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/ipv4/ipip.c | 662 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 662 insertions(+) create mode 100644 net/ipv4/ipip.c (limited to 'net/ipv4/ipip.c') diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c new file mode 100644 index 000000000..abea77759 --- /dev/null +++ b/net/ipv4/ipip.c @@ -0,0 +1,662 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Linux NET3: IP/IP protocol decoder. + * + * Authors: + * Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95 + * + * Fixes: + * Alan Cox : Merged and made usable non modular (its so tiny its silly as + * a module taking up 2 pages). + * Alan Cox : Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph) + * to keep ip_forward happy. + * Alan Cox : More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8). + * Kai Schulte : Fixed #defines for IP_FIREWALL->FIREWALL + * David Woodhouse : Perform some basic ICMP handling. + * IPIP Routing without decapsulation. + * Carlos Picoto : GRE over IP support + * Alexey Kuznetsov: Reworked. Really, now it is truncated version of ipv4/ip_gre.c. + * I do not want to merge them together. + */ + +/* tunnel.c: an IP tunnel driver + + The purpose of this driver is to provide an IP tunnel through + which you can tunnel network traffic transparently across subnets. + + This was written by looking at Nick Holloway's dummy driver + Thanks for the great code! + + -Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95 + + Minor tweaks: + Cleaned up the code a little and added some pre-1.3.0 tweaks. + dev->hard_header/hard_header_len changed to use no headers. + Comments/bracketing tweaked. + Made the tunnels use dev->name not tunnel: when error reporting. + Added tx_dropped stat + + -Alan Cox (alan@lxorguk.ukuu.org.uk) 21 March 95 + + Reworked: + Changed to tunnel to destination gateway in addition to the + tunnel's pointopoint address + Almost completely rewritten + Note: There is currently no firewall or ICMP handling done. + + -Sam Lantinga (slouken@cs.ucdavis.edu) 02/13/96 + +*/ + +/* Things I wish I had known when writing the tunnel driver: + + When the tunnel_xmit() function is called, the skb contains the + packet to be sent (plus a great deal of extra info), and dev + contains the tunnel device that _we_ are. + + When we are passed a packet, we are expected to fill in the + source address with our source IP address. + + What is the proper way to allocate, copy and free a buffer? + After you allocate it, it is a "0 length" chunk of memory + starting at zero. If you want to add headers to the buffer + later, you'll have to call "skb_reserve(skb, amount)" with + the amount of memory you want reserved. Then, you call + "skb_put(skb, amount)" with the amount of space you want in + the buffer. skb_put() returns a pointer to the top (#0) of + that buffer. skb->len is set to the amount of space you have + "allocated" with skb_put(). You can then write up to skb->len + bytes to that buffer. If you need more, you can call skb_put() + again with the additional amount of space you need. You can + find out how much more space you can allocate by calling + "skb_tailroom(skb)". + Now, to add header space, call "skb_push(skb, header_len)". + This creates space at the beginning of the buffer and returns + a pointer to this new space. If later you need to strip a + header from a buffer, call "skb_pull(skb, header_len)". + skb_headroom() will return how much space is left at the top + of the buffer (before the main data). Remember, this headroom + space must be reserved before the skb_put() function is called. + */ + +/* + This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c + + For comments look at net/ipv4/ip_gre.c --ANK + */ + + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + +static unsigned int ipip_net_id __read_mostly; + +static int ipip_tunnel_init(struct net_device *dev); +static struct rtnl_link_ops ipip_link_ops __read_mostly; + +static int ipip_err(struct sk_buff *skb, u32 info) +{ + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + */ + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + const struct iphdr *iph = (const struct iphdr *)skb->data; + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct ip_tunnel *t; + int err = 0; + + t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); + if (!t) { + err = -ENOENT; + goto out; + } + + switch (type) { + case ICMP_DEST_UNREACH: + switch (code) { + case ICMP_SR_FAILED: + /* Impossible event. */ + goto out; + default: + /* All others are translated to HOST_UNREACH. + * rfc2003 contains "deep thoughts" about NET_UNREACH, + * I believe they are just ether pollution. --ANK + */ + break; + } + break; + + case ICMP_TIME_EXCEEDED: + if (code != ICMP_EXC_TTL) + goto out; + break; + + case ICMP_REDIRECT: + break; + + default: + goto out; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol); + goto out; + } + + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, net, t->parms.link, iph->protocol); + goto out; + } + + if (t->parms.iph.daddr == 0) { + err = -ENOENT; + goto out; + } + + if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) + goto out; + + if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) + t->err_count++; + else + t->err_count = 1; + t->err_time = jiffies; + +out: + return err; +} + +static const struct tnl_ptk_info ipip_tpi = { + /* no tunnel info required for ipip. */ + .proto = htons(ETH_P_IP), +}; + +#if IS_ENABLED(CONFIG_MPLS) +static const struct tnl_ptk_info mplsip_tpi = { + /* no tunnel info required for mplsip. */ + .proto = htons(ETH_P_MPLS_UC), +}; +#endif + +static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) +{ + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + struct metadata_dst *tun_dst = NULL; + struct ip_tunnel *tunnel; + const struct iphdr *iph; + + iph = ip_hdr(skb); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + const struct tnl_ptk_info *tpi; + + if (tunnel->parms.iph.protocol != ipproto && + tunnel->parms.iph.protocol != 0) + goto drop; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; +#if IS_ENABLED(CONFIG_MPLS) + if (ipproto == IPPROTO_MPLS) + tpi = &mplsip_tpi; + else +#endif + tpi = &ipip_tpi; + if (iptunnel_pull_header(skb, 0, tpi->proto, false)) + goto drop; + if (tunnel->collect_md) { + tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + if (!tun_dst) + return 0; + } + skb_reset_mac_header(skb); + + return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); + } + + return -1; + +drop: + kfree_skb(skb); + return 0; +} + +static int ipip_rcv(struct sk_buff *skb) +{ + return ipip_tunnel_rcv(skb, IPPROTO_IPIP); +} + +#if IS_ENABLED(CONFIG_MPLS) +static int mplsip_rcv(struct sk_buff *skb) +{ + return ipip_tunnel_rcv(skb, IPPROTO_MPLS); +} +#endif + +/* + * This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ +static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + const struct iphdr *tiph = &tunnel->parms.iph; + u8 ipproto; + + if (!pskb_inet_may_pull(skb)) + goto tx_error; + + switch (skb->protocol) { + case htons(ETH_P_IP): + ipproto = IPPROTO_IPIP; + break; +#if IS_ENABLED(CONFIG_MPLS) + case htons(ETH_P_MPLS_UC): + ipproto = IPPROTO_MPLS; + break; +#endif + default: + goto tx_error; + } + + if (tiph->protocol != ipproto && tiph->protocol != 0) + goto tx_error; + + if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) + goto tx_error; + + skb_set_inner_ipproto(skb, ipproto); + + if (tunnel->collect_md) + ip_md_tunnel_xmit(skb, dev, ipproto, 0); + else + ip_tunnel_xmit(skb, dev, tiph, ipproto); + return NETDEV_TX_OK; + +tx_error: + kfree_skb(skb); + + DEV_STATS_INC(dev, tx_errors); + return NETDEV_TX_OK; +} + +static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) +{ + switch (ipproto) { + case 0: + case IPPROTO_IPIP: +#if IS_ENABLED(CONFIG_MPLS) + case IPPROTO_MPLS: +#endif + return true; + } + + return false; +} + +static int +ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +{ + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { + if (p->iph.version != 4 || + !ipip_tunnel_ioctl_verify_protocol(p->iph.protocol) || + p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) + return -EINVAL; + } + + p->i_key = p->o_key = 0; + p->i_flags = p->o_flags = 0; + return ip_tunnel_ctl(dev, p, cmd); +} + +static const struct net_device_ops ipip_netdev_ops = { + .ndo_init = ipip_tunnel_init, + .ndo_uninit = ip_tunnel_uninit, + .ndo_start_xmit = ipip_tunnel_xmit, + .ndo_siocdevprivate = ip_tunnel_siocdevprivate, + .ndo_change_mtu = ip_tunnel_change_mtu, + .ndo_get_stats64 = dev_get_tstats64, + .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_tunnel_ctl = ipip_tunnel_ctl, +}; + +#define IPIP_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_GSO_SOFTWARE | \ + NETIF_F_HW_CSUM) + +static void ipip_tunnel_setup(struct net_device *dev) +{ + dev->netdev_ops = &ipip_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; + + dev->type = ARPHRD_TUNNEL; + dev->flags = IFF_NOARP; + dev->addr_len = 4; + dev->features |= NETIF_F_LLTX; + netif_keep_dst(dev); + + dev->features |= IPIP_FEATURES; + dev->hw_features |= IPIP_FEATURES; + ip_tunnel_setup(dev, ipip_net_id); +} + +static int ipip_tunnel_init(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + + __dev_addr_set(dev, &tunnel->parms.iph.saddr, 4); + memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + + tunnel->tun_hlen = 0; + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; + return ip_tunnel_init(dev); +} + +static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + u8 proto; + + if (!data || !data[IFLA_IPTUN_PROTO]) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPIP && proto != IPPROTO_MPLS && proto != 0) + return -EINVAL; + + return 0; +} + +static void ipip_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms, bool *collect_md, + __u32 *fwmark) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPIP; + parms->iph.ihl = 5; + *collect_md = false; + + if (!data) + return; + + ip_tunnel_netlink_parms(data, parms); + + if (data[IFLA_IPTUN_COLLECT_METADATA]) + *collect_md = true; + + if (data[IFLA_IPTUN_FWMARK]) + *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); +} + +static int ipip_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm p; + struct ip_tunnel_encap ipencap; + __u32 fwmark = 0; + + if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { + int err = ip_tunnel_encap_setup(t, &ipencap); + + if (err < 0) + return err; + } + + ipip_netlink_parms(data, &p, &t->collect_md, &fwmark); + return ip_tunnel_newlink(dev, tb, &p, fwmark); +} + +static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm p; + struct ip_tunnel_encap ipencap; + bool collect_md; + __u32 fwmark = t->fwmark; + + if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { + int err = ip_tunnel_encap_setup(t, &ipencap); + + if (err < 0) + return err; + } + + ipip_netlink_parms(data, &p, &collect_md, &fwmark); + if (collect_md) + return -EINVAL; + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + return ip_tunnel_changelink(dev, tb, &p, fwmark); +} + +static size_t ipip_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(4) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(4) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_TOS */ + nla_total_size(1) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + + /* IFLA_IPTUN_PMTUDISC */ + nla_total_size(1) + + /* IFLA_IPTUN_ENCAP_TYPE */ + nla_total_size(2) + + /* IFLA_IPTUN_ENCAP_FLAGS */ + nla_total_size(2) + + /* IFLA_IPTUN_ENCAP_SPORT */ + nla_total_size(2) + + /* IFLA_IPTUN_ENCAP_DPORT */ + nla_total_size(2) + + /* IFLA_IPTUN_COLLECT_METADATA */ + nla_total_size(0) + + /* IFLA_IPTUN_FWMARK */ + nla_total_size(4) + + 0; +} + +static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct ip_tunnel_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || + nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || + nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, + !!(parm->iph.frag_off & htons(IP_DF))) || + nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, + tunnel->encap.type) || + nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, + tunnel->encap.sport) || + nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, + tunnel->encap.dport) || + nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, + tunnel->encap.flags)) + goto nla_put_failure; + + if (tunnel->collect_md) + if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, + [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, + [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, + [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, + [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, + [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, + [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops ipip_link_ops __read_mostly = { + .kind = "ipip", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip_tunnel_setup, + .validate = ipip_tunnel_validate, + .newlink = ipip_newlink, + .changelink = ipip_changelink, + .dellink = ip_tunnel_dellink, + .get_size = ipip_get_size, + .fill_info = ipip_fill_info, + .get_link_net = ip_tunnel_get_link_net, +}; + +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = ipip_rcv, + .err_handler = ipip_err, + .priority = 1, +}; + +#if IS_ENABLED(CONFIG_MPLS) +static struct xfrm_tunnel mplsip_handler __read_mostly = { + .handler = mplsip_rcv, + .err_handler = ipip_err, + .priority = 1, +}; +#endif + +static int __net_init ipip_init_net(struct net *net) +{ + return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); +} + +static void __net_exit ipip_exit_batch_net(struct list_head *list_net) +{ + ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); +} + +static struct pernet_operations ipip_net_ops = { + .init = ipip_init_net, + .exit_batch = ipip_exit_batch_net, + .id = &ipip_net_id, + .size = sizeof(struct ip_tunnel_net), +}; + +static int __init ipip_init(void) +{ + int err; + + pr_info("ipip: IPv4 and MPLS over IPv4 tunneling driver\n"); + + err = register_pernet_device(&ipip_net_ops); + if (err < 0) + return err; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: can't register tunnel\n", __func__); + goto xfrm_tunnel_ipip_failed; + } +#if IS_ENABLED(CONFIG_MPLS) + err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); + if (err < 0) { + pr_info("%s: can't register tunnel\n", __func__); + goto xfrm_tunnel_mplsip_failed; + } +#endif + err = rtnl_link_register(&ipip_link_ops); + if (err < 0) + goto rtnl_link_failed; + +out: + return err; + +rtnl_link_failed: +#if IS_ENABLED(CONFIG_MPLS) + xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); +xfrm_tunnel_mplsip_failed: + +#endif + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel_ipip_failed: + unregister_pernet_device(&ipip_net_ops); + goto out; +} + +static void __exit ipip_fini(void) +{ + rtnl_link_unregister(&ipip_link_ops); + if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) + pr_info("%s: can't deregister tunnel\n", __func__); +#if IS_ENABLED(CONFIG_MPLS) + if (xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS)) + pr_info("%s: can't deregister tunnel\n", __func__); +#endif + unregister_pernet_device(&ipip_net_ops); +} + +module_init(ipip_init); +module_exit(ipip_fini); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ipip"); +MODULE_ALIAS_NETDEV("tunl0"); -- cgit v1.2.3