From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- tools/testing/selftests/bpf/progs/test_tc_tunnel.c | 707 +++++++++++++++++++++ 1 file changed, 707 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/test_tc_tunnel.c (limited to 'tools/testing/selftests/bpf/progs/test_tc_tunnel.c') diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c new file mode 100644 index 000000000..e6e678aa9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -0,0 +1,707 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* In-place tunneling */ + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +static const int cfg_port = 8000; + +static const int cfg_udp_src = 20000; + +#define L2_PAD_SZ (sizeof(struct vxlanhdr) + ETH_HLEN) + +#define UDP_PORT 5555 +#define MPLS_OVER_UDP_PORT 6635 +#define ETH_OVER_UDP_PORT 7777 +#define VXLAN_UDP_PORT 8472 + +#define EXTPROTO_VXLAN 0x1 + +#define VXLAN_N_VID (1u << 24) +#define VXLAN_VNI_MASK bpf_htonl((VXLAN_N_VID - 1) << 8) +#define VXLAN_FLAGS 0x8 +#define VXLAN_VNI 1 + +#ifndef NEXTHDR_DEST +#define NEXTHDR_DEST 60 +#endif + +/* MPLS label 1000 with S bit (last label) set and ttl of 255. */ +static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 | + MPLS_LS_S_MASK | 0xff); + +struct vxlanhdr { + __be32 vx_flags; + __be32 vx_vni; +} __attribute__((packed)); + +struct gre_hdr { + __be16 flags; + __be16 protocol; +} __attribute__((packed)); + +union l4hdr { + struct udphdr udp; + struct gre_hdr gre; +}; + +struct v4hdr { + struct iphdr ip; + union l4hdr l4hdr; + __u8 pad[L2_PAD_SZ]; /* space for L2 header / vxlan header ... */ +} __attribute__((packed)); + +struct v6hdr { + struct ipv6hdr ip; + union l4hdr l4hdr; + __u8 pad[L2_PAD_SZ]; /* space for L2 header / vxlan header ... */ +} __attribute__((packed)); + +static __always_inline void set_ipv4_csum(struct iphdr *iph) +{ + __u16 *iph16 = (__u16 *)iph; + __u32 csum; + int i; + + iph->check = 0; + +#pragma clang loop unroll(full) + for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++) + csum += *iph16++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto, __u16 ext_proto) +{ + __u16 udp_dst = UDP_PORT; + struct iphdr iph_inner; + struct v4hdr h_outer; + struct tcphdr tcph; + int olen, l2_len; + __u8 *l2_hdr = NULL; + int tcp_off; + __u64 flags; + + /* Most tests encapsulate a packet into a tunnel with the same + * network protocol, and derive the outer header fields from + * the inner header. + * + * The 6in4 case tests different inner and outer protocols. As + * the inner is ipv6, but the outer expects an ipv4 header as + * input, manually build a struct iphdr based on the ipv6hdr. + */ + if (encap_proto == IPPROTO_IPV6) { + const __u32 saddr = (192 << 24) | (168 << 16) | (1 << 8) | 1; + const __u32 daddr = (192 << 24) | (168 << 16) | (1 << 8) | 2; + struct ipv6hdr iph6_inner; + + /* Read the IPv6 header */ + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph6_inner, + sizeof(iph6_inner)) < 0) + return TC_ACT_OK; + + /* Derive the IPv4 header fields from the IPv6 header */ + memset(&iph_inner, 0, sizeof(iph_inner)); + iph_inner.version = 4; + iph_inner.ihl = 5; + iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) + + bpf_ntohs(iph6_inner.payload_len)); + iph_inner.ttl = iph6_inner.hop_limit - 1; + iph_inner.protocol = iph6_inner.nexthdr; + iph_inner.saddr = __bpf_constant_htonl(saddr); + iph_inner.daddr = __bpf_constant_htonl(daddr); + + tcp_off = sizeof(iph6_inner); + } else { + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + tcp_off = sizeof(iph_inner); + } + + /* filter only packets we want */ + if (iph_inner.ihl != 5 || iph_inner.protocol != IPPROTO_TCP) + return TC_ACT_OK; + + if (bpf_skb_load_bytes(skb, ETH_HLEN + tcp_off, + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + l2_len = 0; + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4; + + switch (l2_proto) { + case ETH_P_MPLS_UC: + l2_len = sizeof(mpls_label); + udp_dst = MPLS_OVER_UDP_PORT; + break; + case ETH_P_TEB: + l2_len = ETH_HLEN; + if (ext_proto & EXTPROTO_VXLAN) { + udp_dst = VXLAN_UDP_PORT; + l2_len += sizeof(struct vxlanhdr); + } else + udp_dst = ETH_OVER_UDP_PORT; + break; + } + flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len); + + switch (encap_proto) { + case IPPROTO_GRE: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE; + olen += sizeof(h_outer.l4hdr.gre); + h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto); + h_outer.l4hdr.gre.flags = 0; + break; + case IPPROTO_UDP: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP; + olen += sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src); + h_outer.l4hdr.udp.dest = bpf_htons(udp_dst); + h_outer.l4hdr.udp.check = 0; + h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) + + sizeof(h_outer.l4hdr.udp) + + l2_len); + break; + case IPPROTO_IPIP: + case IPPROTO_IPV6: + break; + default: + return TC_ACT_OK; + } + + /* add L2 encap (if specified) */ + l2_hdr = (__u8 *)&h_outer + olen; + switch (l2_proto) { + case ETH_P_MPLS_UC: + *(__u32 *)l2_hdr = mpls_label; + break; + case ETH_P_TEB: + flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH; + + if (ext_proto & EXTPROTO_VXLAN) { + struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr; + + vxlan_hdr->vx_flags = VXLAN_FLAGS; + vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8); + + l2_hdr += sizeof(struct vxlanhdr); + } + + if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN)) + return TC_ACT_SHOT; + + break; + } + olen += l2_len; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + h_outer.ip = iph_inner; + h_outer.ip.tot_len = bpf_htons(olen + + bpf_ntohs(h_outer.ip.tot_len)); + h_outer.ip.protocol = encap_proto; + + set_ipv4_csum((void *)&h_outer.ip); + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + /* if changing outer proto type, update eth->h_proto */ + if (encap_proto == IPPROTO_IPV6) { + struct ethhdr eth; + + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IP); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto) +{ + return __encap_ipv4(skb, encap_proto, l2_proto, 0); +} + +static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto, __u16 ext_proto) +{ + __u16 udp_dst = UDP_PORT; + struct ipv6hdr iph_inner; + struct v6hdr h_outer; + struct tcphdr tcph; + int olen, l2_len; + __u8 *l2_hdr = NULL; + __u16 tot_len; + __u64 flags; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + /* filter only packets we want */ + if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(iph_inner), + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + l2_len = 0; + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6; + + switch (l2_proto) { + case ETH_P_MPLS_UC: + l2_len = sizeof(mpls_label); + udp_dst = MPLS_OVER_UDP_PORT; + break; + case ETH_P_TEB: + l2_len = ETH_HLEN; + if (ext_proto & EXTPROTO_VXLAN) { + udp_dst = VXLAN_UDP_PORT; + l2_len += sizeof(struct vxlanhdr); + } else + udp_dst = ETH_OVER_UDP_PORT; + break; + } + flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len); + + switch (encap_proto) { + case IPPROTO_GRE: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE; + olen += sizeof(h_outer.l4hdr.gre); + h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto); + h_outer.l4hdr.gre.flags = 0; + break; + case IPPROTO_UDP: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP; + olen += sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src); + h_outer.l4hdr.udp.dest = bpf_htons(udp_dst); + tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) + + sizeof(h_outer.l4hdr.udp) + l2_len; + h_outer.l4hdr.udp.check = 0; + h_outer.l4hdr.udp.len = bpf_htons(tot_len); + break; + case IPPROTO_IPV6: + break; + default: + return TC_ACT_OK; + } + + /* add L2 encap (if specified) */ + l2_hdr = (__u8 *)&h_outer + olen; + switch (l2_proto) { + case ETH_P_MPLS_UC: + *(__u32 *)l2_hdr = mpls_label; + break; + case ETH_P_TEB: + flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH; + + if (ext_proto & EXTPROTO_VXLAN) { + struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr; + + vxlan_hdr->vx_flags = VXLAN_FLAGS; + vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8); + + l2_hdr += sizeof(struct vxlanhdr); + } + + if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN)) + return TC_ACT_SHOT; + break; + } + olen += l2_len; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + h_outer.ip = iph_inner; + h_outer.ip.payload_len = bpf_htons(olen + + bpf_ntohs(h_outer.ip.payload_len)); + + h_outer.ip.nexthdr = encap_proto; + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +static int encap_ipv6_ipip6(struct __sk_buff *skb) +{ + struct iphdr iph_inner; + struct v6hdr h_outer; + struct tcphdr tcph; + struct ethhdr eth; + __u64 flags; + int olen; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + /* filter only packets we want */ + if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2), + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + memset(&h_outer.ip, 0, sizeof(h_outer.ip)); + h_outer.ip.version = 6; + h_outer.ip.hop_limit = iph_inner.ttl; + h_outer.ip.saddr.s6_addr[1] = 0xfd; + h_outer.ip.saddr.s6_addr[15] = 1; + h_outer.ip.daddr.s6_addr[1] = 0xfd; + h_outer.ip.daddr.s6_addr[15] = 2; + h_outer.ip.payload_len = iph_inner.tot_len; + h_outer.ip.nexthdr = IPPROTO_IPIP; + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + /* update eth->h_proto */ + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IPV6); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto) +{ + return __encap_ipv6(skb, encap_proto, l2_proto, 0); +} + +SEC("encap_ipip_none") +int __encap_ipip_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_IPIP, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_gre_none") +int __encap_gre_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_gre_mpls") +int __encap_gre_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_gre_eth") +int __encap_gre_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_udp_none") +int __encap_udp_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_udp_mpls") +int __encap_udp_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_udp_eth") +int __encap_udp_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_vxlan_eth") +int __encap_vxlan_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return __encap_ipv4(skb, IPPROTO_UDP, + ETH_P_TEB, + EXTPROTO_VXLAN); + else + return TC_ACT_OK; +} + +SEC("encap_sit_none") +int __encap_sit_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv4(skb, IPPROTO_IPV6, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_ip6tnl_none") +int __encap_ip6tnl_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_IPV6, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ipip6_none") +int __encap_ipip6_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv6_ipip6(skb); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_none") +int __encap_ip6gre_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_mpls") +int __encap_ip6gre_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_eth") +int __encap_ip6gre_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_none") +int __encap_ip6udp_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_mpls") +int __encap_ip6udp_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_eth") +int __encap_ip6udp_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_ip6vxlan_eth") +int __encap_ip6vxlan_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return __encap_ipv6(skb, IPPROTO_UDP, + ETH_P_TEB, + EXTPROTO_VXLAN); + else + return TC_ACT_OK; +} + +static int decap_internal(struct __sk_buff *skb, int off, int len, char proto) +{ + __u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO; + struct ipv6_opt_hdr ip6_opt_hdr; + struct gre_hdr greh; + struct udphdr udph; + int olen = len; + + switch (proto) { + case IPPROTO_IPIP: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4; + break; + case IPPROTO_IPV6: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6; + break; + case NEXTHDR_DEST: + if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr, + sizeof(ip6_opt_hdr)) < 0) + return TC_ACT_OK; + switch (ip6_opt_hdr.nexthdr) { + case IPPROTO_IPIP: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4; + break; + case IPPROTO_IPV6: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6; + break; + default: + return TC_ACT_OK; + } + break; + case IPPROTO_GRE: + olen += sizeof(struct gre_hdr); + if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0) + return TC_ACT_OK; + switch (bpf_ntohs(greh.protocol)) { + case ETH_P_MPLS_UC: + olen += sizeof(mpls_label); + break; + case ETH_P_TEB: + olen += ETH_HLEN; + break; + } + break; + case IPPROTO_UDP: + olen += sizeof(struct udphdr); + if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0) + return TC_ACT_OK; + switch (bpf_ntohs(udph.dest)) { + case MPLS_OVER_UDP_PORT: + olen += sizeof(mpls_label); + break; + case ETH_OVER_UDP_PORT: + olen += ETH_HLEN; + break; + case VXLAN_UDP_PORT: + olen += ETH_HLEN + sizeof(struct vxlanhdr); + break; + } + break; + default: + return TC_ACT_OK; + } + + if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +static int decap_ipv4(struct __sk_buff *skb) +{ + struct iphdr iph_outer; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_outer, + sizeof(iph_outer)) < 0) + return TC_ACT_OK; + + if (iph_outer.ihl != 5) + return TC_ACT_OK; + + return decap_internal(skb, ETH_HLEN, sizeof(iph_outer), + iph_outer.protocol); +} + +static int decap_ipv6(struct __sk_buff *skb) +{ + struct ipv6hdr iph_outer; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_outer, + sizeof(iph_outer)) < 0) + return TC_ACT_OK; + + return decap_internal(skb, ETH_HLEN, sizeof(iph_outer), + iph_outer.nexthdr); +} + +SEC("decap") +int decap_f(struct __sk_buff *skb) +{ + switch (skb->protocol) { + case __bpf_constant_htons(ETH_P_IP): + return decap_ipv4(skb); + case __bpf_constant_htons(ETH_P_IPV6): + return decap_ipv6(skb); + default: + /* does not match, ignore */ + return TC_ACT_OK; + } +} + +char __license[] SEC("license") = "GPL"; -- cgit v1.2.3