreach_kfunc(void)
> +{
> + struct icmp_send_unreach *skel;
> + int cgroup_fd = -1, client_fd = 1, srv_fd = -1;
> + int *code;
> +
> + skel = icmp_send_unreach__open_and_load();
> + if (!ASSERT_OK_PTR(skel, "skel_open"))
> + goto cleanup;
> +
> + cgroup_fd = test__join_cgroup("/icmp_send_unreach_cgroup");
> + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
> + goto cleanup;
> +
> + skel->links.egress =
> + bpf_program__attach_cgroup(skel->progs.egress, cgroup_fd);
> + if (!ASSERT_OK_PTR(skel->links.egress, "prog_attach_cgroup"))
> + goto cleanup;
> +
> + code = &skel->bss->unreach_code;
> +
> + for (*code = 0; *code <= NR_ICMP_UNREACH; (*code)++) {
> + // The TCP stack reacts differently when asking for
> + // fragmentation, let's ignore it for now
> + if (*code == ICMP_FRAG_NEEDED)
> + continue;
> +
> + skel->bss->kfunc_ret = -1;
> +
> + srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1",
> + SRV_PORT, TIMEOUT_MS);
> + if (!ASSERT_GE(srv_fd, 0, "start_server"))
> + goto for_cleanup;
> +
> + client_fd = socket(AF_INET, SOCK_STREAM, 0);
> + ASSERT_GE(client_fd, 0, "client_socket");
> +
> + client_fd = connect_to_fd(srv_fd, 0);
> + if (!ASSERT_GE(client_fd, 0, "client_connect"))
> + goto for_cleanup;
> +
> + read_icmp_errqueue(client_fd, *code);
> +
> + ASSERT_EQ(skel->bss->kfunc_ret, SK_DROP, "kfunc_ret");
It might be worth testing that the kfunc returns -EINVAL when the code
is outside the accepted range as well for completeness.
> +for_cleanup:
> + close(client_fd);
> + close(srv_fd);
> + }
> +
> +cleanup:
> + icmp_send_unreach__destroy(skel);
> + close(cgroup_fd);
> +}
> diff --git a/tools/testing/selftests/bpf/progs/icmp_send_unreach.c b/tools/testing/selftests/bpf/progs/icmp_send_unreach.c
> new file mode 100644
> index 000000000000..15783e5d1d65
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/icmp_send_unreach.c
> @@ -0,0 +1,36 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include "vmlinux.h"
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_endian.h>
> +
> +char LICENSE[] SEC("license") = "Dual BSD/GPL";
> +
> +int unreach_code = 0;
> +int kfunc_ret = 0;
> +
> +#define SERVER_PORT 54321
> +#define SERVER_IP 0x7F000001
> +
> +SEC("cgroup_skb/egress")
> +int egress(struct __sk_buff *skb)
> +{
> + void *data = (void *)(long)skb->data;
> + void *data_end = (void *)(long)skb->data_end;
> + struct iphdr *iph;
> + struct tcphdr *tcph;
> +
> + iph = data;
> + if ((void *)(iph + 1) > data_end || iph->version != 4 ||
> + iph->protocol != IPPROTO_TCP || iph->daddr != bpf_htonl(SERVER_IP))
> + return SK_PASS;
> +
> + tcph = (void *)iph + iph->ihl * 4;
> + if ((void *)(tcph + 1) > data_end ||
> + tcph->dest != bpf_htons(SERVER_PORT))
> + return SK_PASS;
> +
> + kfunc_ret = bpf_icmp_send_unreach(skb, unreach_code);
> +
> + /* returns SK_PASS to execute the test case quicker */
> + return SK_PASS;
> +}
> --
> 2.34.1
>
Jordan
