diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2f1d24fef857..8b41c365ddf9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3532,6 +3532,31 @@ union bpf_attr { * Use the mark present in *params*->mark for the fib lookup. * This option should not be used with BPF_FIB_LOOKUP_DIRECT, * as it only has meaning for full lookups. + * **BPF_FIB_LOOKUP_VLAN** + * If the fib lookup resolves to a VLAN device whose + * parent is a real (non-VLAN) device, set + * *params*->h_vlan_proto and *params*->h_vlan_TCI from + * the VLAN device and replace *params*->ifindex with the + * parent's ifindex. *params*->h_vlan_TCI carries the VID + * only, with PCP and DEI bits zero; a consumer wanting to + * set egress priority writes PCP itself. *params*->smac is + * the VLAN device's own address, which can differ from the + * parent's. Only the immediate parent is resolved; if it + * is itself a VLAN device (QinQ) or in another namespace, + * the egress cannot be reduced to a physical device plus + * one tag and the lookup returns + * **BPF_FIB_LKUP_RET_VLAN_FAILURE** with *params*->ifindex + * left at the input. To obtain the VLAN device's own + * ifindex, repeat the lookup without + * **BPF_FIB_LOOKUP_VLAN**, re-initializing *params* + * first: output fields overwrite the inputs they share + * storage with. The swap and the vlan fields + * are written only on success; other output fields keep + * the helper's existing behaviour, so a frag-needed result + * still reports the route mtu in *params*->mtu_result. + * This flag is only valid for XDP programs; tc programs + * receive -EINVAL since they can redirect to the VLAN + * device directly. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -7339,6 +7364,7 @@ enum { BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), BPF_FIB_LOOKUP_MARK = (1U << 5), + BPF_FIB_LOOKUP_VLAN = (1U << 6), }; enum { @@ -7352,6 +7378,7 @@ enum { BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ + BPF_FIB_LKUP_RET_VLAN_FAILURE, /* VLAN egress, parent unresolvable */ }; struct bpf_fib_lookup { @@ -7405,7 +7432,11 @@ struct bpf_fib_lookup { union { struct { - /* output */ + /* + * output with BPF_FIB_LOOKUP_VLAN: set from the + * resolved egress VLAN device (see the flag); zeroed + * on other successful lookups. + */ __be16 h_vlan_proto; __be16 h_vlan_TCI; }; diff --git a/net/core/filter.c b/net/core/filter.c index 056deb9b3fc3..b8f2595ff582 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6206,10 +6206,29 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) -static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) +static int bpf_fib_set_fwd_params(struct net_device *dev, + struct bpf_fib_lookup *params, + u32 flags, u32 mtu, u32 in_ifindex) { params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + +#if IS_ENABLED(CONFIG_VLAN_8021Q) + if ((flags & BPF_FIB_LOOKUP_VLAN) && is_vlan_dev(dev)) { + struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + + if (!is_vlan_dev(real_dev) && + net_eq(dev_net(real_dev), dev_net(dev))) { + params->h_vlan_proto = vlan_dev_vlan_proto(dev); + params->h_vlan_TCI = htons(vlan_dev_vlan_id(dev)); + params->ifindex = real_dev->ifindex; + } else { + params->ifindex = in_ifindex; + return BPF_FIB_LKUP_RET_VLAN_FAILURE; + } + } +#endif + if (mtu) params->mtu_result = mtu; /* union with tot_len */ @@ -6221,6 +6240,7 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { + u32 in_ifindex = params->ifindex; struct neighbour *neigh = NULL; struct fib_nh_common *nhc; struct in_device *in_dev; @@ -6352,7 +6372,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: - return bpf_fib_set_fwd_params(params, mtu); + return bpf_fib_set_fwd_params(dev, params, flags, mtu, in_ifindex); } #endif @@ -6362,6 +6382,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, { struct in6_addr *src = (struct in6_addr *) params->ipv6_src; struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; + u32 in_ifindex = params->ifindex; struct fib6_result res = {}; struct neighbour *neigh; struct net_device *dev; @@ -6491,13 +6512,14 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: - return bpf_fib_set_fwd_params(params, mtu); + return bpf_fib_set_fwd_params(dev, params, flags, mtu, in_ifindex); } #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ - BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) + BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK | \ + BPF_FIB_LOOKUP_VLAN) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) @@ -6546,6 +6568,9 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; + if (flags & BPF_FIB_LOOKUP_VLAN) + return -EINVAL; + if (params->tot_len) check_mtu = true; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2f1d24fef857..8b41c365ddf9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3532,6 +3532,31 @@ union bpf_attr { * Use the mark present in *params*->mark for the fib lookup. * This option should not be used with BPF_FIB_LOOKUP_DIRECT, * as it only has meaning for full lookups. + * **BPF_FIB_LOOKUP_VLAN** + * If the fib lookup resolves to a VLAN device whose + * parent is a real (non-VLAN) device, set + * *params*->h_vlan_proto and *params*->h_vlan_TCI from + * the VLAN device and replace *params*->ifindex with the + * parent's ifindex. *params*->h_vlan_TCI carries the VID + * only, with PCP and DEI bits zero; a consumer wanting to + * set egress priority writes PCP itself. *params*->smac is + * the VLAN device's own address, which can differ from the + * parent's. Only the immediate parent is resolved; if it + * is itself a VLAN device (QinQ) or in another namespace, + * the egress cannot be reduced to a physical device plus + * one tag and the lookup returns + * **BPF_FIB_LKUP_RET_VLAN_FAILURE** with *params*->ifindex + * left at the input. To obtain the VLAN device's own + * ifindex, repeat the lookup without + * **BPF_FIB_LOOKUP_VLAN**, re-initializing *params* + * first: output fields overwrite the inputs they share + * storage with. The swap and the vlan fields + * are written only on success; other output fields keep + * the helper's existing behaviour, so a frag-needed result + * still reports the route mtu in *params*->mtu_result. + * This flag is only valid for XDP programs; tc programs + * receive -EINVAL since they can redirect to the VLAN + * device directly. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -7339,6 +7364,7 @@ enum { BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), BPF_FIB_LOOKUP_MARK = (1U << 5), + BPF_FIB_LOOKUP_VLAN = (1U << 6), }; enum { @@ -7352,6 +7378,7 @@ enum { BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ + BPF_FIB_LKUP_RET_VLAN_FAILURE, /* VLAN egress, parent unresolvable */ }; struct bpf_fib_lookup { @@ -7405,7 +7432,11 @@ struct bpf_fib_lookup { union { struct { - /* output */ + /* + * output with BPF_FIB_LOOKUP_VLAN: set from the + * resolved egress VLAN device (see the flag); zeroed + * on other successful lookups. + */ __be16 h_vlan_proto; __be16 h_vlan_TCI; };