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(). ... --- include/net/ip_tunnels.h | 557 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 557 insertions(+) create mode 100644 include/net/ip_tunnels.h (limited to 'include/net/ip_tunnels.h') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h new file mode 100644 index 000000000..fca357679 --- /dev/null +++ b/include/net/ip_tunnels.h @@ -0,0 +1,557 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_IP_TUNNELS_H +#define __NET_IP_TUNNELS_H 1 + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_IPV6) +#include +#include +#include +#endif + +/* Keep error state on tunnel for 30 sec */ +#define IPTUNNEL_ERR_TIMEO (30*HZ) + +/* Used to memset ip_tunnel padding. */ +#define IP_TUNNEL_KEY_SIZE offsetofend(struct ip_tunnel_key, tp_dst) + +/* Used to memset ipv4 address padding. */ +#define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) +#define IP_TUNNEL_KEY_IPV4_PAD_LEN \ + (sizeof_field(struct ip_tunnel_key, u) - \ + sizeof_field(struct ip_tunnel_key, u.ipv4)) + +struct ip_tunnel_key { + __be64 tun_id; + union { + struct { + __be32 src; + __be32 dst; + } ipv4; + struct { + struct in6_addr src; + struct in6_addr dst; + } ipv6; + } u; + __be16 tun_flags; + u8 tos; /* TOS for IPv4, TC for IPv6 */ + u8 ttl; /* TTL for IPv4, HL for IPv6 */ + __be32 label; /* Flow Label for IPv6 */ + __be16 tp_src; + __be16 tp_dst; + __u8 flow_flags; +}; + +/* Flags for ip_tunnel_info mode. */ +#define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ +#define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ +#define IP_TUNNEL_INFO_BRIDGE 0x04 /* represents a bridged tunnel id */ + +/* Maximum tunnel options length. */ +#define IP_TUNNEL_OPTS_MAX \ + GENMASK((sizeof_field(struct ip_tunnel_info, \ + options_len) * BITS_PER_BYTE) - 1, 0) + +struct ip_tunnel_info { + struct ip_tunnel_key key; +#ifdef CONFIG_DST_CACHE + struct dst_cache dst_cache; +#endif + u8 options_len; + u8 mode; +}; + +/* 6rd prefix/relay information */ +#ifdef CONFIG_IPV6_SIT_6RD +struct ip_tunnel_6rd_parm { + struct in6_addr prefix; + __be32 relay_prefix; + u16 prefixlen; + u16 relay_prefixlen; +}; +#endif + +struct ip_tunnel_encap { + u16 type; + u16 flags; + __be16 sport; + __be16 dport; +}; + +struct ip_tunnel_prl_entry { + struct ip_tunnel_prl_entry __rcu *next; + __be32 addr; + u16 flags; + struct rcu_head rcu_head; +}; + +struct metadata_dst; + +struct ip_tunnel { + struct ip_tunnel __rcu *next; + struct hlist_node hash_node; + + struct net_device *dev; + netdevice_tracker dev_tracker; + + struct net *net; /* netns for packet i/o */ + + unsigned long err_time; /* Time when the last ICMP error + * arrived */ + int err_count; /* Number of arrived ICMP errors */ + + /* These four fields used only by GRE */ + u32 i_seqno; /* The last seen seqno */ + atomic_t o_seqno; /* The last output seqno */ + int tun_hlen; /* Precalculated header length */ + + /* These four fields used only by ERSPAN */ + u32 index; /* ERSPAN type II index */ + u8 erspan_ver; /* ERSPAN version */ + u8 dir; /* ERSPAN direction */ + u16 hwid; /* ERSPAN hardware ID */ + + struct dst_cache dst_cache; + + struct ip_tunnel_parm parms; + + int mlink; + int encap_hlen; /* Encap header length (FOU,GUE) */ + int hlen; /* tun_hlen + encap_hlen */ + struct ip_tunnel_encap encap; + + /* for SIT */ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd_parm ip6rd; +#endif + struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ + unsigned int prl_count; /* # of entries in PRL */ + unsigned int ip_tnl_net_id; + struct gro_cells gro_cells; + __u32 fwmark; + bool collect_md; + bool ignore_df; +}; + +struct tnl_ptk_info { + __be16 flags; + __be16 proto; + __be32 key; + __be32 seq; + int hdr_len; +}; + +#define PACKET_RCVD 0 +#define PACKET_REJECT 1 +#define PACKET_NEXT 2 + +#define IP_TNL_HASH_BITS 7 +#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS) + +struct ip_tunnel_net { + struct net_device *fb_tunnel_dev; + struct rtnl_link_ops *rtnl_link_ops; + struct hlist_head tunnels[IP_TNL_HASH_SIZE]; + struct ip_tunnel __rcu *collect_md_tun; + int type; +}; + +static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, + __be32 saddr, __be32 daddr, + u8 tos, u8 ttl, __be32 label, + __be16 tp_src, __be16 tp_dst, + __be64 tun_id, __be16 tun_flags) +{ + key->tun_id = tun_id; + key->u.ipv4.src = saddr; + key->u.ipv4.dst = daddr; + memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD, + 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); + key->tos = tos; + key->ttl = ttl; + key->label = label; + key->tun_flags = tun_flags; + + /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of + * the upper tunnel are used. + * E.g: GRE over IPSEC, the tp_src and tp_port are zero. + */ + key->tp_src = tp_src; + key->tp_dst = tp_dst; + + /* Clear struct padding. */ + if (sizeof(*key) != IP_TUNNEL_KEY_SIZE) + memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE, + 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); +} + +static inline bool +ip_tunnel_dst_cache_usable(const struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + if (skb->mark) + return false; + if (!info) + return true; + if (info->key.tun_flags & TUNNEL_NOCACHE) + return false; + + return true; +} + +static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info + *tun_info) +{ + return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET; +} + +static inline __be64 key32_to_tunnel_id(__be32 key) +{ +#ifdef __BIG_ENDIAN + return (__force __be64)key; +#else + return (__force __be64)((__force u64)key << 32); +#endif +} + +/* Returns the least-significant 32 bits of a __be64. */ +static inline __be32 tunnel_id_to_key32(__be64 tun_id) +{ +#ifdef __BIG_ENDIAN + return (__force __be32)tun_id; +#else + return (__force __be32)((__force u64)tun_id >> 32); +#endif +} + +#ifdef CONFIG_INET + +static inline void ip_tunnel_init_flow(struct flowi4 *fl4, + int proto, + __be32 daddr, __be32 saddr, + __be32 key, __u8 tos, + struct net *net, int oif, + __u32 mark, __u32 tun_inner_hash, + __u8 flow_flags) +{ + memset(fl4, 0, sizeof(*fl4)); + + if (oif) { + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + /* Legacy VRF/l3mdev use case */ + fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; + } + + fl4->daddr = daddr; + fl4->saddr = saddr; + fl4->flowi4_tos = tos; + fl4->flowi4_proto = proto; + fl4->fl4_gre_key = key; + fl4->flowi4_mark = mark; + fl4->flowi4_multipath_hash = tun_inner_hash; + fl4->flowi4_flags = flow_flags; +} + +int ip_tunnel_init(struct net_device *dev); +void ip_tunnel_uninit(struct net_device *dev); +void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); +struct net *ip_tunnel_get_link_net(const struct net_device *dev); +int ip_tunnel_get_iflink(const struct net_device *dev); +int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, + struct rtnl_link_ops *ops, char *devname); + +void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, + struct rtnl_link_ops *ops); + +void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + const struct iphdr *tnl_params, const u8 protocol); +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + const u8 proto, int tunnel_hlen); +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd); +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); + +struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, + int link, __be16 flags, + __be32 remote, __be32 local, + __be32 key); + +int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, + const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, + bool log_ecn_error); +int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], + struct ip_tunnel_parm *p, __u32 fwmark); +int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], + struct ip_tunnel_parm *p, __u32 fwmark); +void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); + +bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], + struct ip_tunnel_encap *encap); + +void ip_tunnel_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms); + +extern const struct header_ops ip_tunnel_header_ops; +__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); + +struct ip_tunnel_encap_ops { + size_t (*encap_hlen)(struct ip_tunnel_encap *e); + int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4); + int (*err_handler)(struct sk_buff *skb, u32 info); +}; + +#define MAX_IPTUN_ENCAP_OPS 8 + +extern const struct ip_tunnel_encap_ops __rcu * + iptun_encaps[MAX_IPTUN_ENCAP_OPS]; + +int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op, + unsigned int num); +int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, + unsigned int num); + +int ip_tunnel_encap_setup(struct ip_tunnel *t, + struct ip_tunnel_encap *ipencap); + +static inline bool pskb_inet_may_pull(struct sk_buff *skb) +{ + int nhlen; + + switch (skb->protocol) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + default: + nhlen = 0; + } + + return pskb_network_may_pull(skb, nhlen); +} + +static inline int ip_encap_hlen(struct ip_tunnel_encap *e) +{ + const struct ip_tunnel_encap_ops *ops; + int hlen = -EINVAL; + + if (e->type == TUNNEL_ENCAP_NONE) + return 0; + + if (e->type >= MAX_IPTUN_ENCAP_OPS) + return -EINVAL; + + rcu_read_lock(); + ops = rcu_dereference(iptun_encaps[e->type]); + if (likely(ops && ops->encap_hlen)) + hlen = ops->encap_hlen(e); + rcu_read_unlock(); + + return hlen; +} + +static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, + u8 *protocol, struct flowi4 *fl4) +{ + const struct ip_tunnel_encap_ops *ops; + int ret = -EINVAL; + + if (t->encap.type == TUNNEL_ENCAP_NONE) + return 0; + + if (t->encap.type >= MAX_IPTUN_ENCAP_OPS) + return -EINVAL; + + rcu_read_lock(); + ops = rcu_dereference(iptun_encaps[t->encap.type]); + if (likely(ops && ops->build_header)) + ret = ops->build_header(skb, &t->encap, protocol, fl4); + rcu_read_unlock(); + + return ret; +} + +/* Extract dsfield from inner protocol */ +static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, + const struct sk_buff *skb) +{ + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IP)) + return iph->tos; + else if (payload_protocol == htons(ETH_P_IPV6)) + return ipv6_get_dsfield((const struct ipv6hdr *)iph); + else + return 0; +} + +static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, + const struct sk_buff *skb) +{ + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IP)) + return iph->ttl; + else if (payload_protocol == htons(ETH_P_IPV6)) + return ((const struct ipv6hdr *)iph)->hop_limit; + else + return 0; +} + +/* Propogate ECN bits out */ +static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, + const struct sk_buff *skb) +{ + u8 inner = ip_tunnel_get_dsfield(iph, skb); + + return INET_ECN_encapsulate(tos, inner); +} + +int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool raw_proto, bool xnet); + +static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool xnet) +{ + return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, xnet); +} + +void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, + __be32 src, __be32 dst, u8 proto, + u8 tos, u8 ttl, __be16 df, bool xnet); +struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, + gfp_t flags); +int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, + int headroom, bool reply); + +int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); + +static inline int iptunnel_pull_offloads(struct sk_buff *skb) +{ + if (skb_is_gso(skb)) { + int err; + + err = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(err)) + return err; + skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >> + NETIF_F_GSO_SHIFT); + } + + skb->encapsulation = 0; + return 0; +} + +static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) +{ + if (pkt_len > 0) { + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); + u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); + } else { + struct net_device_stats *err_stats = &dev->stats; + + if (pkt_len < 0) { + err_stats->tx_errors++; + err_stats->tx_aborted_errors++; + } else { + err_stats->tx_dropped++; + } + } +} + +static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info) +{ + return info + 1; +} + +static inline void ip_tunnel_info_opts_get(void *to, + const struct ip_tunnel_info *info) +{ + memcpy(to, info + 1, info->options_len); +} + +static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, + const void *from, int len, + __be16 flags) +{ + info->options_len = len; + if (len > 0) { + memcpy(ip_tunnel_info_opts(info), from, len); + info->key.tun_flags |= flags; + } +} + +static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) +{ + return (struct ip_tunnel_info *)lwtstate->data; +} + +DECLARE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); + +/* Returns > 0 if metadata should be collected */ +static inline int ip_tunnel_collect_metadata(void) +{ + return static_branch_unlikely(&ip_tunnel_metadata_cnt); +} + +void __init ip_tunnel_core_init(void); + +void ip_tunnel_need_metadata(void); +void ip_tunnel_unneed_metadata(void); + +#else /* CONFIG_INET */ + +static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) +{ + return NULL; +} + +static inline void ip_tunnel_need_metadata(void) +{ +} + +static inline void ip_tunnel_unneed_metadata(void) +{ +} + +static inline void ip_tunnel_info_opts_get(void *to, + const struct ip_tunnel_info *info) +{ +} + +static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, + const void *from, int len, + __be16 flags) +{ + info->options_len = 0; +} + +#endif /* CONFIG_INET */ + +#endif /* __NET_IP_TUNNELS_H */ -- cgit v1.2.3