diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/arp.c | 6 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 2 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 2 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 2 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 2 | ||||
-rw-r--r-- | net/ipv4/inet_diag.c | 4 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 68 | ||||
-rw-r--r-- | net/ipv4/metrics.c | 2 | ||||
-rw-r--r-- | net/ipv4/route.c | 10 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 128 | ||||
-rw-r--r-- | net/ipv4/tcp_bbr.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_bpf.c | 18 | ||||
-rw-r--r-- | net/ipv4/tcp_cong.c | 5 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 51 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 11 | ||||
-rw-r--r-- | net/ipv4/udp.c | 1 |
17 files changed, 224 insertions, 99 deletions
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 687971d83b4e..922dd73e5740 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); +static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, @@ -156,6 +157,7 @@ struct neigh_table arp_tbl = { .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, + .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, @@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb) arp_process(dev_net(skb->dev), NULL, skb); } +static int arp_is_multicast(const void *pkey) +{ + return ipv4_is_multicast(*((__be32 *)pkey)); +} /* * Receive an arp request from the device layer. diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 43e04382c593..75f67994fc85 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -880,7 +880,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) - nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); + nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 86a23e4a6a50..b87140a1fa28 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -696,7 +696,7 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: -#ifdef CONFIG_IPV6 +#if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 7612ff6111a7..b5400cec4f69 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -973,7 +973,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) char tmp[TCP_CA_NAME_MAX]; bool ecn_ca = false; - nla_strlcpy(tmp, nla, sizeof(tmp)); + nla_strscpy(tmp, nla, sizeof(tmp)); val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); } else { if (nla_len(nla) != sizeof(u32)) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4148f5f78f31..f60869acbef0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL); + inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 366a4507b5a3..93474b1bea4e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -479,8 +479,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - inet_rsk(reqsk)->ir_mark)) + inet_rsk(reqsk)->ir_mark)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8cbe74313f38..45fb450b4522 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -20,6 +20,9 @@ #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/inet6_hashtables.h> +#endif #include <net/secure_seq.h> #include <net/ip.h> #include <net/tcp.h> @@ -508,10 +511,52 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -/* insert a socket into ehash, and eventually remove another one - * (The another one can be a SYN_RECV or TIMEWAIT +/* Searches for an exsiting socket in the ehash bucket list. + * Returns true if found, false otherwise. */ -bool inet_ehash_insert(struct sock *sk, struct sock *osk) +static bool inet_ehash_lookup_by_sk(struct sock *sk, + struct hlist_nulls_head *list) +{ + const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num); + const int sdif = sk->sk_bound_dev_if; + const int dif = sk->sk_bound_dev_if; + const struct hlist_nulls_node *node; + struct net *net = sock_net(sk); + struct sock *esk; + + INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr); + + sk_nulls_for_each_rcu(esk, node, list) { + if (esk->sk_hash != sk->sk_hash) + continue; + if (sk->sk_family == AF_INET) { + if (unlikely(INET_MATCH(esk, net, acookie, + sk->sk_daddr, + sk->sk_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (sk->sk_family == AF_INET6) { + if (unlikely(INET6_MATCH(esk, net, + &sk->sk_v6_daddr, + &sk->sk_v6_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#endif + } + return false; +} + +/* Insert a socket into ehash, and eventually remove another one + * (The another one can be a SYN_RECV or TIMEWAIT) + * If an existing socket already exists, socket sk is not inserted, + * and sets found_dup_sk parameter to true. + */ +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; @@ -530,16 +575,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk) if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { + *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); + if (*found_dup_sk) + ret = false; } + if (ret) __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); + return ret; } -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk) +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - bool ok = inet_ehash_insert(sk, osk); + bool ok = inet_ehash_insert(sk, osk, found_dup_sk); if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -583,7 +635,7 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { - inet_ehash_nolisten(sk, osk); + inet_ehash_nolisten(sk, osk, NULL); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -679,7 +731,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL); + inet_ehash_nolisten(sk, NULL, NULL); spin_unlock_bh(&head->lock); return 0; } @@ -758,7 +810,7 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - inet_ehash_nolisten(sk, (struct sock *)tw); + inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 3205d5f7c8c9..25ea6ac44db9 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; - nla_strlcpy(tmp, nla, sizeof(tmp)); + nla_strscpy(tmp, nla, sizeof(tmp)); val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); if (val == TCP_CA_UNSPEC) { NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm"); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a3b60c41cbad..e26652ff7059 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2872,6 +2872,9 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; + if (rt->dst.lwtstate && + lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) + goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) @@ -3222,7 +3225,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3246,8 +3249,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, - dev, &res); + err = ip_route_input_rcu(skb, dst, src, + rtm->rtm_tos & IPTOS_RT_MASK, dev, + &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 17379f6dd955..75a28b8f4470 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -954,7 +954,7 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags) * importantly be able to generate EPOLLOUT for Edge Trigger epoll() * users. */ -static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) +void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) { if (skb && !skb->len) { tcp_unlink_write_queue(skb, sk); @@ -964,6 +964,68 @@ static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) } } +struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, + struct page *page, int offset, size_t *size) +{ + struct sk_buff *skb = tcp_write_queue_tail(sk); + struct tcp_sock *tp = tcp_sk(sk); + bool can_coalesce; + int copy, i; + + if (!skb || (copy = size_goal - skb->len) <= 0 || + !tcp_skb_can_collapse_to(skb)) { +new_segment: + if (!sk_stream_memory_free(sk)) + return NULL; + + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, + tcp_rtx_and_write_queues_empty(sk)); + if (!skb) + return NULL; + +#ifdef CONFIG_TLS_DEVICE + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif + skb_entail(sk, skb); + copy = size_goal; + } + + if (copy > *size) + copy = *size; + + i = skb_shinfo(skb)->nr_frags; + can_coalesce = skb_can_coalesce(skb, i, page, offset); + if (!can_coalesce && i >= sysctl_max_skb_frags) { + tcp_mark_push(tp, skb); + goto new_segment; + } + if (!sk_wmem_schedule(sk, copy)) + return NULL; + + if (can_coalesce) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + } else { + get_page(page); + skb_fill_page_desc(skb, i, page, offset, copy); + } + + if (!(flags & MSG_NO_SHARED_FRAGS)) + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + + skb->len += copy; + skb->data_len += copy; + skb->truesize += copy; + sk_wmem_queued_add(sk, copy); + sk_mem_charge(sk, copy); + skb->ip_summed = CHECKSUM_PARTIAL; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); + TCP_SKB_CB(skb)->end_seq += copy; + tcp_skb_pcount_set(skb, 0); + + *size = copy; + return skb; +} + ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -999,60 +1061,13 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, goto out_err; while (size > 0) { - struct sk_buff *skb = tcp_write_queue_tail(sk); - int copy, i; - bool can_coalesce; + struct sk_buff *skb; + size_t copy = size; - if (!skb || (copy = size_goal - skb->len) <= 0 || - !tcp_skb_can_collapse_to(skb)) { -new_segment: - if (!sk_stream_memory_free(sk)) - goto wait_for_space; - - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, - tcp_rtx_and_write_queues_empty(sk)); - if (!skb) - goto wait_for_space; - -#ifdef CONFIG_TLS_DEVICE - skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); -#endif - skb_entail(sk, skb); - copy = size_goal; - } - - if (copy > size) - copy = size; - - i = skb_shinfo(skb)->nr_frags; - can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= sysctl_max_skb_frags) { - tcp_mark_push(tp, skb); - goto new_segment; - } - if (!sk_wmem_schedule(sk, copy)) + skb = tcp_build_frag(sk, size_goal, flags, page, offset, ©); + if (!skb) goto wait_for_space; - if (can_coalesce) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); - } else { - get_page(page); - skb_fill_page_desc(skb, i, page, offset, copy); - } - - if (!(flags & MSG_NO_SHARED_FRAGS)) - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; - - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; - sk_wmem_queued_add(sk, copy); - sk_mem_charge(sk, copy); - skb->ip_summed = CHECKSUM_PARTIAL; - WRITE_ONCE(tp->write_seq, tp->write_seq + copy); - TCP_SKB_CB(skb)->end_seq += copy; - tcp_skb_pcount_set(skb, 0); - if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; @@ -2405,13 +2420,12 @@ bool tcp_check_oom(struct sock *sk, int shift) return too_many_orphans || out_of_socket_memory; } -void tcp_close(struct sock *sk, long timeout) +void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; - lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == TCP_LISTEN) { @@ -2575,6 +2589,12 @@ adjudge_to_death: out: bh_unlock_sock(sk); local_bh_enable(); +} + +void tcp_close(struct sock *sk, long timeout) +{ + lock_sock(sk); + __tcp_close(sk, timeout); release_sock(sk); sock_put(sk); } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6c4d79baff26..6ea3dc2e4219 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && - (rs->rtt_us <= bbr->min_rtt_us || + (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 37f4cb2bba5c..bc7d2a586e18 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -15,8 +15,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, { struct iov_iter *iter = &msg->msg_iter; int peek = flags & MSG_PEEK; - int i, ret, copied = 0; struct sk_msg *msg_rx; + int i, copied = 0; msg_rx = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); @@ -37,17 +37,16 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - ret = copy_page_to_iter(page, sge->offset, copy, iter); - if (ret != copy) { - msg_rx->sg.start = i; - return -EFAULT; - } + copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (!copy) + return copied ? copied : -EFAULT; copied += copy; if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - sk_mem_uncharge(sk, copy); + if (!msg_rx->skb) + sk_mem_uncharge(sk, copy); msg_rx->sg.size -= copy; if (!sge->length) { @@ -56,6 +55,11 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, put_page(page); } } else { + /* Lets not optimize peek case if copy_page_to_iter + * didn't copy the entire length lets just break. + */ + if (copy != sge->length) + return copied; sk_msg_iter_var_next(i); } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index db47ac24d057..563d016e7478 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -198,6 +198,11 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fb3a7750f623..9e8a6c1aa019 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6799,18 +6799,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); - af_ops->init_req(req, sk, skb); - - if (security_inet_conn_request(sk, skb, req)) + dst = af_ops->route_req(sk, skb, &fl, req); + if (!dst) goto drop_and_free; if (tmp_opt.tstamp_ok) tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); - dst = af_ops->route_req(sk, &fl, req); - if (!dst) - goto drop_and_free; - if (!want_cookie && !isn) { /* Kill the following clause, if you dislike this way. */ if (!net->ipv4.sysctl_tcp_syncookies && diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7352c097ae48..af2338294598 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -980,17 +980,22 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); - tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; - if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + inet_sk(sk)->tos; + + if (!INET_ECN_is_capable(tos) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tos |= INET_ECN_ECT_0; + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), - tos & ~INET_ECN_MASK); + tos); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1439,9 +1444,15 @@ static void tcp_v4_init_req(struct request_sock *req, } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, + struct sk_buff *skb, struct flowi *fl, - const struct request_sock *req) + struct request_sock *req) { + tcp_v4_init_req(req, sk, skb); + + if (security_inet_conn_request(sk, skb, req)) + return NULL; + return inet_csk_route_req(sk, &fl->u.ip4, req); } @@ -1461,7 +1472,6 @@ 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 - .init_req = tcp_v4_init_req, #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v4_init_sequence, #endif @@ -1498,6 +1508,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, bool *own_req) { struct inet_request_sock *ireq; + bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1575,12 +1586,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { - newinet->inet_opt = NULL; + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } else { + newinet->inet_opt = NULL; + } } return newsk; @@ -2740,6 +2761,20 @@ void tcp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ +/* @wake is one when sk_stream_write_space() calls us. + * This sends EPOLLOUT only if notsent_bytes is half the limit. + * This mimics the strategy used in sock_def_write_space(). + */ +bool tcp_stream_memory_free(const struct sock *sk, int wake) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u32 notsent_bytes = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); + + return (notsent_bytes << wake) < tcp_notsent_lowat(tp); +} +EXPORT_SYMBOL(tcp_stream_memory_free); + struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 99905bc01d40..41880d3521ed 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -445,11 +445,12 @@ struct tcp_out_options { struct mptcp_out_options mptcp; }; -static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) +static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp, + struct tcp_out_options *opts) { #if IS_ENABLED(CONFIG_MPTCP) if (unlikely(OPTION_MPTCP & opts->options)) - mptcp_write_options(ptr, &opts->mptcp); + mptcp_write_options(ptr, tp, &opts->mptcp); #endif } @@ -701,7 +702,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, smc_options_write(ptr, &options); - mptcp_options_write(ptr, opts); + mptcp_options_write(ptr, tp, opts); } static void smc_set_option(const struct tcp_sock *tp, @@ -1346,7 +1347,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, } } - tcp_options_write((__be32 *)(th + 1), tp, &opts); skb_shinfo(skb)->gso_type = sk->sk_gso_type; if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) { th->window = htons(tcp_select_window(sk)); @@ -1357,6 +1357,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, */ th->window = htons(min(tp->rcv_wnd, 65535U)); } + + tcp_options_write((__be32 *)(th + 1), tp, &opts); + #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c732f5acf720..a3f105227ccc 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -550,7 +550,6 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), &udp_table, NULL); } -EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb); /* Must be called under rcu_read_lock(). * Does increment socket refcount. |