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(). ... --- net/netfilter/nft_tunnel.c | 750 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 750 insertions(+) create mode 100644 net/netfilter/nft_tunnel.c (limited to 'net/netfilter/nft_tunnel.c') diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c new file mode 100644 index 000000000..b059aa541 --- /dev/null +++ b/net/netfilter/nft_tunnel.c @@ -0,0 +1,750 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_tunnel { + enum nft_tunnel_keys key:8; + u8 dreg; + enum nft_tunnel_mode mode:8; + u8 len; +}; + +static void nft_tunnel_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + struct ip_tunnel_info *tun_info; + + tun_info = skb_tunnel_info(pkt->skb); + + switch (priv->key) { + case NFT_TUNNEL_PATH: + if (!tun_info) { + nft_reg_store8(dest, false); + return; + } + if (priv->mode == NFT_TUNNEL_MODE_NONE || + (priv->mode == NFT_TUNNEL_MODE_RX && + !(tun_info->mode & IP_TUNNEL_INFO_TX)) || + (priv->mode == NFT_TUNNEL_MODE_TX && + (tun_info->mode & IP_TUNNEL_INFO_TX))) + nft_reg_store8(dest, true); + else + nft_reg_store8(dest, false); + break; + case NFT_TUNNEL_ID: + if (!tun_info) { + regs->verdict.code = NFT_BREAK; + return; + } + if (priv->mode == NFT_TUNNEL_MODE_NONE || + (priv->mode == NFT_TUNNEL_MODE_RX && + !(tun_info->mode & IP_TUNNEL_INFO_TX)) || + (priv->mode == NFT_TUNNEL_MODE_TX && + (tun_info->mode & IP_TUNNEL_INFO_TX))) + *dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id)); + else + regs->verdict.code = NFT_BREAK; + break; + default: + WARN_ON(1); + regs->verdict.code = NFT_BREAK; + } +} + +static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = { + [NFTA_TUNNEL_KEY] = { .type = NLA_U32 }, + [NFTA_TUNNEL_DREG] = { .type = NLA_U32 }, + [NFTA_TUNNEL_MODE] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_tunnel *priv = nft_expr_priv(expr); + u32 len; + + if (!tb[NFTA_TUNNEL_KEY] || + !tb[NFTA_TUNNEL_DREG]) + return -EINVAL; + + priv->key = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY])); + switch (priv->key) { + case NFT_TUNNEL_PATH: + len = sizeof(u8); + break; + case NFT_TUNNEL_ID: + len = sizeof(u32); + break; + default: + return -EOPNOTSUPP; + } + + if (tb[NFTA_TUNNEL_MODE]) { + priv->mode = ntohl(nla_get_be32(tb[NFTA_TUNNEL_MODE])); + if (priv->mode > NFT_TUNNEL_MODE_MAX) + return -EOPNOTSUPP; + } else { + priv->mode = NFT_TUNNEL_MODE_NONE; + } + + priv->len = len; + return nft_parse_register_store(ctx, tb[NFTA_TUNNEL_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); +} + +static int nft_tunnel_get_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY, htonl(priv->key))) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_TUNNEL_DREG, priv->dreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_TUNNEL_MODE, htonl(priv->mode))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static bool nft_tunnel_get_reduce(struct nft_regs_track *track, + const struct nft_expr *expr) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + const struct nft_tunnel *tunnel; + + if (!nft_reg_track_cmp(track, expr, priv->dreg)) { + nft_reg_track_update(track, expr, priv->dreg, priv->len); + return false; + } + + tunnel = nft_expr_priv(track->regs[priv->dreg].selector); + if (priv->key != tunnel->key || + priv->dreg != tunnel->dreg || + priv->mode != tunnel->mode) { + nft_reg_track_update(track, expr, priv->dreg, priv->len); + return false; + } + + if (!track->regs[priv->dreg].bitwise) + return true; + + return false; +} + +static struct nft_expr_type nft_tunnel_type; +static const struct nft_expr_ops nft_tunnel_get_ops = { + .type = &nft_tunnel_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_tunnel)), + .eval = nft_tunnel_get_eval, + .init = nft_tunnel_get_init, + .dump = nft_tunnel_get_dump, + .reduce = nft_tunnel_get_reduce, +}; + +static struct nft_expr_type nft_tunnel_type __read_mostly = { + .name = "tunnel", + .family = NFPROTO_NETDEV, + .ops = &nft_tunnel_get_ops, + .policy = nft_tunnel_policy, + .maxattr = NFTA_TUNNEL_MAX, + .owner = THIS_MODULE, +}; + +struct nft_tunnel_opts { + union { + struct vxlan_metadata vxlan; + struct erspan_metadata erspan; + u8 data[IP_TUNNEL_OPTS_MAX]; + } u; + u32 len; + __be16 flags; +}; + +struct nft_tunnel_obj { + struct metadata_dst *md; + struct nft_tunnel_opts opts; +}; + +static const struct nla_policy nft_tunnel_ip_policy[NFTA_TUNNEL_KEY_IP_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP_SRC] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_IP_DST] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_obj_ip_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_IP_MAX + 1]; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_IP_MAX, attr, + nft_tunnel_ip_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_IP_DST]) + return -EINVAL; + + if (tb[NFTA_TUNNEL_KEY_IP_SRC]) + info->key.u.ipv4.src = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_SRC]); + if (tb[NFTA_TUNNEL_KEY_IP_DST]) + info->key.u.ipv4.dst = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_DST]); + + return 0; +} + +static const struct nla_policy nft_tunnel_ip6_policy[NFTA_TUNNEL_KEY_IP6_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP6_SRC] = { .len = sizeof(struct in6_addr), }, + [NFTA_TUNNEL_KEY_IP6_DST] = { .len = sizeof(struct in6_addr), }, + [NFTA_TUNNEL_KEY_IP6_FLOWLABEL] = { .type = NLA_U32, } +}; + +static int nft_tunnel_obj_ip6_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_IP6_MAX + 1]; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_IP6_MAX, attr, + nft_tunnel_ip6_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_IP6_DST]) + return -EINVAL; + + if (tb[NFTA_TUNNEL_KEY_IP6_SRC]) { + memcpy(&info->key.u.ipv6.src, + nla_data(tb[NFTA_TUNNEL_KEY_IP6_SRC]), + sizeof(struct in6_addr)); + } + if (tb[NFTA_TUNNEL_KEY_IP6_DST]) { + memcpy(&info->key.u.ipv6.dst, + nla_data(tb[NFTA_TUNNEL_KEY_IP6_DST]), + sizeof(struct in6_addr)); + } + if (tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]) + info->key.label = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]); + + info->mode |= IP_TUNNEL_INFO_IPV6; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_vxlan_policy[NFTA_TUNNEL_KEY_VXLAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_VXLAN_MAX + 1]; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_VXLAN_MAX, attr, + nft_tunnel_opts_vxlan_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_VXLAN_GBP]) + return -EINVAL; + + opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP])); + + opts->len = sizeof(struct vxlan_metadata); + opts->flags = TUNNEL_VXLAN_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_ERSPAN_VERSION] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_HWID] = { .type = NLA_U8 }, +}; + +static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1]; + uint8_t hwid, dir; + int err, version; + + err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_ERSPAN_MAX, + attr, nft_tunnel_opts_erspan_policy, + NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION]) + return -EINVAL; + + version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION])); + switch (version) { + case ERSPAN_VERSION: + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]) + return -EINVAL; + + opts->u.erspan.u.index = + nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]); + break; + case ERSPAN_VERSION2: + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] || + !tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]) + return -EINVAL; + + hwid = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]); + dir = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]); + + set_hwid(&opts->u.erspan.u.md2, hwid); + opts->u.erspan.u.md2.dir = dir; + break; + default: + return -EOPNOTSUPP; + } + opts->u.erspan.version = version; + + opts->len = sizeof(struct erspan_metadata); + opts->flags = TUNNEL_ERSPAN_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = { + [NFTA_TUNNEL_KEY_GENEVE_CLASS] = { .type = NLA_U16 }, + [NFTA_TUNNEL_KEY_GENEVE_TYPE] = { .type = NLA_U8 }, + [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, +}; + +static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len; + struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1]; + int err, data_len; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_GENEVE_MAX, attr, + nft_tunnel_opts_geneve_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_GENEVE_CLASS] || + !tb[NFTA_TUNNEL_KEY_GENEVE_TYPE] || + !tb[NFTA_TUNNEL_KEY_GENEVE_DATA]) + return -EINVAL; + + attr = tb[NFTA_TUNNEL_KEY_GENEVE_DATA]; + data_len = nla_len(attr); + if (data_len % 4) + return -EINVAL; + + opts->len += sizeof(*opt) + data_len; + if (opts->len > IP_TUNNEL_OPTS_MAX) + return -EINVAL; + + memcpy(opt->opt_data, nla_data(attr), data_len); + opt->length = data_len / 4; + opt->opt_class = nla_get_be16(tb[NFTA_TUNNEL_KEY_GENEVE_CLASS]); + opt->type = nla_get_u8(tb[NFTA_TUNNEL_KEY_GENEVE_TYPE]); + opts->flags = TUNNEL_GENEVE_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_policy[NFTA_TUNNEL_KEY_OPTS_MAX + 1] = { + [NFTA_TUNNEL_KEY_OPTS_UNSPEC] = { + .strict_start_type = NFTA_TUNNEL_KEY_OPTS_GENEVE }, + [NFTA_TUNNEL_KEY_OPTS_VXLAN] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_OPTS_ERSPAN] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_OPTS_GENEVE] = { .type = NLA_NESTED, }, +}; + +static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info, + struct nft_tunnel_opts *opts) +{ + struct nlattr *nla; + __be16 type = 0; + int err, rem; + + err = nla_validate_nested_deprecated(attr, NFTA_TUNNEL_KEY_OPTS_MAX, + nft_tunnel_opts_policy, NULL); + if (err < 0) + return err; + + nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(nla)) { + case NFTA_TUNNEL_KEY_OPTS_VXLAN: + if (type) + return -EINVAL; + err = nft_tunnel_obj_vxlan_init(nla, opts); + if (err) + return err; + type = TUNNEL_VXLAN_OPT; + break; + case NFTA_TUNNEL_KEY_OPTS_ERSPAN: + if (type) + return -EINVAL; + err = nft_tunnel_obj_erspan_init(nla, opts); + if (err) + return err; + type = TUNNEL_ERSPAN_OPT; + break; + case NFTA_TUNNEL_KEY_OPTS_GENEVE: + if (type && type != TUNNEL_GENEVE_OPT) + return -EINVAL; + err = nft_tunnel_obj_geneve_init(nla, opts); + if (err) + return err; + type = TUNNEL_GENEVE_OPT; + break; + default: + return -EOPNOTSUPP; + } + } + + return err; +} + +static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_IP6] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_ID] = { .type = NLA_U32, }, + [NFTA_TUNNEL_KEY_FLAGS] = { .type = NLA_U32, }, + [NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_SPORT] = { .type = NLA_U16, }, + [NFTA_TUNNEL_KEY_DPORT] = { .type = NLA_U16, }, + [NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, }, +}; + +static int nft_tunnel_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct ip_tunnel_info info; + struct metadata_dst *md; + int err; + + if (!tb[NFTA_TUNNEL_KEY_ID]) + return -EINVAL; + + memset(&info, 0, sizeof(info)); + info.mode = IP_TUNNEL_INFO_TX; + info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID])); + info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + + if (tb[NFTA_TUNNEL_KEY_IP]) { + err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info); + if (err < 0) + return err; + } else if (tb[NFTA_TUNNEL_KEY_IP6]) { + err = nft_tunnel_obj_ip6_init(ctx, tb[NFTA_TUNNEL_KEY_IP6], &info); + if (err < 0) + return err; + } else { + return -EINVAL; + } + + if (tb[NFTA_TUNNEL_KEY_SPORT]) { + info.key.tp_src = nla_get_be16(tb[NFTA_TUNNEL_KEY_SPORT]); + } + if (tb[NFTA_TUNNEL_KEY_DPORT]) { + info.key.tp_dst = nla_get_be16(tb[NFTA_TUNNEL_KEY_DPORT]); + } + + if (tb[NFTA_TUNNEL_KEY_FLAGS]) { + u32 tun_flags; + + tun_flags = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_FLAGS])); + if (tun_flags & ~NFT_TUNNEL_F_MASK) + return -EOPNOTSUPP; + + if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX) + info.key.tun_flags &= ~TUNNEL_CSUM; + if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT) + info.key.tun_flags |= TUNNEL_DONT_FRAGMENT; + if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER) + info.key.tun_flags |= TUNNEL_SEQ; + } + if (tb[NFTA_TUNNEL_KEY_TOS]) + info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); + if (tb[NFTA_TUNNEL_KEY_TTL]) + info.key.ttl = nla_get_u8(tb[NFTA_TUNNEL_KEY_TTL]); + else + info.key.ttl = U8_MAX; + + if (tb[NFTA_TUNNEL_KEY_OPTS]) { + err = nft_tunnel_obj_opts_init(ctx, tb[NFTA_TUNNEL_KEY_OPTS], + &info, &priv->opts); + if (err < 0) + return err; + } + + md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL); + if (!md) + return -ENOMEM; + + memcpy(&md->u.tun_info, &info, sizeof(info)); +#ifdef CONFIG_DST_CACHE + err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL); + if (err < 0) { + metadata_dst_free(md); + return err; + } +#endif + ip_tunnel_info_opts_set(&md->u.tun_info, &priv->opts.u, priv->opts.len, + priv->opts.flags); + priv->md = md; + + return 0; +} + +static inline void nft_tunnel_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct sk_buff *skb = pkt->skb; + + skb_dst_drop(skb); + dst_hold((struct dst_entry *) priv->md); + skb_dst_set(skb, (struct dst_entry *) priv->md); +} + +static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) +{ + struct nlattr *nest; + + if (info->mode & IP_TUNNEL_INFO_IPV6) { + nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_IP6); + if (!nest) + return -1; + + if (nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_SRC, + &info->key.u.ipv6.src) < 0 || + nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_DST, + &info->key.u.ipv6.dst) < 0 || + nla_put_be32(skb, NFTA_TUNNEL_KEY_IP6_FLOWLABEL, + info->key.label)) { + nla_nest_cancel(skb, nest); + return -1; + } + + nla_nest_end(skb, nest); + } else { + nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_IP); + if (!nest) + return -1; + + if (nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_SRC, + info->key.u.ipv4.src) < 0 || + nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_DST, + info->key.u.ipv4.dst) < 0) { + nla_nest_cancel(skb, nest); + return -1; + } + + nla_nest_end(skb, nest); + } + + return 0; +} + +static int nft_tunnel_opts_dump(struct sk_buff *skb, + struct nft_tunnel_obj *priv) +{ + struct nft_tunnel_opts *opts = &priv->opts; + struct nlattr *nest, *inner; + + nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS); + if (!nest) + return -1; + + if (opts->flags & TUNNEL_VXLAN_OPT) { + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_VXLAN); + if (!inner) + goto failure; + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_VXLAN_GBP, + htonl(opts->u.vxlan.gbp))) + goto inner_failure; + nla_nest_end(skb, inner); + } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_ERSPAN); + if (!inner) + goto failure; + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_VERSION, + htonl(opts->u.erspan.version))) + goto inner_failure; + switch (opts->u.erspan.version) { + case ERSPAN_VERSION: + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX, + opts->u.erspan.u.index)) + goto inner_failure; + break; + case ERSPAN_VERSION2: + if (nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_HWID, + get_hwid(&opts->u.erspan.u.md2)) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_DIR, + opts->u.erspan.u.md2.dir)) + goto inner_failure; + break; + } + nla_nest_end(skb, inner); + } else if (opts->flags & TUNNEL_GENEVE_OPT) { + struct geneve_opt *opt; + int offset = 0; + + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_GENEVE); + if (!inner) + goto failure; + while (opts->len > offset) { + opt = (struct geneve_opt *)opts->u.data + offset; + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS, + opt->opt_class) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE, + opt->type) || + nla_put(skb, NFTA_TUNNEL_KEY_GENEVE_DATA, + opt->length * 4, opt->opt_data)) + goto inner_failure; + offset += sizeof(*opt) + opt->length * 4; + } + nla_nest_end(skb, inner); + } + nla_nest_end(skb, nest); + return 0; + +inner_failure: + nla_nest_cancel(skb, inner); +failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static int nft_tunnel_ports_dump(struct sk_buff *skb, + struct ip_tunnel_info *info) +{ + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, info->key.tp_src) < 0 || + nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, info->key.tp_dst) < 0) + return -1; + + return 0; +} + +static int nft_tunnel_flags_dump(struct sk_buff *skb, + struct ip_tunnel_info *info) +{ + u32 flags = 0; + + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + flags |= NFT_TUNNEL_F_DONT_FRAGMENT; + if (!(info->key.tun_flags & TUNNEL_CSUM)) + flags |= NFT_TUNNEL_F_ZERO_CSUM_TX; + if (info->key.tun_flags & TUNNEL_SEQ) + flags |= NFT_TUNNEL_F_SEQ_NUMBER; + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0) + return -1; + + return 0; +} + +static int nft_tunnel_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct ip_tunnel_info *info = &priv->md->u.tun_info; + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ID, + tunnel_id_to_key32(info->key.tun_id)) || + nft_tunnel_ip_dump(skb, info) < 0 || + nft_tunnel_ports_dump(skb, info) < 0 || + nft_tunnel_flags_dump(skb, info) < 0 || + nla_put_u8(skb, NFTA_TUNNEL_KEY_TOS, info->key.tos) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_TTL, info->key.ttl) || + nft_tunnel_opts_dump(skb, priv) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static void nft_tunnel_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + + metadata_dst_free(priv->md); +} + +static struct nft_object_type nft_tunnel_obj_type; +static const struct nft_object_ops nft_tunnel_obj_ops = { + .type = &nft_tunnel_obj_type, + .size = sizeof(struct nft_tunnel_obj), + .eval = nft_tunnel_obj_eval, + .init = nft_tunnel_obj_init, + .destroy = nft_tunnel_obj_destroy, + .dump = nft_tunnel_obj_dump, +}; + +static struct nft_object_type nft_tunnel_obj_type __read_mostly = { + .type = NFT_OBJECT_TUNNEL, + .ops = &nft_tunnel_obj_ops, + .maxattr = NFTA_TUNNEL_KEY_MAX, + .policy = nft_tunnel_key_policy, + .owner = THIS_MODULE, +}; + +static int __init nft_tunnel_module_init(void) +{ + int err; + + err = nft_register_expr(&nft_tunnel_type); + if (err < 0) + return err; + + err = nft_register_obj(&nft_tunnel_obj_type); + if (err < 0) + nft_unregister_expr(&nft_tunnel_type); + + return err; +} + +static void __exit nft_tunnel_module_exit(void) +{ + nft_unregister_obj(&nft_tunnel_obj_type); + nft_unregister_expr(&nft_tunnel_type); +} + +module_init(nft_tunnel_module_init); +module_exit(nft_tunnel_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso "); +MODULE_ALIAS_NFT_EXPR("tunnel"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL); +MODULE_DESCRIPTION("nftables tunnel expression support"); -- cgit v1.2.3