diff mbox series

[bpf-next,v6,6/6] selftests/bpf: add bpf_icmp_send recursion test

Message ID 20260518122842.218522-7-mahe.tardy@gmail.com
State Handled Elsewhere, archived
Headers show
Series bpf: add icmp_send kfunc | expand

Commit Message

Mahe Tardy May 18, 2026, 12:28 p.m. UTC
This test is similar to test_icmp_send_unreach but checks that, in case
of recursion, meaning that the BPF program calling the kfunc was
re-triggered by the icmp_send done by the kfunc, the kfunc will stop
early and return -EBUSY.

The test attaches to the root cgroup to ensure the ICMP packet generated
by the kfunc re-triggers the BPF program. Since it's attached only for
this recursion test, it should not disrupt the whole network.

Signed-off-by: Mahe Tardy <mahe.tardy@gmail.com>
---
 .../bpf/prog_tests/icmp_send_kfunc.c          | 40 +++++++++++++++++++
 tools/testing/selftests/bpf/progs/icmp_send.c | 31 ++++++++++++++
 2 files changed, 71 insertions(+)

--
2.34.1

Comments

bot+bpf-ci@kernel.org May 18, 2026, 1:07 p.m. UTC | #1
> diff --git a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
> index d0ac0502f6df..a9e9806877cf 100644
> --- a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
> +++ b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c

[ ... ]

> diff --git a/tools/testing/selftests/bpf/progs/icmp_send.c b/tools/testing/selftests/bpf/progs/icmp_send.c
> index 6e1ba539eeb0..7830334b747a 100644
> --- a/tools/testing/selftests/bpf/progs/icmp_send.c
> +++ b/tools/testing/selftests/bpf/progs/icmp_send.c
> @@ -13,6 +13,9 @@ int unreach_type = 0;
>  int unreach_code = 0;
>  int kfunc_ret = -1;
>
> +unsigned int rec_count = 0;
> +int rec_kfunc_rets[] = { -1, -1 };
> +
>  SEC("cgroup_skb/egress")
>  int egress(struct __sk_buff *skb)
>  {
> @@ -65,4 +68,32 @@ int egress(struct __sk_buff *skb)
>  	return SK_DROP;
>  }
>
> +SEC("cgroup_skb/egress")
> +int recursion(struct __sk_buff *skb)
> +{
> +	void *data = (void *)(long)skb->data;
> +	void *data_end = (void *)(long)skb->data_end;
> +	struct iphdr *iph;
> +	int ret;
> +
> +	iph = data;
> +	if ((void *)(iph + 1) > data_end || iph->version != 4)
> +		return SK_PASS;
> +
> +	/* This call will provoke a recursion: the ICMP packet generated by the
> +	 * kfunc will re-trigger this program since we are in the root cgroup in
> +	 * which the kernel ICMP socket belongs. However when re-entering the
> +	 * kfunc, it should return EBUSY.
> +	 */
> +	ret = bpf_icmp_send(skb, unreach_type, unreach_code);
> +	rec_kfunc_rets[rec_count & 1] = ret;

Will this program affect background traffic when running on the system?

The recursion program is attached to the root cgroup and intercepts all
IPv4 traffic. While v5 changed SK_DROP to SK_PASS to avoid blocking
traffic, the program still calls bpf_icmp_send() on every IPv4 packet
without filtering for test-specific traffic.

This means background IPv4 traffic (SSH, DNS, other tests) will trigger
ICMP Destination Unreachable messages, potentially causing network
disruption and test races on rec_kfunc_rets and rec_count.

The egress program demonstrates proper filtering by checking for TCP,
SERVER_IP, and server_port:

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 ipv6hdr *ip6h;
	struct tcphdr *tcph;

	iph = data;
	if ((void *)(iph + 1) > data_end || iph->version != 4)
		return SK_PASS;

	if (iph->protocol != IPPROTO_TCP)
		return SK_PASS;

	if (bpf_ntohs(iph->daddr) != SERVER_IP)
		return SK_PASS;

	tcph = (struct tcphdr *)((void *)iph + sizeof(*iph));
	if ((void *)(tcph + 1) > data_end)
		return SK_PASS;

	if (tcph->dest != server_port)
		return SK_PASS;
	...
}

Could the recursion program use similar filtering to explicitly check for
the test's traffic?

> +	__sync_fetch_and_add(&rec_count, 1);
> +
> +	/* Let the first ICMP error message pass */
> +	if (iph->protocol == IPPROTO_ICMP)
> +		return SK_PASS;
> +
> +	return SK_DROP;
> +}
> +
>  char LICENSE[] SEC("license") = "Dual BSD/GPL";


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/26034287312
Mahe Tardy May 18, 2026, 2:39 p.m. UTC | #2
On Mon, May 18, 2026 at 01:07:53PM +0000, bot+bpf-ci@kernel.org wrote:
> > diff --git a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
> > index d0ac0502f6df..a9e9806877cf 100644
> > --- a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
> > +++ b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
> 
> [ ... ]
> 
> > diff --git a/tools/testing/selftests/bpf/progs/icmp_send.c b/tools/testing/selftests/bpf/progs/icmp_send.c
> > index 6e1ba539eeb0..7830334b747a 100644
> > --- a/tools/testing/selftests/bpf/progs/icmp_send.c
> > +++ b/tools/testing/selftests/bpf/progs/icmp_send.c
> > @@ -13,6 +13,9 @@ int unreach_type = 0;
> >  int unreach_code = 0;
> >  int kfunc_ret = -1;
> >
> > +unsigned int rec_count = 0;
> > +int rec_kfunc_rets[] = { -1, -1 };
> > +
> >  SEC("cgroup_skb/egress")
> >  int egress(struct __sk_buff *skb)
> >  {
> > @@ -65,4 +68,32 @@ int egress(struct __sk_buff *skb)
> >  	return SK_DROP;
> >  }
> >
> > +SEC("cgroup_skb/egress")
> > +int recursion(struct __sk_buff *skb)
> > +{
> > +	void *data = (void *)(long)skb->data;
> > +	void *data_end = (void *)(long)skb->data_end;
> > +	struct iphdr *iph;
> > +	int ret;
> > +
> > +	iph = data;
> > +	if ((void *)(iph + 1) > data_end || iph->version != 4)
> > +		return SK_PASS;
> > +
> > +	/* This call will provoke a recursion: the ICMP packet generated by the
> > +	 * kfunc will re-trigger this program since we are in the root cgroup in
> > +	 * which the kernel ICMP socket belongs. However when re-entering the
> > +	 * kfunc, it should return EBUSY.
> > +	 */
> > +	ret = bpf_icmp_send(skb, unreach_type, unreach_code);
> > +	rec_kfunc_rets[rec_count & 1] = ret;
> 
> Will this program affect background traffic when running on the system?
> 
> The recursion program is attached to the root cgroup and intercepts all
> IPv4 traffic. While v5 changed SK_DROP to SK_PASS to avoid blocking
> traffic, the program still calls bpf_icmp_send() on every IPv4 packet
> without filtering for test-specific traffic.
> 
> This means background IPv4 traffic (SSH, DNS, other tests) will trigger
> ICMP Destination Unreachable messages, potentially causing network
> disruption and test races on rec_kfunc_rets and rec_count.
> 
> The egress program demonstrates proper filtering by checking for TCP,
> SERVER_IP, and server_port:
> 
> 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 ipv6hdr *ip6h;
> 	struct tcphdr *tcph;
> 
> 	iph = data;
> 	if ((void *)(iph + 1) > data_end || iph->version != 4)
> 		return SK_PASS;
> 
> 	if (iph->protocol != IPPROTO_TCP)
> 		return SK_PASS;
> 
> 	if (bpf_ntohs(iph->daddr) != SERVER_IP)
> 		return SK_PASS;
> 
> 	tcph = (struct tcphdr *)((void *)iph + sizeof(*iph));
> 	if ((void *)(tcph + 1) > data_end)
> 		return SK_PASS;
> 
> 	if (tcph->dest != server_port)
> 		return SK_PASS;
> 	...
> }
> 
> Could the recursion program use similar filtering to explicitly check for
> the test's traffic?

I could restrict a little bit more by ignoring all traffic that is
non-TCP for the dest port or non-ICMP but not sure this is actually
needed. E.g. writing something like this before bpf_icmp_send:

if (iph->daddr != bpf_htonl(SERVER_IP))
	return SK_PASS;

if (iph->protocol == IPPROTO_TCP) {
	tcph = (void *)iph + iph->ihl * 4;
	if ((void *)(tcph + 1) > data_end ||
	    tcph->dest != bpf_htons(server_port))
		return SK_PASS;
} else if (iph->protocol != IPPROTO_ICMP) {
	return SK_PASS;
}

But not sure this is strictly needed.

> 
> > +	__sync_fetch_and_add(&rec_count, 1);
> > +
> > +	/* Let the first ICMP error message pass */
> > +	if (iph->protocol == IPPROTO_ICMP)
> > +		return SK_PASS;
> > +
> > +	return SK_DROP;
> > +}
> > +
> >  char LICENSE[] SEC("license") = "Dual BSD/GPL";
> 
> 
> ---
> AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
> See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
> 
> CI run summary: https://github.com/kernel-patches/bpf/actions/runs/26034287312
diff mbox series

Patch

diff --git a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
index d0ac0502f6df..a9e9806877cf 100644
--- a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
@@ -1,6 +1,7 @@ 
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include <network_helpers.h>
+#include <cgroup_helpers.h>
 #include <linux/errqueue.h>
 #include <poll.h>
 #include "icmp_send.skel.h"
@@ -10,6 +11,7 @@ 
 #define ICMP_DEST_UNREACH 3
 #define ICMPV6_DEST_UNREACH 1

+#define ICMP_HOST_UNREACH 1
 #define ICMP_FRAG_NEEDED 4
 #define NR_ICMP_UNREACH 15
 #define ICMPV6_REJECT_ROUTE 6
@@ -176,3 +178,41 @@  void test_icmp_send_unreach(void)
 	icmp_send__destroy(skel);
 	close(cgroup_fd);
 }
+
+void test_icmp_send_unreach_recursion(void)
+{
+	struct icmp_send *skel;
+	int cgroup_fd = -1;
+
+	skel = icmp_send__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	if (setup_cgroup_environment()) {
+		fprintf(stderr, "Failed to setup cgroup environment\n");
+		goto cleanup;
+	}
+
+	cgroup_fd = get_root_cgroup();
+	if (!ASSERT_GE(cgroup_fd, 0, "get_root_cgroup"))
+		goto cleanup;
+
+	skel->links.recursion =
+		bpf_program__attach_cgroup(skel->progs.recursion, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.recursion, "prog_attach_cgroup"))
+		goto cleanup;
+
+	trigger_prog_read_icmp_errqueue(skel, ICMP_HOST_UNREACH, AF_INET, "127.0.0.1");
+
+	/* Because there's recursion involved, the first call will return at
+	 * index 1 since it will return the second, and the second call will
+	 * return at index 0 since it will return the first.
+	 */
+	ASSERT_EQ(skel->data->rec_kfunc_rets[0], -EBUSY, "kfunc_rets[0]");
+	ASSERT_EQ(skel->data->rec_kfunc_rets[1], 0, "kfunc_rets[1]");
+
+cleanup:
+	cleanup_cgroup_environment();
+	icmp_send__destroy(skel);
+	close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/progs/icmp_send.c b/tools/testing/selftests/bpf/progs/icmp_send.c
index 6e1ba539eeb0..7830334b747a 100644
--- a/tools/testing/selftests/bpf/progs/icmp_send.c
+++ b/tools/testing/selftests/bpf/progs/icmp_send.c
@@ -13,6 +13,9 @@  int unreach_type = 0;
 int unreach_code = 0;
 int kfunc_ret = -1;

+unsigned int rec_count = 0;
+int rec_kfunc_rets[] = { -1, -1 };
+
 SEC("cgroup_skb/egress")
 int egress(struct __sk_buff *skb)
 {
@@ -65,4 +68,32 @@  int egress(struct __sk_buff *skb)
 	return SK_DROP;
 }

+SEC("cgroup_skb/egress")
+int recursion(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	void *data_end = (void *)(long)skb->data_end;
+	struct iphdr *iph;
+	int ret;
+
+	iph = data;
+	if ((void *)(iph + 1) > data_end || iph->version != 4)
+		return SK_PASS;
+
+	/* This call will provoke a recursion: the ICMP packet generated by the
+	 * kfunc will re-trigger this program since we are in the root cgroup in
+	 * which the kernel ICMP socket belongs. However when re-entering the
+	 * kfunc, it should return EBUSY.
+	 */
+	ret = bpf_icmp_send(skb, unreach_type, unreach_code);
+	rec_kfunc_rets[rec_count & 1] = ret;
+	__sync_fetch_and_add(&rec_count, 1);
+
+	/* Let the first ICMP error message pass */
+	if (iph->protocol == IPPROTO_ICMP)
+		return SK_PASS;
+
+	return SK_DROP;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";