From c00320b0e355c4bf0ae4743a53b4180fea237546 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 19 Jun 2026 19:09:28 +0200 Subject: [PATCH 1/2] net: lwtunnel: Drop skb metadata before LWT encapsulation skb metadata is meant for passing information between XDP and TC. It lives in the skb headroom, immediately before skb->data. LWT programs cannot access the __sk_buff->data_meta pseudo-pointer to metadata. However, LWT encapsulation prepends outer headers, moving skb->data back over the headroom where the metadata sits. On an RX-originated (forwarded) packet that still carries XDP metadata this goes wrong in two different ways, depending on the encap type: 1. Non-BPF LWT encaps (mpls, seg6, ioam6 ...) call skb_push()/skb_pull() and silently overwrite the metadata that sits in the headroom. 2) BPF LWT xmit calls bpf_skb_change_head(), which uses skb_data_move(). That helper expects metadata immediately before skb->data. But since the IP output path runs LWT xmit before neighbour output has built the outgoing L2 header, for forwarded packets skb->data points at the L3 header while skb_mac_header() still points at the old L2 header. skb_data_move() sees metadata ending at skb_mac_header(), not before skb->data, warns and clears metadata: WARNING: CPU: 21 PID: 454557 at include/linux/skbuff.h:4609 skb_data_move+0x47/0x90 CPU: 21 UID: 0 PID: 454557 Comm: napi/iconduit-g Tainted: G O 6.18.21 #1 RIP: 0010:skb_data_move+0x47/0x90 Call Trace: bpf_skb_change_head+0xe6/0x1a0 bpf_prog_...+0x213/0x2e3 run_lwt_bpf.isra.0+0x1d3/0x360 bpf_xmit+0x46/0xe0 lwtunnel_xmit+0xa1/0xf0 ip_finish_output2+0x1e7/0x5e0 ip_output+0x63/0x100 __netif_receive_skb_one_core+0x85/0xa0 process_backlog+0x9c/0x150 __napi_poll+0x2b/0x190 net_rx_action+0x40b/0x7f0 handle_softirqs+0xd2/0x270 do_softirq+0x3f/0x60 That is what happens, as for how to fix it - a received packet that carries metadata can reach an encap through any of the three LWT redirect modes: LWTUNNEL_STATE_INPUT_REDIRECT ip6_rcv_finish dst_input lwtunnel_input LWTUNNEL_STATE_OUTPUT_REDIRECT ip6_rcv_finish dst_input ip6_forward ip6_forward_finish dst_output lwtunnel_output LWTUNNEL_STATE_XMIT_REDIRECT ip6_rcv_finish dst_input ip6_forward ip6_forward_finish dst_output ip6_output ip6_finish_output ip6_finish_output2 lwtunnel_xmit Every encap funnels through the three LWT dispatch helpers, so drop the metadata there, right before handing the skb to the encap op. This single chokepoint covers all encap types and all three redirect modes: - lwtunnel_input(): seg6, rpl, ila, seg6_local - lwtunnel_output(): ioam6 - lwtunnel_xmit(): mpls, LWT BPF xmit Alternatively, we could clear the metadata right after TC ingress hook. That would require a compromise, however. Metadata would become inaccessible from TC egress (in setups where it actually reaches the hook it tact, that is without any L2 tunnels on path). Fixes: 8989d328dfe7 ("net: Helper to move packet data and metadata after skb_push/pull") Signed-off-by: Jakub Sitnicki Link: https://patch.msgid.link/20260619-bpf-lwt-drop-skb-metadata-v3-1-71d6a33ab76b@cloudflare.com Signed-off-by: Jakub Kicinski --- net/core/lwtunnel.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index f9d76d85d04f..b01a395d9a96 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -350,6 +350,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) { + /* Encap pushes outer headers over the metadata; drop it. */ + skb_metadata_clear(skb); dev_xmit_recursion_inc(); ret = ops->output(net, sk, skb); dev_xmit_recursion_dec(); @@ -404,6 +406,8 @@ int lwtunnel_xmit(struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->xmit)) { + /* Encap pushes outer headers over the metadata; drop it. */ + skb_metadata_clear(skb); dev_xmit_recursion_inc(); ret = ops->xmit(skb); dev_xmit_recursion_dec(); @@ -455,6 +459,8 @@ int lwtunnel_input(struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->input)) { + /* Encap pushes outer headers over the metadata; drop it. */ + skb_metadata_clear(skb); dev_xmit_recursion_inc(); ret = ops->input(skb); dev_xmit_recursion_dec(); From 33a971d549d82b06c07ce6ed10c33089f80fa944 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 19 Jun 2026 19:09:29 +0200 Subject: [PATCH 2/2] selftests/bpf: Add LWT encap tests for skb metadata Test that an LWT encapsulation does not silently corrupt XDP metadata sitting in the skb headroom. Exercise all three LWT dispatch paths: - BPF LWT xmit prog reserves headroom on the LWT .xmit redirect, - mpls pushes an MPLS label on the LWT .xmit redirect, - seg6 in encap mode runs on the LWT .input redirect, - ioam6 encap inserts an IOAM Hop-by-Hop option on LWT .output redirect. Signed-off-by: Jakub Sitnicki Link: https://patch.msgid.link/20260619-bpf-lwt-drop-skb-metadata-v3-2-71d6a33ab76b@cloudflare.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/bpf/config | 3 + .../bpf/prog_tests/xdp_context_test_run.c | 175 ++++++++++++++++++ .../selftests/bpf/progs/test_xdp_meta.c | 123 ++++++------ 3 files changed, 249 insertions(+), 52 deletions(-) diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 24855381290d..aebc5082fd77 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -45,13 +45,16 @@ CONFIG_IPV6=y CONFIG_IPV6_FOU=y CONFIG_IPV6_FOU_TUNNEL=y CONFIG_IPV6_GRE=y +CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_IPV6_SEG6_BPF=y +CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SIT=y CONFIG_IPV6_TUNNEL=y CONFIG_KEYS=y CONFIG_LIRC=y CONFIG_LIVEPATCH=y CONFIG_LWTUNNEL=y +CONFIG_LWTUNNEL_BPF=y CONFIG_MODULE_SIG=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_MODULE_UNLOAD=y diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index 26159e0499c7..448807676176 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include +#include #include "test_xdp_context_test_run.skel.h" #include "test_xdp_meta.skel.h" @@ -8,9 +10,12 @@ #define TX_NAME "veth1" #define TX_NETNS "xdp_context_tx" #define RX_NETNS "xdp_context_rx" +#define RX_MAC "02:00:00:00:00:01" +#define TX_MAC "02:00:00:00:00:02" #define TAP_NAME "tap0" #define DUMMY_NAME "dum0" #define TAP_NETNS "xdp_context_tuntap" +#define LWT_NETNS "xdp_context_lwt" #define TEST_PAYLOAD_LEN 32 static const __u8 test_payload[TEST_PAYLOAD_LEN] = { @@ -187,6 +192,42 @@ static int write_test_packet(int tap_fd) return 0; } +/* Inject Ethernet+IPv6+UDP frame into TAP */ +static int write_test_packet_udp(int tap_fd) +{ + __u8 pkt[sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + + sizeof(struct udphdr) + TEST_PAYLOAD_LEN] = {}; + struct ethhdr *eth = (void *)pkt; + struct ipv6hdr *ip6 = (void *)(eth + 1); + struct udphdr *udp = (void *)(ip6 + 1); + __u8 *payload = (void *)(udp + 1); + const __u8 tap_mac[ETH_ALEN] = { 0x02, 0, 0, 0, 0, 0x01 }; + int n; + + memcpy(eth->h_dest, tap_mac, ETH_ALEN); + eth->h_proto = htons(ETH_P_IPV6); + + ip6->version = 6; + ip6->hop_limit = 64; + ip6->nexthdr = IPPROTO_UDP; + ip6->payload_len = htons(sizeof(*udp) + TEST_PAYLOAD_LEN); + inet_pton(AF_INET6, "fd00::2", &ip6->saddr); + inet_pton(AF_INET6, "fd00:1::1", &ip6->daddr); + + udp->source = htons(42); + udp->dest = htons(42); + udp->len = htons(sizeof(*udp) + TEST_PAYLOAD_LEN); + /* UDP checksum is not validated on the forwarding path. */ + + memcpy(payload, test_payload, TEST_PAYLOAD_LEN); + + n = write(tap_fd, pkt, sizeof(pkt)); + if (!ASSERT_EQ(n, sizeof(pkt), "write frame")) + return -1; + + return 0; +} + static void dump_err_stream(const struct bpf_program *prog) { char buf[512]; @@ -518,3 +559,137 @@ void test_xdp_context_tuntap(void) test_xdp_meta__destroy(skel); } + +/* + * Test topology: + * + * tap0 fd00::1 + * RX: injected IPv6 UDP frame, XDP ingress sets metadata + * fwd: encap route prepends outer header(s) + * TX: TC egress validates metadata + * + * A routable IPv6 UDP frame is written into the tap fd, so it enters the RX + * path where XDP stores metadata. Routing then forwards it back out the same + * tap through an encapsulating route that prepends outer header(s). The TC + * egress program checks that the pushed header did not silently corrupt + * metadata. + */ +#define LWT_PIN_PATH "/sys/fs/bpf/xdp_context_lwt_xmit" + +enum lwt_encap_type { + LWT_ENCAP_BPF, + LWT_ENCAP_MPLS, + LWT_ENCAP_SEG6, + LWT_ENCAP_IOAM6, +}; + +static void test_lwt_encap(struct test_xdp_meta *skel, + enum lwt_encap_type type) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_EGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + struct bpf_program *lwt_prog = NULL; + struct netns_obj *ns = NULL; + const char *encap; + bool pinned = false; + int tap_ifindex; + int tap_fd = -1; + int ret; + + skel->bss->test_pass = false; + + switch (type) { + case LWT_ENCAP_BPF: + encap = "encap bpf xmit pinned " LWT_PIN_PATH " via fd00::2"; + lwt_prog = skel->progs.dummy_lwt_xmit; + break; + case LWT_ENCAP_MPLS: + encap = "encap mpls 100 via inet6 fd00::2"; + break; + case LWT_ENCAP_SEG6: + encap = "encap seg6 mode encap segs fd00::2"; + break; + case LWT_ENCAP_IOAM6: + encap = "encap ioam6 mode encap tundst fd00::2 " + "trace prealloc type 0x800000 ns 0 size 4 via fd00::2"; + break; + default: + return; + } + + if (lwt_prog) { + unlink(LWT_PIN_PATH); + ret = bpf_program__pin(lwt_prog, LWT_PIN_PATH); + if (!ASSERT_OK(ret, "pin lwt prog")) + return; + pinned = true; + } + + ns = netns_new(LWT_NETNS, true); + if (!ASSERT_OK_PTR(ns, "netns_new")) + goto close; + + tap_fd = open_tuntap(TAP_NAME, true); + if (!ASSERT_GE(tap_fd, 0, "open_tuntap")) + goto close; + + SYS(close, "ip link set dev " TAP_NAME " address " RX_MAC); + SYS(close, "sysctl -wq net.ipv6.conf.all.forwarding=1"); + SYS(close, "ip addr add fd00::1/64 dev " TAP_NAME " nodad"); + SYS(close, "ip link set dev " TAP_NAME " up"); + SYS(close, "ip neigh add fd00::2 lladdr " TX_MAC " nud permanent dev " TAP_NAME); + SYS(close, "ip -6 route add fd00:1::/64 %s dev %s", encap, TAP_NAME); + + tap_ifindex = if_nametoindex(TAP_NAME); + if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex")) + goto close; + + ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp), + 0, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + tc_hook.ifindex = tap_ifindex; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto close; + + tc_opts.prog_fd = bpf_program__fd(skel->progs.tc_is_meta_empty); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + + ret = write_test_packet_udp(tap_fd); + if (!ASSERT_OK(ret, "write_test_packet_udp")) + goto close; + + if (!ASSERT_TRUE(skel->bss->test_pass, "test_pass")) + dump_err_stream(skel->progs.tc_is_meta_empty); + +close: + if (tap_fd >= 0) + close(tap_fd); + netns_free(ns); + if (pinned) + unlink(LWT_PIN_PATH); +} + +void test_xdp_context_lwt_encap(void) +{ + struct test_xdp_meta *skel; + + skel = test_xdp_meta__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + return; + + if (test__start_subtest("bpf_encap")) + test_lwt_encap(skel, LWT_ENCAP_BPF); + if (test__start_subtest("mpls_encap")) + test_lwt_encap(skel, LWT_ENCAP_MPLS); + if (test__start_subtest("seg6_encap")) + test_lwt_encap(skel, LWT_ENCAP_SEG6); + if (test__start_subtest("ioam6_encap")) + test_lwt_encap(skel, LWT_ENCAP_IOAM6); + + test_xdp_meta__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index fa73b17cb999..08b03be0b891 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -21,10 +21,6 @@ bool test_pass; -static const __u8 smac_want[ETH_ALEN] = { - 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF, -}; - static const __u8 meta_want[META_SIZE] = { 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, @@ -32,11 +28,6 @@ static const __u8 meta_want[META_SIZE] = { 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, }; -static bool check_smac(const struct ethhdr *eth) -{ - return !__builtin_memcmp(eth->h_source, smac_want, ETH_ALEN); -} - static bool check_metadata(const char *file, int line, __u8 *meta_have) { if (!__builtin_memcmp(meta_have, meta_want, META_SIZE)) @@ -280,18 +271,47 @@ int ing_cls_dynptr_offset_oob(struct __sk_buff *ctx) return TC_ACT_SHOT; } +/* Test packets carry test metadata pattern as payload. */ +static bool is_test_packet_xdp(struct xdp_md *ctx) +{ + __u8 meta_have[META_SIZE]; + __u32 len; + + len = bpf_xdp_get_buff_len(ctx); + if (len < META_SIZE) + return false; + if (bpf_xdp_load_bytes(ctx, len - META_SIZE, meta_have, META_SIZE)) + return false; + if (__builtin_memcmp(meta_have, meta_want, META_SIZE)) + return false; + + return true; +} + +/* Test packets carry test metadata pattern as payload. */ +static bool is_test_packet_tc(struct __sk_buff *ctx) +{ + __u8 meta_have[META_SIZE]; + + if (ctx->len < META_SIZE) + return false; + if (bpf_skb_load_bytes(ctx, ctx->len - META_SIZE, meta_have, META_SIZE)) + return false; + if (__builtin_memcmp(meta_have, meta_want, META_SIZE)) + return false; + + return true; +} + /* Reserve and clear space for metadata but don't populate it */ SEC("xdp") int ing_xdp_zalloc_meta(struct xdp_md *ctx) { - struct ethhdr *eth = ctx_ptr(ctx, data); __u8 *meta; int ret; /* Drop any non-test packets */ - if (eth + 1 > ctx_ptr(ctx, data_end)) - return XDP_DROP; - if (!check_smac(eth)) + if (!is_test_packet_xdp(ctx)) return XDP_DROP; ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); @@ -310,33 +330,24 @@ int ing_xdp_zalloc_meta(struct xdp_md *ctx) SEC("xdp") int ing_xdp(struct xdp_md *ctx) { - __u8 *data, *data_meta, *data_end, *payload; - struct ethhdr *eth; + __u8 *data, *data_meta; int ret; + /* Drop any non-test packets */ + if (!is_test_packet_xdp(ctx)) + return XDP_DROP; + ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); if (ret < 0) return XDP_DROP; data_meta = ctx_ptr(ctx, data_meta); - data_end = ctx_ptr(ctx, data_end); data = ctx_ptr(ctx, data); - eth = (struct ethhdr *)data; - payload = data + sizeof(struct ethhdr); - - if (payload + META_SIZE > data_end || - data_meta + META_SIZE > data) + if (data_meta + META_SIZE > data) return XDP_DROP; - /* The Linux networking stack may send other packets on the test - * interface that interfere with the test. Just drop them. - * The test packets can be recognized by their source MAC address. - */ - if (!check_smac(eth)) - return XDP_DROP; - - __builtin_memcpy(data_meta, payload, META_SIZE); + __builtin_memcpy(data_meta, meta_want, META_SIZE); return XDP_PASS; } @@ -353,7 +364,7 @@ int clone_data_meta_survives_data_write(struct __sk_buff *ctx) if (eth + 1 > ctx_ptr(ctx, data_end)) goto out; /* Ignore non-test packets */ - if (!check_smac(eth)) + if (!is_test_packet_tc(ctx)) goto out; if (meta_have + META_SIZE > eth) @@ -383,7 +394,7 @@ int clone_data_meta_survives_meta_write(struct __sk_buff *ctx) if (eth + 1 > ctx_ptr(ctx, data_end)) goto out; /* Ignore non-test packets */ - if (!check_smac(eth)) + if (!is_test_packet_tc(ctx)) goto out; if (meta_have + META_SIZE > eth) @@ -416,7 +427,7 @@ int clone_meta_dynptr_survives_data_slice_write(struct __sk_buff *ctx) if (!eth) goto out; /* Ignore non-test packets */ - if (!check_smac(eth)) + if (!is_test_packet_tc(ctx)) goto out; bpf_dynptr_from_skb_meta(ctx, 0, &meta); @@ -436,16 +447,11 @@ int clone_meta_dynptr_survives_data_slice_write(struct __sk_buff *ctx) SEC("tc") int clone_meta_dynptr_survives_meta_slice_write(struct __sk_buff *ctx) { - struct bpf_dynptr data, meta; - const struct ethhdr *eth; + struct bpf_dynptr meta; __u8 *meta_have; - bpf_dynptr_from_skb(ctx, 0, &data); - eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); - if (!eth) - goto out; /* Ignore non-test packets */ - if (!check_smac(eth)) + if (!is_test_packet_tc(ctx)) goto out; bpf_dynptr_from_skb_meta(ctx, 0, &meta); @@ -471,15 +477,10 @@ int clone_meta_dynptr_rw_before_data_dynptr_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; __u8 meta_have[META_SIZE]; - const struct ethhdr *eth; int err; - bpf_dynptr_from_skb(ctx, 0, &data); - eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); - if (!eth) - goto out; /* Ignore non-test packets */ - if (!check_smac(eth)) + if (!is_test_packet_tc(ctx)) goto out; /* Expect read-write metadata before unclone */ @@ -492,6 +493,7 @@ int clone_meta_dynptr_rw_before_data_dynptr_write(struct __sk_buff *ctx) goto out; /* Helper write to payload will unclone the packet */ + bpf_dynptr_from_skb(ctx, 0, &data); bpf_dynptr_write(&data, offsetof(struct ethhdr, h_proto), "x", 1, 0); err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); @@ -511,17 +513,12 @@ int clone_meta_dynptr_rw_before_data_dynptr_write(struct __sk_buff *ctx) SEC("tc") int clone_meta_dynptr_rw_before_meta_dynptr_write(struct __sk_buff *ctx) { - struct bpf_dynptr data, meta; + struct bpf_dynptr meta; __u8 meta_have[META_SIZE]; - const struct ethhdr *eth; int err; - bpf_dynptr_from_skb(ctx, 0, &data); - eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); - if (!eth) - goto out; /* Ignore non-test packets */ - if (!check_smac(eth)) + if (!is_test_packet_tc(ctx)) goto out; /* Expect read-write metadata before unclone */ @@ -545,6 +542,28 @@ int clone_meta_dynptr_rw_before_meta_dynptr_write(struct __sk_buff *ctx) return TC_ACT_SHOT; } +SEC("lwt_xmit") +int dummy_lwt_xmit(struct __sk_buff *ctx) +{ + if (bpf_skb_change_head(ctx, sizeof(struct ipv6hdr), 0)) + return BPF_DROP; + + return BPF_OK; +} + +SEC("tc") +int tc_is_meta_empty(struct __sk_buff *ctx) +{ + if (!is_test_packet_tc(ctx)) + return TC_ACT_OK; + + if (ctx->data_meta != ctx->data) + return TC_ACT_OK; + + test_pass = true; + return TC_ACT_OK; +} + SEC("tc") int helper_skb_vlan_push_pop(struct __sk_buff *ctx) {