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/dst.h | 560 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 560 insertions(+) create mode 100644 include/net/dst.h (limited to 'include/net/dst.h') diff --git a/include/net/dst.h b/include/net/dst.h new file mode 100644 index 000000000..d67fda89c --- /dev/null +++ b/include/net/dst.h @@ -0,0 +1,560 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * net/dst.h Protocol independent destination cache definitions. + * + * Authors: Alexey Kuznetsov, + * + */ + +#ifndef _NET_DST_H +#define _NET_DST_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct sk_buff; + +struct dst_entry { + struct net_device *dev; + struct dst_ops *ops; + unsigned long _metrics; + unsigned long expires; +#ifdef CONFIG_XFRM + struct xfrm_state *xfrm; +#else + void *__pad1; +#endif + int (*input)(struct sk_buff *); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); + + unsigned short flags; +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOCOUNT 0x0008 +#define DST_FAKE_RTABLE 0x0010 +#define DST_XFRM_TUNNEL 0x0020 +#define DST_XFRM_QUEUE 0x0040 +#define DST_METADATA 0x0080 + + /* A non-zero value of dst->obsolete forces by-hand validation + * of the route entry. Positive values are set by the generic + * dst layer to indicate that the entry has been forcefully + * destroyed. + * + * Negative values are used by the implementation layer code to + * force invocation of the dst_ops->check() method. + */ + short obsolete; +#define DST_OBSOLETE_NONE 0 +#define DST_OBSOLETE_DEAD 2 +#define DST_OBSOLETE_FORCE_CHK -1 +#define DST_OBSOLETE_KILL -2 + unsigned short header_len; /* more space at head required */ + unsigned short trailer_len; /* space to reserve at tail */ + + /* + * __refcnt wants to be on a different cache line from + * input/output/ops or performance tanks badly + */ +#ifdef CONFIG_64BIT + atomic_t __refcnt; /* 64-bit offset 64 */ +#endif + int __use; + unsigned long lastuse; + struct lwtunnel_state *lwtstate; + struct rcu_head rcu_head; + short error; + short __pad; + __u32 tclassid; +#ifndef CONFIG_64BIT + atomic_t __refcnt; /* 32-bit offset 64 */ +#endif + netdevice_tracker dev_tracker; +}; + +struct dst_metrics { + u32 metrics[RTAX_MAX]; + refcount_t refcnt; +} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ +extern const struct dst_metrics dst_default_metrics; + +u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); + +#define DST_METRICS_READ_ONLY 0x1UL +#define DST_METRICS_REFCOUNTED 0x2UL +#define DST_METRICS_FLAGS 0x3UL +#define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_FLAGS)) +#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) + +static inline bool dst_metrics_read_only(const struct dst_entry *dst) +{ + return dst->_metrics & DST_METRICS_READ_ONLY; +} + +void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); + +static inline void dst_destroy_metrics_generic(struct dst_entry *dst) +{ + unsigned long val = dst->_metrics; + if (!(val & DST_METRICS_READ_ONLY)) + __dst_destroy_metrics_generic(dst, val); +} + +static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) +{ + unsigned long p = dst->_metrics; + + BUG_ON(!p); + + if (p & DST_METRICS_READ_ONLY) + return dst->ops->cow_metrics(dst, p); + return __DST_METRICS_PTR(p); +} + +/* This may only be invoked before the entry has reached global + * visibility. + */ +static inline void dst_init_metrics(struct dst_entry *dst, + const u32 *src_metrics, + bool read_only) +{ + dst->_metrics = ((unsigned long) src_metrics) | + (read_only ? DST_METRICS_READ_ONLY : 0); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + u32 *dst_metrics = dst_metrics_write_ptr(dest); + + if (dst_metrics) { + u32 *src_metrics = DST_METRICS_PTR(src); + + memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); + } +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return DST_METRICS_PTR(dst); +} + +static inline u32 +dst_metric_raw(const struct dst_entry *dst, const int metric) +{ + u32 *p = DST_METRICS_PTR(dst); + + return p[metric-1]; +} + +static inline u32 +dst_metric(const struct dst_entry *dst, const int metric) +{ + WARN_ON_ONCE(metric == RTAX_HOPLIMIT || + metric == RTAX_ADVMSS || + metric == RTAX_MTU); + return dst_metric_raw(dst, metric); +} + +static inline u32 +dst_metric_advmss(const struct dst_entry *dst) +{ + u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS); + + if (!advmss) + advmss = dst->ops->default_advmss(dst); + + return advmss; +} + +static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) +{ + u32 *p = dst_metrics_write_ptr(dst); + + if (p) + p[metric-1] = val; +} + +/* Kernel-internal feature bits that are unallocated in user space. */ +#define DST_FEATURE_ECN_CA (1U << 31) + +#define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) +#define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) + +static inline u32 +dst_feature(const struct dst_entry *dst, u32 feature) +{ + return dst_metric(dst, RTAX_FEATURES) & feature; +} + +INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *)); +INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *)); +static inline u32 dst_mtu(const struct dst_entry *dst) +{ + return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); +} + +/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ +static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric) +{ + return msecs_to_jiffies(dst_metric(dst, metric)); +} + +static inline u32 +dst_allfrag(const struct dst_entry *dst) +{ + int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); + return ret; +} + +static inline int +dst_metric_locked(const struct dst_entry *dst, int metric) +{ + return dst_metric(dst, RTAX_LOCK) & (1 << metric); +} + +static inline void dst_hold(struct dst_entry *dst) +{ + /* + * If your kernel compilation stops here, please check + * the placement of __refcnt in struct dst_entry + */ + BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63); + WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); +} + +static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) +{ + if (unlikely(time != dst->lastuse)) { + dst->__use++; + dst->lastuse = time; + } +} + +static inline struct dst_entry *dst_clone(struct dst_entry *dst) +{ + if (dst) + dst_hold(dst); + return dst; +} + +void dst_release(struct dst_entry *dst); + +void dst_release_immediate(struct dst_entry *dst); + +static inline void refdst_drop(unsigned long refdst) +{ + if (!(refdst & SKB_DST_NOREF)) + dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK)); +} + +/** + * skb_dst_drop - drops skb dst + * @skb: buffer + * + * Drops dst reference count if a reference was taken. + */ +static inline void skb_dst_drop(struct sk_buff *skb) +{ + if (skb->_skb_refdst) { + refdst_drop(skb->_skb_refdst); + skb->_skb_refdst = 0UL; + } +} + +static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) +{ + nskb->slow_gro |= !!refdst; + nskb->_skb_refdst = refdst; + if (!(nskb->_skb_refdst & SKB_DST_NOREF)) + dst_clone(skb_dst(nskb)); +} + +static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb) +{ + __skb_dst_copy(nskb, oskb->_skb_refdst); +} + +/** + * dst_hold_safe - Take a reference on a dst if possible + * @dst: pointer to dst entry + * + * This helper returns false if it could not safely + * take a reference on a dst. + */ +static inline bool dst_hold_safe(struct dst_entry *dst) +{ + return atomic_inc_not_zero(&dst->__refcnt); +} + +/** + * skb_dst_force - makes sure skb dst is refcounted + * @skb: buffer + * + * If dst is not yet refcounted and not destroyed, grab a ref on it. + * Returns true if dst is refcounted. + */ +static inline bool skb_dst_force(struct sk_buff *skb) +{ + if (skb_dst_is_noref(skb)) { + struct dst_entry *dst = skb_dst(skb); + + WARN_ON(!rcu_read_lock_held()); + if (!dst_hold_safe(dst)) + dst = NULL; + + skb->_skb_refdst = (unsigned long)dst; + skb->slow_gro |= !!dst; + } + + return skb->_skb_refdst != 0UL; +} + + +/** + * __skb_tunnel_rx - prepare skb for rx reinsert + * @skb: buffer + * @dev: tunnel device + * @net: netns for packet i/o + * + * After decapsulation, packet is going to re-enter (netif_rx()) our stack, + * so make some cleanups. (no accounting done) + */ +static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, + struct net *net) +{ + skb->dev = dev; + + /* + * Clear hash so that we can recalulate the hash for the + * encapsulated packet, unless we have already determine the hash + * over the L4 4-tuple. + */ + skb_clear_hash_if_not_l4(skb); + skb_set_queue_mapping(skb, 0); + skb_scrub_packet(skb, !net_eq(net, dev_net(dev))); +} + +/** + * skb_tunnel_rx - prepare skb for rx reinsert + * @skb: buffer + * @dev: tunnel device + * @net: netns for packet i/o + * + * After decapsulation, packet is going to re-enter (netif_rx()) our stack, + * so make some cleanups, and perform accounting. + * Note: this accounting is not SMP safe. + */ +static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, + struct net *net) +{ + DEV_STATS_INC(dev, rx_packets); + DEV_STATS_ADD(dev, rx_bytes, skb->len); + __skb_tunnel_rx(skb, dev, net); +} + +static inline u32 dst_tclassid(const struct sk_buff *skb) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + const struct dst_entry *dst; + + dst = skb_dst(skb); + if (dst) + return dst->tclassid; +#endif + return 0; +} + +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); +static inline int dst_discard(struct sk_buff *skb) +{ + return dst_discard_out(&init_net, skb->sk, skb); +} +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, + int initial_obsolete, unsigned short flags); +void dst_init(struct dst_entry *dst, struct dst_ops *ops, + struct net_device *dev, int initial_ref, int initial_obsolete, + unsigned short flags); +struct dst_entry *dst_destroy(struct dst_entry *dst); +void dst_dev_put(struct dst_entry *dst); + +static inline void dst_confirm(struct dst_entry *dst) +{ +} + +static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr); + return IS_ERR(n) ? NULL : n; +} + +static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, + struct sk_buff *skb) +{ + struct neighbour *n; + + if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) + return NULL; + + n = dst->ops->neigh_lookup(dst, skb, NULL); + + return IS_ERR(n) ? NULL : n; +} + +static inline void dst_confirm_neigh(const struct dst_entry *dst, + const void *daddr) +{ + if (dst->ops->confirm_neigh) + dst->ops->confirm_neigh(dst, daddr); +} + +static inline void dst_link_failure(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + if (dst && dst->ops && dst->ops->link_failure) + dst->ops->link_failure(skb); +} + +static inline void dst_set_expires(struct dst_entry *dst, int timeout) +{ + unsigned long expires = jiffies + timeout; + + if (expires == 0) + expires = 1; + + if (dst->expires == 0 || time_before(expires, dst->expires)) + dst->expires = expires; +} + +INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, + struct sk_buff *)); +/* Output packet to network from transport. */ +static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return INDIRECT_CALL_INET(skb_dst(skb)->output, + ip6_output, ip_output, + net, sk, skb); +} + +INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); +/* Input packet from network to transport. */ +static inline int dst_input(struct sk_buff *skb) +{ + return INDIRECT_CALL_INET(skb_dst(skb)->input, + ip6_input, ip_local_deliver, skb); +} + +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, + u32)); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); +static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) +{ + if (dst->obsolete) + dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, + ipv4_dst_check, dst, cookie); + return dst; +} + +/* Flags for xfrm_lookup flags argument. */ +enum { + XFRM_LOOKUP_ICMP = 1 << 0, + XFRM_LOOKUP_QUEUE = 1 << 1, + XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, +}; + +struct flowi; +#ifndef CONFIG_XFRM +static inline struct dst_entry *xfrm_lookup(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, + int flags) +{ + return dst_orig; +} + +static inline struct dst_entry * +xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags, u32 if_id) +{ + return dst_orig; +} + +static inline struct dst_entry *xfrm_lookup_route(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, + int flags) +{ + return dst_orig; +} + +static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) +{ + return NULL; +} + +#else +struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags); + +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, int flags, + u32 if_id); + +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags); + +/* skb attached with this dst needs transformation if dst->xfrm is valid */ +static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) +{ + return dst->xfrm; +} +#endif + +static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, true); +} + +/* update dst pmtu but not do neighbor confirm */ +static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); +} + +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, bool confirm_neigh); +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); +unsigned int dst_blackhole_mtu(const struct dst_entry *dst); + +#endif /* _NET_DST_H */ -- cgit v1.2.3