Merge branch 'bpf-update-transport_header-when-encapsulating-udp-tunnel-in-lwt'

Leon Hwang says:

====================
bpf: Update transport_header when encapsulating UDP tunnel in lwt

Currently, bpf_lwt_push_ip_encap() does not update skb->transport_header.
When a driver, e.g. ice, reuses the stale skb->transport_header to
offload checksum computation to NIC hardware, VxLAN packets encapsulated
by bpf_lwt_push_encap() helper may be dropped due to incorrect checksum.

Update skb->transport_header in bpf_lwt_push_ip_encap() whenever the
encapsulated packet uses UDP, so checksum offload works correctly.

Changes:
v3 -> v4:
* Address comments from Emil:
  * Make the logic of skb_set_transport_header() clearer in patch #1.
  * Fold the code of fexit_lwt_push_ip_encap() into test_lwt_ip_encap.c in
    patch #2.
  * Resolve assorted issues of test in patch #2.
* v3: https://lore.kernel.org/bpf/20260601150203.20352-1-leon.hwang@linux.dev/

v2 -> v3:
* Drop patch #1 and #2 of v2 that aim to resolve potential issues
  reported by sashiko (per Alexei).
* Check target IP version and UDP tunnel in test (per sashiko).
* v2: https://lore.kernel.org/bpf/20260529151351.69911-1-leon.hwang@linux.dev/

v1 -> v2:
* Address sashiko's reviews:
  * Fix TOCTOU issue in lwt to avoid changing hdr after checks.
  * Add check iph->ihl < 5 in lwt to avoid infinite-loop in MIPS driver.
  * Update comment style in selftests with BPF comment style.
* v1: https://lore.kernel.org/bpf/20260525142650.2569-1-leon.hwang@linux.dev/
====================

Link: https://patch.msgid.link/20260602150931.49629-1-leon.hwang@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 302 insertions, 10 deletions

diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index f71ef82a5f3d..bf588f508b79 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -599,6 +599,7 @@ static int handle_gso_encap(struct sk_buff *skb, bool ipv4, int encap_len)
 
 int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
 {
+	bool is_udp_tunnel;
 	struct iphdr *iph;
 	bool ipv4;
 	int err;
@@ -612,10 +613,16 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
 		ipv4 = true;
 		if (unlikely(len < iph->ihl * 4))
 			return -EINVAL;
+		is_udp_tunnel = iph->protocol == IPPROTO_UDP;
+		if (unlikely(is_udp_tunnel && len < iph->ihl * 4 + sizeof(struct udphdr)))
+			return -EINVAL;
 	} else if (iph->version == 6) {
 		ipv4 = false;
 		if (unlikely(len < sizeof(struct ipv6hdr)))
 			return -EINVAL;
+		is_udp_tunnel = ((struct ipv6hdr *)iph)->nexthdr == NEXTHDR_UDP;
+		if (unlikely(is_udp_tunnel && len < sizeof(struct ipv6hdr) + sizeof(struct udphdr)))
+			return -EINVAL;
 	} else {
 		return -EINVAL;
 	}
@@ -637,6 +644,11 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
 	if (ingress)
 		skb_postpush_rcsum(skb, iph, len);
 	skb_reset_network_header(skb);
+	if (is_udp_tunnel) {
+		size_t iph_sz = ipv4 ? iph->ihl * 4 : sizeof(struct ipv6hdr);
+
+		skb_set_transport_header(skb, skb_network_offset(skb) + iph_sz);
+	}
 	memcpy(skb_network_header(skb), hdr, len);
 	bpf_compute_data_pointers(skb);
 	skb_clear_hash(skb);
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 b6391af5f6f9..6606f0ed9a9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
@@ -3,6 +3,7 @@
 
 #include "network_helpers.h"
 #include "test_progs.h"
+#include "test_lwt_ip_encap.skel.h"
 
 #define BPF_FILE "test_lwt_ip_encap.bpf.o"
 
@@ -32,6 +33,9 @@
 #define IP6_ADDR_8 "fb08::1"
 #define IP6_ADDR_GRE "fb10::1"
 
+#define IP4_ADDR_VXLAN  "172.16.17.100"
+#define IP6_ADDR_VXLAN  "fb11::1"
+
 #define IP6_ADDR_SRC IP6_ADDR_1
 #define IP6_ADDR_DST IP6_ADDR_4
 
@@ -538,3 +542,144 @@ void test_lwt_ip_encap_ipv4(void)
 	if (test__start_subtest("ingress"))
 		lwt_ip_encap(IPV4_ENCAP, INGRESS, "");
 }
+
+/*
+ * VxLAN Setup/topology:
+ *
+ * NS1 (IP*_ADDR_1)                NS2                  NS3 (IP*_ADDR_4)
+ *       [ping src]
+ *           |                          top route
+ *         veth1 (LWT encap)  <<-- veth2        veth3  <<-- veth4 (ping dst)
+ *           |                                                ^
+ *       (bottom route)                                       | (inner pkt)
+ *           v                        bottom route            |
+ *         veth5              -->> veth6        veth7  -->> veth8 (vxlan decap)
+ *                                                          (IP*_ADDR_VXLAN)
+ *
+ * Add the VxLAN endpoint addresses to NS3's veth8, create standard
+ * VxLAN decap devices bound to those addresses, and install routes so
+ * NS1/NS2 can reach the endpoints via the bottom route.  NS2 here is to
+ * make sure the LWT-encap VxLAN packets are routed to NS3 correctly.
+ */
+static int setup_vxlan_routes(const char *ns3, const char *ns1, const char *ns2)
+{
+	struct nstoken *nstoken;
+
+	nstoken = open_netns(ns3);
+	if (!ASSERT_OK_PTR(nstoken, "open ns3 for vxlan"))
+		return -1;
+
+	SYS(fail_close, "ip    a add %s/32  dev veth8", IP4_ADDR_VXLAN);
+	SYS(fail_close, "ip -6 a add %s/128 dev veth8", IP6_ADDR_VXLAN);
+	/*
+	 * Standard VxLAN devices to decap the encapsulated packets.  The inner
+	 * Ethernet frame uses a broadcast dst MAC so the IP stack accepts it
+	 * without ARP or FDB configuration.
+	 */
+	SYS(fail_close, "ip link add vxlan4 type vxlan id 1 dstport 4789 local %s dev veth8 nolearning noudpcsum",
+	    IP4_ADDR_VXLAN);
+	SYS(fail_close, "ip link set vxlan4 up");
+	SYS(fail_close, "ip link add vxlan6 type vxlan id 1 dstport 4789 local %s dev veth8 nolearning udp6zerocsumrx",
+	    IP6_ADDR_VXLAN);
+	SYS(fail_close, "ip link set vxlan6 up");
+	close_netns(nstoken);
+
+	SYS(fail, "ip -n %s    route add %s/32  dev veth5 via %s",
+	    ns1, IP4_ADDR_VXLAN, IP4_ADDR_6);
+	SYS(fail, "ip -n %s    route add %s/32  dev veth7 via %s",
+	    ns2, IP4_ADDR_VXLAN, IP4_ADDR_8);
+	SYS(fail, "ip -n %s -6 route add %s/128 dev veth5 via %s",
+	    ns1, IP6_ADDR_VXLAN, IP6_ADDR_6);
+	SYS(fail, "ip -n %s -6 route add %s/128 dev veth7 via %s",
+	    ns2, IP6_ADDR_VXLAN, IP6_ADDR_8);
+	return 0;
+
+fail_close:
+	close_netns(nstoken);
+fail:
+	return -1;
+}
+
+static void lwt_ip_encap_vxlan(bool ipv4_encap)
+{
+	char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-";
+	char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-";
+	char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-";
+	const char *sec = ipv4_encap ? "encap_vxlan" : "encap_vxlan6";
+	int expected_offset = ipv4_encap ? (int)sizeof(struct iphdr)
+					 : (int)sizeof(struct ipv6hdr);
+	struct test_lwt_ip_encap *skel = NULL;
+	int thdr_offset, err;
+
+	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;
+
+	if (!ASSERT_OK(setup_vxlan_routes(ns3, ns1, ns2), "setup vxlan routes"))
+		goto out;
+
+	skel = test_lwt_ip_encap__open();
+	if (!ASSERT_OK_PTR(skel, "test_lwt_ip_encap__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.fexit_lwt_push_ip_encap, true);
+	skel->rodata->tgt_ip_version = ipv4_encap ? 4 : 6;
+
+	err = test_lwt_ip_encap__load(skel);
+	if (!ASSERT_OK(err, "test_lwt_ip_encap__load"))
+		goto out;
+
+	err = test_lwt_ip_encap__attach(skel);
+	if (!ASSERT_OK(err, "test_lwt_ip_encap__attach"))
+		goto out;
+
+	/* Remove the direct NS2->DST route so packets must go via LWT encap. */
+	SYS(out, "ip -n %s    route del %s/32  dev veth3", ns2, IP4_ADDR_DST);
+	SYS(out, "ip -n %s -6 route del %s/128 dev veth3", ns2, IP6_ADDR_DST);
+
+	if (ipv4_encap)
+		SYS(out, "ip -n %s route add %s encap bpf xmit obj %s sec %s dev veth1",
+		    ns1, IP4_ADDR_DST, BPF_FILE, sec);
+	else
+		SYS(out, "ip -n %s -6 route add %s encap bpf xmit obj %s sec %s dev veth1",
+		    ns1, IP6_ADDR_DST, BPF_FILE, sec);
+
+	skel->bss->fexit_triggered = false;
+
+	if (ipv4_encap)
+		SYS(out, "ip netns exec %s ping  -c 1 -W1 %s", ns1, IP4_ADDR_DST);
+	else
+		SYS(out, "ip netns exec %s ping6 -c 1 -W1 %s", ns1, IP6_ADDR_DST);
+
+	if (!ASSERT_TRUE(skel->bss->fexit_triggered, "fexit_triggered"))
+		goto out;
+
+	thdr_offset = (int)skel->bss->transport_hdr - (int)skel->bss->network_hdr;
+	ASSERT_EQ(thdr_offset, expected_offset, "transport_hdr offset");
+
+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);
+}
+
+void test_lwt_ip_encap_vxlan_ipv4(void)
+{
+	lwt_ip_encap_vxlan(IPV4_ENCAP);
+}
+
+void test_lwt_ip_encap_vxlan_ipv6(void)
+{
+	lwt_ip_encap_vxlan(IPV6_ENCAP);
+}
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 d6cb986e7533..4a934fccf8f5 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
@@ -1,11 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stddef.h>
+#include "vmlinux.h"
 #include <string.h>
-#include <linux/bpf.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
 
 struct grehdr {
 	__be16 flags;
@@ -64,13 +62,13 @@ int bpf_lwt_encap_gre6(struct __sk_buff *skb)
 	hdr.ip6hdr.nexthdr = 47;  /* IPPROTO_GRE */
 	hdr.ip6hdr.hop_limit = 0x40;
 	/* fb01::1 */
-	hdr.ip6hdr.saddr.s6_addr[0] = 0xfb;
-	hdr.ip6hdr.saddr.s6_addr[1] = 1;
-	hdr.ip6hdr.saddr.s6_addr[15] = 1;
+	hdr.ip6hdr.saddr.in6_u.u6_addr8[0] = 0xfb;
+	hdr.ip6hdr.saddr.in6_u.u6_addr8[1] = 1;
+	hdr.ip6hdr.saddr.in6_u.u6_addr8[15] = 1;
 	/* fb10::1 */
-	hdr.ip6hdr.daddr.s6_addr[0] = 0xfb;
-	hdr.ip6hdr.daddr.s6_addr[1] = 0x10;
-	hdr.ip6hdr.daddr.s6_addr[15] = 1;
+	hdr.ip6hdr.daddr.in6_u.u6_addr8[0] = 0xfb;
+	hdr.ip6hdr.daddr.in6_u.u6_addr8[1] = 0x10;
+	hdr.ip6hdr.daddr.in6_u.u6_addr8[15] = 1;
 
 	hdr.greh.protocol = skb->protocol;
 
@@ -82,4 +80,141 @@ int bpf_lwt_encap_gre6(struct __sk_buff *skb)
 	return BPF_LWT_REROUTE;
 }
 
+#define VXLAN_PORT  4789
+#define VXLAN_FLAGS 0x08000000
+#define VXLAN_VNI   1
+
+#define ETH_ALEN	6		/* Octets in one ethernet addr	 */
+#define ETH_P_IP	0x0800		/* Internet Protocol packet	*/
+#define ETH_P_IPV6	0x86DD		/* IPv6 over bluebook		*/
+
+static const __u8 bcast[ETH_ALEN] = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+};
+
+static const __u8 srcmac[ETH_ALEN] = {
+	0x02, 0x00, 0x00, 0x00, 0x00, 0x01,
+};
+
+SEC("encap_vxlan")
+int bpf_lwt_encap_vxlan(struct __sk_buff *skb)
+{
+	struct encap_hdr {
+		struct iphdr    iph;
+		struct udphdr   udph;
+		struct vxlanhdr vxh;
+		struct ethhdr   eth;
+	} __attribute__((__packed__)) hdr;
+	int err;
+
+	memset(&hdr, 0, sizeof(hdr));
+
+	hdr.iph.ihl      = 5;
+	hdr.iph.version  = 4;
+	hdr.iph.ttl      = 0x40;
+	hdr.iph.protocol = 17; /* IPPROTO_UDP */
+	hdr.iph.tot_len  = bpf_htons(skb->len + sizeof(hdr));
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	hdr.iph.saddr = 0x640510ac;  /* 172.16.5.100  */
+	hdr.iph.daddr = 0x641110ac;  /* 172.16.17.100 */
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	hdr.iph.saddr = 0xac100564;  /* 172.16.5.100 */
+	hdr.iph.daddr = 0xac101164;  /* 172.16.17.100 */
+#else
+#error "Fix your compiler's __BYTE_ORDER__?!"
+#endif
+
+	hdr.udph.source = bpf_htons(VXLAN_PORT);
+	hdr.udph.dest   = bpf_htons(VXLAN_PORT);
+	hdr.udph.len    = bpf_htons(skb->len + sizeof(hdr.udph) + sizeof(hdr.vxh) +
+				    sizeof(hdr.eth));
+
+	hdr.vxh.vx_flags = bpf_htonl(VXLAN_FLAGS);
+	hdr.vxh.vx_vni   = bpf_htonl(VXLAN_VNI << 8);
+
+	__builtin_memcpy(hdr.eth.h_dest, bcast, ETH_ALEN);
+	__builtin_memcpy(hdr.eth.h_source, srcmac, ETH_ALEN);
+	hdr.eth.h_proto = bpf_htons(ETH_P_IP);
+
+	err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr, sizeof(hdr));
+	if (err)
+		return BPF_DROP;
+
+	return BPF_LWT_REROUTE;
+}
+
+SEC("encap_vxlan6")
+int bpf_lwt_encap_vxlan6(struct __sk_buff *skb)
+{
+	struct encap_hdr {
+		struct ipv6hdr  ip6hdr;
+		struct udphdr   udph;
+		struct vxlanhdr vxh;
+		struct ethhdr   eth;
+	} __attribute__((__packed__)) hdr;
+	int err;
+
+	memset(&hdr, 0, sizeof(hdr));
+
+	hdr.ip6hdr.version     = 6;
+	hdr.ip6hdr.nexthdr     = 17; /* IPPROTO_UDP */
+	hdr.ip6hdr.hop_limit   = 0x40;
+	hdr.ip6hdr.payload_len = bpf_htons(skb->len + sizeof(hdr.udph) + sizeof(hdr.vxh) +
+					   sizeof(hdr.eth));
+	/* fb05::1 */
+	hdr.ip6hdr.saddr.in6_u.u6_addr8[0]  = 0xfb;
+	hdr.ip6hdr.saddr.in6_u.u6_addr8[1]  = 0x05;
+	hdr.ip6hdr.saddr.in6_u.u6_addr8[15] = 1;
+	/* fb11::1 */
+	hdr.ip6hdr.daddr.in6_u.u6_addr8[0]  = 0xfb;
+	hdr.ip6hdr.daddr.in6_u.u6_addr8[1]  = 0x11;
+	hdr.ip6hdr.daddr.in6_u.u6_addr8[15] = 1;
+
+	hdr.udph.source = bpf_htons(VXLAN_PORT);
+	hdr.udph.dest   = bpf_htons(VXLAN_PORT);
+	hdr.udph.len    = bpf_htons(skb->len + sizeof(hdr.udph) + sizeof(hdr.vxh) +
+				    sizeof(hdr.eth));
+
+	hdr.vxh.vx_flags = bpf_htonl(VXLAN_FLAGS);
+	hdr.vxh.vx_vni   = bpf_htonl(VXLAN_VNI << 8);
+
+	__builtin_memcpy(hdr.eth.h_dest, bcast, ETH_ALEN);
+	__builtin_memcpy(hdr.eth.h_source, srcmac, ETH_ALEN);
+	hdr.eth.h_proto = bpf_htons(ETH_P_IPV6);
+
+	err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr, sizeof(hdr));
+	if (err)
+		return BPF_DROP;
+
+	return BPF_LWT_REROUTE;
+}
+
+volatile const int tgt_ip_version;
+
+__u16 transport_hdr = 0;
+__u16 network_hdr = 0;
+bool fexit_triggered = false;
+
+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,
+	     int retval)
+{
+	struct iphdr *iph;
+
+	if (retval || fexit_triggered)
+		return 0;
+
+	iph = (typeof(iph)) (skb->head + skb->network_header);
+	if (iph->version != tgt_ip_version)
+		return 0;
+
+	if ((iph->version == 4 && iph->protocol == 17 /* IPPROTO_UDP */) ||
+	    (iph->version == 6 && ((struct ipv6hdr *)iph)->nexthdr == 17 /* IPPROTO_UDP */)) {
+		fexit_triggered = true;
+		transport_hdr   = skb->transport_header;
+		network_hdr     = skb->network_header;
+	}
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";