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/ip6_fib.h | 654 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 654 insertions(+) create mode 100644 include/net/ip6_fib.h (limited to 'include/net/ip6_fib.h') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h new file mode 100644 index 000000000..6268963d9 --- /dev/null +++ b/include/net/ip6_fib.h @@ -0,0 +1,654 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Linux INET6 implementation + * + * Authors: + * Pedro Roque + */ + +#ifndef _IP6_FIB_H +#define _IP6_FIB_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +#define FIB6_TABLE_HASHSZ 256 +#else +#define FIB6_TABLE_HASHSZ 1 +#endif + +#define RT6_DEBUG 2 + +#if RT6_DEBUG >= 3 +#define RT6_TRACE(x...) pr_debug(x) +#else +#define RT6_TRACE(x...) do { ; } while (0) +#endif + +struct rt6_info; +struct fib6_info; + +struct fib6_config { + u32 fc_table; + u32 fc_metric; + int fc_dst_len; + int fc_src_len; + int fc_ifindex; + u32 fc_flags; + u32 fc_protocol; + u16 fc_type; /* only 8 bits are used */ + u16 fc_delete_all_nh : 1, + fc_ignore_dev_down:1, + __unused : 14; + u32 fc_nh_id; + + struct in6_addr fc_dst; + struct in6_addr fc_src; + struct in6_addr fc_prefsrc; + struct in6_addr fc_gateway; + + unsigned long fc_expires; + struct nlattr *fc_mx; + int fc_mx_len; + int fc_mp_len; + struct nlattr *fc_mp; + + struct nl_info fc_nlinfo; + struct nlattr *fc_encap; + u16 fc_encap_type; + bool fc_is_fdb; +}; + +struct fib6_node { + struct fib6_node __rcu *parent; + struct fib6_node __rcu *left; + struct fib6_node __rcu *right; +#ifdef CONFIG_IPV6_SUBTREES + struct fib6_node __rcu *subtree; +#endif + struct fib6_info __rcu *leaf; + + __u16 fn_bit; /* bit key */ + __u16 fn_flags; + int fn_sernum; + struct fib6_info __rcu *rr_ptr; + struct rcu_head rcu; +}; + +struct fib6_gc_args { + int timeout; + int more; +}; + +#ifndef CONFIG_IPV6_SUBTREES +#define FIB6_SUBTREE(fn) NULL + +static inline bool fib6_routes_require_src(const struct net *net) +{ + return false; +} + +static inline void fib6_routes_require_src_inc(struct net *net) {} +static inline void fib6_routes_require_src_dec(struct net *net) {} + +#else + +static inline bool fib6_routes_require_src(const struct net *net) +{ + return net->ipv6.fib6_routes_require_src > 0; +} + +static inline void fib6_routes_require_src_inc(struct net *net) +{ + net->ipv6.fib6_routes_require_src++; +} + +static inline void fib6_routes_require_src_dec(struct net *net) +{ + net->ipv6.fib6_routes_require_src--; +} + +#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) +#endif + +/* + * routing information + * + */ + +struct rt6key { + struct in6_addr addr; + int plen; +}; + +struct fib6_table; + +struct rt6_exception_bucket { + struct hlist_head chain; + int depth; +}; + +struct rt6_exception { + struct hlist_node hlist; + struct rt6_info *rt6i; + unsigned long stamp; + struct rcu_head rcu; +}; + +#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 +#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) +#define FIB6_MAX_DEPTH 5 + +struct fib6_nh { + struct fib_nh_common nh_common; + +#ifdef CONFIG_IPV6_ROUTER_PREF + unsigned long last_probe; +#endif + + struct rt6_info * __percpu *rt6i_pcpu; + struct rt6_exception_bucket __rcu *rt6i_exception_bucket; +}; + +struct fib6_info { + struct fib6_table *fib6_table; + struct fib6_info __rcu *fib6_next; + struct fib6_node __rcu *fib6_node; + + /* Multipath routes: + * siblings is a list of fib6_info that have the same metric/weight, + * destination, but not the same gateway. nsiblings is just a cache + * to speed up lookup. + */ + union { + struct list_head fib6_siblings; + struct list_head nh_list; + }; + unsigned int fib6_nsiblings; + + refcount_t fib6_ref; + unsigned long expires; + struct dst_metrics *fib6_metrics; +#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] + + struct rt6key fib6_dst; + u32 fib6_flags; + struct rt6key fib6_src; + struct rt6key fib6_prefsrc; + + u32 fib6_metric; + u8 fib6_protocol; + u8 fib6_type; + + u8 offload; + u8 trap; + u8 offload_failed; + + u8 should_flush:1, + dst_nocount:1, + dst_nopolicy:1, + fib6_destroying:1, + unused:4; + + struct rcu_head rcu; + struct nexthop *nh; + struct fib6_nh fib6_nh[]; +}; + +struct rt6_info { + struct dst_entry dst; + struct fib6_info __rcu *from; + int sernum; + + struct rt6key rt6i_dst; + struct rt6key rt6i_src; + struct in6_addr rt6i_gateway; + struct inet6_dev *rt6i_idev; + u32 rt6i_flags; + + struct list_head rt6i_uncached; + struct uncached_list *rt6i_uncached_list; + + /* more non-fragment space at head required */ + unsigned short rt6i_nfheader_len; +}; + +struct fib6_result { + struct fib6_nh *nh; + struct fib6_info *f6i; + u32 fib6_flags; + u8 fib6_type; + struct rt6_info *rt6; +}; + +#define for_each_fib6_node_rt_rcu(fn) \ + for (rt = rcu_dereference((fn)->leaf); rt; \ + rt = rcu_dereference(rt->fib6_next)) + +#define for_each_fib6_walker_rt(w) \ + for (rt = (w)->leaf; rt; \ + rt = rcu_dereference_protected(rt->fib6_next, 1)) + +static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) +{ + return ((struct rt6_info *)dst)->rt6i_idev; +} + +static inline bool fib6_requires_src(const struct fib6_info *rt) +{ + return rt->fib6_src.plen > 0; +} + +static inline void fib6_clean_expires(struct fib6_info *f6i) +{ + f6i->fib6_flags &= ~RTF_EXPIRES; + f6i->expires = 0; +} + +static inline void fib6_set_expires(struct fib6_info *f6i, + unsigned long expires) +{ + f6i->expires = expires; + f6i->fib6_flags |= RTF_EXPIRES; +} + +static inline bool fib6_check_expired(const struct fib6_info *f6i) +{ + if (f6i->fib6_flags & RTF_EXPIRES) + return time_after(jiffies, f6i->expires); + return false; +} + +/* Function to safely get fn->fn_sernum for passed in rt + * and store result in passed in cookie. + * Return true if we can get cookie safely + * Return false if not + */ +static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, + u32 *cookie) +{ + struct fib6_node *fn; + bool status = false; + + fn = rcu_dereference(f6i->fib6_node); + + if (fn) { + *cookie = READ_ONCE(fn->fn_sernum); + /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ + smp_rmb(); + status = true; + } + + return status; +} + +static inline u32 rt6_get_cookie(const struct rt6_info *rt) +{ + struct fib6_info *from; + u32 cookie = 0; + + if (rt->sernum) + return rt->sernum; + + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (from) + fib6_get_cookie_safe(from, &cookie); + + rcu_read_unlock(); + + return cookie; +} + +static inline void ip6_rt_put(struct rt6_info *rt) +{ + /* dst_release() accepts a NULL parameter. + * We rely on dst being first structure in struct rt6_info + */ + BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0); + dst_release(&rt->dst); +} + +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); +void fib6_info_destroy_rcu(struct rcu_head *head); + +static inline void fib6_info_hold(struct fib6_info *f6i) +{ + refcount_inc(&f6i->fib6_ref); +} + +static inline bool fib6_info_hold_safe(struct fib6_info *f6i) +{ + return refcount_inc_not_zero(&f6i->fib6_ref); +} + +static inline void fib6_info_release(struct fib6_info *f6i) +{ + if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) + call_rcu(&f6i->rcu, fib6_info_destroy_rcu); +} + +enum fib6_walk_state { +#ifdef CONFIG_IPV6_SUBTREES + FWS_S, +#endif + FWS_L, + FWS_R, + FWS_C, + FWS_U +}; + +struct fib6_walker { + struct list_head lh; + struct fib6_node *root, *node; + struct fib6_info *leaf; + enum fib6_walk_state state; + unsigned int skip; + unsigned int count; + unsigned int skip_in_node; + int (*func)(struct fib6_walker *); + void *args; +}; + +struct rt6_statistics { + __u32 fib_nodes; /* all fib6 nodes */ + __u32 fib_route_nodes; /* intermediate nodes */ + __u32 fib_rt_entries; /* rt entries in fib table */ + __u32 fib_rt_cache; /* cached rt entries in exception table */ + __u32 fib_discarded_routes; /* total number of routes delete */ + + /* The following stat is not protected by any lock */ + atomic_t fib_rt_alloc; /* total number of routes alloced */ +}; + +#define RTN_TL_ROOT 0x0001 +#define RTN_ROOT 0x0002 /* tree root node */ +#define RTN_RTINFO 0x0004 /* node with valid routing info */ + +/* + * priority levels (or metrics) + * + */ + + +struct fib6_table { + struct hlist_node tb6_hlist; + u32 tb6_id; + spinlock_t tb6_lock; + struct fib6_node tb6_root; + struct inet_peer_base tb6_peers; + unsigned int flags; + unsigned int fib_seq; +#define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) +}; + +#define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC +#define RT6_TABLE_MAIN RT_TABLE_MAIN +#define RT6_TABLE_DFLT RT6_TABLE_MAIN +#define RT6_TABLE_INFO RT6_TABLE_MAIN +#define RT6_TABLE_PREFIX RT6_TABLE_MAIN + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +#define FIB6_TABLE_MIN 1 +#define FIB6_TABLE_MAX RT_TABLE_MAX +#define RT6_TABLE_LOCAL RT_TABLE_LOCAL +#else +#define FIB6_TABLE_MIN RT_TABLE_MAIN +#define FIB6_TABLE_MAX FIB6_TABLE_MIN +#define RT6_TABLE_LOCAL RT6_TABLE_MAIN +#endif + +typedef struct rt6_info *(*pol_lookup_t)(struct net *, + struct fib6_table *, + struct flowi6 *, + const struct sk_buff *, int); + +struct fib6_entry_notifier_info { + struct fib_notifier_info info; /* must be first */ + struct fib6_info *rt; + unsigned int nsiblings; +}; + +/* + * exported functions + */ + +struct fib6_table *fib6_get_table(struct net *net, u32 id); +struct fib6_table *fib6_new_table(struct net *net, u32 id); +struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + const struct sk_buff *skb, + int flags, pol_lookup_t lookup); + +/* called with rcu lock held; can return error pointer + * caller needs to select path + */ +int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, + struct fib6_result *res, int flags); + +/* called with rcu lock held; caller needs to select path */ +int fib6_table_lookup(struct net *net, struct fib6_table *table, + int oif, struct flowi6 *fl6, struct fib6_result *res, + int strict); + +void fib6_select_path(const struct net *net, struct fib6_result *res, + struct flowi6 *fl6, int oif, bool have_oif_match, + const struct sk_buff *skb, int strict); +struct fib6_node *fib6_node_lookup(struct fib6_node *root, + const struct in6_addr *daddr, + const struct in6_addr *saddr); + +struct fib6_node *fib6_locate(struct fib6_node *root, + const struct in6_addr *daddr, int dst_len, + const struct in6_addr *saddr, int src_len, + bool exact_match); + +void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), + void *arg); +void fib6_clean_all_skip_notify(struct net *net, + int (*func)(struct fib6_info *, void *arg), + void *arg); + +int fib6_add(struct fib6_node *root, struct fib6_info *rt, + struct nl_info *info, struct netlink_ext_ack *extack); +int fib6_del(struct fib6_info *rt, struct nl_info *info); + +static inline +void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) +{ + const struct fib6_info *from; + + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (from) { + *addr = from->fib6_prefsrc.addr; + } else { + struct in6_addr in6_zero = {}; + + *addr = in6_zero; + } + + rcu_read_unlock(); +} + +int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, + struct fib6_config *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); +void fib6_nh_release(struct fib6_nh *fib6_nh); +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); + +int call_fib6_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + struct netlink_ext_ack *extack); +int call_fib6_multipath_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + unsigned int nsiblings, + struct netlink_ext_ack *extack); +int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt); +void fib6_rt_update(struct net *net, struct fib6_info *rt, + struct nl_info *info); +void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, + unsigned int flags); + +void fib6_run_gc(unsigned long expires, struct net *net, bool force); + +void fib6_gc_cleanup(void); + +int fib6_init(void); + +struct ipv6_route_iter { + struct seq_net_private p; + struct fib6_walker w; + loff_t skip; + struct fib6_table *tbl; + int sernum; +}; + +extern const struct seq_operations ipv6_route_seq_ops; + +int call_fib6_notifier(struct notifier_block *nb, + enum fib_event_type event_type, + struct fib_notifier_info *info); +int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info); + +int __net_init fib6_notifier_init(struct net *net); +void __net_exit fib6_notifier_exit(struct net *net); + +unsigned int fib6_tables_seq_read(struct net *net); +int fib6_tables_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); + +void fib6_update_sernum(struct net *net, struct fib6_info *rt); +void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); +void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i); + +void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); +static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) +{ + return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); +} +void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, + bool offload, bool trap, bool offload_failed); + +#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) +struct bpf_iter__ipv6_route { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct fib6_info *, rt); +}; +#endif + +INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags)); +INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags)); +INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags)); +INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags)); +static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup, + struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) +{ + return INDIRECT_CALL_4(lookup, + ip6_pol_route_output, + ip6_pol_route_input, + ip6_pol_route_lookup, + __ip6_route_redirect, + net, table, fl6, skb, flags); +} + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +static inline bool fib6_has_custom_rules(const struct net *net) +{ + return net->ipv6.fib6_has_custom_rules; +} + +int fib6_rules_init(void); +void fib6_rules_cleanup(void); +bool fib6_rule_default(const struct fib_rule *rule); +int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); +unsigned int fib6_rules_seq_read(struct net *net); + +static inline bool fib6_rules_early_flow_dissect(struct net *net, + struct sk_buff *skb, + struct flowi6 *fl6, + struct flow_keys *flkeys) +{ + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + + if (!net->ipv6.fib6_rules_require_fldissect) + return false; + + skb_flow_dissect_flow_keys(skb, flkeys, flag); + fl6->fl6_sport = flkeys->ports.src; + fl6->fl6_dport = flkeys->ports.dst; + fl6->flowi6_proto = flkeys->basic.ip_proto; + + return true; +} +#else +static inline bool fib6_has_custom_rules(const struct net *net) +{ + return false; +} +static inline int fib6_rules_init(void) +{ + return 0; +} +static inline void fib6_rules_cleanup(void) +{ + return ; +} +static inline bool fib6_rule_default(const struct fib_rule *rule) +{ + return true; +} +static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + return 0; +} +static inline unsigned int fib6_rules_seq_read(struct net *net) +{ + return 0; +} +static inline bool fib6_rules_early_flow_dissect(struct net *net, + struct sk_buff *skb, + struct flowi6 *fl6, + struct flow_keys *flkeys) +{ + return false; +} +#endif +#endif -- cgit v1.2.3