[PATCH bpf-next v8 7/7] selftests/bpf: add bpf_icmp_send recursion test

[Mahe Tardy <mahe.tardy@gmail.com>]

This test is similar to test_icmp_send_unreach_cgroup 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          | 45 +++++++++++++++
 tools/testing/selftests/bpf/progs/icmp_send.c | 56 +++++++++++++++++++
 2 files changed, 101 insertions(+)

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 66447681f72d..fd4b8fa78a01 100644
--- a/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/icmp_send_kfunc.c
@@ -1,8 +1,10 @@
 // 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 <unistd.h>
 #include "icmp_send.skel.h"

 #define TIMEOUT_MS 1000
@@ -10,6 +12,7 @@
 #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
@@ -203,3 +206,45 @@ void test_icmp_send_unreach_tc(void)
 	bpf_link__destroy(link);
 	icmp_send__destroy(skel);
 }
+
+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_OK_FD(cgroup_fd, "get_root_cgroup"))
+		goto cleanup;
+
+	skel->data->target_pid = getpid();
+	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);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/progs/icmp_send.c b/tools/testing/selftests/bpf/progs/icmp_send.c
index 5fa5467bdb70..fd9c7684797b 100644
--- a/tools/testing/selftests/bpf/progs/icmp_send.c
+++ b/tools/testing/selftests/bpf/progs/icmp_send.c
@@ -13,6 +13,10 @@ __u16 server_port = 0;
 int unreach_type = 0;
 int unreach_code = 0;
 int kfunc_ret = -1;
+int target_pid = -1;
+
+unsigned int rec_count = 0;
+int rec_kfunc_rets[] = { -1, -1 };

 SEC("cgroup_skb/egress")
 int egress(struct __sk_buff *skb)
@@ -125,4 +129,56 @@ int tc_egress(struct __sk_buff *skb)
 	return TCX_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 icmphdr *icmph;
+	struct tcphdr *tcph;
+	struct iphdr *iph;
+	int ret;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return SK_PASS;
+
+	iph = data;
+	if ((void *)(iph + 1) > data_end || iph->version != 4)
+		return SK_PASS;
+
+	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) {
+		icmph = (void *)iph + iph->ihl * 4;
+		if ((void *)(icmph + 1) > data_end ||
+		    icmph->type != unreach_type ||
+		    icmph->code != unreach_code)
+			return SK_PASS;
+	} else {
+		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";
--
2.34.1