[PATCH v4 2/2] selftests/bpf: cover stale CB after LWT IP encapsulation

[Weiming Shi <bestswngs@gmail.com>]

Add compact regression coverage to the existing LWT IP encapsulation
test. Send an IPv4 ping with a Record Route option through an ingress LWT
program which prepends a TTL-one IPv4 header, then observe __icmp_send()
with fentry and verify that the restored protocol control block no longer
contains the inner header's cached option offsets.

Read ctx->cb[0] in the LWT program so the test exercises
bpf_prog_run_save_cb()'s save/restore path before the post-run check.

Link: https://lore.kernel.org/bpf/DLKB3UXOH0IS.1UL8NV9HSJFXG@gmail.com/
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
---
 .../selftests/bpf/prog_tests/lwt_ip_encap.c   | 45 ++++++++++++++++++
 .../selftests/bpf/progs/test_lwt_ip_encap.c   | 47 +++++++++++++++++++
 2 files changed, 92 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
index 39e8a3b8b6af..14ba33eaeb96 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
@@ -686,3 +686,48 @@ void test_lwt_ip_encap_vxlan_ipv6(void)
 {
 	lwt_ip_encap_vxlan(IPV6_ENCAP);
 }
+
+void test_lwt_ip_encap_stale_cb(void)
+{
+	char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-";
+	char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-";
+	char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-";
+	struct test_lwt_ip_encap *skel = NULL;
+
+	if (!ASSERT_OK(create_ns(ns1, NETNS_NAME_SIZE), "create ns1"))
+		goto out;
+	if (!ASSERT_OK(create_ns(ns2, NETNS_NAME_SIZE), "create ns2"))
+		goto out;
+	if (!ASSERT_OK(create_ns(ns3, NETNS_NAME_SIZE), "create ns3"))
+		goto out;
+	if (!ASSERT_OK(setup_network(ns1, ns2, ns3, ""), "setup network"))
+		goto out;
+
+	skel = test_lwt_ip_encap__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		goto out;
+	bpf_program__set_autoload(skel->progs.bpf_lwt_encap_gre, false);
+	bpf_program__set_autoload(skel->progs.bpf_lwt_encap_gre6, false);
+	bpf_program__set_autoload(skel->progs.bpf_lwt_encap_vxlan, false);
+	bpf_program__set_autoload(skel->progs.bpf_lwt_encap_vxlan6, false);
+	bpf_program__set_autoload(skel->progs.bpf_lwt_encap_stale, false);
+	if (!ASSERT_OK(test_lwt_ip_encap__load(skel), "load"))
+		goto out;
+	if (!ASSERT_OK(test_lwt_ip_encap__attach(skel), "attach"))
+		goto out;
+
+	SYS(out, "ip -n %s route replace %s/32 encap bpf in obj %s sec encap_stale dev veth3",
+	    ns2, IP4_ADDR_DST, BPF_FILE);
+	skel->bss->stale_cb_seen = false;
+	skel->bss->stale_cb_cleared = false;
+	SYS_NOFAIL("ip netns exec %s ping -q -R -c 1 -W 1 -I veth1 %s >/dev/null 2>&1",
+		   ns1, IP4_ADDR_DST);
+	ASSERT_TRUE(skel->bss->stale_cb_seen, "stale_cb_seen");
+	ASSERT_TRUE(skel->bss->stale_cb_cleared, "stale_cb_cleared");
+
+out:
+	test_lwt_ip_encap__destroy(skel);
+	SYS_NOFAIL("ip netns del %s", ns1);
+	SYS_NOFAIL("ip netns del %s", ns2);
+	SYS_NOFAIL("ip netns del %s", ns3);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
index 4a934fccf8f5..8b57c7fb7fa8 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "vmlinux.h"
 #include <string.h>
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 #include <bpf/bpf_tracing.h>
@@ -10,6 +11,8 @@ struct grehdr {
 	__be16 protocol;
 };
 
+#define ICMP_TIME_EXCEEDED 11
+
 SEC("encap_gre")
 int bpf_lwt_encap_gre(struct __sk_buff *skb)
 {
@@ -80,6 +83,29 @@ int bpf_lwt_encap_gre6(struct __sk_buff *skb)
 	return BPF_LWT_REROUTE;
 }
 
+SEC("encap_stale")
+int bpf_lwt_encap_stale(struct __sk_buff *skb)
+{
+	struct iphdr iph = {};
+
+	/* Exercise CB restore before post-run invalidation. */
+	if (skb->cb[0])
+		return BPF_DROP;
+
+	iph.version = 4;
+	iph.ihl = 5;
+	iph.ttl = 1;
+	iph.protocol = IPPROTO_IPIP;
+	iph.tot_len = bpf_htons(skb->len + sizeof(iph));
+	iph.saddr = bpf_htonl(0xac100264); /* 172.16.2.100 */
+	iph.daddr = bpf_htonl(0xac100464); /* 172.16.4.100 */
+
+	if (bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &iph, sizeof(iph)))
+		return BPF_DROP;
+
+	return BPF_OK;
+}
+
 #define VXLAN_PORT  4789
 #define VXLAN_FLAGS 0x08000000
 #define VXLAN_VNI   1
@@ -194,6 +220,27 @@ volatile const int tgt_ip_version;
 __u16 transport_hdr = 0;
 __u16 network_hdr = 0;
 bool fexit_triggered = false;
+bool stale_cb_cleared = false;
+bool stale_cb_seen = false;
+
+SEC("fentry/__icmp_send")
+int BPF_PROG(fentry_icmp_send, struct sk_buff *skb, int type, int code,
+	     __be32 info, const struct inet_skb_parm *parm)
+{
+	struct iphdr *iph;
+
+	if (type != ICMP_TIME_EXCEEDED)
+		return 0;
+
+	iph = (void *)BPF_CORE_READ(skb, head) + BPF_CORE_READ(skb, network_header);
+	if (BPF_CORE_READ(iph, daddr) != bpf_htonl(0xac100464))
+		return 0;
+
+	stale_cb_seen = true;
+	stale_cb_cleared = !BPF_CORE_READ(parm, opt.optlen) &&
+			   !BPF_CORE_READ(parm, opt.rr);
+	return 0;
+}
 
 SEC("?fexit/bpf_lwt_push_ip_encap")
 int BPF_PROG(fexit_lwt_push_ip_encap, struct sk_buff *skb, void *hdr, u32 len, bool ingress,
-- 
2.55.0