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/xfrm4_policy.c | 259 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 259 insertions(+) create mode 100644 net/ipv4/xfrm4_policy.c (limited to 'net/ipv4/xfrm4_policy.c') diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c new file mode 100644 index 000000000..3d0dfa6cf --- /dev/null +++ b/net/ipv4/xfrm4_policy.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * xfrm4_policy.c + * + * Changes: + * Kazunori MIYAZAWA @USAGI + * YOSHIFUJI Hideaki @USAGI + * Split up af-specific portion + * + */ + +#include +#include +#include +#include +#include +#include +#include + +static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, + int tos, int oif, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr, + u32 mark) +{ + struct rtable *rt; + + memset(fl4, 0, sizeof(*fl4)); + fl4->daddr = daddr->a4; + fl4->flowi4_tos = tos; + fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(net, oif); + fl4->flowi4_mark = mark; + if (saddr) + fl4->saddr = saddr->a4; + + rt = __ip_route_output_key(net, fl4); + if (!IS_ERR(rt)) + return &rt->dst; + + return ERR_CAST(rt); +} + +static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr, + u32 mark) +{ + struct flowi4 fl4; + + return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark); +} + +static int xfrm4_get_saddr(struct net *net, int oif, + xfrm_address_t *saddr, xfrm_address_t *daddr, + u32 mark) +{ + struct dst_entry *dst; + struct flowi4 fl4; + + dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark); + if (IS_ERR(dst)) + return -EHOSTUNREACH; + + saddr->a4 = fl4.saddr; + dst_release(dst); + return 0; +} + +static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, + const struct flowi *fl) +{ + struct rtable *rt = (struct rtable *)xdst->route; + const struct flowi4 *fl4 = &fl->u.ip4; + + xdst->u.rt.rt_iif = fl4->flowi4_iif; + + xdst->u.dst.dev = dev; + netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); + + /* Sheit... I remember I did this right. Apparently, + * it was magically lost, so this code needs audit */ + xdst->u.rt.rt_is_input = rt->rt_is_input; + xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | + RTCF_LOCAL); + xdst->u.rt.rt_type = rt->rt_type; + xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; + xdst->u.rt.rt_gw_family = rt->rt_gw_family; + if (rt->rt_gw_family == AF_INET) + xdst->u.rt.rt_gw4 = rt->rt_gw4; + else if (rt->rt_gw_family == AF_INET6) + xdst->u.rt.rt_gw6 = rt->rt_gw6; + xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; + INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + rt_add_uncached_list(&xdst->u.rt); + + return 0; +} + +static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); +} + +static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->redirect(path, sk, skb); +} + +static void xfrm4_dst_destroy(struct dst_entry *dst) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + + dst_destroy_metrics_generic(dst); + if (xdst->u.rt.rt_uncached_list) + rt_del_uncached_list(&xdst->u.rt); + xfrm_dst_destroy(xdst); +} + +static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int unregister) +{ + if (!unregister) + return; + + xfrm_dst_ifdown(dst, dev); +} + +static struct dst_ops xfrm4_dst_ops_template = { + .family = AF_INET, + .update_pmtu = xfrm4_update_pmtu, + .redirect = xfrm4_redirect, + .cow_metrics = dst_cow_metrics_generic, + .destroy = xfrm4_dst_destroy, + .ifdown = xfrm4_dst_ifdown, + .local_out = __ip_local_out, + .gc_thresh = 32768, +}; + +static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = { + .dst_ops = &xfrm4_dst_ops_template, + .dst_lookup = xfrm4_dst_lookup, + .get_saddr = xfrm4_get_saddr, + .fill_dst = xfrm4_fill_dst, + .blackhole_route = ipv4_blackhole_route, +}; + +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm4_policy_table[] = { + { + .procname = "xfrm4_gc_thresh", + .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static __net_init int xfrm4_net_sysctl_init(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = xfrm4_policy_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; + } + + hdr = register_net_sysctl(net, "net/ipv4", table); + if (!hdr) + goto err_reg; + + net->ipv4.xfrm4_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static __net_exit void xfrm4_net_sysctl_exit(struct net *net) +{ + struct ctl_table *table; + + if (!net->ipv4.xfrm4_hdr) + return; + + table = net->ipv4.xfrm4_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} +#else /* CONFIG_SYSCTL */ +static inline int xfrm4_net_sysctl_init(struct net *net) +{ + return 0; +} + +static inline void xfrm4_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm4_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, + sizeof(xfrm4_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); + if (ret) + return ret; + + ret = xfrm4_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); + + return ret; +} + +static void __net_exit xfrm4_net_exit(struct net *net) +{ + xfrm4_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); +} + +static struct pernet_operations __net_initdata xfrm4_net_ops = { + .init = xfrm4_net_init, + .exit = xfrm4_net_exit, +}; + +static void __init xfrm4_policy_init(void) +{ + xfrm_policy_register_afinfo(&xfrm4_policy_afinfo, AF_INET); +} + +void __init xfrm4_init(void) +{ + xfrm4_state_init(); + xfrm4_policy_init(); + xfrm4_protocol_init(); + register_pernet_subsys(&xfrm4_net_ops); +} -- cgit v1.2.3