From 861602b57730a5c6d3e0b1e4ca7133ca9a8b8538 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 19 Nov 2020 13:23:51 -0800 Subject: tcp: Allow full IP tos/IPv6 tclass to be reflected in L3 header An issue was recently found where DCTCP SYN/ACK packets did not have the ECT bit set in the L3 header. A bit of code review found that the recent change referenced below had gone though and added a mask that prevented the ECN bits from being populated in the L3 header. This patch addresses that by rolling back the mask so that it is only applied to the flags coming from the incoming TCP request instead of applying it to the socket tos/tclass field. Doing this the ECT bits were restored in the SYN/ACK packets in my testing. One thing that is not addressed by this patch set is the fact that tcp_reflect_tos appears to be incompatible with ECN based congestion avoidance algorithms. At a minimum the feature should likely be documented which it currently isn't. Fixes: ac8f1710c12b ("tcp: reflect tos value received in SYN to the socket") Signed-off-by: Alexander Duyck Acked-by: Wei Wang Signed-off-by: Jakub Kicinski --- net/ipv6/tcp_ipv6.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8db59f4e5f13..3d49e8d0afee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -530,12 +530,12 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); opt = ireq->ipv6_opt; tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : np->tclass; + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + np->tclass; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, - tclass & ~INET_ECN_MASK, - sk->sk_priority); + tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } -- cgit v1.2.3-70-g09d2 From 01770a166165738a6e05c3d911fb4609cc4eb416 Mon Sep 17 00:00:00 2001 From: Ricardo Dias Date: Fri, 20 Nov 2020 11:11:33 +0000 Subject: tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 5 +-- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/inet_hashtables.c | 68 ++++++++++++++++++++++++++++++++++++----- net/ipv4/tcp_ipv4.c | 15 +++++++-- net/ipv6/tcp_ipv6.c | 13 +++++++- 7 files changed, 91 insertions(+), 16 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 92560974ea67..ca6a3ea9057e 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -247,8 +247,9 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long high_limit); int inet_hashinfo2_init_mod(struct inet_hashinfo *h); -bool inet_ehash_insert(struct sock *sk, struct sock *osk); -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk); +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, + bool *found_dup_sk); int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index bb3d70664dde..b0b6e6a4784e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -427,7 +427,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, 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), NULL); if (*own_req) ireq->ireq_opt = NULL; else diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ef4ab28cfde0..78ee1b5acf1f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -533,7 +533,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); 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_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 #include #include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif #include #include #include @@ -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/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 25d35a56ceba..c95fcdfeed42 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1499,6 +1499,7 @@ 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; @@ -1576,12 +1577,22 @@ 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; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3d49e8d0afee..d2502911b7fa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1193,6 +1193,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; + bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG @@ -1368,7 +1369,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * tcp_done(newsk); goto out; } - *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 (*own_req) { tcp_move_syn(newtp, req); @@ -1383,6 +1385,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * skb_set_owner_r(newnp->pktoptions, newsk); } } + } else { + 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; + } } return newsk; -- cgit v1.2.3-70-g09d2 From 407c85c7ddd6b84d3cbdd2275616f70c27c17913 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Nov 2020 19:47:44 -0800 Subject: tcp: Set ECT0 bit in tos/tclass for synack when BPF needs ECN When a BPF program is used to select between a type of TCP congestion control algorithm that uses either ECN or not there is a case where the synack for the frame was coming up without the ECT0 bit set. A bit of research found that this was due to the final socket being configured to dctcp while the listener socket was staying in cubic. To reproduce it all that is needed is to monitor TCP traffic while running the sample bpf program "samples/bpf/tcp_cong_kern.c". What is observed, assuming tcp_dctcp module is loaded or compiled in and the traffic matches the rules in the sample file, is that for all frames with the exception of the synack the ECT0 bit is set. To address that it is necessary to make one additional call to tcp_bpf_ca_needs_ecn using the request socket and then use the output of that to set the ECT0 bit for the tos/tclass of the packet. Fixes: 91b5b21c7c16 ("bpf: Add support for changing congestion control") Signed-off-by: Alexander Duyck Link: https://lore.kernel.org/r/160593039663.2604.1374502006916871573.stgit@localhost.localdomain Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 12 ++++++++---- net/ipv6/tcp_ipv6.c | 9 +++++++-- 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c95fcdfeed42..8391aa29e7a4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -980,13 +980,17 @@ 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_ECN_MASK : - 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, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d2502911b7fa..992cbf3eb9e3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -527,11 +527,16 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); - rcu_read_lock(); - opt = ireq->ipv6_opt; tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : np->tclass; + + if (!INET_ECN_is_capable(tclass) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tclass |= INET_ECN_ECT_0; + + rcu_read_lock(); + opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, -- cgit v1.2.3-70-g09d2