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/ipv6/ping.c | 306 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 306 insertions(+) create mode 100644 net/ipv6/ping.c (limited to 'net/ipv6/ping.c') diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c new file mode 100644 index 000000000..808983bc2 --- /dev/null +++ b/net/ipv6/ping.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * "Ping" sockets + * + * Based on ipv4/ping.c code. + * + * Authors: Lorenzo Colitti (IPv6 support) + * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), + * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Compatibility glue so we can support IPv6 when it's compiled as a module */ +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) +{ + return -EAFNOSUPPORT; +} +static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ +} +static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) +{ + return -EAFNOSUPPORT; +} +static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) {} +static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) +{ + return 0; +} + +static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + /* This check is replicated from __ip6_datagram_connect() and + * intended to prevent BPF program called below from accessing + * bytes that are out of the bound specified by user in addr_len. + */ + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); +} + +static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct icmp6hdr user_icmph; + int addr_type; + struct in6_addr *daddr; + int oif = 0; + struct flowi6 fl6; + int err; + struct dst_entry *dst; + struct rt6_info *rt; + struct pingfakehdr pfh; + struct ipcm6_cookie ipc6; + + err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, + sizeof(user_icmph)); + if (err) + return err; + + memset(&fl6, 0, sizeof(fl6)); + + if (msg->msg_name) { + DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); + if (msg->msg_namelen < sizeof(*u)) + return -EINVAL; + if (u->sin6_family != AF_INET6) { + return -EAFNOSUPPORT; + } + daddr = &(u->sin6_addr); + if (np->sndflow) + fl6.flowlabel = u->sin6_flowinfo & IPV6_FLOWINFO_MASK; + if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) + oif = u->sin6_scope_id; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = &sk->sk_v6_daddr; + fl6.flowlabel = np->flow_label; + } + + if (!oif) + oif = sk->sk_bound_dev_if; + + if (!oif) + oif = np->sticky_pktinfo.ipi6_ifindex; + + if (!oif && ipv6_addr_is_multicast(daddr)) + oif = np->mcast_oif; + else if (!oif) + oif = np->ucast_oif; + + addr_type = ipv6_addr_type(daddr); + if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || + (addr_type & IPV6_ADDR_MAPPED) || + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) + return -EINVAL; + + ipcm6_init_sk(&ipc6, np); + ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.mark = sk->sk_mark; + + fl6.flowi6_oif = oif; + + if (msg->msg_controllen) { + struct ipv6_txoptions opt = {}; + + opt.tot_len = sizeof(opt); + ipc6.opt = &opt; + + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); + if (err < 0) + return err; + + /* Changes to txoptions and flow info are not implemented, yet. + * Drop the options. + */ + ipc6.opt = NULL; + } + + fl6.flowi6_proto = IPPROTO_ICMPV6; + fl6.saddr = np->saddr; + fl6.daddr = *daddr; + fl6.flowi6_mark = ipc6.sockc.mark; + fl6.flowi6_uid = sk->sk_uid; + fl6.fl6_icmp_type = user_icmph.icmp6_type; + fl6.fl6_icmp_code = user_icmph.icmp6_code; + security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); + + fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); + + dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); + if (IS_ERR(dst)) + return PTR_ERR(dst); + rt = (struct rt6_info *) dst; + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + pfh.icmph.type = user_icmph.icmp6_type; + pfh.icmph.code = user_icmph.icmp6_code; + pfh.icmph.checksum = 0; + pfh.icmph.un.echo.id = inet->inet_sport; + pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; + pfh.msg = msg; + pfh.wcheck = 0; + pfh.family = AF_INET6; + + if (ipc6.hlimit < 0) + ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + + lock_sock(sk); + err = ip6_append_data(sk, ping_getfrag, &pfh, len, + sizeof(struct icmp6hdr), &ipc6, &fl6, rt, + MSG_DONTWAIT); + + if (err) { + ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); + ip6_flush_pending_frames(sk); + } else { + icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *)&pfh.icmph, len); + } + release_sock(sk); + + dst_release(dst); + + if (err) + return err; + + return len; +} + +struct proto pingv6_prot = { + .name = "PINGv6", + .owner = THIS_MODULE, + .init = ping_init_sock, + .close = ping_close, + .pre_connect = ping_v6_pre_connect, + .connect = ip6_datagram_connect_v6_only, + .disconnect = __udp_disconnect, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .sendmsg = ping_v6_sendmsg, + .recvmsg = ping_recvmsg, + .bind = ping_bind, + .backlog_rcv = ping_queue_rcv_skb, + .hash = ping_hash, + .unhash = ping_unhash, + .get_port = ping_get_port, + .put_port = ping_unhash, + .obj_size = sizeof(struct raw6_sock), +}; +EXPORT_SYMBOL_GPL(pingv6_prot); + +static struct inet_protosw pingv6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMPV6, + .prot = &pingv6_prot, + .ops = &inet6_sockraw_ops, + .flags = INET_PROTOSW_REUSE, +}; + +#ifdef CONFIG_PROC_FS +static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) +{ + return ping_seq_start(seq, pos, AF_INET6); +} + +static int ping_v6_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct ping_iter_state *) seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } + return 0; +} + +static const struct seq_operations ping_v6_seq_ops = { + .start = ping_v6_seq_start, + .show = ping_v6_seq_show, + .next = ping_seq_next, + .stop = ping_seq_stop, +}; + +static int __net_init ping_v6_proc_init_net(struct net *net) +{ + if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops, + sizeof(struct ping_iter_state))) + return -ENOMEM; + return 0; +} + +static void __net_exit ping_v6_proc_exit_net(struct net *net) +{ + remove_proc_entry("icmp6", net->proc_net); +} + +static struct pernet_operations ping_v6_net_ops = { + .init = ping_v6_proc_init_net, + .exit = ping_v6_proc_exit_net, +}; +#endif + +int __init pingv6_init(void) +{ +#ifdef CONFIG_PROC_FS + int ret = register_pernet_subsys(&ping_v6_net_ops); + if (ret) + return ret; +#endif + pingv6_ops.ipv6_recv_error = ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = + ip6_datagram_recv_specific_ctl; + pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; + return inet6_register_protosw(&pingv6_protosw); +} + +/* This never gets called because it's not possible to unload the ipv6 module, + * but just in case. + */ +void pingv6_exit(void) +{ + pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; +#ifdef CONFIG_PROC_FS + unregister_pernet_subsys(&ping_v6_net_ops); +#endif + inet6_unregister_protosw(&pingv6_protosw); +} -- cgit v1.2.3