diff options
Diffstat (limited to 'net/ipv4')
36 files changed, 3990 insertions, 701 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 2dfb12230f08..8e94ed7c56a0 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -741,10 +741,27 @@ config DEFAULT_TCP_CONG default "bbr" if DEFAULT_BBR default "cubic" +config TCP_SIGPOOL + tristate + +config TCP_AO + bool "TCP: Authentication Option (RFC5925)" + select CRYPTO + select TCP_SIGPOOL + depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64) + help + TCP-AO specifies the use of stronger Message Authentication Codes (MACs), + protects against replays for long-lived TCP connections, and + provides more details on the association of security with TCP + connections than TCP MD5 (See RFC5925) + + If unsure, say N. + config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO select CRYPTO_MD5 + select TCP_SIGPOOL help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index b18ba8ef93ad..e144a02a6a61 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -62,12 +62,14 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o +obj-$(CONFIG_TCP_SIGPOOL) += tcp_sigpool.o obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o +obj-$(CONFIG_TCP_AO) += tcp_ao.o ifeq ($(CONFIG_BPF_JIT),y) obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3d2e30e20473..fb81de10d332 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -452,7 +452,7 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* 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, + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; @@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; - sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; - sk->sk_wait_pending--; return timeo; } @@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { + sk->sk_disconnects++; err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; @@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; + int dis = sk->sk_disconnects; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) @@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; + + if (dis != sk->sk_disconnects) { + err = -EPIPE; + goto out; + } } /* Connection was closed by RST, timeout, ICMP error @@ -725,6 +730,7 @@ out: sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; + sk->sk_disconnects++; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; @@ -788,6 +794,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); + int sin_addr_len = sizeof(*sin); sin->sin_family = AF_INET; lock_sock(sk); @@ -800,7 +807,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; @@ -808,12 +815,12 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - return sizeof(*sin); + return sin_addr_len; } EXPORT_SYMBOL(inet_getname); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index cb5dbee9e018..2cc50cbfc2a3 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -39,11 +39,11 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len saddr = inet->inet_saddr; if (ipv4_is_multicast(usin->sin_addr.s_addr)) { if (!oif || netif_index_is_l3_master(sock_net(sk), oif)) - oif = inet->mc_index; + oif = READ_ONCE(inet->mc_index); if (!saddr) - saddr = inet->mc_addr; + saddr = READ_ONCE(inet->mc_addr); } else if (!oif) { - oif = inet->uc_index; + oif = READ_ONCE(inet->uc_index); } fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, oif, diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 2be2d4922557..4ccfc104f13a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -784,7 +786,7 @@ int esp_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index eafa4a033515..5eb1b8d302bb 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope) { struct fib_nh *nh; + __be32 saddr; if (nhc->nhc_family != AF_INET) return inet_select_addr(nhc->nhc_dev, 0, scope); nh = container_of(nhc, struct fib_nh, nh_common); - nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); + saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - return nh->nh_saddr; + WRITE_ONCE(nh->nh_saddr, saddr); + WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid)); + + return saddr; } __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) @@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); - if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) - return nh->nh_saddr; + if (READ_ONCE(nh->nh_saddr_genid) == + atomic_read(&net->ipv4.dev_addr_genid)) + return READ_ONCE(nh->nh_saddr); } return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope); @@ -1887,6 +1891,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; + fi->pfsrc_removed = true; ret++; } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d13fb9e76b97..9bdfdab906fe 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2027,6 +2027,7 @@ void fib_table_flush_external(struct fib_table *tb) int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; + struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; @@ -2089,6 +2090,9 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); + if (fi->pfsrc_removed) + rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, + KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index aeebe8816689..394a498c2823 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); - newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e13a84433413..f01aee832aab 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -134,7 +134,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, * hence this needs to be included regardless of socket family. */ if (ext & (1 << (INET_DIAG_TOS - 1))) - if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0) + if (nla_put_u8(skb, INET_DIAG_TOS, READ_ONCE(inet->tos)) < 0) goto errout; #if IS_ENABLED(CONFIG_IPV6) @@ -165,7 +165,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, * For cgroup2 classid is always zero. */ if (!classid) - classid = sk->sk_priority; + classid = READ_ONCE(sk->sk_priority); if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c32f5e28758b..598c1b114d2c 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb2->family) - return false; + if (sk->sk_family != tb2->family) { + if (sk->sk_family == AF_INET) + return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) && + tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; + + return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) && + sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr; + } if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb2->v6_rcv_saddr, @@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, tb->l3mdev != l3mdev) return false; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) { - if (sk->sk_family == AF_INET) - return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) && - tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; - - return false; - } - - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); -#endif - return tb->rcv_saddr == sk->sk_rcv_saddr; + return inet_bind2_bucket_addr_match(tb, sk); } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 66fac1216d46..8b65f12583eb 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -66,8 +66,6 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s { struct ip_options *opt = &(IPCB(skb)->opt); - __IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); - #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); @@ -130,6 +128,8 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; + __IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); + IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4ab877cf6d35..b06f678b03a1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -101,6 +101,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); + iph_set_totlen(iph, skb->len); ip_send_check(iph); @@ -544,7 +546,7 @@ EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { - return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos); + return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos)); } EXPORT_SYMBOL(ip_queue_xmit); @@ -1387,8 +1389,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, struct ip_options *opt = NULL; struct rtable *rt = (struct rtable *)cork->dst; struct iphdr *iph; + u8 pmtudisc, ttl; __be16 df = 0; - __u8 ttl; skb = __skb_dequeue(queue); if (!skb) @@ -1418,8 +1420,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk, /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ - if (inet->pmtudisc == IP_PMTUDISC_DO || - inet->pmtudisc == IP_PMTUDISC_PROBE || + pmtudisc = READ_ONCE(inet->pmtudisc); + if (pmtudisc == IP_PMTUDISC_DO || + pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); @@ -1430,14 +1433,14 @@ struct sk_buff *__ip_make_skb(struct sock *sk, if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) - ttl = inet->mc_ttl; + ttl = READ_ONCE(inet->mc_ttl); else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; - iph->tos = (cork->tos != -1) ? cork->tos : inet->tos; + iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos); iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; @@ -1449,7 +1452,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_options_build(skb, opt, cork->addr, rt); } - skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; + skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; skb->tstamp = cork->transmit_time; /* diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cce9cb25f3b3..2efc53526a38 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -587,12 +587,14 @@ out: void __ip_sock_set_tos(struct sock *sk, int val) { + u8 old_tos = inet_sk(sk)->tos; + if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; - val |= inet_sk(sk)->tos & INET_ECN_MASK; + val |= old_tos & INET_ECN_MASK; } - if (inet_sk(sk)->tos != val) { - inet_sk(sk)->tos = val; + if (old_tos != val) { + WRITE_ONCE(inet_sk(sk)->tos, val); WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } @@ -600,9 +602,9 @@ void __ip_sock_set_tos(struct sock *sk, int val) void ip_sock_set_tos(struct sock *sk, int val) { - lock_sock(sk); + sockopt_lock_sock(sk); __ip_sock_set_tos(sk, val); - release_sock(sk); + sockopt_release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_tos); @@ -622,9 +624,7 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val) { if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) return -EINVAL; - lock_sock(sk); - inet_sk(sk)->pmtudisc = val; - release_sock(sk); + WRITE_ONCE(inet_sk(sk)->pmtudisc, val); return 0; } EXPORT_SYMBOL(ip_sock_set_mtu_discover); @@ -1039,6 +1039,22 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, WRITE_ONCE(inet->min_ttl, val); return 0; + case IP_MULTICAST_TTL: + if (sk->sk_type == SOCK_STREAM) + return -EINVAL; + if (optlen < 1) + return -EINVAL; + if (val == -1) + val = 1; + if (val < 0 || val > 255) + return -EINVAL; + WRITE_ONCE(inet->mc_ttl, val); + return 0; + case IP_MTU_DISCOVER: + return ip_sock_set_mtu_discover(sk, val); + case IP_TOS: /* This sets both TOS and Precedence */ + ip_sock_set_tos(sk, val); + return 0; } err = 0; @@ -1093,25 +1109,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, } } break; - case IP_TOS: /* This sets both TOS and Precedence */ - __ip_sock_set_tos(sk, val); - break; - case IP_MTU_DISCOVER: - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) - goto e_inval; - inet->pmtudisc = val; - break; - case IP_MULTICAST_TTL: - if (sk->sk_type == SOCK_STREAM) - goto e_inval; - if (optlen < 1) - goto e_inval; - if (val == -1) - val = 1; - if (val < 0 || val > 255) - goto e_inval; - inet->mc_ttl = val; - break; case IP_UNICAST_IF: { struct net_device *dev = NULL; @@ -1123,7 +1120,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, ifindex = (__force int)ntohl((__force __be32)val); if (ifindex == 0) { - inet->uc_index = 0; + WRITE_ONCE(inet->uc_index, 0); err = 0; break; } @@ -1140,7 +1137,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; - inet->uc_index = ifindex; + WRITE_ONCE(inet->uc_index, ifindex); err = 0; break; } @@ -1178,8 +1175,8 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, if (!mreq.imr_ifindex) { if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) { - inet->mc_index = 0; - inet->mc_addr = 0; + WRITE_ONCE(inet->mc_index, 0); + WRITE_ONCE(inet->mc_addr, 0); err = 0; break; } @@ -1204,8 +1201,8 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, midx != sk->sk_bound_dev_if) break; - inet->mc_index = mreq.imr_ifindex; - inet->mc_addr = mreq.imr_address.s_addr; + WRITE_ONCE(inet->mc_index, mreq.imr_ifindex); + WRITE_ONCE(inet->mc_addr, mreq.imr_address.s_addr); err = 0; break; } @@ -1592,27 +1589,29 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MINTTL: val = READ_ONCE(inet->min_ttl); goto copyval; - } - - if (needs_rtnl) - rtnl_lock(); - sockopt_lock_sock(sk); - - switch (optname) { + case IP_MULTICAST_TTL: + val = READ_ONCE(inet->mc_ttl); + goto copyval; + case IP_MTU_DISCOVER: + val = READ_ONCE(inet->pmtudisc); + goto copyval; + case IP_TOS: + val = READ_ONCE(inet->tos); + goto copyval; case IP_OPTIONS: { unsigned char optbuf[sizeof(struct ip_options)+40]; struct ip_options *opt = (struct ip_options *)optbuf; struct ip_options_rcu *inet_opt; - inet_opt = rcu_dereference_protected(inet->inet_opt, - lockdep_sock_is_held(sk)); + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); opt->optlen = 0; if (inet_opt) memcpy(optbuf, &inet_opt->opt, sizeof(struct ip_options) + inet_opt->opt.optlen); - sockopt_release_sock(sk); + rcu_read_unlock(); if (opt->optlen == 0) { len = 0; @@ -1628,12 +1627,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } - case IP_TOS: - val = inet->tos; - break; - case IP_MTU_DISCOVER: - val = inet->pmtudisc; - break; case IP_MTU: { struct dst_entry *dst; @@ -1643,24 +1636,55 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, val = dst_mtu(dst); dst_release(dst); } - if (!val) { - sockopt_release_sock(sk); + if (!val) return -ENOTCONN; + goto copyval; + } + case IP_PKTOPTIONS: + { + struct msghdr msg; + + if (sk->sk_type != SOCK_STREAM) + return -ENOPROTOOPT; + + if (optval.is_kernel) { + msg.msg_control_is_user = false; + msg.msg_control = optval.kernel; + } else { + msg.msg_control_is_user = true; + msg.msg_control_user = optval.user; } - break; + msg.msg_controllen = len; + msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; + + if (inet_test_bit(PKTINFO, sk)) { + struct in_pktinfo info; + + info.ipi_addr.s_addr = READ_ONCE(inet->inet_rcv_saddr); + info.ipi_spec_dst.s_addr = READ_ONCE(inet->inet_rcv_saddr); + info.ipi_ifindex = READ_ONCE(inet->mc_index); + put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); + } + if (inet_test_bit(TTL, sk)) { + int hlim = READ_ONCE(inet->mc_ttl); + + put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); + } + if (inet_test_bit(TOS, sk)) { + int tos = READ_ONCE(inet->rcv_tos); + put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); + } + len -= msg.msg_controllen; + return copy_to_sockptr(optlen, &len, sizeof(int)); } - case IP_MULTICAST_TTL: - val = inet->mc_ttl; - break; case IP_UNICAST_IF: - val = (__force int)htonl((__u32) inet->uc_index); - break; + val = (__force int)htonl((__u32) READ_ONCE(inet->uc_index)); + goto copyval; case IP_MULTICAST_IF: { struct in_addr addr; len = min_t(unsigned int, len, sizeof(struct in_addr)); - addr.s_addr = inet->mc_addr; - sockopt_release_sock(sk); + addr.s_addr = READ_ONCE(inet->mc_addr); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; @@ -1668,6 +1692,13 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } + } + + if (needs_rtnl) + rtnl_lock(); + sockopt_lock_sock(sk); + + switch (optname) { case IP_MSFILTER: { struct ip_msfilter msf; @@ -1690,44 +1721,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, else err = ip_get_mcast_msfilter(sk, optval, optlen, len); goto out; - case IP_PKTOPTIONS: - { - struct msghdr msg; - - sockopt_release_sock(sk); - - if (sk->sk_type != SOCK_STREAM) - return -ENOPROTOOPT; - - if (optval.is_kernel) { - msg.msg_control_is_user = false; - msg.msg_control = optval.kernel; - } else { - msg.msg_control_is_user = true; - msg.msg_control_user = optval.user; - } - msg.msg_controllen = len; - msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; - - if (inet_test_bit(PKTINFO, sk)) { - struct in_pktinfo info; - - info.ipi_addr.s_addr = inet->inet_rcv_saddr; - info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr; - info.ipi_ifindex = inet->mc_index; - put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); - } - if (inet_test_bit(TTL, sk)) { - int hlim = inet->mc_ttl; - put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); - } - if (inet_test_bit(TOS, sk)) { - int tos = inet->rcv_tos; - put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); - } - len -= msg.msg_controllen; - return copy_to_sockptr(optlen, &len, sizeof(int)); - } case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 3abb430af9e6..385d945d8ebe 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -36,12 +36,12 @@ static const struct xt_table packet_mangler = { static unsigned int ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; + unsigned int ret, verdict; const struct iphdr *iph; - u_int8_t tos; __be32 saddr, daddr; - u_int32_t mark; + u32 mark; int err; + u8 tos; /* Save things which could affect route */ mark = skb->mark; @@ -51,8 +51,9 @@ ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat tos = iph->tos; ret = ipt_do_table(priv, skb, state); + verdict = ret & NF_VERDICT_MASK; /* Reroute for ANY change. */ - if (ret != NF_DROP && ret != NF_STOLEN) { + if (verdict != NF_DROP && verdict != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 4dd809b7b188..823306487a82 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -301,7 +301,7 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ @@ -551,7 +551,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ ipv4_sk_update_pmtu(skb, sk, info); - if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { + if (READ_ONCE(inet_sock->pmtudisc) != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; @@ -773,11 +773,11 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) - ipc.oif = inet->mc_index; + ipc.oif = READ_ONCE(inet->mc_index); if (!saddr) - saddr = inet->mc_addr; + saddr = READ_ONCE(inet->mc_addr); } else if (!ipc.oif) - ipc.oif = inet->uc_index; + ipc.oif = READ_ONCE(inet->uc_index); flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index eaf1d3113b62..5f4654ebff48 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -83,7 +83,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS), SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS), - SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -93,6 +93,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("FragOKs", IPSTATS_MIB_FRAGOKS), SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS), SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES), + SNMP_MIB_ITEM("OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; @@ -298,6 +299,11 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH), + SNMP_MIB_ITEM("TCPAORequired", LINUX_MIB_TCPAOREQUIRED), + SNMP_MIB_ITEM("TCPAOBad", LINUX_MIB_TCPAOBAD), + SNMP_MIB_ITEM("TCPAOKeyNotFound", LINUX_MIB_TCPAOKEYNOTFOUND), + SNMP_MIB_ITEM("TCPAOGood", LINUX_MIB_TCPAOGOOD), + SNMP_MIB_ITEM("TCPAODroppedIcmps", LINUX_MIB_TCPAODROPPEDICMPS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4b5db5d1edc2..27da9d7294c0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -239,7 +239,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (code > NR_ICMP_UNREACH) break; if (code == ICMP_FRAG_NEEDED) { - harderr = inet->pmtudisc != IP_PMTUDISC_DONT; + harderr = READ_ONCE(inet->pmtudisc) != IP_PMTUDISC_DONT; err = EMSGSIZE; } else { err = icmp_err_convert[code].errno; @@ -482,7 +482,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int free = 0; __be32 daddr; __be32 saddr; - int err; + int uc_index, err; struct ip_options_data opt_copy; struct raw_frag_vec rfv; int hdrincl; @@ -576,24 +576,25 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); + uc_index = READ_ONCE(inet->uc_index); if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) - ipc.oif = inet->mc_index; + ipc.oif = READ_ONCE(inet->mc_index); if (!saddr) - saddr = inet->mc_addr; + saddr = READ_ONCE(inet->mc_addr); } else if (!ipc.oif) { - ipc.oif = inet->uc_index; - } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { + ipc.oif = uc_index; + } else if (ipv4_is_lbcast(daddr) && uc_index) { /* oif is set, packet is to local broadcast * and uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. */ - if (ipc.oif != inet->uc_index && + if (ipc.oif != uc_index && ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk), - inet->uc_index)) { - ipc.oif = inet->uc_index; + uc_index)) { + ipc.oif = uc_index; } } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fb3045692b99..3290a4442b4a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) @@ -2883,54 +2885,6 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); -struct rtable *ip_route_output_tunnel(struct sk_buff *skb, - struct net_device *dev, - struct net *net, __be32 *saddr, - const struct ip_tunnel_info *info, - u8 protocol, bool use_cache) -{ -#ifdef CONFIG_DST_CACHE - struct dst_cache *dst_cache; -#endif - struct rtable *rt = NULL; - struct flowi4 fl4; - __u8 tos; - -#ifdef CONFIG_DST_CACHE - dst_cache = (struct dst_cache *)&info->dst_cache; - if (use_cache) { - rt = dst_cache_get_ip4(dst_cache, saddr); - if (rt) - return rt; - } -#endif - memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_mark = skb->mark; - fl4.flowi4_proto = protocol; - fl4.daddr = info->key.u.ipv4.dst; - fl4.saddr = info->key.u.ipv4.src; - tos = info->key.tos; - fl4.flowi4_tos = RT_TOS(tos); - - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) { - netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); - return ERR_PTR(-ENETUNREACH); - } - if (rt->dst.dev == dev) { /* is this necessary? */ - netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); - ip_rt_put(rt); - return ERR_PTR(-ELOOP); - } -#ifdef CONFIG_DST_CACHE - if (use_cache) - dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); -#endif - *saddr = fl4.saddr; - return rt; -} -EXPORT_SYMBOL_GPL(ip_route_output_tunnel); - /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, @@ -3415,6 +3369,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = + READ_ONCE(fa->offload_failed); break; } } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index dc478a0574cb..98b25e5d147b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -41,7 +41,6 @@ static siphash_aligned_key_t syncookie_secret[2]; * requested/supported by the syn/synack exchange. */ #define TSBITS 6 -#define TSMASK (((__u32)1 << TSBITS) - 1) static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) @@ -52,6 +51,14 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, count, &syncookie_secret[c]); } +/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ +static u64 tcp_ns_to_ts(bool usec_ts, u64 val) +{ + if (usec_ts) + return div_u64(val, NSEC_PER_USEC); + + return div_u64(val, NSEC_PER_MSEC); +} /* * when syncookies are in effect and tcp timestamps are enabled we encode @@ -62,27 +69,24 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, */ u64 cookie_init_timestamp(struct request_sock *req, u64 now) { - struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_ns_to_ts(now); + const struct inet_request_sock *ireq = inet_rsk(req); + u64 ts, ts_now = tcp_ns_to_ts(false, now); u32 options = 0; - ireq = inet_rsk(req); - options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK; if (ireq->sack_ok) options |= TS_OPT_SACK; if (ireq->ecn_ok) options |= TS_OPT_ECN; - ts = ts_now & ~TSMASK; + ts = (ts_now >> TSBITS) << TSBITS; ts |= options; - if (ts > ts_now) { - ts >>= TSBITS; - ts--; - ts <<= TSBITS; - ts |= options; - } - return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ); + if (ts > ts_now) + ts -= (1UL << TSBITS); + + if (tcp_rsk(req)->req_usec_ts) + return ts * NSEC_PER_USEC; + return ts * NSEC_PER_MSEC; } @@ -302,6 +306,8 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, treq->af_specific = af_ops; treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; + treq->req_usec_ts = -1; + #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); if (treq->is_mptcp) { @@ -338,6 +344,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u8 rcv_wscale; struct flowi4 fl4; u32 tsoff = 0; + int l3index; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) @@ -399,6 +406,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->ir_iif = inet_request_bound_dev_if(sk, skb); + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); + tcp_ao_syncookie(sk, skb, treq, AF_INET, l3index); + /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e7f024d93572..f63a545a7374 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1498,6 +1498,14 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "tcp_pingpong_thresh", + .data = &init_net.ipv4.sysctl_tcp_pingpong_thresh, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ONE, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 69b8d7073708..53bcc17c91e4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) + break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -925,10 +927,11 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -/* In some cases, both sendmsg() could have added an skb to the write queue, - * but failed adding payload on it. We need to remove it to consume less +/* In some cases, sendmsg() could have added an skb to the write queue, + * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger - * epoll() users. + * epoll() users. Another reason is that tcp_write_xmit() does not like + * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { @@ -1287,6 +1290,7 @@ new_segment: wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); @@ -1621,16 +1625,13 @@ EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; struct sk_buff *skb; int copied = 0; - u32 offset; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; @@ -1643,13 +1644,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) copied = used; break; } - seq += used; copied += used; - if (tcp_flags & TCPHDR_FIN) { - ++seq; + if (tcp_flags & TCPHDR_FIN) break; - } } return copied; } @@ -2448,7 +2446,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); - sk_wait_data(sk, &timeo, last); + err = sk_wait_data(sk, &timeo, last); + if (err < 0) { + err = copied ? : err; + goto out; + } } if ((flags & MSG_PEEK) && @@ -2972,12 +2974,6 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -3597,6 +3593,31 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, __tcp_sock_set_quickack(sk, val); break; + case TCP_AO_REPAIR: + err = tcp_ao_set_repair(sk, optval, optlen); + break; +#ifdef CONFIG_TCP_AO + case TCP_AO_ADD_KEY: + case TCP_AO_DEL_KEY: + case TCP_AO_INFO: { + /* If this is the first TCP-AO setsockopt() on the socket, + * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR + * in any state. + */ + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + goto ao_parse; + if (rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk))) + goto ao_parse; + if (tp->repair) + goto ao_parse; + err = -EISCONN; + break; +ao_parse: + err = tp->af_specific->ao_parse(sk, optname, optval, optlen); + break; + } +#endif #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: @@ -3635,10 +3656,16 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: - if (!tp->repair) + if (!tp->repair) { err = -EPERM; - else - WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); + break; + } + /* val is an opaque field, + * and low order bit contains usec_ts enable bit. + * Its a best effort, and we do not care if user makes an error. + */ + tp->tcp_usec_ts = val & 1; + WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -3760,9 +3787,12 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; + if (tp->tcp_usec_ts) + info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); - info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato); + info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, + tcp_delack_max(sk))); info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; @@ -3822,10 +3852,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; - if (tp->rto_stamp) { - info->tcpi_total_rto_time += tcp_time_stamp_raw() - - tp->rto_stamp; - } + if (tp->rto_stamp) + info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; unlock_sock_fast(sk, slow); } @@ -4150,7 +4178,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); + val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); + if (tp->tcp_usec_ts) + val |= 1; + else + val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); @@ -4260,6 +4292,21 @@ zerocopy_rcv_out: return err; } #endif + case TCP_AO_REPAIR: + return tcp_ao_get_repair(sk, optval, optlen); + case TCP_AO_GET_KEYS: + case TCP_AO_INFO: { + int err; + + sockopt_lock_sock(sk); + if (optname == TCP_AO_GET_KEYS) + err = tcp_ao_get_mkts(sk, optval, optlen); + else + err = tcp_ao_get_sock_info(sk, optval, optlen); + sockopt_release_sock(sk); + + return err; + } default: return -ENOPROTOOPT; } @@ -4298,141 +4345,52 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, EXPORT_SYMBOL(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG -static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool); -static DEFINE_MUTEX(tcp_md5sig_mutex); -static bool tcp_md5sig_pool_populated = false; - -static void __tcp_alloc_md5sig_pool(void) -{ - struct crypto_ahash *hash; - int cpu; - - hash = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(hash)) - return; +int tcp_md5_sigpool_id = -1; +EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id); - for_each_possible_cpu(cpu) { - void *scratch = per_cpu(tcp_md5sig_pool, cpu).scratch; - struct ahash_request *req; - - if (!scratch) { - scratch = kmalloc_node(sizeof(union tcp_md5sum_block) + - sizeof(struct tcphdr), - GFP_KERNEL, - cpu_to_node(cpu)); - if (!scratch) - return; - per_cpu(tcp_md5sig_pool, cpu).scratch = scratch; - } - if (per_cpu(tcp_md5sig_pool, cpu).md5_req) - continue; - - req = ahash_request_alloc(hash, GFP_KERNEL); - if (!req) - return; - - ahash_request_set_callback(req, 0, NULL, NULL); - - per_cpu(tcp_md5sig_pool, cpu).md5_req = req; - } - /* before setting tcp_md5sig_pool_populated, we must commit all writes - * to memory. See smp_rmb() in tcp_get_md5sig_pool() - */ - smp_wmb(); - /* Paired with READ_ONCE() from tcp_alloc_md5sig_pool() - * and tcp_get_md5sig_pool(). - */ - WRITE_ONCE(tcp_md5sig_pool_populated, true); -} - -bool tcp_alloc_md5sig_pool(void) +int tcp_md5_alloc_sigpool(void) { - /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ - if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { - mutex_lock(&tcp_md5sig_mutex); - - if (!tcp_md5sig_pool_populated) - __tcp_alloc_md5sig_pool(); + size_t scratch_size; + int ret; - mutex_unlock(&tcp_md5sig_mutex); + scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr); + ret = tcp_sigpool_alloc_ahash("md5", scratch_size); + if (ret >= 0) { + /* As long as any md5 sigpool was allocated, the return + * id would stay the same. Re-write the id only for the case + * when previously all MD5 keys were deleted and this call + * allocates the first MD5 key, which may return a different + * sigpool id than was used previously. + */ + WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */ + return 0; } - /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ - return READ_ONCE(tcp_md5sig_pool_populated); + return ret; } -EXPORT_SYMBOL(tcp_alloc_md5sig_pool); - -/** - * tcp_get_md5sig_pool - get md5sig_pool for this user - * - * We use percpu structure, so if we succeed, we exit with preemption - * and BH disabled, to make sure another thread or softirq handling - * wont try to get same context. - */ -struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) +void tcp_md5_release_sigpool(void) { - local_bh_disable(); - - /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ - if (READ_ONCE(tcp_md5sig_pool_populated)) { - /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ - smp_rmb(); - return this_cpu_ptr(&tcp_md5sig_pool); - } - local_bh_enable(); - return NULL; + tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id)); } -EXPORT_SYMBOL(tcp_get_md5sig_pool); -int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, - const struct sk_buff *skb, unsigned int header_len) +void tcp_md5_add_sigpool(void) { - struct scatterlist sg; - const struct tcphdr *tp = tcp_hdr(skb); - struct ahash_request *req = hp->md5_req; - unsigned int i; - const unsigned int head_data_len = skb_headlen(skb) > header_len ? - skb_headlen(skb) - header_len : 0; - const struct skb_shared_info *shi = skb_shinfo(skb); - struct sk_buff *frag_iter; - - sg_init_table(&sg, 1); - - sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len); - ahash_request_set_crypt(req, &sg, NULL, head_data_len); - if (crypto_ahash_update(req)) - return 1; - - for (i = 0; i < shi->nr_frags; ++i) { - const skb_frag_t *f = &shi->frags[i]; - unsigned int offset = skb_frag_off(f); - struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); - - sg_set_page(&sg, page, skb_frag_size(f), - offset_in_page(offset)); - ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f)); - if (crypto_ahash_update(req)) - return 1; - } - - skb_walk_frags(skb, frag_iter) - if (tcp_md5_hash_skb_data(hp, frag_iter, 0)) - return 1; - - return 0; + tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id)); } -EXPORT_SYMBOL(tcp_md5_hash_skb_data); -int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) +int tcp_md5_hash_key(struct tcp_sigpool *hp, + const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; sg_init_one(&sg, key->key, keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + ahash_request_set_crypt(hp->req, &sg, NULL, keylen); - /* We use data_race() because tcp_md5_do_add() might change key->key under us */ - return data_race(crypto_ahash_update(hp->md5_req)); + /* We use data_race() because tcp_md5_do_add() might change + * key->key under us + */ + return data_race(crypto_ahash_update(hp->req)); } EXPORT_SYMBOL(tcp_md5_hash_key); @@ -4440,42 +4398,24 @@ EXPORT_SYMBOL(tcp_md5_hash_key); enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, - int family, int dif, int sdif) + int family, int l3index, const __u8 *hash_location) { - /* - * This gets called for each TCP segment that arrives - * so we want to be efficient. + /* This gets called for each TCP segment that has TCP-MD5 option. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ - const __u8 *hash_location = NULL; - struct tcp_md5sig_key *hash_expected; - const struct tcphdr *th = tcp_hdr(skb); const struct tcp_sock *tp = tcp_sk(sk); - int genhash, l3index; + struct tcp_md5sig_key *key; u8 newhash[16]; + int genhash; - /* sdif set, means packet ingressed via a device - * in an L3 domain and dif is set to the l3mdev - */ - l3index = sdif ? dif : 0; - - hash_expected = tcp_md5_do_lookup(sk, l3index, saddr, family); - hash_location = tcp_parse_md5sig_option(th); - - /* We've parsed the options - do we have a hash? */ - if (!hash_expected && !hash_location) - return SKB_NOT_DROPPED_YET; + key = tcp_md5_do_lookup(sk, l3index, saddr, family); - if (hash_expected && !hash_location) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - return SKB_DROP_REASON_TCP_MD5NOTFOUND; - } - - if (!hash_expected && hash_location) { + if (!key && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); + tcp_hash_fail("Unexpected MD5 Hash found", family, skb, ""); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } @@ -4484,27 +4424,26 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, * IPv4-mapped case. */ if (family == AF_INET) - genhash = tcp_v4_md5_hash_skb(newhash, - hash_expected, - NULL, skb); + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else - genhash = tp->af_specific->calc_md5_hash(newhash, - hash_expected, + genhash = tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); - if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); if (family == AF_INET) { - net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", - saddr, ntohs(th->source), - daddr, ntohs(th->dest), - genhash ? " tcp_v4_calc_md5_hash failed" - : "", l3index); + tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d", + genhash ? "tcp_v4_calc_md5_hash failed" + : "", l3index); } else { - net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n", - genhash ? "failed" : "mismatch", - saddr, ntohs(th->source), - daddr, ntohs(th->dest), l3index); + if (genhash) { + tcp_hash_fail("MD5 Hash failed", + AF_INET6, skb, "L3 index %d", + l3index); + } else { + tcp_hash_fail("MD5 Hash mismatch", + AF_INET6, skb, "L3 index %d", + l3index); + } } return SKB_DROP_REASON_TCP_MD5FAILURE; } diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c new file mode 100644 index 000000000000..6a845e906a1d --- /dev/null +++ b/net/ipv4/tcp_ao.c @@ -0,0 +1,2392 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * INET An implementation of the TCP Authentication Option (TCP-AO). + * See RFC5925. + * + * Authors: Dmitry Safonov <dima@arista.com> + * Francesco Ruggeri <fruggeri@arista.com> + * Salam Noureddine <noureddine@arista.com> + */ +#define pr_fmt(fmt) "TCP: " fmt + +#include <crypto/hash.h> +#include <linux/inetdevice.h> +#include <linux/tcp.h> + +#include <net/tcp.h> +#include <net/ipv6.h> +#include <net/icmp.h> + +DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_ao_needed, HZ); + +int tcp_ao_calc_traffic_key(struct tcp_ao_key *mkt, u8 *key, void *ctx, + unsigned int len, struct tcp_sigpool *hp) +{ + struct scatterlist sg; + int ret; + + if (crypto_ahash_setkey(crypto_ahash_reqtfm(hp->req), + mkt->key, mkt->keylen)) + goto clear_hash; + + ret = crypto_ahash_init(hp->req); + if (ret) + goto clear_hash; + + sg_init_one(&sg, ctx, len); + ahash_request_set_crypt(hp->req, &sg, key, len); + crypto_ahash_update(hp->req); + + ret = crypto_ahash_final(hp->req); + if (ret) + goto clear_hash; + + return 0; +clear_hash: + memset(key, 0, tcp_ao_digest_size(mkt)); + return 1; +} + +bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code) +{ + bool ignore_icmp = false; + struct tcp_ao_info *ao; + + if (!static_branch_unlikely(&tcp_ao_needed.key)) + return false; + + /* RFC5925, 7.8: + * >> A TCP-AO implementation MUST default to ignore incoming ICMPv4 + * messages of Type 3 (destination unreachable), Codes 2-4 (protocol + * unreachable, port unreachable, and fragmentation needed -- ’hard + * errors’), and ICMPv6 Type 1 (destination unreachable), Code 1 + * (administratively prohibited) and Code 4 (port unreachable) intended + * for connections in synchronized states (ESTABLISHED, FIN-WAIT-1, FIN- + * WAIT-2, CLOSE-WAIT, CLOSING, LAST-ACK, TIME-WAIT) that match MKTs. + */ + if (family == AF_INET) { + if (type != ICMP_DEST_UNREACH) + return false; + if (code < ICMP_PROT_UNREACH || code > ICMP_FRAG_NEEDED) + return false; + } else { + if (type != ICMPV6_DEST_UNREACH) + return false; + if (code != ICMPV6_ADM_PROHIBITED && code != ICMPV6_PORT_UNREACH) + return false; + } + + rcu_read_lock(); + switch (sk->sk_state) { + case TCP_TIME_WAIT: + ao = rcu_dereference(tcp_twsk(sk)->ao_info); + break; + case TCP_SYN_SENT: + case TCP_SYN_RECV: + case TCP_LISTEN: + case TCP_NEW_SYN_RECV: + /* RFC5925 specifies to ignore ICMPs *only* on connections + * in synchronized states. + */ + rcu_read_unlock(); + return false; + default: + ao = rcu_dereference(tcp_sk(sk)->ao_info); + } + + if (ao && !ao->accept_icmps) { + ignore_icmp = true; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAODROPPEDICMPS); + atomic64_inc(&ao->counters.dropped_icmp); + } + rcu_read_unlock(); + + return ignore_icmp; +} + +/* Optimized version of tcp_ao_do_lookup(): only for sockets for which + * it's known that the keys in ao_info are matching peer's + * family/address/VRF/etc. + */ +struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao, + int sndid, int rcvid) +{ + struct tcp_ao_key *key; + + hlist_for_each_entry_rcu(key, &ao->head, node) { + if ((sndid >= 0 && key->sndid != sndid) || + (rcvid >= 0 && key->rcvid != rcvid)) + continue; + return key; + } + + return NULL; +} + +static int ipv4_prefix_cmp(const struct in_addr *addr1, + const struct in_addr *addr2, + unsigned int prefixlen) +{ + __be32 mask = inet_make_mask(prefixlen); + __be32 a1 = addr1->s_addr & mask; + __be32 a2 = addr2->s_addr & mask; + + if (a1 == a2) + return 0; + return memcmp(&a1, &a2, sizeof(a1)); +} + +static int __tcp_ao_key_cmp(const struct tcp_ao_key *key, int l3index, + const union tcp_ao_addr *addr, u8 prefixlen, + int family, int sndid, int rcvid) +{ + if (sndid >= 0 && key->sndid != sndid) + return (key->sndid > sndid) ? 1 : -1; + if (rcvid >= 0 && key->rcvid != rcvid) + return (key->rcvid > rcvid) ? 1 : -1; + if (l3index >= 0 && (key->keyflags & TCP_AO_KEYF_IFINDEX)) { + if (key->l3index != l3index) + return (key->l3index > l3index) ? 1 : -1; + } + + if (family == AF_UNSPEC) + return 0; + if (key->family != family) + return (key->family > family) ? 1 : -1; + + if (family == AF_INET) { + if (ntohl(key->addr.a4.s_addr) == INADDR_ANY) + return 0; + if (ntohl(addr->a4.s_addr) == INADDR_ANY) + return 0; + return ipv4_prefix_cmp(&key->addr.a4, &addr->a4, prefixlen); +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (ipv6_addr_any(&key->addr.a6) || ipv6_addr_any(&addr->a6)) + return 0; + if (ipv6_prefix_equal(&key->addr.a6, &addr->a6, prefixlen)) + return 0; + return memcmp(&key->addr.a6, &addr->a6, sizeof(addr->a6)); +#endif + } + return -1; +} + +static int tcp_ao_key_cmp(const struct tcp_ao_key *key, int l3index, + const union tcp_ao_addr *addr, u8 prefixlen, + int family, int sndid, int rcvid) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && ipv6_addr_v4mapped(&addr->a6)) { + __be32 addr4 = addr->a6.s6_addr32[3]; + + return __tcp_ao_key_cmp(key, l3index, + (union tcp_ao_addr *)&addr4, + prefixlen, AF_INET, sndid, rcvid); + } +#endif + return __tcp_ao_key_cmp(key, l3index, addr, + prefixlen, family, sndid, rcvid); +} + +static struct tcp_ao_key *__tcp_ao_do_lookup(const struct sock *sk, int l3index, + const union tcp_ao_addr *addr, int family, u8 prefix, + int sndid, int rcvid) +{ + struct tcp_ao_key *key; + struct tcp_ao_info *ao; + + if (!static_branch_unlikely(&tcp_ao_needed.key)) + return NULL; + + ao = rcu_dereference_check(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + if (!ao) + return NULL; + + hlist_for_each_entry_rcu(key, &ao->head, node) { + u8 prefixlen = min(prefix, key->prefixlen); + + if (!tcp_ao_key_cmp(key, l3index, addr, prefixlen, + family, sndid, rcvid)) + return key; + } + return NULL; +} + +struct tcp_ao_key *tcp_ao_do_lookup(const struct sock *sk, int l3index, + const union tcp_ao_addr *addr, + int family, int sndid, int rcvid) +{ + return __tcp_ao_do_lookup(sk, l3index, addr, family, U8_MAX, sndid, rcvid); +} + +static struct tcp_ao_info *tcp_ao_alloc_info(gfp_t flags) +{ + struct tcp_ao_info *ao; + + ao = kzalloc(sizeof(*ao), flags); + if (!ao) + return NULL; + INIT_HLIST_HEAD(&ao->head); + refcount_set(&ao->refcnt, 1); + + return ao; +} + +static void tcp_ao_link_mkt(struct tcp_ao_info *ao, struct tcp_ao_key *mkt) +{ + hlist_add_head_rcu(&mkt->node, &ao->head); +} + +static struct tcp_ao_key *tcp_ao_copy_key(struct sock *sk, + struct tcp_ao_key *key) +{ + struct tcp_ao_key *new_key; + + new_key = sock_kmalloc(sk, tcp_ao_sizeof_key(key), + GFP_ATOMIC); + if (!new_key) + return NULL; + + *new_key = *key; + INIT_HLIST_NODE(&new_key->node); + tcp_sigpool_get(new_key->tcp_sigpool_id); + atomic64_set(&new_key->pkt_good, 0); + atomic64_set(&new_key->pkt_bad, 0); + + return new_key; +} + +static void tcp_ao_key_free_rcu(struct rcu_head *head) +{ + struct tcp_ao_key *key = container_of(head, struct tcp_ao_key, rcu); + + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); +} + +void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +{ + struct tcp_ao_info *ao; + struct tcp_ao_key *key; + struct hlist_node *n; + + if (twsk) { + ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1); + tcp_twsk(sk)->ao_info = NULL; + } else { + ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1); + tcp_sk(sk)->ao_info = NULL; + } + + if (!ao || !refcount_dec_and_test(&ao->refcnt)) + return; + + hlist_for_each_entry_safe(key, n, &ao->head, node) { + hlist_del_rcu(&key->node); + if (!twsk) + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + } + + kfree_rcu(ao, rcu); + static_branch_slow_dec_deferred(&tcp_ao_needed); +} + +void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp) +{ + struct tcp_ao_info *ao_info = rcu_dereference_protected(tp->ao_info, 1); + + if (ao_info) { + struct tcp_ao_key *key; + struct hlist_node *n; + int omem = 0; + + hlist_for_each_entry_safe(key, n, &ao_info->head, node) { + omem += tcp_ao_sizeof_key(key); + } + + refcount_inc(&ao_info->refcnt); + atomic_sub(omem, &(((struct sock *)tp)->sk_omem_alloc)); + rcu_assign_pointer(tcptw->ao_info, ao_info); + } else { + tcptw->ao_info = NULL; + } +} + +/* 4 tuple and ISNs are expected in NBO */ +static int tcp_v4_ao_calc_key(struct tcp_ao_key *mkt, u8 *key, + __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, + __be32 sisn, __be32 disn) +{ + /* See RFC5926 3.1.1 */ + struct kdf_input_block { + u8 counter; + u8 label[6]; + struct tcp4_ao_context ctx; + __be16 outlen; + } __packed * tmp; + struct tcp_sigpool hp; + int err; + + err = tcp_sigpool_start(mkt->tcp_sigpool_id, &hp); + if (err) + return err; + + tmp = hp.scratch; + tmp->counter = 1; + memcpy(tmp->label, "TCP-AO", 6); + tmp->ctx.saddr = saddr; + tmp->ctx.daddr = daddr; + tmp->ctx.sport = sport; + tmp->ctx.dport = dport; + tmp->ctx.sisn = sisn; + tmp->ctx.disn = disn; + tmp->outlen = htons(tcp_ao_digest_size(mkt) * 8); /* in bits */ + + err = tcp_ao_calc_traffic_key(mkt, key, tmp, sizeof(*tmp), &hp); + tcp_sigpool_end(&hp); + + return err; +} + +int tcp_v4_ao_calc_key_sk(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, + __be32 sisn, __be32 disn, bool send) +{ + if (send) + return tcp_v4_ao_calc_key(mkt, key, sk->sk_rcv_saddr, + sk->sk_daddr, htons(sk->sk_num), + sk->sk_dport, sisn, disn); + else + return tcp_v4_ao_calc_key(mkt, key, sk->sk_daddr, + sk->sk_rcv_saddr, sk->sk_dport, + htons(sk->sk_num), disn, sisn); +} + +static int tcp_ao_calc_key_sk(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, + __be32 sisn, __be32 disn, bool send) +{ + if (mkt->family == AF_INET) + return tcp_v4_ao_calc_key_sk(mkt, key, sk, sisn, disn, send); +#if IS_ENABLED(CONFIG_IPV6) + else if (mkt->family == AF_INET6) + return tcp_v6_ao_calc_key_sk(mkt, key, sk, sisn, disn, send); +#endif + else + return -EOPNOTSUPP; +} + +int tcp_v4_ao_calc_key_rsk(struct tcp_ao_key *mkt, u8 *key, + struct request_sock *req) +{ + struct inet_request_sock *ireq = inet_rsk(req); + + return tcp_v4_ao_calc_key(mkt, key, + ireq->ir_loc_addr, ireq->ir_rmt_addr, + htons(ireq->ir_num), ireq->ir_rmt_port, + htonl(tcp_rsk(req)->snt_isn), + htonl(tcp_rsk(req)->rcv_isn)); +} + +static int tcp_v4_ao_calc_key_skb(struct tcp_ao_key *mkt, u8 *key, + const struct sk_buff *skb, + __be32 sisn, __be32 disn) +{ + const struct iphdr *iph = ip_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); + + return tcp_v4_ao_calc_key(mkt, key, iph->saddr, iph->daddr, + th->source, th->dest, sisn, disn); +} + +static int tcp_ao_calc_key_skb(struct tcp_ao_key *mkt, u8 *key, + const struct sk_buff *skb, + __be32 sisn, __be32 disn, int family) +{ + if (family == AF_INET) + return tcp_v4_ao_calc_key_skb(mkt, key, skb, sisn, disn); +#if IS_ENABLED(CONFIG_IPV6) + else if (family == AF_INET6) + return tcp_v6_ao_calc_key_skb(mkt, key, skb, sisn, disn); +#endif + return -EAFNOSUPPORT; +} + +static int tcp_v4_ao_hash_pseudoheader(struct tcp_sigpool *hp, + __be32 daddr, __be32 saddr, + int nbytes) +{ + struct tcp4_pseudohdr *bp; + struct scatterlist sg; + + bp = hp->scratch; + bp->saddr = saddr; + bp->daddr = daddr; + bp->pad = 0; + bp->protocol = IPPROTO_TCP; + bp->len = cpu_to_be16(nbytes); + + sg_init_one(&sg, bp, sizeof(*bp)); + ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp)); + return crypto_ahash_update(hp->req); +} + +static int tcp_ao_hash_pseudoheader(unsigned short int family, + const struct sock *sk, + const struct sk_buff *skb, + struct tcp_sigpool *hp, int nbytes) +{ + const struct tcphdr *th = tcp_hdr(skb); + + /* TODO: Can we rely on checksum being zero to mean outbound pkt? */ + if (!th->check) { + if (family == AF_INET) + return tcp_v4_ao_hash_pseudoheader(hp, sk->sk_daddr, + sk->sk_rcv_saddr, skb->len); +#if IS_ENABLED(CONFIG_IPV6) + else if (family == AF_INET6) + return tcp_v6_ao_hash_pseudoheader(hp, &sk->sk_v6_daddr, + &sk->sk_v6_rcv_saddr, skb->len); +#endif + else + return -EAFNOSUPPORT; + } + + if (family == AF_INET) { + const struct iphdr *iph = ip_hdr(skb); + + return tcp_v4_ao_hash_pseudoheader(hp, iph->daddr, + iph->saddr, skb->len); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + const struct ipv6hdr *iph = ipv6_hdr(skb); + + return tcp_v6_ao_hash_pseudoheader(hp, &iph->daddr, + &iph->saddr, skb->len); +#endif + } + return -EAFNOSUPPORT; +} + +u32 tcp_ao_compute_sne(u32 next_sne, u32 next_seq, u32 seq) +{ + u32 sne = next_sne; + + if (before(seq, next_seq)) { + if (seq > next_seq) + sne--; + } else { + if (seq < next_seq) + sne++; + } + + return sne; +} + +/* tcp_ao_hash_sne(struct tcp_sigpool *hp) + * @hp - used for hashing + * @sne - sne value + */ +static int tcp_ao_hash_sne(struct tcp_sigpool *hp, u32 sne) +{ + struct scatterlist sg; + __be32 *bp; + + bp = (__be32 *)hp->scratch; + *bp = htonl(sne); + + sg_init_one(&sg, bp, sizeof(*bp)); + ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp)); + return crypto_ahash_update(hp->req); +} + +static int tcp_ao_hash_header(struct tcp_sigpool *hp, + const struct tcphdr *th, + bool exclude_options, u8 *hash, + int hash_offset, int hash_len) +{ + int err, len = th->doff << 2; + struct scatterlist sg; + u8 *hdr = hp->scratch; + + /* We are not allowed to change tcphdr, make a local copy */ + if (exclude_options) { + len = sizeof(*th) + sizeof(struct tcp_ao_hdr) + hash_len; + memcpy(hdr, th, sizeof(*th)); + memcpy(hdr + sizeof(*th), + (u8 *)th + hash_offset - sizeof(struct tcp_ao_hdr), + sizeof(struct tcp_ao_hdr)); + memset(hdr + sizeof(*th) + sizeof(struct tcp_ao_hdr), + 0, hash_len); + ((struct tcphdr *)hdr)->check = 0; + } else { + len = th->doff << 2; + memcpy(hdr, th, len); + /* zero out tcp-ao hash */ + ((struct tcphdr *)hdr)->check = 0; + memset(hdr + hash_offset, 0, hash_len); + } + + sg_init_one(&sg, hdr, len); + ahash_request_set_crypt(hp->req, &sg, NULL, len); + err = crypto_ahash_update(hp->req); + WARN_ON_ONCE(err != 0); + return err; +} + +int tcp_ao_hash_hdr(unsigned short int family, char *ao_hash, + struct tcp_ao_key *key, const u8 *tkey, + const union tcp_ao_addr *daddr, + const union tcp_ao_addr *saddr, + const struct tcphdr *th, u32 sne) +{ + int tkey_len = tcp_ao_digest_size(key); + int hash_offset = ao_hash - (char *)th; + struct tcp_sigpool hp; + void *hash_buf = NULL; + + hash_buf = kmalloc(tkey_len, GFP_ATOMIC); + if (!hash_buf) + goto clear_hash_noput; + + if (tcp_sigpool_start(key->tcp_sigpool_id, &hp)) + goto clear_hash_noput; + + if (crypto_ahash_setkey(crypto_ahash_reqtfm(hp.req), tkey, tkey_len)) + goto clear_hash; + + if (crypto_ahash_init(hp.req)) + goto clear_hash; + + if (tcp_ao_hash_sne(&hp, sne)) + goto clear_hash; + if (family == AF_INET) { + if (tcp_v4_ao_hash_pseudoheader(&hp, daddr->a4.s_addr, + saddr->a4.s_addr, th->doff * 4)) + goto clear_hash; +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + if (tcp_v6_ao_hash_pseudoheader(&hp, &daddr->a6, + &saddr->a6, th->doff * 4)) + goto clear_hash; +#endif + } else { + WARN_ON_ONCE(1); + goto clear_hash; + } + if (tcp_ao_hash_header(&hp, th, + !!(key->keyflags & TCP_AO_KEYF_EXCLUDE_OPT), + ao_hash, hash_offset, tcp_ao_maclen(key))) + goto clear_hash; + ahash_request_set_crypt(hp.req, NULL, hash_buf, 0); + if (crypto_ahash_final(hp.req)) + goto clear_hash; + + memcpy(ao_hash, hash_buf, tcp_ao_maclen(key)); + tcp_sigpool_end(&hp); + kfree(hash_buf); + return 0; + +clear_hash: + tcp_sigpool_end(&hp); +clear_hash_noput: + memset(ao_hash, 0, tcp_ao_maclen(key)); + kfree(hash_buf); + return 1; +} + +int tcp_ao_hash_skb(unsigned short int family, + char *ao_hash, struct tcp_ao_key *key, + const struct sock *sk, const struct sk_buff *skb, + const u8 *tkey, int hash_offset, u32 sne) +{ + const struct tcphdr *th = tcp_hdr(skb); + int tkey_len = tcp_ao_digest_size(key); + struct tcp_sigpool hp; + void *hash_buf = NULL; + + hash_buf = kmalloc(tkey_len, GFP_ATOMIC); + if (!hash_buf) + goto clear_hash_noput; + + if (tcp_sigpool_start(key->tcp_sigpool_id, &hp)) + goto clear_hash_noput; + + if (crypto_ahash_setkey(crypto_ahash_reqtfm(hp.req), tkey, tkey_len)) + goto clear_hash; + + /* For now use sha1 by default. Depends on alg in tcp_ao_key */ + if (crypto_ahash_init(hp.req)) + goto clear_hash; + + if (tcp_ao_hash_sne(&hp, sne)) + goto clear_hash; + if (tcp_ao_hash_pseudoheader(family, sk, skb, &hp, skb->len)) + goto clear_hash; + if (tcp_ao_hash_header(&hp, th, + !!(key->keyflags & TCP_AO_KEYF_EXCLUDE_OPT), + ao_hash, hash_offset, tcp_ao_maclen(key))) + goto clear_hash; + if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) + goto clear_hash; + ahash_request_set_crypt(hp.req, NULL, hash_buf, 0); + if (crypto_ahash_final(hp.req)) + goto clear_hash; + + memcpy(ao_hash, hash_buf, tcp_ao_maclen(key)); + tcp_sigpool_end(&hp); + kfree(hash_buf); + return 0; + +clear_hash: + tcp_sigpool_end(&hp); +clear_hash_noput: + memset(ao_hash, 0, tcp_ao_maclen(key)); + kfree(hash_buf); + return 1; +} + +int tcp_v4_ao_hash_skb(char *ao_hash, struct tcp_ao_key *key, + const struct sock *sk, const struct sk_buff *skb, + const u8 *tkey, int hash_offset, u32 sne) +{ + return tcp_ao_hash_skb(AF_INET, ao_hash, key, sk, skb, + tkey, hash_offset, sne); +} + +int tcp_v4_ao_synack_hash(char *ao_hash, struct tcp_ao_key *ao_key, + struct request_sock *req, const struct sk_buff *skb, + int hash_offset, u32 sne) +{ + void *hash_buf = NULL; + int err; + + hash_buf = kmalloc(tcp_ao_digest_size(ao_key), GFP_ATOMIC); + if (!hash_buf) + return -ENOMEM; + + err = tcp_v4_ao_calc_key_rsk(ao_key, hash_buf, req); + if (err) + goto out; + + err = tcp_ao_hash_skb(AF_INET, ao_hash, ao_key, req_to_sk(req), skb, + hash_buf, hash_offset, sne); +out: + kfree(hash_buf); + return err; +} + +struct tcp_ao_key *tcp_v4_ao_lookup_rsk(const struct sock *sk, + struct request_sock *req, + int sndid, int rcvid) +{ + struct inet_request_sock *ireq = inet_rsk(req); + union tcp_ao_addr *addr = (union tcp_ao_addr *)&ireq->ir_rmt_addr; + int l3index; + + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); + return tcp_ao_do_lookup(sk, l3index, addr, AF_INET, sndid, rcvid); +} + +struct tcp_ao_key *tcp_v4_ao_lookup(const struct sock *sk, struct sock *addr_sk, + int sndid, int rcvid) +{ + int l3index = l3mdev_master_ifindex_by_index(sock_net(sk), + addr_sk->sk_bound_dev_if); + union tcp_ao_addr *addr = (union tcp_ao_addr *)&addr_sk->sk_daddr; + + return tcp_ao_do_lookup(sk, l3index, addr, AF_INET, sndid, rcvid); +} + +int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb, + const struct tcp_ao_hdr *aoh, int l3index, u32 seq, + struct tcp_ao_key **key, char **traffic_key, + bool *allocated_traffic_key, u8 *keyid, u32 *sne) +{ + const struct tcphdr *th = tcp_hdr(skb); + struct tcp_ao_info *ao_info; + + *allocated_traffic_key = false; + /* If there's no socket - than initial sisn/disn are unknown. + * Drop the segment. RFC5925 (7.7) advises to require graceful + * restart [RFC4724]. Alternatively, the RFC5925 advises to + * save/restore traffic keys before/after reboot. + * Linux TCP-AO support provides TCP_AO_ADD_KEY and TCP_AO_REPAIR + * options to restore a socket post-reboot. + */ + if (!sk) + return -ENOTCONN; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) { + unsigned int family = READ_ONCE(sk->sk_family); + union tcp_ao_addr *addr; + __be32 disn, sisn; + + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + + sisn = htonl(tcp_rsk(req)->rcv_isn); + disn = htonl(tcp_rsk(req)->snt_isn); + *sne = tcp_ao_compute_sne(0, tcp_rsk(req)->snt_isn, seq); + } else { + sisn = th->seq; + disn = 0; + } + if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) + addr = (union tcp_md5_addr *)&ipv6_hdr(skb)->saddr; + else + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && ipv6_addr_v4mapped(&sk->sk_v6_daddr)) + family = AF_INET; +#endif + + sk = sk_const_to_full_sk(sk); + ao_info = rcu_dereference(tcp_sk(sk)->ao_info); + if (!ao_info) + return -ENOENT; + *key = tcp_ao_do_lookup(sk, l3index, addr, family, + -1, aoh->rnext_keyid); + if (!*key) + return -ENOENT; + *traffic_key = kmalloc(tcp_ao_digest_size(*key), GFP_ATOMIC); + if (!*traffic_key) + return -ENOMEM; + *allocated_traffic_key = true; + if (tcp_ao_calc_key_skb(*key, *traffic_key, skb, + sisn, disn, family)) + return -1; + *keyid = (*key)->rcvid; + } else { + struct tcp_ao_key *rnext_key; + u32 snd_basis; + + if (sk->sk_state == TCP_TIME_WAIT) { + ao_info = rcu_dereference(tcp_twsk(sk)->ao_info); + snd_basis = tcp_twsk(sk)->tw_snd_nxt; + } else { + ao_info = rcu_dereference(tcp_sk(sk)->ao_info); + snd_basis = tcp_sk(sk)->snd_una; + } + if (!ao_info) + return -ENOENT; + + *key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1); + if (!*key) + return -ENOENT; + *traffic_key = snd_other_key(*key); + rnext_key = READ_ONCE(ao_info->rnext_key); + *keyid = rnext_key->rcvid; + *sne = tcp_ao_compute_sne(READ_ONCE(ao_info->snd_sne), + snd_basis, seq); + } + return 0; +} + +int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, + struct tcp_ao_key *key, struct tcphdr *th, + __u8 *hash_location) +{ + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_ao_info *ao; + void *tkey_buf = NULL; + u8 *traffic_key; + u32 sne; + + ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + traffic_key = snd_other_key(key); + if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { + __be32 disn; + + if (!(tcb->tcp_flags & TCPHDR_ACK)) { + disn = 0; + tkey_buf = kmalloc(tcp_ao_digest_size(key), GFP_ATOMIC); + if (!tkey_buf) + return -ENOMEM; + traffic_key = tkey_buf; + } else { + disn = ao->risn; + } + tp->af_specific->ao_calc_key_sk(key, traffic_key, + sk, ao->lisn, disn, true); + } + sne = tcp_ao_compute_sne(READ_ONCE(ao->snd_sne), READ_ONCE(tp->snd_una), + ntohl(th->seq)); + tp->af_specific->calc_ao_hash(hash_location, key, sk, skb, traffic_key, + hash_location - (u8 *)th, sne); + kfree(tkey_buf); + return 0; +} + +static struct tcp_ao_key *tcp_ao_inbound_lookup(unsigned short int family, + const struct sock *sk, const struct sk_buff *skb, + int sndid, int rcvid, int l3index) +{ + if (family == AF_INET) { + const struct iphdr *iph = ip_hdr(skb); + + return tcp_ao_do_lookup(sk, l3index, + (union tcp_ao_addr *)&iph->saddr, + AF_INET, sndid, rcvid); + } else { + const struct ipv6hdr *iph = ipv6_hdr(skb); + + return tcp_ao_do_lookup(sk, l3index, + (union tcp_ao_addr *)&iph->saddr, + AF_INET6, sndid, rcvid); + } +} + +void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, + struct tcp_request_sock *treq, + unsigned short int family, int l3index) +{ + const struct tcphdr *th = tcp_hdr(skb); + const struct tcp_ao_hdr *aoh; + struct tcp_ao_key *key; + + treq->maclen = 0; + + if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh) + return; + + key = tcp_ao_inbound_lookup(family, sk, skb, -1, aoh->keyid, l3index); + if (!key) + /* Key not found, continue without TCP-AO */ + return; + + treq->ao_rcv_next = aoh->keyid; + treq->ao_keyid = aoh->rnext_keyid; + treq->maclen = tcp_ao_maclen(key); +} + +static enum skb_drop_reason +tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, + unsigned short int family, struct tcp_ao_info *info, + const struct tcp_ao_hdr *aoh, struct tcp_ao_key *key, + u8 *traffic_key, u8 *phash, u32 sne, int l3index) +{ + u8 maclen = aoh->length - sizeof(struct tcp_ao_hdr); + const struct tcphdr *th = tcp_hdr(skb); + void *hash_buf = NULL; + + if (maclen != tcp_ao_maclen(key)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + atomic64_inc(&info->counters.pkt_bad); + atomic64_inc(&key->pkt_bad); + tcp_hash_fail("AO hash wrong length", family, skb, + "%u != %d L3index: %d", maclen, + tcp_ao_maclen(key), l3index); + return SKB_DROP_REASON_TCP_AOFAILURE; + } + + hash_buf = kmalloc(tcp_ao_digest_size(key), GFP_ATOMIC); + if (!hash_buf) + return SKB_DROP_REASON_NOT_SPECIFIED; + + /* XXX: make it per-AF callback? */ + tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key, + (phash - (u8 *)th), sne); + if (memcmp(phash, hash_buf, maclen)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + atomic64_inc(&info->counters.pkt_bad); + atomic64_inc(&key->pkt_bad); + tcp_hash_fail("AO hash mismatch", family, skb, + "L3index: %d", l3index); + kfree(hash_buf); + return SKB_DROP_REASON_TCP_AOFAILURE; + } + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOGOOD); + atomic64_inc(&info->counters.pkt_good); + atomic64_inc(&key->pkt_good); + kfree(hash_buf); + return SKB_NOT_DROPPED_YET; +} + +enum skb_drop_reason +tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, + unsigned short int family, const struct request_sock *req, + int l3index, const struct tcp_ao_hdr *aoh) +{ + const struct tcphdr *th = tcp_hdr(skb); + u8 *phash = (u8 *)(aoh + 1); /* hash goes just after the header */ + struct tcp_ao_info *info; + enum skb_drop_reason ret; + struct tcp_ao_key *key; + __be32 sisn, disn; + u8 *traffic_key; + u32 sne = 0; + + info = rcu_dereference(tcp_sk(sk)->ao_info); + if (!info) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); + tcp_hash_fail("AO key not found", family, skb, + "keyid: %u L3index: %d", aoh->keyid, l3index); + return SKB_DROP_REASON_TCP_AOUNEXPECTED; + } + + if (unlikely(th->syn)) { + sisn = th->seq; + disn = 0; + } + + /* Fast-path */ + if (likely((1 << sk->sk_state) & TCP_AO_ESTABLISHED)) { + enum skb_drop_reason err; + struct tcp_ao_key *current_key; + + /* Check if this socket's rnext_key matches the keyid in the + * packet. If not we lookup the key based on the keyid + * matching the rcvid in the mkt. + */ + key = READ_ONCE(info->rnext_key); + if (key->rcvid != aoh->keyid) { + key = tcp_ao_established_key(info, -1, aoh->keyid); + if (!key) + goto key_not_found; + } + + /* Delayed retransmitted SYN */ + if (unlikely(th->syn && !th->ack)) + goto verify_hash; + + sne = tcp_ao_compute_sne(info->rcv_sne, tcp_sk(sk)->rcv_nxt, + ntohl(th->seq)); + /* Established socket, traffic key are cached */ + traffic_key = rcv_other_key(key); + err = tcp_ao_verify_hash(sk, skb, family, info, aoh, key, + traffic_key, phash, sne, l3index); + if (err) + return err; + current_key = READ_ONCE(info->current_key); + /* Key rotation: the peer asks us to use new key (RNext) */ + if (unlikely(aoh->rnext_keyid != current_key->sndid)) { + /* If the key is not found we do nothing. */ + key = tcp_ao_established_key(info, aoh->rnext_keyid, -1); + if (key) + /* pairs with tcp_ao_del_cmd */ + WRITE_ONCE(info->current_key, key); + } + return SKB_NOT_DROPPED_YET; + } + + /* Lookup key based on peer address and keyid. + * current_key and rnext_key must not be used on tcp listen + * sockets as otherwise: + * - request sockets would race on those key pointers + * - tcp_ao_del_cmd() allows async key removal + */ + key = tcp_ao_inbound_lookup(family, sk, skb, -1, aoh->keyid, l3index); + if (!key) + goto key_not_found; + + if (th->syn && !th->ack) + goto verify_hash; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) { + /* Make the initial syn the likely case here */ + if (unlikely(req)) { + sne = tcp_ao_compute_sne(0, tcp_rsk(req)->rcv_isn, + ntohl(th->seq)); + sisn = htonl(tcp_rsk(req)->rcv_isn); + disn = htonl(tcp_rsk(req)->snt_isn); + } else if (unlikely(th->ack && !th->syn)) { + /* Possible syncookie packet */ + sisn = htonl(ntohl(th->seq) - 1); + disn = htonl(ntohl(th->ack_seq) - 1); + sne = tcp_ao_compute_sne(0, ntohl(sisn), + ntohl(th->seq)); + } else if (unlikely(!th->syn)) { + /* no way to figure out initial sisn/disn - drop */ + return SKB_DROP_REASON_TCP_FLAGS; + } + } else if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + disn = info->lisn; + if (th->syn || th->rst) + sisn = th->seq; + else + sisn = info->risn; + } else { + WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", sk->sk_state); + return SKB_DROP_REASON_TCP_AOFAILURE; + } +verify_hash: + traffic_key = kmalloc(tcp_ao_digest_size(key), GFP_ATOMIC); + if (!traffic_key) + return SKB_DROP_REASON_NOT_SPECIFIED; + tcp_ao_calc_key_skb(key, traffic_key, skb, sisn, disn, family); + ret = tcp_ao_verify_hash(sk, skb, family, info, aoh, key, + traffic_key, phash, sne, l3index); + kfree(traffic_key); + return ret; + +key_not_found: + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); + atomic64_inc(&info->counters.key_not_found); + tcp_hash_fail("Requested by the peer AO key id not found", + family, skb, "L3index: %d", l3index); + return SKB_DROP_REASON_TCP_AOKEYNOTFOUND; +} + +static int tcp_ao_cache_traffic_keys(const struct sock *sk, + struct tcp_ao_info *ao, + struct tcp_ao_key *ao_key) +{ + u8 *traffic_key = snd_other_key(ao_key); + int ret; + + ret = tcp_ao_calc_key_sk(ao_key, traffic_key, sk, + ao->lisn, ao->risn, true); + if (ret) + return ret; + + traffic_key = rcv_other_key(ao_key); + ret = tcp_ao_calc_key_sk(ao_key, traffic_key, sk, + ao->lisn, ao->risn, false); + return ret; +} + +void tcp_ao_connect_init(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_ao_info *ao_info; + union tcp_ao_addr *addr; + struct tcp_ao_key *key; + int family, l3index; + + ao_info = rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held(sk)); + if (!ao_info) + return; + + /* Remove all keys that don't match the peer */ + family = sk->sk_family; + if (family == AF_INET) + addr = (union tcp_ao_addr *)&sk->sk_daddr; +#if IS_ENABLED(CONFIG_IPV6) + else if (family == AF_INET6) + addr = (union tcp_ao_addr *)&sk->sk_v6_daddr; +#endif + else + return; + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), + sk->sk_bound_dev_if); + + hlist_for_each_entry_rcu(key, &ao_info->head, node) { + if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1)) + continue; + + if (key == ao_info->current_key) + ao_info->current_key = NULL; + if (key == ao_info->rnext_key) + ao_info->rnext_key = NULL; + hlist_del_rcu(&key->node); + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + } + + key = tp->af_specific->ao_lookup(sk, sk, -1, -1); + if (key) { + /* if current_key or rnext_key were not provided, + * use the first key matching the peer + */ + if (!ao_info->current_key) + ao_info->current_key = key; + if (!ao_info->rnext_key) + ao_info->rnext_key = key; + tp->tcp_header_len += tcp_ao_len(key); + + ao_info->lisn = htonl(tp->write_seq); + ao_info->snd_sne = 0; + } else { + /* Can't happen: tcp_connect() verifies that there's + * at least one tcp-ao key that matches the remote peer. + */ + WARN_ON_ONCE(1); + rcu_assign_pointer(tp->ao_info, NULL); + kfree(ao_info); + } +} + +void tcp_ao_established(struct sock *sk) +{ + struct tcp_ao_info *ao; + struct tcp_ao_key *key; + + ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + if (!ao) + return; + + hlist_for_each_entry_rcu(key, &ao->head, node) + tcp_ao_cache_traffic_keys(sk, ao, key); +} + +void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_ao_info *ao; + struct tcp_ao_key *key; + + ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + if (!ao) + return; + + WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); + ao->rcv_sne = 0; + + hlist_for_each_entry_rcu(key, &ao->head, node) + tcp_ao_cache_traffic_keys(sk, ao, key); +} + +int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, + struct request_sock *req, struct sk_buff *skb, + int family) +{ + struct tcp_ao_key *key, *new_key, *first_key; + struct tcp_ao_info *new_ao, *ao; + struct hlist_node *key_head; + int l3index, ret = -ENOMEM; + union tcp_ao_addr *addr; + bool match = false; + + ao = rcu_dereference(tcp_sk(sk)->ao_info); + if (!ao) + return 0; + + /* New socket without TCP-AO on it */ + if (!tcp_rsk_used_ao(req)) + return 0; + + new_ao = tcp_ao_alloc_info(GFP_ATOMIC); + if (!new_ao) + return -ENOMEM; + new_ao->lisn = htonl(tcp_rsk(req)->snt_isn); + new_ao->risn = htonl(tcp_rsk(req)->rcv_isn); + new_ao->ao_required = ao->ao_required; + new_ao->accept_icmps = ao->accept_icmps; + + if (family == AF_INET) { + addr = (union tcp_ao_addr *)&newsk->sk_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + addr = (union tcp_ao_addr *)&newsk->sk_v6_daddr; +#endif + } else { + ret = -EAFNOSUPPORT; + goto free_ao; + } + l3index = l3mdev_master_ifindex_by_index(sock_net(newsk), + newsk->sk_bound_dev_if); + + hlist_for_each_entry_rcu(key, &ao->head, node) { + if (tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1)) + continue; + + new_key = tcp_ao_copy_key(newsk, key); + if (!new_key) + goto free_and_exit; + + tcp_ao_cache_traffic_keys(newsk, new_ao, new_key); + tcp_ao_link_mkt(new_ao, new_key); + match = true; + } + + if (!match) { + /* RFC5925 (7.4.1) specifies that the TCP-AO status + * of a connection is determined on the initial SYN. + * At this point the connection was TCP-AO enabled, so + * it can't switch to being unsigned if peer's key + * disappears on the listening socket. + */ + ret = -EKEYREJECTED; + goto free_and_exit; + } + + if (!static_key_fast_inc_not_disabled(&tcp_ao_needed.key.key)) { + ret = -EUSERS; + goto free_and_exit; + } + + key_head = rcu_dereference(hlist_first_rcu(&new_ao->head)); + first_key = hlist_entry_safe(key_head, struct tcp_ao_key, node); + + key = tcp_ao_established_key(new_ao, tcp_rsk(req)->ao_keyid, -1); + if (key) + new_ao->current_key = key; + else + new_ao->current_key = first_key; + + /* set rnext_key */ + key = tcp_ao_established_key(new_ao, -1, tcp_rsk(req)->ao_rcv_next); + if (key) + new_ao->rnext_key = key; + else + new_ao->rnext_key = first_key; + + sk_gso_disable(newsk); + rcu_assign_pointer(tcp_sk(newsk)->ao_info, new_ao); + + return 0; + +free_and_exit: + hlist_for_each_entry_safe(key, key_head, &new_ao->head, node) { + hlist_del(&key->node); + tcp_sigpool_release(key->tcp_sigpool_id); + atomic_sub(tcp_ao_sizeof_key(key), &newsk->sk_omem_alloc); + kfree_sensitive(key); + } +free_ao: + kfree(new_ao); + return ret; +} + +static bool tcp_ao_can_set_current_rnext(struct sock *sk) +{ + /* There aren't current/rnext keys on TCP_LISTEN sockets */ + if (sk->sk_state == TCP_LISTEN) + return false; + return true; +} + +static int tcp_ao_verify_ipv4(struct sock *sk, struct tcp_ao_add *cmd, + union tcp_ao_addr **addr) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)&cmd->addr; + struct inet_sock *inet = inet_sk(sk); + + if (sin->sin_family != AF_INET) + return -EINVAL; + + /* Currently matching is not performed on port (or port ranges) */ + if (sin->sin_port != 0) + return -EINVAL; + + /* Check prefix and trailing 0's in addr */ + if (cmd->prefix != 0) { + __be32 mask; + + if (ntohl(sin->sin_addr.s_addr) == INADDR_ANY) + return -EINVAL; + if (cmd->prefix > 32) + return -EINVAL; + + mask = inet_make_mask(cmd->prefix); + if (sin->sin_addr.s_addr & ~mask) + return -EINVAL; + + /* Check that MKT address is consistent with socket */ + if (ntohl(inet->inet_daddr) != INADDR_ANY && + (inet->inet_daddr & mask) != sin->sin_addr.s_addr) + return -EINVAL; + } else { + if (ntohl(sin->sin_addr.s_addr) != INADDR_ANY) + return -EINVAL; + } + + *addr = (union tcp_ao_addr *)&sin->sin_addr; + return 0; +} + +static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key) +{ + unsigned int syn_tcp_option_space; + bool is_kdf_aes_128_cmac = false; + struct crypto_ahash *tfm; + struct tcp_sigpool hp; + void *tmp_key = NULL; + int err; + + /* RFC5926, 3.1.1.2. KDF_AES_128_CMAC */ + if (!strcmp("cmac(aes128)", cmd->alg_name)) { + strscpy(cmd->alg_name, "cmac(aes)", sizeof(cmd->alg_name)); + is_kdf_aes_128_cmac = (cmd->keylen != 16); + tmp_key = kmalloc(cmd->keylen, GFP_KERNEL); + if (!tmp_key) + return -ENOMEM; + } + + key->maclen = cmd->maclen ?: 12; /* 12 is the default in RFC5925 */ + + /* Check: maclen + tcp-ao header <= (MAX_TCP_OPTION_SPACE - mss + * - tstamp - wscale - sackperm), + * see tcp_syn_options(), tcp_synack_options(), commit 33ad798c924b. + * + * In order to allow D-SACK with TCP-AO, the header size should be: + * (MAX_TCP_OPTION_SPACE - TCPOLEN_TSTAMP_ALIGNED + * - TCPOLEN_SACK_BASE_ALIGNED + * - 2 * TCPOLEN_SACK_PERBLOCK) = 8 (maclen = 4), + * see tcp_established_options(). + * + * RFC5925, 2.2: + * Typical MACs are 96-128 bits (12-16 bytes), but any length + * that fits in the header of the segment being authenticated + * is allowed. + * + * RFC5925, 7.6: + * TCP-AO continues to consume 16 bytes in non-SYN segments, + * leaving a total of 24 bytes for other options, of which + * the timestamp consumes 10. This leaves 14 bytes, of which 10 + * are used for a single SACK block. When two SACK blocks are used, + * such as to handle D-SACK, a smaller TCP-AO MAC would be required + * to make room for the additional SACK block (i.e., to leave 18 + * bytes for the D-SACK variant of the SACK option) [RFC2883]. + * Note that D-SACK is not supportable in TCP MD5 in the presence + * of timestamps, because TCP MD5’s MAC length is fixed and too + * large to leave sufficient option space. + */ + syn_tcp_option_space = MAX_TCP_OPTION_SPACE; + syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED; + syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED; + syn_tcp_option_space -= TCPOLEN_SACKPERM_ALIGNED; + if (tcp_ao_len(key) > syn_tcp_option_space) { + err = -EMSGSIZE; + goto err_kfree; + } + + key->keylen = cmd->keylen; + memcpy(key->key, cmd->key, cmd->keylen); + + err = tcp_sigpool_start(key->tcp_sigpool_id, &hp); + if (err) + goto err_kfree; + + tfm = crypto_ahash_reqtfm(hp.req); + if (is_kdf_aes_128_cmac) { + void *scratch = hp.scratch; + struct scatterlist sg; + + memcpy(tmp_key, cmd->key, cmd->keylen); + sg_init_one(&sg, tmp_key, cmd->keylen); + + /* Using zero-key of 16 bytes as described in RFC5926 */ + memset(scratch, 0, 16); + err = crypto_ahash_setkey(tfm, scratch, 16); + if (err) + goto err_pool_end; + + err = crypto_ahash_init(hp.req); + if (err) + goto err_pool_end; + + ahash_request_set_crypt(hp.req, &sg, key->key, cmd->keylen); + err = crypto_ahash_update(hp.req); + if (err) + goto err_pool_end; + + err |= crypto_ahash_final(hp.req); + if (err) + goto err_pool_end; + key->keylen = 16; + } + + err = crypto_ahash_setkey(tfm, key->key, key->keylen); + if (err) + goto err_pool_end; + + tcp_sigpool_end(&hp); + kfree_sensitive(tmp_key); + + if (tcp_ao_maclen(key) > key->digest_size) + return -EINVAL; + + return 0; + +err_pool_end: + tcp_sigpool_end(&hp); +err_kfree: + kfree_sensitive(tmp_key); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int tcp_ao_verify_ipv6(struct sock *sk, struct tcp_ao_add *cmd, + union tcp_ao_addr **paddr, + unsigned short int *family) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd->addr; + struct in6_addr *addr = &sin6->sin6_addr; + u8 prefix = cmd->prefix; + + if (sin6->sin6_family != AF_INET6) + return -EINVAL; + + /* Currently matching is not performed on port (or port ranges) */ + if (sin6->sin6_port != 0) + return -EINVAL; + + /* Check prefix and trailing 0's in addr */ + if (cmd->prefix != 0 && ipv6_addr_v4mapped(addr)) { + __be32 addr4 = addr->s6_addr32[3]; + __be32 mask; + + if (prefix > 32 || ntohl(addr4) == INADDR_ANY) + return -EINVAL; + + mask = inet_make_mask(prefix); + if (addr4 & ~mask) + return -EINVAL; + + /* Check that MKT address is consistent with socket */ + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + __be32 daddr4 = sk->sk_v6_daddr.s6_addr32[3]; + + if (!ipv6_addr_v4mapped(&sk->sk_v6_daddr)) + return -EINVAL; + if ((daddr4 & mask) != addr4) + return -EINVAL; + } + + *paddr = (union tcp_ao_addr *)&addr->s6_addr32[3]; + *family = AF_INET; + return 0; + } else if (cmd->prefix != 0) { + struct in6_addr pfx; + + if (ipv6_addr_any(addr) || prefix > 128) + return -EINVAL; + + ipv6_addr_prefix(&pfx, addr, prefix); + if (ipv6_addr_cmp(&pfx, addr)) + return -EINVAL; + + /* Check that MKT address is consistent with socket */ + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_prefix_equal(&sk->sk_v6_daddr, addr, prefix)) + + return -EINVAL; + } else { + if (!ipv6_addr_any(addr)) + return -EINVAL; + } + + *paddr = (union tcp_ao_addr *)addr; + return 0; +} +#else +static int tcp_ao_verify_ipv6(struct sock *sk, struct tcp_ao_add *cmd, + union tcp_ao_addr **paddr, + unsigned short int *family) +{ + return -EOPNOTSUPP; +} +#endif + +static struct tcp_ao_info *setsockopt_ao_info(struct sock *sk) +{ + if (sk_fullsock(sk)) { + return rcu_dereference_protected(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + } else if (sk->sk_state == TCP_TIME_WAIT) { + return rcu_dereference_protected(tcp_twsk(sk)->ao_info, + lockdep_sock_is_held(sk)); + } + return ERR_PTR(-ESOCKTNOSUPPORT); +} + +static struct tcp_ao_info *getsockopt_ao_info(struct sock *sk) +{ + if (sk_fullsock(sk)) + return rcu_dereference(tcp_sk(sk)->ao_info); + else if (sk->sk_state == TCP_TIME_WAIT) + return rcu_dereference(tcp_twsk(sk)->ao_info); + + return ERR_PTR(-ESOCKTNOSUPPORT); +} + +#define TCP_AO_KEYF_ALL (TCP_AO_KEYF_IFINDEX | TCP_AO_KEYF_EXCLUDE_OPT) +#define TCP_AO_GET_KEYF_VALID (TCP_AO_KEYF_IFINDEX) + +static struct tcp_ao_key *tcp_ao_key_alloc(struct sock *sk, + struct tcp_ao_add *cmd) +{ + const char *algo = cmd->alg_name; + unsigned int digest_size; + struct crypto_ahash *tfm; + struct tcp_ao_key *key; + struct tcp_sigpool hp; + int err, pool_id; + size_t size; + + /* Force null-termination of alg_name */ + cmd->alg_name[ARRAY_SIZE(cmd->alg_name) - 1] = '\0'; + + /* RFC5926, 3.1.1.2. KDF_AES_128_CMAC */ + if (!strcmp("cmac(aes128)", algo)) + algo = "cmac(aes)"; + + /* Full TCP header (th->doff << 2) should fit into scratch area, + * see tcp_ao_hash_header(). + */ + pool_id = tcp_sigpool_alloc_ahash(algo, 60); + if (pool_id < 0) + return ERR_PTR(pool_id); + + err = tcp_sigpool_start(pool_id, &hp); + if (err) + goto err_free_pool; + + tfm = crypto_ahash_reqtfm(hp.req); + if (crypto_ahash_alignmask(tfm) > TCP_AO_KEY_ALIGN) { + err = -EOPNOTSUPP; + goto err_pool_end; + } + digest_size = crypto_ahash_digestsize(tfm); + tcp_sigpool_end(&hp); + + size = sizeof(struct tcp_ao_key) + (digest_size << 1); + key = sock_kmalloc(sk, size, GFP_KERNEL); + if (!key) { + err = -ENOMEM; + goto err_free_pool; + } + + key->tcp_sigpool_id = pool_id; + key->digest_size = digest_size; + return key; + +err_pool_end: + tcp_sigpool_end(&hp); +err_free_pool: + tcp_sigpool_release(pool_id); + return ERR_PTR(err); +} + +static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, + sockptr_t optval, int optlen) +{ + struct tcp_ao_info *ao_info; + union tcp_ao_addr *addr; + struct tcp_ao_key *key; + struct tcp_ao_add cmd; + int ret, l3index = 0; + bool first = false; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + ret = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (ret) + return ret; + + if (cmd.keylen > TCP_AO_MAXKEYLEN) + return -EINVAL; + + if (cmd.reserved != 0 || cmd.reserved2 != 0) + return -EINVAL; + + if (family == AF_INET) + ret = tcp_ao_verify_ipv4(sk, &cmd, &addr); + else + ret = tcp_ao_verify_ipv6(sk, &cmd, &addr, &family); + if (ret) + return ret; + + if (cmd.keyflags & ~TCP_AO_KEYF_ALL) + return -EINVAL; + + if (cmd.set_current || cmd.set_rnext) { + if (!tcp_ao_can_set_current_rnext(sk)) + return -EINVAL; + } + + if (cmd.ifindex && !(cmd.keyflags & TCP_AO_KEYF_IFINDEX)) + return -EINVAL; + + /* For cmd.tcp_ifindex = 0 the key will apply to the default VRF */ + if (cmd.keyflags & TCP_AO_KEYF_IFINDEX && cmd.ifindex) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cmd.ifindex); + if (dev && netif_is_l3_master(dev)) + l3index = dev->ifindex; + rcu_read_unlock(); + + if (!dev || !l3index) + return -EINVAL; + + /* It's still possible to bind after adding keys or even + * re-bind to a different dev (with CAP_NET_RAW). + * So, no reason to return error here, rather try to be + * nice and warn the user. + */ + if (bound_dev_if && bound_dev_if != cmd.ifindex) + net_warn_ratelimited("AO key ifindex %d != sk bound ifindex %d\n", + cmd.ifindex, bound_dev_if); + } + + /* Don't allow keys for peers that have a matching TCP-MD5 key */ + if (cmd.keyflags & TCP_AO_KEYF_IFINDEX) { + /* Non-_exact version of tcp_md5_do_lookup() will + * as well match keys that aren't bound to a specific VRF + * (that will make them match AO key with + * sysctl_tcp_l3dev_accept = 1 + */ + if (tcp_md5_do_lookup(sk, l3index, addr, family)) + return -EKEYREJECTED; + } else { + if (tcp_md5_do_lookup_any_l3index(sk, addr, family)) + return -EKEYREJECTED; + } + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + + if (!ao_info) { + ao_info = tcp_ao_alloc_info(GFP_KERNEL); + if (!ao_info) + return -ENOMEM; + first = true; + } else { + /* Check that neither RecvID nor SendID match any + * existing key for the peer, RFC5925 3.1: + * > The IDs of MKTs MUST NOT overlap where their + * > TCP connection identifiers overlap. + */ + if (__tcp_ao_do_lookup(sk, l3index, addr, family, cmd.prefix, -1, cmd.rcvid)) + return -EEXIST; + if (__tcp_ao_do_lookup(sk, l3index, addr, family, + cmd.prefix, cmd.sndid, -1)) + return -EEXIST; + } + + key = tcp_ao_key_alloc(sk, &cmd); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto err_free_ao; + } + + INIT_HLIST_NODE(&key->node); + memcpy(&key->addr, addr, (family == AF_INET) ? sizeof(struct in_addr) : + sizeof(struct in6_addr)); + key->prefixlen = cmd.prefix; + key->family = family; + key->keyflags = cmd.keyflags; + key->sndid = cmd.sndid; + key->rcvid = cmd.rcvid; + key->l3index = l3index; + atomic64_set(&key->pkt_good, 0); + atomic64_set(&key->pkt_bad, 0); + + ret = tcp_ao_parse_crypto(&cmd, key); + if (ret < 0) + goto err_free_sock; + + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) { + tcp_ao_cache_traffic_keys(sk, ao_info, key); + if (first) { + ao_info->current_key = key; + ao_info->rnext_key = key; + } + } + + tcp_ao_link_mkt(ao_info, key); + if (first) { + if (!static_branch_inc(&tcp_ao_needed.key)) { + ret = -EUSERS; + goto err_free_sock; + } + sk_gso_disable(sk); + rcu_assign_pointer(tcp_sk(sk)->ao_info, ao_info); + } + + if (cmd.set_current) + WRITE_ONCE(ao_info->current_key, key); + if (cmd.set_rnext) + WRITE_ONCE(ao_info->rnext_key, key); + return 0; + +err_free_sock: + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); +err_free_ao: + if (first) + kfree(ao_info); + return ret; +} + +static int tcp_ao_delete_key(struct sock *sk, struct tcp_ao_info *ao_info, + bool del_async, struct tcp_ao_key *key, + struct tcp_ao_key *new_current, + struct tcp_ao_key *new_rnext) +{ + int err; + + hlist_del_rcu(&key->node); + + /* Support for async delete on listening sockets: as they don't + * need current_key/rnext_key maintaining, we don't need to check + * them and we can just free all resources in RCU fashion. + */ + if (del_async) { + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + return 0; + } + + /* At this moment another CPU could have looked this key up + * while it was unlinked from the list. Wait for RCU grace period, + * after which the key is off-list and can't be looked up again; + * the rx path [just before RCU came] might have used it and set it + * as current_key (very unlikely). + * Free the key with next RCU grace period (in case it was + * current_key before tcp_ao_current_rnext() might have + * changed it in forced-delete). + */ + synchronize_rcu(); + if (new_current) + WRITE_ONCE(ao_info->current_key, new_current); + if (new_rnext) + WRITE_ONCE(ao_info->rnext_key, new_rnext); + + if (unlikely(READ_ONCE(ao_info->current_key) == key || + READ_ONCE(ao_info->rnext_key) == key)) { + err = -EBUSY; + goto add_key; + } + + atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); + call_rcu(&key->rcu, tcp_ao_key_free_rcu); + + return 0; +add_key: + hlist_add_head_rcu(&key->node, &ao_info->head); + return err; +} + +#define TCP_AO_DEL_KEYF_ALL (TCP_AO_KEYF_IFINDEX) +static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, + sockptr_t optval, int optlen) +{ + struct tcp_ao_key *key, *new_current = NULL, *new_rnext = NULL; + int err, addr_len, l3index = 0; + struct tcp_ao_info *ao_info; + union tcp_ao_addr *addr; + struct tcp_ao_del cmd; + __u8 prefix; + u16 port; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + err = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (err) + return err; + + if (cmd.reserved != 0 || cmd.reserved2 != 0) + return -EINVAL; + + if (cmd.set_current || cmd.set_rnext) { + if (!tcp_ao_can_set_current_rnext(sk)) + return -EINVAL; + } + + if (cmd.keyflags & ~TCP_AO_DEL_KEYF_ALL) + return -EINVAL; + + /* No sanity check for TCP_AO_KEYF_IFINDEX as if a VRF + * was destroyed, there still should be a way to delete keys, + * that were bound to that l3intf. So, fail late at lookup stage + * if there is no key for that ifindex. + */ + if (cmd.ifindex && !(cmd.keyflags & TCP_AO_KEYF_IFINDEX)) + return -EINVAL; + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + if (!ao_info) + return -ENOENT; + + /* For sockets in TCP_CLOSED it's possible set keys that aren't + * matching the future peer (address/VRF/etc), + * tcp_ao_connect_init() will choose a correct matching MKT + * if there's any. + */ + if (cmd.set_current) { + new_current = tcp_ao_established_key(ao_info, cmd.current_key, -1); + if (!new_current) + return -ENOENT; + } + if (cmd.set_rnext) { + new_rnext = tcp_ao_established_key(ao_info, -1, cmd.rnext); + if (!new_rnext) + return -ENOENT; + } + if (cmd.del_async && sk->sk_state != TCP_LISTEN) + return -EINVAL; + + if (family == AF_INET) { + struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.addr; + + addr = (union tcp_ao_addr *)&sin->sin_addr; + addr_len = sizeof(struct in_addr); + port = ntohs(sin->sin_port); + } else { + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.addr; + struct in6_addr *addr6 = &sin6->sin6_addr; + + if (ipv6_addr_v4mapped(addr6)) { + addr = (union tcp_ao_addr *)&addr6->s6_addr32[3]; + addr_len = sizeof(struct in_addr); + family = AF_INET; + } else { + addr = (union tcp_ao_addr *)addr6; + addr_len = sizeof(struct in6_addr); + } + port = ntohs(sin6->sin6_port); + } + prefix = cmd.prefix; + + /* Currently matching is not performed on port (or port ranges) */ + if (port != 0) + return -EINVAL; + + /* We could choose random present key here for current/rnext + * but that's less predictable. Let's be strict and don't + * allow removing a key that's in use. RFC5925 doesn't + * specify how-to coordinate key removal, but says: + * "It is presumed that an MKT affecting a particular + * connection cannot be destroyed during an active connection" + */ + hlist_for_each_entry_rcu(key, &ao_info->head, node) { + if (cmd.sndid != key->sndid || + cmd.rcvid != key->rcvid) + continue; + + if (family != key->family || + prefix != key->prefixlen || + memcmp(addr, &key->addr, addr_len)) + continue; + + if ((cmd.keyflags & TCP_AO_KEYF_IFINDEX) != + (key->keyflags & TCP_AO_KEYF_IFINDEX)) + continue; + + if (key->l3index != l3index) + continue; + + if (key == new_current || key == new_rnext) + continue; + + return tcp_ao_delete_key(sk, ao_info, cmd.del_async, key, + new_current, new_rnext); + } + return -ENOENT; +} + +/* cmd.ao_required makes a socket TCP-AO only. + * Don't allow any md5 keys for any l3intf on the socket together with it. + * Restricting it early in setsockopt() removes a check for + * ao_info->ao_required on inbound tcp segment fast-path. + */ +static int tcp_ao_required_verify(struct sock *sk) +{ +#ifdef CONFIG_TCP_MD5SIG + const struct tcp_md5sig_info *md5sig; + + if (!static_branch_unlikely(&tcp_md5_needed.key)) + return 0; + + md5sig = rcu_dereference_check(tcp_sk(sk)->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) + return 0; + + if (rcu_dereference_check(hlist_first_rcu(&md5sig->head), + lockdep_sock_is_held(sk))) + return 1; +#endif + return 0; +} + +static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, + sockptr_t optval, int optlen) +{ + struct tcp_ao_key *new_current = NULL, *new_rnext = NULL; + struct tcp_ao_info *ao_info; + struct tcp_ao_info_opt cmd; + bool first = false; + int err; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + err = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (err) + return err; + + if (cmd.set_current || cmd.set_rnext) { + if (!tcp_ao_can_set_current_rnext(sk)) + return -EINVAL; + } + + if (cmd.reserved != 0 || cmd.reserved2 != 0) + return -EINVAL; + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + if (!ao_info) { + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) + return -EINVAL; + ao_info = tcp_ao_alloc_info(GFP_KERNEL); + if (!ao_info) + return -ENOMEM; + first = true; + } + + if (cmd.ao_required && tcp_ao_required_verify(sk)) + return -EKEYREJECTED; + + /* For sockets in TCP_CLOSED it's possible set keys that aren't + * matching the future peer (address/port/VRF/etc), + * tcp_ao_connect_init() will choose a correct matching MKT + * if there's any. + */ + if (cmd.set_current) { + new_current = tcp_ao_established_key(ao_info, cmd.current_key, -1); + if (!new_current) { + err = -ENOENT; + goto out; + } + } + if (cmd.set_rnext) { + new_rnext = tcp_ao_established_key(ao_info, -1, cmd.rnext); + if (!new_rnext) { + err = -ENOENT; + goto out; + } + } + if (cmd.set_counters) { + atomic64_set(&ao_info->counters.pkt_good, cmd.pkt_good); + atomic64_set(&ao_info->counters.pkt_bad, cmd.pkt_bad); + atomic64_set(&ao_info->counters.key_not_found, cmd.pkt_key_not_found); + atomic64_set(&ao_info->counters.ao_required, cmd.pkt_ao_required); + atomic64_set(&ao_info->counters.dropped_icmp, cmd.pkt_dropped_icmp); + } + + ao_info->ao_required = cmd.ao_required; + ao_info->accept_icmps = cmd.accept_icmps; + if (new_current) + WRITE_ONCE(ao_info->current_key, new_current); + if (new_rnext) + WRITE_ONCE(ao_info->rnext_key, new_rnext); + if (first) { + if (!static_branch_inc(&tcp_ao_needed.key)) { + err = -EUSERS; + goto out; + } + sk_gso_disable(sk); + rcu_assign_pointer(tcp_sk(sk)->ao_info, ao_info); + } + return 0; +out: + if (first) + kfree(ao_info); + return err; +} + +int tcp_parse_ao(struct sock *sk, int cmd, unsigned short int family, + sockptr_t optval, int optlen) +{ + if (WARN_ON_ONCE(family != AF_INET && family != AF_INET6)) + return -EAFNOSUPPORT; + + switch (cmd) { + case TCP_AO_ADD_KEY: + return tcp_ao_add_cmd(sk, family, optval, optlen); + case TCP_AO_DEL_KEY: + return tcp_ao_del_cmd(sk, family, optval, optlen); + case TCP_AO_INFO: + return tcp_ao_info_cmd(sk, family, optval, optlen); + default: + WARN_ON_ONCE(1); + return -EINVAL; + } +} + +int tcp_v4_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen) +{ + return tcp_parse_ao(sk, cmd, AF_INET, optval, optlen); +} + +/* tcp_ao_copy_mkts_to_user(ao_info, optval, optlen) + * + * @ao_info: struct tcp_ao_info on the socket that + * socket getsockopt(TCP_AO_GET_KEYS) is executed on + * @optval: pointer to array of tcp_ao_getsockopt structures in user space. + * Must be != NULL. + * @optlen: pointer to size of tcp_ao_getsockopt structure. + * Must be != NULL. + * + * Return value: 0 on success, a negative error number otherwise. + * + * optval points to an array of tcp_ao_getsockopt structures in user space. + * optval[0] is used as both input and output to getsockopt. It determines + * which keys are returned by the kernel. + * optval[0].nkeys is the size of the array in user space. On return it contains + * the number of keys matching the search criteria. + * If tcp_ao_getsockopt::get_all is set, then all keys in the socket are + * returned, otherwise only keys matching <addr, prefix, sndid, rcvid> + * in optval[0] are returned. + * optlen is also used as both input and output. The user provides the size + * of struct tcp_ao_getsockopt in user space, and the kernel returns the size + * of the structure in kernel space. + * The size of struct tcp_ao_getsockopt may differ between user and kernel. + * There are three cases to consider: + * * If usize == ksize, then keys are copied verbatim. + * * If usize < ksize, then the userspace has passed an old struct to a + * newer kernel. The rest of the trailing bytes in optval[0] + * (ksize - usize) are interpreted as 0 by the kernel. + * * If usize > ksize, then the userspace has passed a new struct to an + * older kernel. The trailing bytes unknown to the kernel (usize - ksize) + * are checked to ensure they are zeroed, otherwise -E2BIG is returned. + * On return the kernel fills in min(usize, ksize) in each entry of the array. + * The layout of the fields in the user and kernel structures is expected to + * be the same (including in the 32bit vs 64bit case). + */ +static int tcp_ao_copy_mkts_to_user(struct tcp_ao_info *ao_info, + sockptr_t optval, sockptr_t optlen) +{ + struct tcp_ao_getsockopt opt_in, opt_out; + struct tcp_ao_key *key, *current_key; + bool do_address_matching = true; + union tcp_ao_addr *addr = NULL; + int err, l3index, user_len; + unsigned int max_keys; /* maximum number of keys to copy to user */ + size_t out_offset = 0; + size_t bytes_to_write; /* number of bytes to write to user level */ + u32 matched_keys; /* keys from ao_info matched so far */ + int optlen_out; + __be16 port = 0; + + if (copy_from_sockptr(&user_len, optlen, sizeof(int))) + return -EFAULT; + + if (user_len <= 0) + return -EINVAL; + + memset(&opt_in, 0, sizeof(struct tcp_ao_getsockopt)); + err = copy_struct_from_sockptr(&opt_in, sizeof(opt_in), + optval, user_len); + if (err < 0) + return err; + + if (opt_in.pkt_good || opt_in.pkt_bad) + return -EINVAL; + if (opt_in.keyflags & ~TCP_AO_GET_KEYF_VALID) + return -EINVAL; + if (opt_in.ifindex && !(opt_in.keyflags & TCP_AO_KEYF_IFINDEX)) + return -EINVAL; + + if (opt_in.reserved != 0) + return -EINVAL; + + max_keys = opt_in.nkeys; + l3index = (opt_in.keyflags & TCP_AO_KEYF_IFINDEX) ? opt_in.ifindex : -1; + + if (opt_in.get_all || opt_in.is_current || opt_in.is_rnext) { + if (opt_in.get_all && (opt_in.is_current || opt_in.is_rnext)) + return -EINVAL; + do_address_matching = false; + } + + switch (opt_in.addr.ss_family) { + case AF_INET: { + struct sockaddr_in *sin; + __be32 mask; + + sin = (struct sockaddr_in *)&opt_in.addr; + port = sin->sin_port; + addr = (union tcp_ao_addr *)&sin->sin_addr; + + if (opt_in.prefix > 32) + return -EINVAL; + + if (ntohl(sin->sin_addr.s_addr) == INADDR_ANY && + opt_in.prefix != 0) + return -EINVAL; + + mask = inet_make_mask(opt_in.prefix); + if (sin->sin_addr.s_addr & ~mask) + return -EINVAL; + + break; + } + case AF_INET6: { + struct sockaddr_in6 *sin6; + struct in6_addr *addr6; + + sin6 = (struct sockaddr_in6 *)&opt_in.addr; + addr = (union tcp_ao_addr *)&sin6->sin6_addr; + addr6 = &sin6->sin6_addr; + port = sin6->sin6_port; + + /* We don't have to change family and @addr here if + * ipv6_addr_v4mapped() like in key adding: + * tcp_ao_key_cmp() does it. Do the sanity checks though. + */ + if (opt_in.prefix != 0) { + if (ipv6_addr_v4mapped(addr6)) { + __be32 mask, addr4 = addr6->s6_addr32[3]; + + if (opt_in.prefix > 32 || + ntohl(addr4) == INADDR_ANY) + return -EINVAL; + mask = inet_make_mask(opt_in.prefix); + if (addr4 & ~mask) + return -EINVAL; + } else { + struct in6_addr pfx; + + if (ipv6_addr_any(addr6) || + opt_in.prefix > 128) + return -EINVAL; + + ipv6_addr_prefix(&pfx, addr6, opt_in.prefix); + if (ipv6_addr_cmp(&pfx, addr6)) + return -EINVAL; + } + } else if (!ipv6_addr_any(addr6)) { + return -EINVAL; + } + break; + } + case 0: + if (!do_address_matching) + break; + fallthrough; + default: + return -EAFNOSUPPORT; + } + + if (!do_address_matching) { + /* We could just ignore those, but let's do stricter checks */ + if (addr || port) + return -EINVAL; + if (opt_in.prefix || opt_in.sndid || opt_in.rcvid) + return -EINVAL; + } + + bytes_to_write = min_t(int, user_len, sizeof(struct tcp_ao_getsockopt)); + matched_keys = 0; + /* May change in RX, while we're dumping, pre-fetch it */ + current_key = READ_ONCE(ao_info->current_key); + + hlist_for_each_entry_rcu(key, &ao_info->head, node) { + if (opt_in.get_all) + goto match; + + if (opt_in.is_current || opt_in.is_rnext) { + if (opt_in.is_current && key == current_key) + goto match; + if (opt_in.is_rnext && key == ao_info->rnext_key) + goto match; + continue; + } + + if (tcp_ao_key_cmp(key, l3index, addr, opt_in.prefix, + opt_in.addr.ss_family, + opt_in.sndid, opt_in.rcvid) != 0) + continue; +match: + matched_keys++; + if (matched_keys > max_keys) + continue; + + memset(&opt_out, 0, sizeof(struct tcp_ao_getsockopt)); + + if (key->family == AF_INET) { + struct sockaddr_in *sin_out = (struct sockaddr_in *)&opt_out.addr; + + sin_out->sin_family = key->family; + sin_out->sin_port = 0; + memcpy(&sin_out->sin_addr, &key->addr, sizeof(struct in_addr)); + } else { + struct sockaddr_in6 *sin6_out = (struct sockaddr_in6 *)&opt_out.addr; + + sin6_out->sin6_family = key->family; + sin6_out->sin6_port = 0; + memcpy(&sin6_out->sin6_addr, &key->addr, sizeof(struct in6_addr)); + } + opt_out.sndid = key->sndid; + opt_out.rcvid = key->rcvid; + opt_out.prefix = key->prefixlen; + opt_out.keyflags = key->keyflags; + opt_out.is_current = (key == current_key); + opt_out.is_rnext = (key == ao_info->rnext_key); + opt_out.nkeys = 0; + opt_out.maclen = key->maclen; + opt_out.keylen = key->keylen; + opt_out.ifindex = key->l3index; + opt_out.pkt_good = atomic64_read(&key->pkt_good); + opt_out.pkt_bad = atomic64_read(&key->pkt_bad); + memcpy(&opt_out.key, key->key, key->keylen); + tcp_sigpool_algo(key->tcp_sigpool_id, opt_out.alg_name, 64); + + /* Copy key to user */ + if (copy_to_sockptr_offset(optval, out_offset, + &opt_out, bytes_to_write)) + return -EFAULT; + out_offset += user_len; + } + + optlen_out = (int)sizeof(struct tcp_ao_getsockopt); + if (copy_to_sockptr(optlen, &optlen_out, sizeof(int))) + return -EFAULT; + + out_offset = offsetof(struct tcp_ao_getsockopt, nkeys); + if (copy_to_sockptr_offset(optval, out_offset, + &matched_keys, sizeof(u32))) + return -EFAULT; + + return 0; +} + +int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + struct tcp_ao_info *ao_info; + + ao_info = setsockopt_ao_info(sk); + if (IS_ERR(ao_info)) + return PTR_ERR(ao_info); + if (!ao_info) + return -ENOENT; + + return tcp_ao_copy_mkts_to_user(ao_info, optval, optlen); +} + +int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + struct tcp_ao_info_opt out, in = {}; + struct tcp_ao_key *current_key; + struct tcp_ao_info *ao; + int err, len; + + if (copy_from_sockptr(&len, optlen, sizeof(int))) + return -EFAULT; + + if (len <= 0) + return -EINVAL; + + /* Copying this "in" only to check ::reserved, ::reserved2, + * that may be needed to extend (struct tcp_ao_info_opt) and + * what getsockopt() provides in future. + */ + err = copy_struct_from_sockptr(&in, sizeof(in), optval, len); + if (err) + return err; + + if (in.reserved != 0 || in.reserved2 != 0) + return -EINVAL; + + ao = setsockopt_ao_info(sk); + if (IS_ERR(ao)) + return PTR_ERR(ao); + if (!ao) + return -ENOENT; + + memset(&out, 0, sizeof(out)); + out.ao_required = ao->ao_required; + out.accept_icmps = ao->accept_icmps; + out.pkt_good = atomic64_read(&ao->counters.pkt_good); + out.pkt_bad = atomic64_read(&ao->counters.pkt_bad); + out.pkt_key_not_found = atomic64_read(&ao->counters.key_not_found); + out.pkt_ao_required = atomic64_read(&ao->counters.ao_required); + out.pkt_dropped_icmp = atomic64_read(&ao->counters.dropped_icmp); + + current_key = READ_ONCE(ao->current_key); + if (current_key) { + out.set_current = 1; + out.current_key = current_key->sndid; + } + if (ao->rnext_key) { + out.set_rnext = 1; + out.rnext = ao->rnext_key->rcvid; + } + + if (copy_to_sockptr(optval, &out, min_t(int, len, sizeof(out)))) + return -EFAULT; + + return 0; +} + +int tcp_ao_set_repair(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_ao_repair cmd; + struct tcp_ao_key *key; + struct tcp_ao_info *ao; + int err; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + err = copy_struct_from_sockptr(&cmd, sizeof(cmd), optval, optlen); + if (err) + return err; + + if (!tp->repair) + return -EPERM; + + ao = setsockopt_ao_info(sk); + if (IS_ERR(ao)) + return PTR_ERR(ao); + if (!ao) + return -ENOENT; + + WRITE_ONCE(ao->lisn, cmd.snt_isn); + WRITE_ONCE(ao->risn, cmd.rcv_isn); + WRITE_ONCE(ao->snd_sne, cmd.snd_sne); + WRITE_ONCE(ao->rcv_sne, cmd.rcv_sne); + + hlist_for_each_entry_rcu(key, &ao->head, node) + tcp_ao_cache_traffic_keys(sk, ao, key); + + return 0; +} + +int tcp_ao_get_repair(struct sock *sk, sockptr_t optval, sockptr_t optlen) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_ao_repair opt; + struct tcp_ao_info *ao; + int len; + + if (copy_from_sockptr(&len, optlen, sizeof(int))) + return -EFAULT; + + if (len <= 0) + return -EINVAL; + + if (!tp->repair) + return -EPERM; + + rcu_read_lock(); + ao = getsockopt_ao_info(sk); + if (IS_ERR_OR_NULL(ao)) { + rcu_read_unlock(); + return ao ? PTR_ERR(ao) : -ENOENT; + } + + opt.snt_isn = ao->lisn; + opt.rcv_isn = ao->risn; + opt.snd_sne = READ_ONCE(ao->snd_sne); + opt.rcv_sne = READ_ONCE(ao->rcv_sne); + rcu_read_unlock(); + + if (copy_to_sockptr(optval, &opt, min_t(int, len, sizeof(opt)))) + return -EFAULT; + return 0; +} diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 146792cd26fe..22358032dd48 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -258,7 +258,7 @@ static unsigned long bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain) u64 rate = bw; rate = bbr_rate_bytes_per_sec(sk, rate, gain); - rate = min_t(u64, rate, sk->sk_max_pacing_rate); + rate = min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate)); return rate; } @@ -278,7 +278,8 @@ static void bbr_init_pacing_rate_from_rtt(struct sock *sk) } bw = (u64)tcp_snd_cwnd(tp) * BW_UNIT; do_div(bw, rtt_us); - sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain); + WRITE_ONCE(sk->sk_pacing_rate, + bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain)); } /* Pace using current bw estimate and a gain factor. */ @@ -290,14 +291,14 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) if (unlikely(!bbr->has_seen_rtt && tp->srtt_us)) bbr_init_pacing_rate_from_rtt(sk); - if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate) - sk->sk_pacing_rate = rate; + if (bbr_full_bw_reached(sk) || rate > READ_ONCE(sk->sk_pacing_rate)) + WRITE_ONCE(sk->sk_pacing_rate, rate); } /* override sysctl_tcp_min_tso_segs */ __bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk) { - return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; + return READ_ONCE(sk->sk_pacing_rate) < (bbr_min_tso_rate >> 3) ? 1 : 2; } static u32 bbr_tso_segs_goal(struct sock *sk) @@ -309,7 +310,7 @@ static u32 bbr_tso_segs_goal(struct sock *sk) * driver provided sk_gso_max_size. */ bytes = min_t(unsigned long, - sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), + READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift), GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 81f0dff69e0b..53b0d62fd2c2 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -222,6 +222,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int *addr_len) { struct tcp_sock *tcp = tcp_sk(sk); + int peek = flags & MSG_PEEK; u32 seq = tcp->copied_seq; struct sk_psock *psock; int copied = 0; @@ -306,15 +307,22 @@ msg_bytes_ready: } data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + copied = data; + goto unlock; + } if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; } out: - WRITE_ONCE(tcp->copied_seq, seq); + if (!peek) + WRITE_ONCE(tcp->copied_seq, seq); tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); + +unlock: release_sock(sk); sk_psock_put(sk, psock); return copied; @@ -349,6 +357,10 @@ msg_bytes_ready: timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + ret = data; + goto unlock; + } if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -359,6 +371,8 @@ msg_bytes_ready: copied = -EAGAIN; } ret = copied; + +unlock: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 584825ddd0a0..50aaa1527150 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -253,6 +253,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); + /* If the skb has a len of exactly 1*MSS and has the PSH bit + * set then it is likely the end of an application write. So + * more data may not be arriving soon, and yet the data sender + * may be waiting for an ACK if cwnd-bound or using TX zero + * copy. So we set ICSK_ACK_PUSHED here so that + * tcp_cleanup_rbuf() will send an ACK immediately if the app + * reads all of the data and is not ping-pong. If len > MSS + * then this logic does not matter (and does not hurt) because + * tcp_cleanup_rbuf() will always ACK immediately if the app + * reads data and there is more than an MSS of unACKed data. + */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. @@ -680,6 +693,23 @@ new_measure: tp->rcv_rtt_est.time = tp->tcp_mstamp; } +static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp) +{ + u32 delta, delta_us; + + delta = tcp_time_stamp_ts(tp) - tp->rx_opt.rcv_tsecr; + if (tp->tcp_usec_ts) + return delta; + + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + return delta_us; + } + return -1; +} + static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { @@ -691,15 +721,10 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, if (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { - u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us; - - if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { - if (!delta) - delta = 1; - delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - tcp_rcv_rtt_update(tp, delta_us, 0); - } + s32 delta = tcp_rtt_tsopt_us(tp); + + if (delta >= 0) + tcp_rcv_rtt_update(tp, delta, 0); } } @@ -765,6 +790,16 @@ new_measure: tp->rcvq_space.time = tp->tcp_mstamp; } +static void tcp_save_lrcv_flowlabel(struct sock *sk, const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct inet_connection_sock *icsk = inet_csk(sk); + + if (skb->protocol == htons(ETH_P_IPV6)) + icsk->icsk_ack.lrcv_flowlabel = ntohl(ip6_flowlabel(ipv6_hdr(skb))); +#endif +} + /* There is something which you must keep in mind when you analyze the * behavior of the tp->ato delayed ack timeout interval. When a * connection starts up, we want to ack as quickly as possible. The @@ -813,6 +848,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) } } icsk->icsk_ack.lrcvtime = now; + tcp_save_lrcv_flowlabel(sk, skb); tcp_ecn_check_ce(sk, skb); @@ -927,8 +963,8 @@ static void tcp_update_pacing_rate(struct sock *sk) * without any lock. We want to make sure compiler wont store * intermediate values in this location. */ - WRITE_ONCE(sk->sk_pacing_rate, min_t(u64, rate, - sk->sk_max_pacing_rate)); + WRITE_ONCE(sk->sk_pacing_rate, + min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate))); } /* Calculate rto without backoff. This is the second half of Van Jacobson's @@ -2198,16 +2234,17 @@ void tcp_enter_loss(struct sock *sk) * restore sanity to the SACK scoreboard. If the apparent reneging * persists until this RTO then we'll clear the SACK scoreboard. */ -static bool tcp_check_sack_reneging(struct sock *sk, int flag) +static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag) { - if (flag & FLAG_SACK_RENEGING && - flag & FLAG_SND_UNA_ADVANCED) { + if (*ack_flag & FLAG_SACK_RENEGING && + *ack_flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); + *ack_flag &= ~FLAG_SET_XMIT_TIMER; return true; } return false; @@ -2418,7 +2455,7 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp, const struct sk_buff *skb) { return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) && - tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb)); + tcp_tsopt_ecr_before(tp, tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); } /* Nothing was retransmitted or returned timestamp is less @@ -2832,7 +2869,7 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack) static void tcp_update_rto_time(struct tcp_sock *tp) { if (tp->rto_stamp) { - tp->total_rto_time += tcp_time_stamp(tp) - tp->rto_stamp; + tp->total_rto_time += tcp_time_stamp_ms(tp) - tp->rto_stamp; tp->rto_stamp = 0; } } @@ -2985,7 +3022,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tp->prior_ssthresh = 0; /* B. In all the states check for reneging SACKs. */ - if (tcp_check_sack_reneging(sk, flag)) + if (tcp_check_sack_reneging(sk, ack_flag)) return; /* C. Check consistency of the current state. */ @@ -3122,17 +3159,10 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) { - u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - - if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { - if (!delta) - delta = 1; - seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - ca_rtt_us = seq_rtt_us; - } - } + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && + tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) + seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp); + rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) return false; @@ -3542,6 +3572,21 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp, (ack_seq == tp->snd_wl1 && (nwin > tp->snd_wnd || !nwin)); } +static void tcp_snd_sne_update(struct tcp_sock *tp, u32 ack) +{ +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao; + + if (!static_branch_unlikely(&tcp_ao_needed.key)) + return; + + ao = rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held((struct sock *)tp)); + if (ao && ack < tp->snd_una) + ao->snd_sne++; +#endif +} + /* If we update tp->snd_una, also update tp->bytes_acked */ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) { @@ -3549,9 +3594,25 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) sock_owned_by_me((struct sock *)tp); tp->bytes_acked += delta; + tcp_snd_sne_update(tp, ack); tp->snd_una = ack; } +static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq) +{ +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao; + + if (!static_branch_unlikely(&tcp_ao_needed.key)) + return; + + ao = rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held((struct sock *)tp)); + if (ao && seq < tp->rcv_nxt) + ao->rcv_sne++; +#endif +} + /* If we update tp->rcv_nxt, also update tp->bytes_received */ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { @@ -3559,6 +3620,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) sock_owned_by_me((struct sock *)tp); tp->bytes_received += delta; + tcp_rcv_sne_update(tp, seq); WRITE_ONCE(tp->rcv_nxt, seq); } @@ -4225,39 +4287,58 @@ static bool tcp_fast_parse_options(const struct net *net, return true; } -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) /* - * Parse MD5 Signature option + * Parse Signature options */ -const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) +int tcp_do_parse_auth_options(const struct tcphdr *th, + const u8 **md5_hash, const u8 **ao_hash) { int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); + unsigned int minlen = TCPOLEN_MD5SIG; + + if (IS_ENABLED(CONFIG_TCP_AO)) + minlen = sizeof(struct tcp_ao_hdr) + 1; + + *md5_hash = NULL; + *ao_hash = NULL; /* If not enough data remaining, we can short cut */ - while (length >= TCPOLEN_MD5SIG) { + while (length >= minlen) { int opcode = *ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: - return NULL; + return 0; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2 || opsize > length) - return NULL; - if (opcode == TCPOPT_MD5SIG) - return opsize == TCPOLEN_MD5SIG ? ptr : NULL; + return -EINVAL; + if (opcode == TCPOPT_MD5SIG) { + if (opsize != TCPOLEN_MD5SIG) + return -EINVAL; + if (unlikely(*md5_hash || *ao_hash)) + return -EEXIST; + *md5_hash = ptr; + } else if (opcode == TCPOPT_AO) { + if (opsize <= sizeof(struct tcp_ao_hdr)) + return -EINVAL; + if (unlikely(*md5_hash || *ao_hash)) + return -EEXIST; + *ao_hash = ptr; + } } ptr += opsize - 2; length -= opsize; } - return NULL; + return 0; } -EXPORT_SYMBOL(tcp_parse_md5sig_option); +EXPORT_SYMBOL(tcp_do_parse_auth_options); #endif /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM @@ -4500,12 +4581,23 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) { /* When the ACK path fails or drops most ACKs, the sender would * timeout and spuriously retransmit the same segment repeatedly. - * The receiver remembers and reflects via DSACKs. Leverage the - * DSACK state and change the txhash to re-route speculatively. + * If it seems our ACKs are not reaching the other side, + * based on receiving a duplicate data segment with new flowlabel + * (suggesting the sender suffered an RTO), and we are not already + * repathing due to our own RTO, then rehash the socket to repath our + * packets. */ - if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq && +#if IS_ENABLED(CONFIG_IPV6) + if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss && + skb->protocol == htons(ETH_P_IPV6) && + (tcp_sk(sk)->inet_conn.icsk_ack.lrcv_flowlabel != + ntohl(ip6_flowlabel(ipv6_hdr(skb)))) && sk_rethink_txhash(sk)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH); + + /* Save last flowlabel after a spurious retrans. */ + tcp_save_lrcv_flowlabel(sk, skb); +#endif } static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) @@ -4822,6 +4914,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) u32 seq, end_seq; bool fragstolen; + tcp_save_lrcv_flowlabel(sk, skb); tcp_ecn_check_ce(sk, skb); if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { @@ -6109,6 +6202,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + tcp_ao_finish_connect(sk, skb); tcp_set_state(sk, TCP_ESTABLISHED); icsk->icsk_ack.lrcvtime = tcp_jiffies32; @@ -6257,7 +6351,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp(tp))) { + tcp_time_stamp_ts(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -6394,6 +6488,16 @@ consume: * simultaneous connect with crossed SYNs. * Particularly, it can be connect to self. */ +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao; + + ao = rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held(sk)); + if (ao) { + WRITE_ONCE(ao->risn, th->seq); + ao->rcv_sne = 0; + } +#endif tcp_set_state(sk, TCP_SYN_RECV); if (tp->rx_opt.saw_tstamp) { @@ -6606,6 +6710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) skb); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } + tcp_ao_established(sk); smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); @@ -6982,6 +7087,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct flowi fl; u8 syncookies; +#ifdef CONFIG_TCP_AO + const struct tcp_ao_hdr *aoh; +#endif + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); /* TW buckets are converted to open requests without @@ -7006,6 +7115,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, req->syncookie = want_cookie; tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; + tcp_rsk(req)->req_usec_ts = -1; #if IS_ENABLED(CONFIG_MPTCP) tcp_rsk(req)->is_mptcp = 0; #endif @@ -7067,6 +7177,17 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, inet_rsk(req)->ecn_ok = 0; } +#ifdef CONFIG_TCP_AO + if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) + goto drop_and_release; /* Invalid TCP options */ + if (aoh) { + tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr); + tcp_rsk(req)->ao_rcv_next = aoh->keyid; + tcp_rsk(req)->ao_keyid = aoh->rnext_keyid; + } else { + tcp_rsk(req)->maclen = 0; + } +#endif tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f13eb7e23d03..5f693bbd578d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -194,7 +194,7 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, sock_owned_by_me(sk); - return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, &addr_len); } /* This will initiate an outgoing connection. */ @@ -296,6 +296,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; goto failure; } + tp->tcp_usec_ts = dst_tcp_usec_ts(&rt->dst); /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); @@ -493,6 +494,8 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { + /* To increase the counter of ignored icmps for TCP-AO */ + tcp_ao_ignore_icmp(sk, AF_INET, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } @@ -506,6 +509,11 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) return 0; } + if (tcp_ao_ignore_icmp(sk, AF_INET, type, code)) { + sock_put(sk); + return 0; + } + bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. @@ -656,6 +664,52 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_v4_send_check); +#define REPLY_OPTIONS_LEN (MAX_TCP_OPTION_SPACE / sizeof(__be32)) + +static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb, + const struct tcp_ao_hdr *aoh, + struct ip_reply_arg *arg, struct tcphdr *reply, + __be32 reply_options[REPLY_OPTIONS_LEN]) +{ +#ifdef CONFIG_TCP_AO + int sdif = tcp_v4_sdif(skb); + int dif = inet_iif(skb); + int l3index = sdif ? dif : 0; + bool allocated_traffic_key; + struct tcp_ao_key *key; + char *traffic_key; + bool drop = true; + u32 ao_sne = 0; + u8 keyid; + + rcu_read_lock(); + if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, ntohl(reply->seq), + &key, &traffic_key, &allocated_traffic_key, + &keyid, &ao_sne)) + goto out; + + reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) | + (aoh->rnext_keyid << 8) | keyid); + arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4); + reply->doff = arg->iov[0].iov_len / 4; + + if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1], + key, traffic_key, + (union tcp_ao_addr *)&ip_hdr(skb)->saddr, + (union tcp_ao_addr *)&ip_hdr(skb)->daddr, + reply, ao_sne)) + goto out; + drop = false; +out: + rcu_read_unlock(); + if (allocated_traffic_key) + kfree(traffic_key); + return drop; +#else + return true; +#endif +} + /* * This routine will send an RST to the other tcp. * @@ -669,26 +723,21 @@ EXPORT_SYMBOL(tcp_v4_send_check); * Exception: precedence violation. We do not implement it in any case. */ -#ifdef CONFIG_TCP_MD5SIG -#define OPTION_BYTES TCPOLEN_MD5SIG_ALIGNED -#else -#define OPTION_BYTES sizeof(__be32) -#endif - static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; - __be32 opt[OPTION_BYTES / sizeof(__be32)]; + __be32 opt[REPLY_OPTIONS_LEN]; } rep; + const __u8 *md5_hash_location = NULL; + const struct tcp_ao_hdr *aoh; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key = NULL; - const __u8 *hash_location = NULL; unsigned char newhash[16]; - int genhash; struct sock *sk1 = NULL; + int genhash; #endif u64 transmit_time = 0; struct sock *ctl_sk; @@ -725,9 +774,16 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len = sizeof(rep.th); net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); + + /* Invalid TCP option size or twice included auth */ + if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh)) + return; + + if (aoh && tcp_v4_ao_sign_reset(sk, skb, aoh, &arg, &rep.th, rep.opt)) + return; + #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); - hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { const union tcp_md5_addr *addr; int l3index; @@ -738,7 +794,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); - } else if (hash_location) { + } else if (md5_hash_location) { const union tcp_md5_addr *addr; int sdif = tcp_v4_sdif(skb); int dif = inet_iif(skb); @@ -770,7 +826,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (genhash || memcmp(hash_location, newhash, 16) != 0) + if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) goto out; } @@ -828,7 +884,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_priority : sk->sk_priority; + inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); txhash = (sk->sk_state == TCP_TIME_WAIT) ? @@ -862,17 +918,13 @@ out: static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, - struct tcp_md5sig_key *key, + struct tcp_key *key, int reply_flags, u8 tos, u32 txhash) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; - __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2) -#ifdef CONFIG_TCP_MD5SIG - + (TCPOLEN_MD5SIG_ALIGNED >> 2) -#endif - ]; + __be32 opt[(MAX_TCP_OPTION_SPACE >> 2)]; } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; @@ -903,7 +955,7 @@ static void tcp_v4_send_ack(const struct sock *sk, rep.th.window = htons(win); #ifdef CONFIG_TCP_MD5SIG - if (key) { + if (tcp_key_is_md5(key)) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | @@ -914,10 +966,28 @@ static void tcp_v4_send_ack(const struct sock *sk, rep.th.doff = arg.iov[0].iov_len/4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], - key, ip_hdr(skb)->saddr, + key->md5_key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif +#ifdef CONFIG_TCP_AO + if (tcp_key_is_ao(key)) { + int offset = (tsecr) ? 3 : 0; + + rep.opt[offset++] = htonl((TCPOPT_AO << 24) | + (tcp_ao_len(key->ao_key) << 16) | + (key->ao_key->sndid << 8) | + key->rcv_next); + arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4); + rep.th.doff = arg.iov[0].iov_len / 4; + + tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], + key->ao_key, key->traffic_key, + (union tcp_ao_addr *)&ip_hdr(skb)->saddr, + (union tcp_ao_addr *)&ip_hdr(skb)->daddr, + &rep.th, key->sne); + } +#endif arg.flags = reply_flags; arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ @@ -950,18 +1020,53 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); + struct tcp_key key = {}; +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao_info; + + if (static_branch_unlikely(&tcp_ao_needed.key)) { + /* FIXME: the segment to-be-acked is not verified yet */ + ao_info = rcu_dereference(tcptw->ao_info); + if (ao_info) { + const struct tcp_ao_hdr *aoh; + + if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) { + inet_twsk_put(tw); + return; + } + + if (aoh) + key.ao_key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1); + } + } + if (key.ao_key) { + struct tcp_ao_key *rnext_key; + + key.traffic_key = snd_other_key(key.ao_key); + key.sne = READ_ONCE(ao_info->snd_sne); + rnext_key = READ_ONCE(ao_info->rnext_key); + key.rcv_next = rnext_key->rcvid; + key.type = TCP_KEY_AO; +#else + if (0) { +#endif +#ifdef CONFIG_TCP_MD5SIG + } else if (static_branch_unlikely(&tcp_md5_needed.key)) { + key.md5_key = tcp_twsk_md5_key(tcptw); + if (key.md5_key) + key.type = TCP_KEY_MD5; +#endif + } tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp_raw() + tcptw->tw_ts_offset, + tcp_tw_tsval(tcptw), tcptw->tw_ts_recent, - tw->tw_bound_dev_if, - tcp_twsk_md5_key(tcptw), + tw->tw_bound_dev_if, &key, tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, tw->tw_tos, - tw->tw_txhash - ); + tw->tw_txhash); inet_twsk_put(tw); } @@ -969,8 +1074,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - const union tcp_md5_addr *addr; - int l3index; + struct tcp_key key = {}; /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. @@ -978,23 +1082,77 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; +#ifdef CONFIG_TCP_AO + if (static_branch_unlikely(&tcp_ao_needed.key) && + tcp_rsk_used_ao(req)) { + const union tcp_md5_addr *addr; + const struct tcp_ao_hdr *aoh; + int l3index; + + /* Invalid TCP option size or twice included auth */ + if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) + return; + if (!aoh) + return; + + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; + key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, + aoh->rnext_keyid, -1); + if (unlikely(!key.ao_key)) { + /* Send ACK with any matching MKT for the peer */ + key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, -1, -1); + /* Matching key disappeared (user removed the key?) + * let the handshake timeout. + */ + if (!key.ao_key) { + net_info_ratelimited("TCP-AO key for (%pI4, %d)->(%pI4, %d) suddenly disappeared, won't ACK new connection\n", + addr, + ntohs(tcp_hdr(skb)->source), + &ip_hdr(skb)->daddr, + ntohs(tcp_hdr(skb)->dest)); + return; + } + } + key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC); + if (!key.traffic_key) + return; + + key.type = TCP_KEY_AO; + key.rcv_next = aoh->keyid; + tcp_v4_ao_calc_key_rsk(key.ao_key, key.traffic_key, req); +#else + if (0) { +#endif +#ifdef CONFIG_TCP_MD5SIG + } else if (static_branch_unlikely(&tcp_md5_needed.key)) { + const union tcp_md5_addr *addr; + int l3index; + + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; + key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); + if (key.md5_key) + key.type = TCP_KEY_MD5; +#endif + } + /* RFC 7323 2.3 * The window field (SEG.WND) of every outgoing segment, with the * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ - addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; - l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, + tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), - 0, - tcp_md5_do_lookup(sk, l3index, addr, AF_INET), + 0, &key, inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos, READ_ONCE(tcp_rsk(req)->txhash)); + if (tcp_key_is_ao(&key)) + kfree(key.traffic_key); } /* @@ -1024,10 +1182,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); - tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? - (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | - (inet_sk(sk)->tos & INET_ECN_MASK) : - inet_sk(sk)->tos; + tos = READ_ONCE(inet_sk(sk)->tos); + + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) + tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (tos & INET_ECN_MASK); if (!INET_ECN_is_capable(tos) && tcp_bpf_ca_needs_ecn((struct sock *)req)) @@ -1080,7 +1239,7 @@ static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key * /* Find the Key structure for an address. */ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, - int family) + int family, bool any_l3index) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1099,7 +1258,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, lockdep_sock_is_held(sk)) { if (key->family != family) continue; - if (key->flags & TCP_MD5SIG_FLAG_IFINDEX && key->l3index != l3index) + if (!any_l3index && key->flags & TCP_MD5SIG_FLAG_IFINDEX && + key->l3index != l3index) continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); @@ -1219,10 +1379,6 @@ static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; - if (!tcp_alloc_md5sig_pool()) { - sock_kfree_s(sk, key, sizeof(*key)); - return -ENOMEM; - } memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; @@ -1244,15 +1400,21 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { - if (tcp_md5sig_info_add(sk, GFP_KERNEL)) + if (tcp_md5_alloc_sigpool()) return -ENOMEM; + if (tcp_md5sig_info_add(sk, GFP_KERNEL)) { + tcp_md5_release_sigpool(); + return -ENOMEM; + } + if (!static_branch_inc(&tcp_md5_needed.key)) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); + tcp_md5_release_sigpool(); return -EUSERS; } } @@ -1269,8 +1431,12 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { - if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) + tcp_md5_add_sigpool(); + + if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) { + tcp_md5_release_sigpool(); return -ENOMEM; + } if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { struct tcp_md5sig_info *md5sig; @@ -1279,6 +1445,7 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); + tcp_md5_release_sigpool(); return -EUSERS; } } @@ -1304,7 +1471,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, } EXPORT_SYMBOL(tcp_md5_do_del); -static void tcp_clear_md5_list(struct sock *sk) +void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1328,6 +1495,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, const union tcp_md5_addr *addr; u8 prefixlen = 32; int l3index = 0; + bool l3flag; u8 flags; if (optlen < sizeof(cmd)) @@ -1340,6 +1508,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; + l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { @@ -1374,11 +1543,17 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; + /* Don't allow keys for peers that have a matching TCP-AO key. + * See the comment in tcp_ao_add_cmd() + */ + if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false)) + return -EKEYREJECTED; + return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } -static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, +static int tcp_v4_md5_hash_headers(struct tcp_sigpool *hp, __be32 daddr, __be32 saddr, const struct tcphdr *th, int nbytes) { @@ -1398,38 +1573,35 @@ static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, + ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp) + sizeof(*th)); - return crypto_ahash_update(hp->md5_req); + return crypto_ahash_update(hp->req); } static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { - struct tcp_md5sig_pool *hp; - struct ahash_request *req; + struct tcp_sigpool hp; - hp = tcp_get_md5sig_pool(); - if (!hp) - goto clear_hash_noput; - req = hp->md5_req; + if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) + goto clear_hash_nostart; - if (crypto_ahash_init(req)) + if (crypto_ahash_init(hp.req)) goto clear_hash; - if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2)) + if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; - if (tcp_md5_hash_key(hp, key)) + if (tcp_md5_hash_key(&hp, key)) goto clear_hash; - ahash_request_set_crypt(req, NULL, md5_hash, 0); - if (crypto_ahash_final(req)) + ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); + if (crypto_ahash_final(hp.req)) goto clear_hash; - tcp_put_md5sig_pool(); + tcp_sigpool_end(&hp); return 0; clear_hash: - tcp_put_md5sig_pool(); -clear_hash_noput: + tcp_sigpool_end(&hp); +clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } @@ -1438,9 +1610,8 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { - struct tcp_md5sig_pool *hp; - struct ahash_request *req; const struct tcphdr *th = tcp_hdr(skb); + struct tcp_sigpool hp; __be32 saddr, daddr; if (sk) { /* valid for establish/request sockets */ @@ -1452,30 +1623,28 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, daddr = iph->daddr; } - hp = tcp_get_md5sig_pool(); - if (!hp) - goto clear_hash_noput; - req = hp->md5_req; + if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) + goto clear_hash_nostart; - if (crypto_ahash_init(req)) + if (crypto_ahash_init(hp.req)) goto clear_hash; - if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len)) + if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) goto clear_hash; - if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) + if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) goto clear_hash; - if (tcp_md5_hash_key(hp, key)) + if (tcp_md5_hash_key(&hp, key)) goto clear_hash; - ahash_request_set_crypt(req, NULL, md5_hash, 0); - if (crypto_ahash_final(req)) + ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); + if (crypto_ahash_final(hp.req)) goto clear_hash; - tcp_put_md5sig_pool(); + tcp_sigpool_end(&hp); return 0; clear_hash: - tcp_put_md5sig_pool(); -clear_hash_noput: + tcp_sigpool_end(&hp); +clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } @@ -1524,6 +1693,11 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif +#ifdef CONFIG_TCP_AO + .ao_lookup = tcp_v4_ao_lookup_rsk, + .ao_calc_key = tcp_v4_ao_calc_key_rsk, + .ao_synack_hash = tcp_v4_ao_synack_hash, +#endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v4_init_sequence, #endif @@ -1625,12 +1799,16 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, /* Copy over the MD5 key from the original socket */ addr = (union tcp_md5_addr *)&newinet->inet_daddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); - if (key) { + if (key && !tcp_rsk_used_ao(req)) { if (tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key)) goto put_and_exit; sk_gso_disable(newsk); } #endif +#ifdef CONFIG_TCP_AO + if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET)) + goto put_and_exit; /* OOM, release back memory */ +#endif if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; @@ -1869,6 +2047,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif + !mptcp_skb_can_collapse(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; @@ -2040,9 +2219,9 @@ process: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) drop_reason = SKB_DROP_REASON_XFRM_POLICY; else - drop_reason = tcp_inbound_md5_hash(sk, skb, - &iph->saddr, &iph->daddr, - AF_INET, dif, sdif); + drop_reason = tcp_inbound_hash(sk, req, skb, + &iph->saddr, &iph->daddr, + AF_INET, dif, sdif); if (unlikely(drop_reason)) { sk_drops_add(sk, skb); reqsk_put(req); @@ -2119,8 +2298,8 @@ process: goto discard_and_relse; } - drop_reason = tcp_inbound_md5_hash(sk, skb, &iph->saddr, - &iph->daddr, AF_INET, dif, sdif); + drop_reason = tcp_inbound_hash(sk, NULL, skb, &iph->saddr, &iph->daddr, + AF_INET, dif, sdif); if (drop_reason) goto discard_and_relse; @@ -2267,11 +2446,19 @@ const struct inet_connection_sock_af_ops ipv4_specific = { }; EXPORT_SYMBOL(ipv4_specific); -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, +#endif +#ifdef CONFIG_TCP_AO + .ao_lookup = tcp_v4_ao_lookup, + .calc_ao_hash = tcp_v4_ao_hash_skb, + .ao_parse = tcp_v4_parse_ao, + .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, +#endif }; #endif @@ -2286,13 +2473,25 @@ static int tcp_v4_init_sock(struct sock *sk) icsk->icsk_af_ops = &ipv4_specific; -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif return 0; } +#ifdef CONFIG_TCP_MD5SIG +static void tcp_md5sig_info_free_rcu(struct rcu_head *head) +{ + struct tcp_md5sig_info *md5sig; + + md5sig = container_of(head, struct tcp_md5sig_info, rcu); + kfree(md5sig); + static_branch_slow_dec_deferred(&tcp_md5_needed); + tcp_md5_release_sigpool(); +} +#endif + void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2317,12 +2516,15 @@ void tcp_v4_destroy_sock(struct sock *sk) #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, 1); tcp_clear_md5_list(sk); - kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); - tp->md5sig_info = NULL; - static_branch_slow_dec_deferred(&tcp_md5_needed); + call_rcu(&md5sig->rcu, tcp_md5sig_info_free_rcu); + rcu_assign_pointer(tp->md5sig_info, NULL); } #endif + tcp_ao_destroy_sock(sk, false); /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) @@ -3287,6 +3489,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_syn_linear_timeouts = 4; net->ipv4.sysctl_tcp_shrink_window = 0; + net->ipv4.sysctl_tcp_pingpong_thresh = 1; + return 0; } diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ae36780977d2..52fe17167460 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -272,7 +272,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); - u32 now = tcp_time_stamp(tp); + u32 now = tcp_time_stamp_ts(tp); u32 delta; if (sample->rtt_us > 0) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c196759f1d3b..c2a925538542 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -470,11 +470,15 @@ void tcp_init_metrics(struct sock *sk) u32 val, crtt = 0; /* cached RTT scaled by 8 */ sk_dst_confirm(sk); + /* ssthresh may have been reduced unnecessarily during. + * 3WHS. Restore it back to its initial default. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; if (!dst) goto reset; rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); + tm = tcp_get_metrics(sk, dst, false); if (!tm) { rcu_read_unlock(); goto reset; @@ -489,11 +493,6 @@ void tcp_init_metrics(struct sock *sk) tp->snd_ssthresh = val; if (tp->snd_ssthresh > tp->snd_cwnd_clamp) tp->snd_ssthresh = tp->snd_cwnd_clamp; - } else { - /* ssthresh may have been reduced unnecessarily during. - * 3WHS. Restore it back to its initial default. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; } val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val && tp->reordering != val) @@ -899,22 +898,25 @@ static void tcp_metrics_flush_all(struct net *net) unsigned int row; for (row = 0; row < max_rows; row++, hb++) { - struct tcp_metrics_block __rcu **pp; + struct tcp_metrics_block __rcu **pp = &hb->chain; bool match; + if (!rcu_access_pointer(*pp)) + continue; + spin_lock_bh(&tcp_metrics_lock); - pp = &hb->chain; for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { match = net ? net_eq(tm_net(tm), net) : !refcount_read(&tm_net(tm)->ns.count); if (match) { - *pp = tm->tcpm_next; + rcu_assign_pointer(*pp, tm->tcpm_next); kfree_rcu(tm, rcu_head); } else { pp = &tm->tcpm_next; } } spin_unlock_bh(&tcp_metrics_lock); + cond_resched(); } } @@ -949,7 +951,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) if (addr_same(&tm->tcpm_daddr, &daddr) && (!src || addr_same(&tm->tcpm_saddr, &saddr)) && net_eq(tm_net(tm), net)) { - *pp = tm->tcpm_next; + rcu_assign_pointer(*pp, tm->tcpm_next); kfree_rcu(tm, rcu_head); found = true; } else { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index eee8ab1bfa0e..a9807eeb311c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -51,6 +51,18 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw, return TCP_TW_SUCCESS; } +static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq) +{ +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao; + + ao = rcu_dereference(tcptw->ao_info); + if (unlikely(ao && seq < tcptw->tw_rcv_nxt)) + WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1); +#endif + tcptw->tw_rcv_nxt = seq; +} + /* * * Main purpose of TIME-WAIT state is to close connection gracefully, * when one of ends sits in LAST-ACK or CLOSING retransmitting FIN @@ -136,7 +148,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, /* FIN arrived, enter true time-wait state. */ tw->tw_substate = TCP_TIME_WAIT; - tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq; + twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq); + if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent_stamp = ktime_get_seconds(); tcptw->tw_ts_recent = tmp_opt.rcv_tsval; @@ -261,10 +274,9 @@ static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); if (!tcptw->tw_md5_key) return; - if (!tcp_alloc_md5sig_pool()) - goto out_free; if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) goto out_free; + tcp_md5_add_sigpool(); } return; out_free: @@ -280,7 +292,7 @@ out_free: void tcp_time_wait(struct sock *sk, int state, int timeo) { const struct inet_connection_sock *icsk = inet_csk(sk); - const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_timewait_sock *tw; @@ -292,7 +304,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_mark = sk->sk_mark; - tw->tw_priority = sk->sk_priority; + tw->tw_priority = READ_ONCE(sk->sk_priority); tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -300,6 +312,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_ts_recent = tp->rx_opt.ts_recent; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; tcptw->tw_ts_offset = tp->tsoffset; + tw->tw_usec_ts = tp->tcp_usec_ts; tcptw->tw_last_oow_ack_time = 0; tcptw->tw_tx_delay = tp->tcp_tx_delay; tw->tw_txhash = sk->sk_txhash; @@ -316,6 +329,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) #endif tcp_time_wait_init(sk, tcptw); + tcp_ao_time_wait(tcptw, tp); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -348,18 +362,29 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } EXPORT_SYMBOL(tcp_time_wait); +#ifdef CONFIG_TCP_MD5SIG +static void tcp_md5_twsk_free_rcu(struct rcu_head *head) +{ + struct tcp_md5sig_key *key; + + key = container_of(head, struct tcp_md5sig_key, rcu); + kfree(key); + static_branch_slow_dec_deferred(&tcp_md5_needed); + tcp_md5_release_sigpool(); +} +#endif + void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed.key)) { struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) { - kfree_rcu(twsk->tw_md5_key, rcu); - static_branch_slow_dec_deferred(&tcp_md5_needed); - } + if (twsk->tw_md5_key) + call_rcu(&twsk->tw_md5_key->rcu, tcp_md5_twsk_free_rcu); } #endif + tcp_ao_destroy_sock(sk, true); } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); @@ -494,6 +519,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, const struct tcp_sock *oldtp; struct tcp_sock *newtp; u32 seq; +#ifdef CONFIG_TCP_AO + struct tcp_ao_key *ao_key; +#endif if (!newsk) return NULL; @@ -554,26 +582,41 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { + newtp->tcp_usec_ts = treq->req_usec_ts; newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { + newtp->tcp_usec_ts = 0; newtp->rx_opt.ts_recent_stamp = 0; newtp->tcp_header_len = sizeof(struct tcphdr); } if (req->num_timeout) { - newtp->undo_marker = treq->snt_isn; - newtp->retrans_stamp = div_u64(treq->snt_synack, - USEC_PER_SEC / TCP_TS_HZ); newtp->total_rto = req->num_timeout; - newtp->total_rto_recoveries = 1; - newtp->total_rto_time = tcp_time_stamp_raw() - + newtp->undo_marker = treq->snt_isn; + if (newtp->tcp_usec_ts) { + newtp->retrans_stamp = treq->snt_synack; + newtp->total_rto_time = (u32)(tcp_clock_us() - + newtp->retrans_stamp) / USEC_PER_MSEC; + } else { + newtp->retrans_stamp = div_u64(treq->snt_synack, + USEC_PER_SEC / TCP_TS_HZ); + newtp->total_rto_time = tcp_clock_ms() - newtp->retrans_stamp; + } + newtp->total_rto_recoveries = 1; } newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ #endif +#ifdef CONFIG_TCP_AO + newtp->ao_info = NULL; + ao_key = treq->af_specific->ao_lookup(sk, req, + tcp_rsk(req)->ao_keyid, -1); + if (ao_key) + newtp->tcp_header_len += tcp_ao_len(ao_key); + #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1fc1f879cfd6..f558c054cf6e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -170,15 +170,14 @@ static void tcp_event_data_sent(struct tcp_sock *tp, tp->lsndtime = now; /* If it is a reply for ato after last received - * packet, enter pingpong mode. + * packet, increase pingpong count. */ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - inet_csk_enter_pingpong_mode(sk); + inet_csk_inc_pingpong_cnt(sk); } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -423,6 +422,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) +#define OPTION_AO BIT(11) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -615,19 +615,52 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, - struct tcp_out_options *opts) + const struct tcp_request_sock *tcprsk, + struct tcp_out_options *opts, + struct tcp_key *key) { __be32 *ptr = (__be32 *)(th + 1); u16 options = opts->options; /* mungable copy */ - if (unlikely(OPTION_MD5 & options)) { + if (tcp_key_is_md5(key)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; - } + } else if (tcp_key_is_ao(key)) { +#ifdef CONFIG_TCP_AO + u8 maclen = tcp_ao_maclen(key->ao_key); + + if (tcprsk) { + u8 aolen = maclen + sizeof(struct tcp_ao_hdr); + *ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) | + (tcprsk->ao_keyid << 8) | + (tcprsk->ao_rcv_next)); + } else { + struct tcp_ao_key *rnext_key; + struct tcp_ao_info *ao_info; + + ao_info = rcu_dereference_check(tp->ao_info, + lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk)); + rnext_key = READ_ONCE(ao_info->rnext_key); + if (WARN_ON_ONCE(!rnext_key)) + goto out_ao; + *ptr++ = htonl((TCPOPT_AO << 24) | + (tcp_ao_len(key->ao_key) << 16) | + (key->ao_key->sndid << 8) | + (rnext_key->rcvid)); + } + opts->hash_location = (__u8 *)ptr; + ptr += maclen / sizeof(*ptr); + if (unlikely(maclen % sizeof(*ptr))) { + memset(ptr, TCPOPT_NOP, sizeof(*ptr)); + ptr++; + } +out_ao: +#endif + } if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | @@ -768,23 +801,25 @@ static void mptcp_set_option_cond(const struct request_sock *req, */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) + struct tcp_key *key) { struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; + bool timestamps; - *md5 = NULL; -#ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed.key) && - rcu_access_pointer(tp->md5sig_info)) { - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (*md5) { - opts->options |= OPTION_MD5; - remaining -= TCPOLEN_MD5SIG_ALIGNED; + /* Better than switch (key.type) as it has static branches */ + if (tcp_key_is_md5(key)) { + timestamps = false; + opts->options |= OPTION_MD5; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + } else { + timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps); + if (tcp_key_is_ao(key)) { + opts->options |= OPTION_AO; + remaining -= tcp_ao_len(key->ao_key); } } -#endif /* We always get an MSS option. The option bytes which will be seen in * normal data packets should timestamps be used, must be in the MSS @@ -798,9 +833,9 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { + if (likely(timestamps)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; + opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -851,7 +886,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, - const struct tcp_md5sig_key *md5, + const struct tcp_key *key, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) @@ -859,8 +894,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; -#ifdef CONFIG_TCP_MD5SIG - if (md5) { + if (tcp_key_is_md5(key)) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; @@ -871,8 +905,11 @@ static unsigned int tcp_synack_options(const struct sock *sk, */ if (synack_type != TCP_SYNACK_COOKIE) ireq->tstamp_ok &= !ireq->sack_ok; + } else if (tcp_key_is_ao(key)) { + opts->options |= OPTION_AO; + remaining -= tcp_ao_len(key->ao_key); + ireq->tstamp_ok &= !ireq->sack_ok; } -#endif /* We always send an MSS option. */ opts->mss = mss; @@ -885,7 +922,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; + opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) + + tcp_rsk(req)->ts_off; opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -922,7 +960,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) + struct tcp_key *key) { struct tcp_sock *tp = tcp_sk(sk); unsigned int size = 0; @@ -930,21 +968,19 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->options = 0; - *md5 = NULL; -#ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed.key) && - rcu_access_pointer(tp->md5sig_info)) { - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (*md5) { - opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; - } + /* Better than switch (key.type) as it has static branches */ + if (tcp_key_is_md5(key)) { + opts->options |= OPTION_MD5; + size += TCPOLEN_MD5SIG_ALIGNED; + } else if (tcp_key_is_ao(key)) { + opts->options |= OPTION_AO; + size += tcp_ao_len(key->ao_key); } -#endif if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; + opts->tsval = skb ? tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } @@ -1201,7 +1237,7 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); if (sk->sk_pacing_status != SK_PACING_NONE) { - unsigned long rate = sk->sk_pacing_rate; + unsigned long rate = READ_ONCE(sk->sk_pacing_rate); /* Original sch_fq does not pace first 10 MSS * Note that tp->data_segs_out overflows after 2^32 packets, @@ -1244,7 +1280,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, struct tcp_out_options opts; unsigned int tcp_options_size, tcp_header_size; struct sk_buff *oskb = NULL; - struct tcp_md5sig_key *md5; + struct tcp_key key; struct tcphdr *th; u64 prior_wstamp; int err; @@ -1276,11 +1312,11 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); + tcp_get_current_key(sk, &key); if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { - tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); + tcp_options_size = tcp_syn_options(sk, skb, &opts, &key); } else { - tcp_options_size = tcp_established_options(sk, skb, &opts, - &md5); + tcp_options_size = tcp_established_options(sk, skb, &opts, &key); /* Force a PSH flag on all (GSO) packets to expedite GRO flush * at receiver : This slightly improve GRO performance. * Note that we do not force the PSH flag for non GSO packets, @@ -1325,7 +1361,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); + skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; @@ -1361,16 +1397,25 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, th->window = htons(min(tp->rcv_wnd, 65535U)); } - tcp_options_write(th, tp, &opts); + tcp_options_write(th, tp, NULL, &opts, &key); + if (tcp_key_is_md5(&key)) { #ifdef CONFIG_TCP_MD5SIG - /* Calculate the MD5 hash, as we have all we need now */ - if (md5) { + /* Calculate the MD5 hash, as we have all we need now */ sk_gso_disable(sk); tp->af_specific->calc_md5_hash(opts.hash_location, - md5, sk, skb); - } + key.md5_key, sk, skb); #endif + } else if (tcp_key_is_ao(&key)) { + int err; + + err = tcp_ao_transmit_skb(sk, skb, key.ao_key, th, + opts.hash_location); + if (err) { + kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); + return -ENOMEM; + } + } /* BPF prog is the last one writing header option */ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); @@ -1380,7 +1425,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1697,14 +1742,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mss_now -= icsk->icsk_af_ops->net_frag_header_len; - } - /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1732,21 +1769,11 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - int mtu; - mtu = mss + + return mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; - - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mtu += icsk->icsk_af_ops->net_frag_header_len; - } - return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); @@ -1821,7 +1848,7 @@ unsigned int tcp_current_mss(struct sock *sk) u32 mss_now; unsigned int header_len; struct tcp_out_options opts; - struct tcp_md5sig_key *md5; + struct tcp_key key; mss_now = tp->mss_cache; @@ -1830,8 +1857,8 @@ unsigned int tcp_current_mss(struct sock *sk) if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } - - header_len = tcp_established_options(sk, NULL, &opts, &md5) + + tcp_get_current_key(sk, &key); + header_len = tcp_established_options(sk, NULL, &opts, &key) + sizeof(struct tcphdr); /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK @@ -1973,7 +2000,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, unsigned long bytes; u32 r; - bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift); + bytes = READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift); r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log); if (r < BITS_PER_TYPE(sk->sk_gso_max_size)) @@ -2450,6 +2477,7 @@ static int tcp_mtu_probe(struct sock *sk) /* build the payload, and be prepared to abort if this fails. */ if (tcp_clone_payload(sk, nskb, probe_size)) { + tcp_skb_tsorted_anchor_cleanup(nskb); consume_skb(nskb); return -1; } @@ -2535,6 +2563,18 @@ static bool tcp_pacing_check(struct sock *sk) return true; } +static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) +{ + const struct rb_node *node = sk->tcp_rtx_queue.rb_node; + + /* No skb in the rtx queue. */ + if (!node) + return true; + + /* Only one skb in rtx queue. */ + return !node->rb_left && !node->rb_right; +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2553,7 +2593,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); + READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); @@ -2561,7 +2601,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, if (static_branch_unlikely(&tcp_tx_delay_enabled) && tcp_sk(sk)->tcp_tx_delay) { - u64 extra_bytes = (u64)sk->sk_pacing_rate * tcp_sk(sk)->tcp_tx_delay; + u64 extra_bytes = (u64)READ_ONCE(sk->sk_pacing_rate) * + tcp_sk(sk)->tcp_tx_delay; /* TSQ is based on skb truesize sum (sk_wmem_alloc), so we * approximate our needs assuming an ~100% skb->truesize overhead. @@ -2572,12 +2613,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send skb if rtx queue is empty. + /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (tcp_rtx_queue_empty(sk)) + if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2781,7 +2822,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2805,11 +2846,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } @@ -3365,7 +3407,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); + tp->retrans_stamp = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; @@ -3613,8 +3655,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_key *md5 = NULL; struct tcp_out_options opts; + struct tcp_key key = {}; struct sk_buff *skb; int tcp_header_size; struct tcphdr *th; @@ -3651,6 +3693,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); + if (tcp_rsk(req)->req_usec_ts < 0) + tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) @@ -3664,16 +3708,48 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } -#ifdef CONFIG_TCP_MD5SIG +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_lock(); - md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif + if (tcp_rsk_used_ao(req)) { +#ifdef CONFIG_TCP_AO + struct tcp_ao_key *ao_key = NULL; + u8 maclen = tcp_rsk(req)->maclen; + u8 keyid = tcp_rsk(req)->ao_keyid; + + ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), + keyid, -1); + /* If there is no matching key - avoid sending anything, + * especially usigned segments. It could try harder and lookup + * for another peer-matching key, but the peer has requested + * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. + */ + if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) { + u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0; + + rcu_read_unlock(); + kfree_skb(skb); + net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n", + keyid, maclen, key_maclen); + return NULL; + } + key.ao_key = ao_key; + key.type = TCP_KEY_AO; +#endif + } else { +#ifdef CONFIG_TCP_MD5SIG + key.md5_key = tcp_rsk(req)->af_specific->req_md5_lookup(sk, + req_to_sk(req)); + if (key.md5_key) + key.type = TCP_KEY_MD5; +#endif + } skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; - tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc, synack_type, - syn_skb) + sizeof(*th); + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, + &key, foc, synack_type, syn_skb) + + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3693,15 +3769,24 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); - tcp_options_write(th, NULL, &opts); + tcp_options_write(th, NULL, tcp_rsk(req), &opts, &key); th->doff = (tcp_header_size >> 2); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); -#ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ - if (md5) + if (tcp_key_is_md5(&key)) { +#ifdef CONFIG_TCP_MD5SIG tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, - md5, req_to_sk(req), skb); + key.md5_key, req_to_sk(req), skb); +#endif + } else if (tcp_key_is_ao(&key)) { +#ifdef CONFIG_TCP_AO + tcp_rsk(req)->af_specific->ao_synack_hash(opts.hash_location, + key.ao_key, req, skb, + opts.hash_location - (u8 *)th, 0); +#endif + } +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_unlock(); #endif @@ -3749,6 +3834,8 @@ static void tcp_connect_init(struct sock *sk) if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; + tcp_ao_connect_init(sk); + /* If user gave his TCP_MAXSEG, record it to clamp */ if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; @@ -3931,6 +4018,53 @@ int tcp_connect(struct sock *sk) tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL); +#if defined(CONFIG_TCP_MD5SIG) && defined(CONFIG_TCP_AO) + /* Has to be checked late, after setting daddr/saddr/ops. + * Return error if the peer has both a md5 and a tcp-ao key + * configured as this is ambiguous. + */ + if (unlikely(rcu_dereference_protected(tp->md5sig_info, + lockdep_sock_is_held(sk)))) { + bool needs_ao = !!tp->af_specific->ao_lookup(sk, sk, -1, -1); + bool needs_md5 = !!tp->af_specific->md5_lookup(sk, sk); + struct tcp_ao_info *ao_info; + + ao_info = rcu_dereference_check(tp->ao_info, + lockdep_sock_is_held(sk)); + if (ao_info) { + /* This is an extra check: tcp_ao_required() in + * tcp_v{4,6}_parse_md5_keys() should prevent adding + * md5 keys on ao_required socket. + */ + needs_ao |= ao_info->ao_required; + WARN_ON_ONCE(ao_info->ao_required && needs_md5); + } + if (needs_md5 && needs_ao) + return -EKEYREJECTED; + + /* If we have a matching md5 key and no matching tcp-ao key + * then free up ao_info if allocated. + */ + if (needs_md5) { + tcp_ao_destroy_sock(sk, false); + } else if (needs_ao) { + tcp_clear_md5_list(sk); + kfree(rcu_replace_pointer(tp->md5sig_info, NULL, + lockdep_sock_is_held(sk))); + } + } +#endif +#ifdef CONFIG_TCP_AO + if (unlikely(rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held(sk)))) { + /* Don't allow connecting if ao is configured but no + * matching key is found. + */ + if (!tp->af_specific->ao_lookup(sk, sk, -1, -1)) + return -EKEYREJECTED; + } +#endif + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ @@ -3947,7 +4081,7 @@ int tcp_connect(struct sock *sk) tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tcp_mstamp_refresh(tp); - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); @@ -3977,6 +4111,20 @@ int tcp_connect(struct sock *sk) } EXPORT_SYMBOL(tcp_connect); +u32 tcp_delack_max(const struct sock *sk) +{ + const struct dst_entry *dst = __sk_dst_get(sk); + u32 delack_max = inet_csk(sk)->icsk_delack_max; + + if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) { + u32 rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); + u32 delack_from_rto_min = max_t(int, 1, rto_min - 1); + + delack_max = min_t(u32, delack_max, delack_from_rto_min); + } + return delack_max; +} + /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. @@ -4012,7 +4160,7 @@ void tcp_send_delayed_ack(struct sock *sk) ato = min(ato, max_ato); } - ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); + ato = min_t(u32, ato, tcp_delack_max(sk)); /* Stay within the limit we were given */ timeout = jiffies + ato; diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index acf4869c5d3b..bba10110fbbc 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk) tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; + timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c new file mode 100644 index 000000000000..65a8eaae2fec --- /dev/null +++ b/net/ipv4/tcp_sigpool.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <crypto/hash.h> +#include <linux/cpu.h> +#include <linux/kref.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/workqueue.h> +#include <net/tcp.h> + +static size_t __scratch_size; +static DEFINE_PER_CPU(void __rcu *, sigpool_scratch); + +struct sigpool_entry { + struct crypto_ahash *hash; + const char *alg; + struct kref kref; + uint16_t needs_key:1, + reserved:15; +}; + +#define CPOOL_SIZE (PAGE_SIZE / sizeof(struct sigpool_entry)) +static struct sigpool_entry cpool[CPOOL_SIZE]; +static unsigned int cpool_populated; +static DEFINE_MUTEX(cpool_mutex); + +/* Slow-path */ +struct scratches_to_free { + struct rcu_head rcu; + unsigned int cnt; + void *scratches[]; +}; + +static void free_old_scratches(struct rcu_head *head) +{ + struct scratches_to_free *stf; + + stf = container_of(head, struct scratches_to_free, rcu); + while (stf->cnt--) + kfree(stf->scratches[stf->cnt]); + kfree(stf); +} + +/** + * sigpool_reserve_scratch - re-allocates scratch buffer, slow-path + * @size: request size for the scratch/temp buffer + */ +static int sigpool_reserve_scratch(size_t size) +{ + struct scratches_to_free *stf; + size_t stf_sz = struct_size(stf, scratches, num_possible_cpus()); + int cpu, err = 0; + + lockdep_assert_held(&cpool_mutex); + if (__scratch_size >= size) + return 0; + + stf = kmalloc(stf_sz, GFP_KERNEL); + if (!stf) + return -ENOMEM; + stf->cnt = 0; + + size = max(size, __scratch_size); + cpus_read_lock(); + for_each_possible_cpu(cpu) { + void *scratch, *old_scratch; + + scratch = kmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); + if (!scratch) { + err = -ENOMEM; + break; + } + + old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch, cpu), + scratch, lockdep_is_held(&cpool_mutex)); + if (!cpu_online(cpu) || !old_scratch) { + kfree(old_scratch); + continue; + } + stf->scratches[stf->cnt++] = old_scratch; + } + cpus_read_unlock(); + if (!err) + __scratch_size = size; + + call_rcu(&stf->rcu, free_old_scratches); + return err; +} + +static void sigpool_scratch_free(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + kfree(rcu_replace_pointer(per_cpu(sigpool_scratch, cpu), + NULL, lockdep_is_held(&cpool_mutex))); + __scratch_size = 0; +} + +static int __cpool_try_clone(struct crypto_ahash *hash) +{ + struct crypto_ahash *tmp; + + tmp = crypto_clone_ahash(hash); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); + + crypto_free_ahash(tmp); + return 0; +} + +static int __cpool_alloc_ahash(struct sigpool_entry *e, const char *alg) +{ + struct crypto_ahash *cpu0_hash; + int ret; + + e->alg = kstrdup(alg, GFP_KERNEL); + if (!e->alg) + return -ENOMEM; + + cpu0_hash = crypto_alloc_ahash(alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(cpu0_hash)) { + ret = PTR_ERR(cpu0_hash); + goto out_free_alg; + } + + e->needs_key = crypto_ahash_get_flags(cpu0_hash) & CRYPTO_TFM_NEED_KEY; + + ret = __cpool_try_clone(cpu0_hash); + if (ret) + goto out_free_cpu0_hash; + e->hash = cpu0_hash; + kref_init(&e->kref); + return 0; + +out_free_cpu0_hash: + crypto_free_ahash(cpu0_hash); +out_free_alg: + kfree(e->alg); + e->alg = NULL; + return ret; +} + +/** + * tcp_sigpool_alloc_ahash - allocates pool for ahash requests + * @alg: name of async hash algorithm + * @scratch_size: reserve a tcp_sigpool::scratch buffer of this size + */ +int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size) +{ + int i, ret; + + /* slow-path */ + mutex_lock(&cpool_mutex); + ret = sigpool_reserve_scratch(scratch_size); + if (ret) + goto out; + for (i = 0; i < cpool_populated; i++) { + if (!cpool[i].alg) + continue; + if (strcmp(cpool[i].alg, alg)) + continue; + + if (kref_read(&cpool[i].kref) > 0) + kref_get(&cpool[i].kref); + else + kref_init(&cpool[i].kref); + ret = i; + goto out; + } + + for (i = 0; i < cpool_populated; i++) { + if (!cpool[i].alg) + break; + } + if (i >= CPOOL_SIZE) { + ret = -ENOSPC; + goto out; + } + + ret = __cpool_alloc_ahash(&cpool[i], alg); + if (!ret) { + ret = i; + if (i == cpool_populated) + cpool_populated++; + } +out: + mutex_unlock(&cpool_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(tcp_sigpool_alloc_ahash); + +static void __cpool_free_entry(struct sigpool_entry *e) +{ + crypto_free_ahash(e->hash); + kfree(e->alg); + memset(e, 0, sizeof(*e)); +} + +static void cpool_cleanup_work_cb(struct work_struct *work) +{ + bool free_scratch = true; + unsigned int i; + + mutex_lock(&cpool_mutex); + for (i = 0; i < cpool_populated; i++) { + if (kref_read(&cpool[i].kref) > 0) { + free_scratch = false; + continue; + } + if (!cpool[i].alg) + continue; + __cpool_free_entry(&cpool[i]); + } + if (free_scratch) + sigpool_scratch_free(); + mutex_unlock(&cpool_mutex); +} + +static DECLARE_WORK(cpool_cleanup_work, cpool_cleanup_work_cb); +static void cpool_schedule_cleanup(struct kref *kref) +{ + schedule_work(&cpool_cleanup_work); +} + +/** + * tcp_sigpool_release - decreases number of users for a pool. If it was + * the last user of the pool, releases any memory that was consumed. + * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() + */ +void tcp_sigpool_release(unsigned int id) +{ + if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg)) + return; + + /* slow-path */ + kref_put(&cpool[id].kref, cpool_schedule_cleanup); +} +EXPORT_SYMBOL_GPL(tcp_sigpool_release); + +/** + * tcp_sigpool_get - increases number of users (refcounter) for a pool + * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() + */ +void tcp_sigpool_get(unsigned int id) +{ + if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg)) + return; + kref_get(&cpool[id].kref); +} +EXPORT_SYMBOL_GPL(tcp_sigpool_get); + +int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c) __cond_acquires(RCU_BH) +{ + struct crypto_ahash *hash; + + rcu_read_lock_bh(); + if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg)) { + rcu_read_unlock_bh(); + return -EINVAL; + } + + hash = crypto_clone_ahash(cpool[id].hash); + if (IS_ERR(hash)) { + rcu_read_unlock_bh(); + return PTR_ERR(hash); + } + + c->req = ahash_request_alloc(hash, GFP_ATOMIC); + if (!c->req) { + crypto_free_ahash(hash); + rcu_read_unlock_bh(); + return -ENOMEM; + } + ahash_request_set_callback(c->req, 0, NULL, NULL); + + /* Pairs with tcp_sigpool_reserve_scratch(), scratch area is + * valid (allocated) until tcp_sigpool_end(). + */ + c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch)); + return 0; +} +EXPORT_SYMBOL_GPL(tcp_sigpool_start); + +void tcp_sigpool_end(struct tcp_sigpool *c) __releases(RCU_BH) +{ + struct crypto_ahash *hash = crypto_ahash_reqtfm(c->req); + + rcu_read_unlock_bh(); + ahash_request_free(c->req); + crypto_free_ahash(hash); +} +EXPORT_SYMBOL_GPL(tcp_sigpool_end); + +/** + * tcp_sigpool_algo - return algorithm of tcp_sigpool + * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() + * @buf: buffer to return name of algorithm + * @buf_len: size of @buf + */ +size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len) +{ + if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg)) + return -EINVAL; + + return strscpy(buf, cpool[id].alg, buf_len); +} +EXPORT_SYMBOL_GPL(tcp_sigpool_algo); + +/** + * tcp_sigpool_hash_skb_data - hash data in skb with initialized tcp_sigpool + * @hp: tcp_sigpool pointer + * @skb: buffer to add sign for + * @header_len: TCP header length for this segment + */ +int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, + const struct sk_buff *skb, + unsigned int header_len) +{ + const unsigned int head_data_len = skb_headlen(skb) > header_len ? + skb_headlen(skb) - header_len : 0; + const struct skb_shared_info *shi = skb_shinfo(skb); + const struct tcphdr *tp = tcp_hdr(skb); + struct ahash_request *req = hp->req; + struct sk_buff *frag_iter; + struct scatterlist sg; + unsigned int i; + + sg_init_table(&sg, 1); + + sg_set_buf(&sg, ((u8 *)tp) + header_len, head_data_len); + ahash_request_set_crypt(req, &sg, NULL, head_data_len); + if (crypto_ahash_update(req)) + return 1; + + for (i = 0; i < shi->nr_frags; ++i) { + const skb_frag_t *f = &shi->frags[i]; + unsigned int offset = skb_frag_off(f); + struct page *page; + + page = skb_frag_page(f) + (offset >> PAGE_SHIFT); + sg_set_page(&sg, page, skb_frag_size(f), offset_in_page(offset)); + ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f)); + if (crypto_ahash_update(req)) + return 1; + } + + skb_walk_frags(skb, frag_iter) + if (tcp_sigpool_hash_skb_data(hp, frag_iter, 0)) + return 1; + + return 0; +} +EXPORT_SYMBOL(tcp_sigpool_hash_skb_data); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Per-CPU pool of crypto requests"); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 3f61c6a70a1f..1f9f6c1c196b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -26,14 +26,18 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - u32 elapsed, start_ts, user_timeout; + const struct tcp_sock *tp = tcp_sk(sk); + u32 elapsed, user_timeout; s32 remaining; - start_ts = tcp_sk(sk)->retrans_stamp; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout) return icsk->icsk_rto; - elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; + + elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp; + if (tp->tcp_usec_ts) + elapsed /= USEC_PER_MSEC; + remaining = user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ @@ -212,12 +216,13 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - unsigned int start_ts; + struct tcp_sock *tp = tcp_sk(sk); + unsigned int start_ts, delta; if (!inet_csk(sk)->icsk_retransmits) return false; - start_ts = tcp_sk(sk)->retrans_stamp; + start_ts = tp->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; @@ -226,7 +231,12 @@ static bool retransmits_timed_out(struct sock *sk, timeout = tcp_model_timeout(sk, boundary, rto_base); } - return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; + if (tp->tcp_usec_ts) { + /* delta maybe off up to a jiffy due to timer granularity. */ + delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1); + return (s32)(delta - timeout * USEC_PER_MSEC) >= 0; + } + return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ @@ -322,7 +332,7 @@ void tcp_delack_timer_handler(struct sock *sk) if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ - icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); + icsk->icsk_ack.ato = min_t(u32, icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. @@ -422,7 +432,7 @@ static void tcp_update_rto_stats(struct sock *sk) if (!icsk->icsk_retransmits) { tp->total_rto_recoveries++; - tp->rto_stamp = tcp_time_stamp(tp); + tp->rto_stamp = tcp_time_stamp_ms(tp); } icsk->icsk_retransmits++; tp->total_rto++; @@ -462,26 +472,24 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, req->timeout << req->num_timeout, TCP_RTO_MAX); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, - const struct sk_buff *skb) + const struct sk_buff *skb, + u32 rtx_delta) { const struct tcp_sock *tp = tcp_sk(sk); const int timeout = TCP_RTO_MAX * 2; - u32 rcv_delta, rtx_delta; + u32 rcv_delta; rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; - rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); - - return rtx_delta > timeout; + return msecs_to_jiffies(rtx_delta) > timeout; } /** @@ -534,7 +542,11 @@ void tcp_retransmit_timer(struct sock *sk) struct inet_sock *inet = inet_sk(sk); u32 rtx_delta; - rtx_delta = tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb)); + rtx_delta = tcp_time_stamp_ts(tp) - (tp->retrans_stamp ?: + tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); + if (tp->tcp_usec_ts) + rtx_delta /= USEC_PER_MSEC; + if (sk->sk_family == AF_INET) { net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", &inet->inet_daddr, ntohs(inet->inet_dport), @@ -551,7 +563,7 @@ void tcp_retransmit_timer(struct sock *sk) rtx_delta); } #endif - if (tcp_rtx_probe0_timed_out(sk, skb)) { + if (tcp_rtx_probe0_timed_out(sk, skb, rtx_delta)) { tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7fdc250e0679..89e5a806b82e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -750,7 +750,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ ipv4_sk_update_pmtu(skb, sk, info); - if (inet->pmtudisc != IP_PMTUDISC_DONT) { + if (READ_ONCE(inet->pmtudisc) != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; @@ -1055,6 +1055,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; + int uc_index; if (len > 0xFFFF) return -EMSGSIZE; @@ -1143,7 +1144,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, - (struct sockaddr *)usin, &ipc.addr); + (struct sockaddr *)usin, + &msg->msg_namelen, + &ipc.addr); if (err) goto out_free; if (usin) { @@ -1173,25 +1176,26 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (scope == RT_SCOPE_LINK) connected = 0; + uc_index = READ_ONCE(inet->uc_index); if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) - ipc.oif = inet->mc_index; + ipc.oif = READ_ONCE(inet->mc_index); if (!saddr) - saddr = inet->mc_addr; + saddr = READ_ONCE(inet->mc_addr); connected = 0; } else if (!ipc.oif) { - ipc.oif = inet->uc_index; - } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { + ipc.oif = uc_index; + } else if (ipv4_is_lbcast(daddr) && uc_index) { /* oif is set, packet is to local broadcast and * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. */ - if (ipc.oif != inet->uc_index && + if (ipc.oif != uc_index && ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk), - inet->uc_index)) { - ipc.oif = inet->uc_index; + uc_index)) { + ipc.oif = uc_index; } } @@ -1865,7 +1869,8 @@ try_again: *addr_len = sizeof(*sin); BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, - (struct sockaddr *)sin); + (struct sockaddr *)sin, + addr_len); } if (udp_test_bit(GRO_ENABLED, sk)) @@ -1904,7 +1909,7 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } EXPORT_SYMBOL(udp_pre_connect); diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 1e7e4aecdc48..a87defb2b167 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -204,4 +204,53 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); +struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, + struct net_device *dev, + struct net *net, int oif, + __be32 *saddr, + const struct ip_tunnel_key *key, + __be16 sport, __be16 dport, u8 tos, + struct dst_cache *dst_cache) +{ + struct rtable *rt = NULL; + struct flowi4 fl4; + +#ifdef CONFIG_DST_CACHE + if (dst_cache) { + rt = dst_cache_get_ip4(dst_cache, saddr); + if (rt) + return rt; + } +#endif + + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = IPPROTO_UDP; + fl4.flowi4_oif = oif; + fl4.daddr = key->u.ipv4.dst; + fl4.saddr = key->u.ipv4.src; + fl4.fl4_dport = dport; + fl4.fl4_sport = sport; + fl4.flowi4_tos = RT_TOS(tos); + fl4.flowi4_flags = key->flow_flags; + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) { + netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (rt->dst.dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); + ip_rt_put(rt); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (dst_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); +#endif + *saddr = fl4.saddr; + return rt; +} +EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup); + MODULE_LICENSE("GPL"); diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index 029219749785..b6d2d16189c0 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -47,7 +47,7 @@ struct udp_tunnel_nic { unsigned int n_tables; unsigned long missed; - struct udp_tunnel_nic_table_entry **entries; + struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. @@ -725,16 +725,12 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, struct udp_tunnel_nic *utn; unsigned int i; - utn = kzalloc(sizeof(*utn), GFP_KERNEL); + utn = kzalloc(struct_size(utn, entries, n_tables), GFP_KERNEL); if (!utn) return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); - utn->entries = kmalloc_array(n_tables, sizeof(void *), GFP_KERNEL); - if (!utn->entries) - goto err_free_utn; - for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, sizeof(*utn->entries[i]), GFP_KERNEL); @@ -747,8 +743,6 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, err_free_prev_entries: while (i--) kfree(utn->entries[i]); - kfree(utn->entries); -err_free_utn: kfree(utn); return NULL; } @@ -759,7 +753,6 @@ static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); - kfree(utn->entries); kfree(utn); } |