diff options
Diffstat (limited to 'net/ipv6/af_inet6.c')
| -rw-r--r-- | net/ipv6/af_inet6.c | 483 |
1 files changed, 357 insertions, 126 deletions
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a88b5b5b7955..b705751eb73c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * PF_INET6 socket protocol family * Linux INET6 implementation @@ -11,11 +12,6 @@ * piggy, Karl Knutson : Socket protocol table * Hideaki YOSHIFUJI : sin6_scope_id support * Arnaldo Melo : check proc_net_create return, cleanups - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define pr_fmt(fmt) "IPv6: " fmt @@ -56,12 +52,19 @@ #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> +#include <net/ipv6_stubs.h> #include <net/ndisc.h> #ifdef CONFIG_IPV6_TUNNEL #include <net/ip6_tunnel.h> #endif #include <net/calipso.h> #include <net/seg6.h> +#include <net/rpl.h> +#include <net/compat.h> +#include <net/xfrm.h> +#include <net/ioam6.h> +#include <net/rawv6.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/mroute6.h> @@ -100,13 +103,20 @@ bool ipv6_mod_enabled(void) } EXPORT_SYMBOL_GPL(ipv6_mod_enabled); -static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) +static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { - const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); + const int offset = sk->sk_prot->ipv6_pinfo_offset; return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } +void inet6_sock_destruct(struct sock *sk) +{ + inet6_cleanup_sock(sk); + inet_sock_destruct(sk); +} +EXPORT_SYMBOL_GPL(inet6_sock_destruct); + static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -190,16 +200,19 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); - inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; + inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) - inet->hdrincl = 1; + inet_set_bit(HDRINCL, sk); } - sk->sk_destruct = inet_sock_destruct; + sk->sk_destruct = inet6_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol; @@ -208,36 +221,29 @@ lookup_protocol: inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk); np->hop_limit = -1; np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; - np->mc_loop = 1; + inet6_set_bit(MC6_LOOP, sk); + inet6_set_bit(MC6_ALL, sk); np->pmtudisc = IPV6_PMTUDISC_WANT; - np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk)); + inet6_assign_bit(REPFLOW, sk, net->ipv6.sysctl.flowlabel_reflect & + FLOWLABEL_REFLECT_ESTABLISHED); sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. */ inet->uc_ttl = -1; - inet->mc_loop = 1; + inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet->mc_index = 0; - inet->mc_list = NULL; + RCU_INIT_POINTER(inet->mc_list, NULL); inet->rcv_tos = 0; - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; - /* - * Increment only the relevant sk_prot->socks debug field, this changes - * the previous behaviour of incrementing both the equivalent to - * answer->prot->socks (inet6_sock_nr) and inet_sock_nr. - * - * This allows better debug granularity as we'll know exactly how many - * UDPv6, TCPv6, etc socks were allocated, not the sum of all IPv6 - * transport protocol socks. -acme - */ - sk_refcnt_debug_inc(sk); if (inet->inet_num) { /* It assumes that any protocol which allows @@ -246,67 +252,59 @@ lookup_protocol: */ inet->inet_sport = htons(inet->inet_num); err = sk->sk_prot->hash(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; +out_sk_release: + sk_common_release(sk); + sock->sk = NULL; + goto out; } - -/* bind for INET6 API */ -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int __inet6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, + u32 flags) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; - struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); __be32 v4addr = 0; unsigned short snum; + bool saved_ipv6only; int addr_type = 0; int err = 0; - /* If the socket has its own bind function then use it. */ - if (sk->sk_prot->bind) - return sk->sk_prot->bind(sk, uaddr, addr_len); - - if (addr_len < SIN6_LEN_RFC2133) - return -EINVAL; - if (addr->sin6_family != AF_INET6) return -EAFNOSUPPORT; addr_type = ipv6_addr_type(&addr->sin6_addr); - if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM) + if ((addr_type & IPV6_ADDR_MULTICAST) && sk->sk_type == SOCK_STREAM) return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && snum < inet_prot_sock(net) && + if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && + snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; - lock_sock(sk); + if (flags & BIND_WITH_LOCK) + lock_sock(sk); /* Check these errors (active socket, double bind). */ if (sk->sk_state != TCP_CLOSE || inet->inet_num) { @@ -316,25 +314,33 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { + struct net_device *dev = NULL; int chk_addr_ret; /* Binding to v4-mapped address on a v6-only socket * makes no sense */ - if (sk->sk_ipv6only) { + if (ipv6_only_sock(sk)) { err = -EINVAL; goto out; } + rcu_read_lock(); + if (sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + err = -ENODEV; + goto out_unlock; + } + } + /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; - chk_addr_ret = inet_addr_type(net, v4addr); - if (!net->ipv4.sysctl_ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && - v4addr != htonl(INADDR_ANY) && - chk_addr_ret != RTN_LOCAL && - chk_addr_ret != RTN_MULTICAST && - chk_addr_ret != RTN_BROADCAST) { + chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr); + rcu_read_unlock(); + + if (!inet_addr_valid_or_nonlocal(net, inet, v4addr, + chk_addr_ret)) { err = -EADDRNOTAVAIL; goto out; } @@ -357,6 +363,9 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = -EINVAL; goto out_unlock; } + } + + if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; @@ -369,8 +378,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!net->ipv6.sysctl.ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!ipv6_can_nonlocal_bind(net, inet) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; @@ -389,31 +397,78 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; + saved_ipv6only = sk->sk_ipv6only; + if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED) + sk->sk_ipv6only = 1; + /* Make sure we are allowed to bind here. */ - if ((snum || !inet->bind_address_no_port) && - sk->sk_prot->get_port(sk, snum)) { - inet_reset_saddr(sk); - err = -EADDRINUSE; - goto out; + if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || + (flags & BIND_FORCE_ADDRESS_NO_PORT))) { + err = sk->sk_prot->get_port(sk, snum); + if (err) { + sk->sk_ipv6only = saved_ipv6only; + inet_reset_saddr(sk); + goto out; + } + if (!(flags & BIND_FROM_BPF)) { + err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk); + if (err) { + sk->sk_ipv6only = saved_ipv6only; + inet_reset_saddr(sk); + if (sk->sk_prot->put_port) + sk->sk_prot->put_port(sk); + goto out; + } + } } - if (addr_type != IPV6_ADDR_ANY) { + if (addr_type != IPV6_ADDR_ANY) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; - if (addr_type != IPV6_ADDR_MAPPED) - sk->sk_ipv6only = 1; - } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); inet->inet_dport = 0; inet->inet_daddr = 0; out: - release_sock(sk); + if (flags & BIND_WITH_LOCK) + release_sock(sk); return err; out_unlock: rcu_read_unlock(); goto out; } + +int inet6_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) +{ + u32 flags = BIND_WITH_LOCK; + const struct proto *prot; + int err = 0; + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + /* If the socket has its own bind function then use it. */ + if (prot->bind) + return prot->bind(sk, uaddr, addr_len); + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + /* BPF prog is run before any checks are done so that if the prog + * changes context in a wrong way it will be caught. + */ + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, + CGROUP_INET6_BIND, &flags); + if (err) + return err; + + return __inet6_bind(sk, uaddr, addr_len, flags); +} + +/* bind for INET6 API */ +int inet6_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) +{ + return inet6_bind_sk(sock->sk, uaddr, addr_len); +} EXPORT_SYMBOL(inet6_bind); int inet6_release(struct socket *sock) @@ -433,7 +488,7 @@ int inet6_release(struct socket *sock) } EXPORT_SYMBOL(inet6_release); -void inet6_destroy_sock(struct sock *sk) +void inet6_cleanup_sock(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -442,34 +497,32 @@ void inet6_destroy_sock(struct sock *sk) /* Release rx options */ skb = xchg(&np->pktoptions, NULL); - if (skb) - kfree_skb(skb); + kfree_skb(skb); skb = xchg(&np->rxpmtu, NULL); - if (skb) - kfree_skb(skb); + kfree_skb(skb); /* Free flowlabels */ fl6_free_socklist(sk); /* Free tx options */ - opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL); + opt = unrcu_pointer(xchg(&np->opt, NULL)); if (opt) { atomic_sub(opt->tot_len, &sk->sk_omem_alloc); txopt_put(opt); } } -EXPORT_SYMBOL_GPL(inet6_destroy_sock); +EXPORT_SYMBOL_GPL(inet6_cleanup_sock); /* * This does both peername and sockname. */ - int inet6_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; + int sin_addr_len = sizeof(*sin); struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -477,64 +530,158 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; + lock_sock(sk); if (peer) { - if (!inet->inet_dport) - return -ENOTCONN; - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && - peer == 1) + if (!inet->inet_dport || + (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && + peer == 1)) { + release_sock(sk); return -ENOTCONN; + } sin->sin6_port = inet->inet_dport; sin->sin6_addr = sk->sk_v6_daddr; - if (np->sndflow) + if (inet6_test_bit(SNDFLOW, sk)) sin->sin6_flowinfo = np->flow_label; + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, + CGROUP_INET6_GETPEERNAME); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else sin->sin6_addr = sk->sk_v6_rcv_saddr; - sin->sin6_port = inet->inet_sport; + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, + CGROUP_INET6_GETSOCKNAME); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); - *uaddr_len = sizeof(*sin); - return 0; + release_sock(sk); + return sin_addr_len; } EXPORT_SYMBOL(inet6_getname); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { + void __user *argp = (void __user *)arg; struct sock *sk = sock->sk; struct net *net = sock_net(sk); + const struct proto *prot; switch (cmd) { - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *)arg); - - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, (struct timespec __user *)arg); - case SIOCADDRT: - case SIOCDELRT: - - return ipv6_route_ioctl(net, cmd, (void __user *)arg); + case SIOCDELRT: { + struct in6_rtmsg rtmsg; + if (copy_from_user(&rtmsg, argp, sizeof(rtmsg))) + return -EFAULT; + return ipv6_route_ioctl(net, cmd, &rtmsg); + } case SIOCSIFADDR: - return addrconf_add_ifaddr(net, (void __user *) arg); + return addrconf_add_ifaddr(net, argp); case SIOCDIFADDR: - return addrconf_del_ifaddr(net, (void __user *) arg); + return addrconf_del_ifaddr(net, argp); case SIOCSIFDSTADDR: - return addrconf_set_dstaddr(net, (void __user *) arg); + return addrconf_set_dstaddr(net, argp); default: - if (!sk->sk_prot->ioctl) + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + if (!prot->ioctl) return -ENOIOCTLCMD; - return sk->sk_prot->ioctl(sk, cmd, arg); + return sk_ioctl(sk, cmd, (void __user *)arg); } /*NOTREACHED*/ return 0; } EXPORT_SYMBOL(inet6_ioctl); +#ifdef CONFIG_COMPAT +struct compat_in6_rtmsg { + struct in6_addr rtmsg_dst; + struct in6_addr rtmsg_src; + struct in6_addr rtmsg_gateway; + u32 rtmsg_type; + u16 rtmsg_dst_len; + u16 rtmsg_src_len; + u32 rtmsg_metric; + u32 rtmsg_info; + u32 rtmsg_flags; + s32 rtmsg_ifindex; +}; + +static int inet6_compat_routing_ioctl(struct sock *sk, unsigned int cmd, + struct compat_in6_rtmsg __user *ur) +{ + struct in6_rtmsg rt; + + if (copy_from_user(&rt.rtmsg_dst, &ur->rtmsg_dst, + 3 * sizeof(struct in6_addr)) || + get_user(rt.rtmsg_type, &ur->rtmsg_type) || + get_user(rt.rtmsg_dst_len, &ur->rtmsg_dst_len) || + get_user(rt.rtmsg_src_len, &ur->rtmsg_src_len) || + get_user(rt.rtmsg_metric, &ur->rtmsg_metric) || + get_user(rt.rtmsg_info, &ur->rtmsg_info) || + get_user(rt.rtmsg_flags, &ur->rtmsg_flags) || + get_user(rt.rtmsg_ifindex, &ur->rtmsg_ifindex)) + return -EFAULT; + + + return ipv6_route_ioctl(sock_net(sk), cmd, &rt); +} + +int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + void __user *argp = compat_ptr(arg); + struct sock *sk = sock->sk; + + switch (cmd) { + case SIOCADDRT: + case SIOCDELRT: + return inet6_compat_routing_ioctl(sk, cmd, argp); + default: + return -ENOIOCTLCMD; + } +} +EXPORT_SYMBOL_GPL(inet6_compat_ioctl); +#endif /* CONFIG_COMPAT */ + +INDIRECT_CALLABLE_DECLARE(int udpv6_sendmsg(struct sock *, struct msghdr *, + size_t)); +int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) +{ + struct sock *sk = sock->sk; + const struct proto *prot; + + if (unlikely(inet_send_prepare(sk))) + return -EAGAIN; + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + return INDIRECT_CALL_2(prot->sendmsg, tcp_sendmsg, udpv6_sendmsg, + sk, msg, size); +} + +INDIRECT_CALLABLE_DECLARE(int udpv6_recvmsg(struct sock *, struct msghdr *, + size_t, int, int *)); +int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) +{ + struct sock *sk = sock->sk; + const struct proto *prot; + int addr_len = 0; + int err; + + if (likely(!(flags & MSG_ERRQUEUE))) + sock_rps_record_flow(sk); + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + err = INDIRECT_CALL_2(prot->recvmsg, tcp_recvmsg, udpv6_recvmsg, + sk, msg, size, flags, &addr_len); + if (err >= 0) + msg->msg_namelen = addr_len; + return err; +} + const struct proto_ops inet6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, @@ -546,22 +693,29 @@ const struct proto_ops inet6_stream_ops = { .getname = inet6_getname, .poll = tcp_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ + .gettstamp = sock_gettstamp, .listen = inet_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = inet_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = inet_sendpage, + .sendmsg = inet6_sendmsg, /* retpoline's sake */ + .recvmsg = inet6_recvmsg, /* retpoline's sake */ +#ifdef CONFIG_MMU + .mmap = tcp_mmap, +#endif + .splice_eof = inet_splice_eof, + .sendmsg_locked = tcp_sendmsg_locked, .splice_read = tcp_splice_read, + .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, + .read_skb = tcp_read_skb, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet6_compat_ioctl, #endif + .set_rcvlowat = tcp_set_rcvlowat, }; +EXPORT_SYMBOL_GPL(inet6_stream_ops); const struct proto_ops inet6_dgram_ops = { .family = PF_INET6, @@ -574,18 +728,18 @@ const struct proto_ops inet6_dgram_ops = { .getname = inet6_getname, .poll = udp_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ + .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = inet_recvmsg, /* ok */ + .sendmsg = inet6_sendmsg, /* retpoline's sake */ + .recvmsg = inet6_recvmsg, /* retpoline's sake */ + .read_skb = udp_read_skb, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet6_compat_ioctl, #endif }; @@ -688,22 +842,22 @@ int inet6_sk_rebuild_header(struct sock *sk) fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; - fl6.flowi6_uid = sk->sk_uid; - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + fl6.flowi6_uid = sk_uid(sk); + security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); rcu_read_lock(); final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; - sk->sk_err_soft = -PTR_ERR(dst); + WRITE_ONCE(sk->sk_err_soft, -PTR_ERR(dst)); return PTR_ERR(dst); } - ip6_dst_store(sk, dst, NULL, NULL); + ip6_dst_store(sk, dst, false, false); } return 0; @@ -728,11 +882,11 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, } return false; } -EXPORT_SYMBOL_GPL(ipv6_opt_accepted); static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, + .list_func = ipv6_list_rcv, }; static int __init ipv6_packet_init(void) @@ -802,13 +956,35 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; + net->ipv6.sysctl.icmpv6_echo_ignore_all = 0; + net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0; + net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0; + net->ipv6.sysctl.icmpv6_error_anycast_as_unicast = 0; + net->ipv6.sysctl.icmpv6_errors_extension_mask = 0; + + /* By default, rate limit error messages. + * Except for pmtu discovery, it would break it. + * proc_do_large_bitmap needs pointer to the bitmap. + */ + bitmap_set(net->ipv6.sysctl.icmpv6_ratemask, 0, ICMPV6_ERRMSG_MAX + 1); + bitmap_clear(net->ipv6.sysctl.icmpv6_ratemask, ICMPV6_PKT_TOOBIG, 1); + net->ipv6.sysctl.icmpv6_ratemask_ptr = net->ipv6.sysctl.icmpv6_ratemask; + net->ipv6.sysctl.flowlabel_consistency = 1; net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS; net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; net->ipv6.sysctl.flowlabel_state_ranges = 0; + net->ipv6.sysctl.max_dst_opts_cnt = IP6_DEFAULT_MAX_DST_OPTS_CNT; + net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; + net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; + net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; + net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); + net->ipv6.sysctl.ioam6_id = IOAM6_DEFAULT_ID; + net->ipv6.sysctl.ioam6_id_wide = IOAM6_DEFAULT_ID_WIDE; + err = ipv6_init_mibs(net); if (err) return err; @@ -851,13 +1027,48 @@ static struct pernet_operations inet6_net_ops = { .exit = inet6_net_exit, }; +static int ipv6_route_input(struct sk_buff *skb) +{ + ip6_route_input(skb); + return skb_dst(skb)->error; +} + static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, + .ipv6_route_input = ipv6_route_input, + .fib6_get_table = fib6_get_table, + .fib6_table_lookup = fib6_table_lookup, + .fib6_lookup = fib6_lookup, + .fib6_select_path = fib6_select_path, + .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, + .fib6_nh_init = fib6_nh_init, + .fib6_nh_release = fib6_nh_release, + .fib6_nh_release_dsts = fib6_nh_release_dsts, + .fib6_update_sernum = fib6_update_sernum_stub, + .fib6_rt_update = fib6_rt_update, + .ip6_del_rt = ip6_del_rt, .udpv6_encap_enable = udpv6_encap_enable, .ndisc_send_na = ndisc_send_na, +#if IS_ENABLED(CONFIG_XFRM) + .xfrm6_local_rxpmtu = xfrm6_local_rxpmtu, + .xfrm6_udp_encap_rcv = xfrm6_udp_encap_rcv, + .xfrm6_gro_udp_encap_rcv = xfrm6_gro_udp_encap_rcv, + .xfrm6_rcv_encap = xfrm6_rcv_encap, +#endif .nd_tbl = &nd_tbl, + .ipv6_fragment = ip6_fragment, + .ipv6_dev_find = ipv6_dev_find, + .ip6_xmit = ip6_xmit, +}; + +static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { + .inet6_bind = __inet6_bind, + .udp6_lib_lookup = __udp6_lib_lookup, + .ipv6_setsockopt = do_ipv6_setsockopt, + .ipv6_getsockopt = do_ipv6_getsockopt, + .ipv6_dev_get_saddr = ipv6_dev_get_saddr, }; static int __init inet6_init(void) @@ -871,6 +1082,8 @@ static int __init inet6_init(void) for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); + raw_hashinfo_init(&raw_v6_hashinfo); + if (disable_ipv6_mod) { pr_info("Loaded, but administratively disabled, reboot required to enable\n"); goto out; @@ -894,14 +1107,14 @@ static int __init inet6_init(void) err = proto_register(&pingv6_prot, 1); if (err) - goto out_unregister_ping_proto; + goto out_unregister_raw_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ err = rawv6_init(); if (err) - goto out_unregister_raw_proto; + goto out_unregister_ping_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) @@ -957,6 +1170,9 @@ static int __init inet6_init(void) err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; + err = ipv6_anycast_init(); + if (err) + goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; @@ -1003,6 +1219,14 @@ static int __init inet6_init(void) if (err) goto seg6_fail; + err = rpl_init(); + if (err) + goto rpl_fail; + + err = ioam6_init(); + if (err) + goto ioam6_fail; + err = igmp6_late_init(); if (err) goto igmp6_late_err; @@ -1016,6 +1240,7 @@ static int __init inet6_init(void) /* ensure that ipv6 stubs are visible only after ipv6 is ready */ wmb(); ipv6_stub = &ipv6_stub_impl; + ipv6_bpf_stub = &ipv6_bpf_stub_impl; out: return err; @@ -1024,6 +1249,10 @@ sysctl_fail: igmp6_late_cleanup(); #endif igmp6_late_err: + ioam6_exit(); +ioam6_fail: + rpl_exit(); +rpl_fail: seg6_exit(); seg6_fail: calipso_exit(); @@ -1046,6 +1275,8 @@ ipv6_frag_fail: ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: + ipv6_anycast_cleanup(); +ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); @@ -1068,11 +1299,11 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: - ip6_mr_cleanup(); + icmpv6_cleanup(); icmp_fail: - unregister_pernet_subsys(&inet6_net_ops); + ip6_mr_cleanup(); ipmr_fail: - icmpv6_cleanup(); + unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); |