diff options
author | Pablo Neira Ayuso <pablo@netfilter.org> | 2012-09-03 13:28:30 (GMT) |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2012-09-03 13:34:51 (GMT) |
commit | ace1fe1231bdfffd60b5e703aa5b7283fbf98dbd (patch) | |
tree | 06c7492a8f3cc65f916768616ca24c6bc7171761 /net/ipv4 | |
parent | ce9f3f31efb88841e4df98794b13dbac8c4901da (diff) | |
parent | a2dc375e12334b3d8f787a48b2fb6172ccfb80ae (diff) | |
download | linux-fsl-qoriq-ace1fe1231bdfffd60b5e703aa5b7283fbf98dbd.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
This merges (3f509c6 netfilter: nf_nat_sip: fix incorrect handling
of EBUSY for RTCP expectation) to Patrick McHardy's IPv6 NAT changes.
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 28 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 6 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 7 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 57 | ||||
-rw-r--r-- | net/ipv4/inet_diag.c | 21 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 14 | ||||
-rw-r--r-- | net/ipv4/ping.c | 22 | ||||
-rw-r--r-- | net/ipv4/proc.c | 4 | ||||
-rw-r--r-- | net/ipv4/raw.c | 4 | ||||
-rw-r--r-- | net/ipv4/route.c | 11 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 1 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 87 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 49 | ||||
-rw-r--r-- | net/ipv4/tcp_fastopen.c | 83 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 90 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 275 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 61 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 21 | ||||
-rw-r--r-- | net/ipv4/tcp_timer.c | 39 | ||||
-rw-r--r-- | net/ipv4/udp.c | 4 | ||||
-rw-r--r-- | net/ipv4/udp_diag.c | 5 |
21 files changed, 760 insertions, 129 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6681ccf..4f70ef0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -149,6 +149,11 @@ void inet_sock_destruct(struct sock *sk) pr_err("Attempt to release alive inet socket %p\n", sk); return; } + if (sk->sk_type == SOCK_STREAM) { + struct fastopen_queue *fastopenq = + inet_csk(sk)->icsk_accept_queue.fastopenq; + kfree(fastopenq); + } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(atomic_read(&sk->sk_wmem_alloc)); @@ -212,6 +217,26 @@ int inet_listen(struct socket *sock, int backlog) * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { + /* Check special setups for testing purpose to enable TFO w/o + * requiring TCP_FASTOPEN sockopt. + * Note that only TCP sockets (SOCK_STREAM) will reach here. + * Also fastopenq may already been allocated because this + * socket was in TCP_LISTEN state previously but was + * shutdown() (rather than close()). + */ + if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && + inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) { + if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) + err = fastopen_init_queue(sk, backlog); + else if ((sysctl_tcp_fastopen & + TFO_SERVER_WO_SOCKOPT2) != 0) + err = fastopen_init_queue(sk, + ((uint)sysctl_tcp_fastopen) >> 16); + else + err = 0; + if (err) + goto out; + } err = inet_csk_listen_start(sk, backlog); if (err) goto out; @@ -701,7 +726,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & - (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE))); + (TCPF_ESTABLISHED | TCPF_SYN_RECV | + TCPF_CLOSE_WAIT | TCPF_CLOSE))); sock_graft(sk2, newsock); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6a5e6e4..adf273f 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1147,12 +1147,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct in_device *in_dev; - - if (event == NETDEV_UNREGISTER_FINAL) - goto out; + struct in_device *in_dev = __in_dev_get_rtnl(dev); - in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fd7d9ae..acdee32 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1050,9 +1050,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo return NOTIFY_DONE; } - if (event == NETDEV_UNREGISTER_FINAL) - return NOTIFY_DONE; - in_dev = __in_dev_get_rtnl(dev); switch (event) { @@ -1064,14 +1061,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(net, -1); break; case NETDEV_DOWN: fib_disable_ip(dev, 0, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(net, 0); break; } return NOTIFY_DONE; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7f75f21..8464b79 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -283,7 +283,9 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) { struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct sock *newsk; + struct request_sock *req; int error; lock_sock(sk); @@ -296,7 +298,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) goto out_err; /* Find already established connection */ - if (reqsk_queue_empty(&icsk->icsk_accept_queue)) { + if (reqsk_queue_empty(queue)) { long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ @@ -308,14 +310,32 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) if (error) goto out_err; } - - newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk); - WARN_ON(newsk->sk_state == TCP_SYN_RECV); + req = reqsk_queue_remove(queue); + newsk = req->sk; + + sk_acceptq_removed(sk); + if (sk->sk_type == SOCK_STREAM && queue->fastopenq != NULL) { + spin_lock_bh(&queue->fastopenq->lock); + if (tcp_rsk(req)->listener) { + /* We are still waiting for the final ACK from 3WHS + * so can't free req now. Instead, we set req->sk to + * NULL to signify that the child socket is taken + * so reqsk_fastopen_remove() will free the req + * when 3WHS finishes (or is aborted). + */ + req->sk = NULL; + req = NULL; + } + spin_unlock_bh(&queue->fastopenq->lock); + } out: release_sock(sk); + if (req) + __reqsk_free(req); return newsk; out_err: newsk = NULL; + req = NULL; *err = error; goto out; } @@ -720,13 +740,14 @@ EXPORT_SYMBOL_GPL(inet_csk_listen_start); void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *acc_req; struct request_sock *req; inet_csk_delete_keepalive_timer(sk); /* make all the listen_opt local to us */ - acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue); + acc_req = reqsk_queue_yank_acceptq(queue); /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) @@ -736,7 +757,7 @@ void inet_csk_listen_stop(struct sock *sk) * To be honest, we are not able to make either * of the variants now. --ANK */ - reqsk_queue_destroy(&icsk->icsk_accept_queue); + reqsk_queue_destroy(queue); while ((req = acc_req) != NULL) { struct sock *child = req->sk; @@ -754,6 +775,19 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); + if (sk->sk_type == SOCK_STREAM && tcp_rsk(req)->listener) { + BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(sk != tcp_rsk(req)->listener); + + /* Paranoid, to prevent race condition if + * an inbound pkt destined for child is + * blocked by sock lock in tcp_v4_rcv(). + * Also to satisfy an assertion in + * tcp_v4_destroy_sock(). + */ + tcp_sk(child)->fastopen_rsk = NULL; + sock_put(sk); + } inet_csk_destroy_sock(child); bh_unlock_sock(child); @@ -763,6 +797,17 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); __reqsk_free(req); } + if (queue->fastopenq != NULL) { + /* Free all the reqs queued in rskq_rst_head. */ + spin_lock_bh(&queue->fastopenq->lock); + acc_req = queue->fastopenq->rskq_rst_head; + queue->fastopenq->rskq_rst_head = NULL; + spin_unlock_bh(&queue->fastopenq->lock); + while ((req = acc_req) != NULL) { + acc_req = req->dl_next; + __reqsk_free(req); + } + } WARN_ON(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 570e61f..8bc005b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -69,6 +69,7 @@ static inline void inet_diag_unlock_handler( int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, + struct user_namespace *user_ns, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { @@ -124,7 +125,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, } #endif - r->idiag_uid = sock_i_uid(sk); + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { @@ -199,11 +200,12 @@ EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_csk_diag_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_req_v2 *req, + struct user_namespace *user_ns, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { return inet_sk_diag_fill(sk, inet_csk(sk), - skb, req, pid, seq, nlmsg_flags, unlh); + skb, req, user_ns, pid, seq, nlmsg_flags, unlh); } static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, @@ -256,14 +258,16 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, - struct inet_diag_req_v2 *r, u32 pid, u32 seq, u16 nlmsg_flags, + struct inet_diag_req_v2 *r, + struct user_namespace *user_ns, + u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill((struct inet_timewait_sock *)sk, skb, r, pid, seq, nlmsg_flags, unlh); - return inet_csk_diag_fill(sk, skb, r, pid, seq, nlmsg_flags, unlh); + return inet_csk_diag_fill(sk, skb, r, user_ns, pid, seq, nlmsg_flags, unlh); } int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, @@ -311,6 +315,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s } err = sk_diag_fill(sk, rep, req, + sk_user_ns(NETLINK_CB(in_skb).ssk), NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { @@ -551,6 +556,7 @@ static int inet_csk_diag_dump(struct sock *sk, return 0; return inet_csk_diag_fill(sk, skb, r, + sk_user_ns(NETLINK_CB(cb->skb).ssk), NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } @@ -591,7 +597,9 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, } static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, - struct request_sock *req, u32 pid, u32 seq, + struct request_sock *req, + struct user_namespace *user_ns, + u32 pid, u32 seq, const struct nlmsghdr *unlh) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -625,7 +633,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_expires = jiffies_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; - r->idiag_uid = sock_i_uid(sk); + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = 0; #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { @@ -702,6 +710,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, } err = inet_diag_fill_req(skb, sk, req, + sk_user_ns(NETLINK_CB(cb->skb).ssk), NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, cb->nlh); if (err < 0) { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3a57570..8aa7a4c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -124,6 +124,8 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ipmr_new_table(struct net *net, u32 id); +static void ipmr_free_table(struct mr_table *mrt); + static int ip_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *cache, int local); @@ -131,6 +133,7 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); +static void mroute_clean_tables(struct mr_table *mrt); static void ipmr_expire_process(unsigned long arg); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES @@ -271,7 +274,7 @@ static void __net_exit ipmr_rules_exit(struct net *net) list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { list_del(&mrt->list); - kfree(mrt); + ipmr_free_table(mrt); } fib_rules_unregister(net->ipv4.mr_rules_ops); } @@ -299,7 +302,7 @@ static int __net_init ipmr_rules_init(struct net *net) static void __net_exit ipmr_rules_exit(struct net *net) { - kfree(net->ipv4.mrt); + ipmr_free_table(net->ipv4.mrt); } #endif @@ -336,6 +339,13 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) return mrt; } +static void ipmr_free_table(struct mr_table *mrt) +{ + del_timer_sync(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); +} + /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 6232d47..8f3d054 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -185,10 +185,10 @@ exit: return sk; } -static void inet_get_ping_group_range_net(struct net *net, gid_t *low, - gid_t *high) +static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, + kgid_t *high) { - gid_t *data = net->ipv4.sysctl_ping_group_range; + kgid_t *data = net->ipv4.sysctl_ping_group_range; unsigned int seq; do { @@ -203,19 +203,13 @@ static void inet_get_ping_group_range_net(struct net *net, gid_t *low, static int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); - gid_t group = current_egid(); - gid_t range[2]; + kgid_t group = current_egid(); struct group_info *group_info = get_current_groups(); int i, j, count = group_info->ngroups; kgid_t low, high; - inet_get_ping_group_range_net(net, range, range+1); - low = make_kgid(&init_user_ns, range[0]); - high = make_kgid(&init_user_ns, range[1]); - if (!gid_valid(low) || !gid_valid(high) || gid_lt(high, low)) - return -EACCES; - - if (range[0] <= group && group <= range[1]) + inet_get_ping_group_range_net(net, &low, &high); + if (gid_lte(low, group) && gid_lte(group, high)) return 0; for (i = 0; i < group_info->nblocks; i++) { @@ -845,7 +839,9 @@ static void ping_format_sock(struct sock *sp, struct seq_file *f, bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), - 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops), len); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 957acd1..8de53e1 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -263,6 +263,10 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), + SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE), + SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL), + SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), + SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff0f071..f242578 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -992,7 +992,9 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) i, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), - 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 50f6d3a..dc9549b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -934,12 +934,14 @@ static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; + rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, 0, mtu, jiffies + ip_rt_mtu_expires); } + rcu_read_unlock(); return mtu; } @@ -956,7 +958,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, dst->obsolete = DST_OBSOLETE_KILL; } else { rt->rt_pmtu = mtu; - dst_set_expires(&rt->dst, ip_rt_mtu_expires); + rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires); } } @@ -1132,10 +1134,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) const struct rtable *rt = (const struct rtable *) dst; unsigned int mtu = rt->rt_pmtu; - if (mtu && time_after_eq(jiffies, rt->dst.expires)) - mtu = 0; - - if (!mtu) + if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu && rt_is_output_route(rt)) @@ -1263,7 +1262,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; - if (dst->flags & DST_NOCACHE) { + if (!list_empty(&rt->rt_uncached)) { spin_lock_bh(&rt_uncached_lock); list_del(&rt->rt_uncached); spin_unlock_bh(&rt_uncached_lock); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 650e152..ba48e79 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -319,6 +319,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->listener = NULL; /* 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 1b5ce96..9205e49 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -76,9 +76,9 @@ static int ipv4_local_port_range(ctl_table *table, int write, } -static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high) +static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high) { - gid_t *data = table->data; + kgid_t *data = table->data; unsigned int seq; do { seq = read_seqbegin(&sysctl_local_ports.lock); @@ -89,12 +89,12 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, } /* Update system visible IP port range */ -static void set_ping_group_range(struct ctl_table *table, gid_t range[2]) +static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high) { - gid_t *data = table->data; + kgid_t *data = table->data; write_seqlock(&sysctl_local_ports.lock); - data[0] = range[0]; - data[1] = range[1]; + data[0] = low; + data[1] = high; write_sequnlock(&sysctl_local_ports.lock); } @@ -103,21 +103,33 @@ static int ipv4_ping_group_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct user_namespace *user_ns = current_user_ns(); int ret; - gid_t range[2]; + gid_t urange[2]; + kgid_t low, high; ctl_table tmp = { - .data = &range, - .maxlen = sizeof(range), + .data = &urange, + .maxlen = sizeof(urange), .mode = table->mode, .extra1 = &ip_ping_group_range_min, .extra2 = &ip_ping_group_range_max, }; - inet_get_ping_group_range_table(table, range, range + 1); + inet_get_ping_group_range_table(table, &low, &high); + urange[0] = from_kgid_munged(user_ns, low); + urange[1] = from_kgid_munged(user_ns, high); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); - if (write && ret == 0) - set_ping_group_range(table, range); + if (write && ret == 0) { + low = make_kgid(user_ns, urange[0]); + high = make_kgid(user_ns, urange[1]); + if (!gid_valid(low) || !gid_valid(high) || + (urange[1] < urange[0]) || gid_lt(high, low)) { + low = make_kgid(&init_user_ns, 1); + high = make_kgid(&init_user_ns, 0); + } + set_ping_group_range(table, low, high); + } return ret; } @@ -220,6 +232,45 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, return 0; } +int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; + struct tcp_fastopen_context *ctxt; + int ret; + u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + + tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); + if (!tbl.data) + return -ENOMEM; + + rcu_read_lock(); + ctxt = rcu_dereference(tcp_fastopen_ctx); + if (ctxt) + memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + rcu_read_unlock(); + + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", + user_key[0], user_key[1], user_key[2], user_key[3]); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + + if (write && ret == 0) { + if (sscanf(tbl.data, "%x-%x-%x-%x", user_key, user_key + 1, + user_key + 2, user_key + 3) != 4) { + ret = -EINVAL; + goto bad_key; + } + tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); + } + +bad_key: + pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", + user_key[0], user_key[1], user_key[2], user_key[3], + (char *)tbl.data, ret); + kfree(tbl.data); + return ret; +} + static struct ctl_table ipv4_table[] = { { .procname = "tcp_timestamps", @@ -374,6 +425,12 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "tcp_fastopen_key", + .mode = 0600, + .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), + .proc_handler = proc_tcp_fastopen_key, + }, + { .procname = "tcp_tw_recycle", .data = &tcp_death_row.sysctl_tw_recycle, .maxlen = sizeof(int), @@ -786,7 +843,7 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "ping_group_range", .data = &init_net.ipv4.sysctl_ping_group_range, - .maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range), + .maxlen = sizeof(gid_t)*2, .mode = 0644, .proc_handler = ipv4_ping_group_range, }, @@ -830,8 +887,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) * Sane defaults - nobody may create ping sockets. * Boot scripts should set this to distro-specific group. */ - net->ipv4.sysctl_ping_group_range[0] = 1; - net->ipv4.sysctl_ping_group_range[1] = 0; + net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1); + net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0); tcp_init_mem(net); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2109ff4..df83d74 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -486,8 +486,9 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLIN | POLLRDNORM | POLLRDHUP; - /* Connected? */ - if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) { + /* Connected or passive Fast Open socket? */ + if (sk->sk_state != TCP_SYN_SENT && + (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -840,10 +841,15 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* Wait for a connection to finish. */ - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) + /* Wait for a connection to finish. One exception is TCP Fast Open + * (passive side) where data is allowed to be sent before a connection + * is fully established. + */ + if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && + !tcp_passive_fastopen(sk)) { if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_err; + } clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -1042,10 +1048,15 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* Wait for a connection to finish. */ - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) + /* Wait for a connection to finish. One exception is TCP Fast Open + * (passive side) where data is allowed to be sent before a connection + * is fully established. + */ + if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && + !tcp_passive_fastopen(sk)) { if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto do_error; + } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { @@ -2144,6 +2155,10 @@ void tcp_close(struct sock *sk, long timeout) * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK + * XXX (TFO) - To start off we don't support SYN+ACK+FIN + * in a single packet! (May consider it later but will + * probably need API support or TCP_CORK SYN-ACK until + * data is written and socket is closed.) */ tcp_send_fin(sk); } @@ -2215,8 +2230,16 @@ adjudge_to_death: } } - if (sk->sk_state == TCP_CLOSE) + if (sk->sk_state == TCP_CLOSE) { + struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + /* We could get here with a non-NULL req if the socket is + * aborted (e.g., closed with unread data) before 3WHS + * finishes. + */ + if (req != NULL) + reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); + } /* Otherwise, socket is reprieved until protocol close. */ out: @@ -2688,6 +2711,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else icsk->icsk_user_timeout = msecs_to_jiffies(val); break; + + case TCP_FASTOPEN: + if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | + TCPF_LISTEN))) + err = fastopen_init_queue(sk, val); + else + err = -EINVAL; + break; default: err = -ENOPROTOOPT; break; @@ -3501,11 +3532,15 @@ EXPORT_SYMBOL(tcp_cookie_generator); void tcp_done(struct sock *sk) { + struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); + if (req != NULL) + reqsk_fastopen_remove(sk, req, false); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index a7f729c..8f7ef0a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -1,10 +1,91 @@ +#include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/list.h> +#include <linux/tcp.h> +#include <linux/rcupdate.h> +#include <linux/rculist.h> +#include <net/inetpeer.h> +#include <net/tcp.h> -int sysctl_tcp_fastopen; +int sysctl_tcp_fastopen __read_mostly; + +struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; + +static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); + +static void tcp_fastopen_ctx_free(struct rcu_head *head) +{ + struct tcp_fastopen_context *ctx = + container_of(head, struct tcp_fastopen_context, rcu); + crypto_free_cipher(ctx->tfm); + kfree(ctx); +} + +int tcp_fastopen_reset_cipher(void *key, unsigned int len) +{ + int err; + struct tcp_fastopen_context *ctx, *octx; + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + ctx->tfm = crypto_alloc_cipher("aes", 0, 0); + + if (IS_ERR(ctx->tfm)) { + err = PTR_ERR(ctx->tfm); +error: kfree(ctx); + pr_err("TCP: TFO aes cipher alloc error: %d\n", err); + return err; + } + err = crypto_cipher_setkey(ctx->tfm, key, len); + if (err) { + pr_err("TCP: TFO cipher key error: %d\n", err); + crypto_free_cipher(ctx->tfm); + goto error; + } + memcpy(ctx->key, key, len); + + spin_lock(&tcp_fastopen_ctx_lock); + + octx = rcu_dereference_protected(tcp_fastopen_ctx, + lockdep_is_held(&tcp_fastopen_ctx_lock)); + rcu_assign_pointer(tcp_fastopen_ctx, ctx); + spin_unlock(&tcp_fastopen_ctx_lock); + + if (octx) + call_rcu(&octx->rcu, tcp_fastopen_ctx_free); + return err; +} + +/* Computes the fastopen cookie for the peer. + * The peer address is a 128 bits long (pad with zeros for IPv4). + * + * The caller must check foc->len to determine if a valid cookie + * has been generated successfully. +*/ +void tcp_fastopen_cookie_gen(__be32 addr, struct tcp_fastopen_cookie *foc) +{ + __be32 peer_addr[4] = { addr, 0, 0, 0 }; + struct tcp_fastopen_context *ctx; + + rcu_read_lock(); + ctx = rcu_dereference(tcp_fastopen_ctx); + if (ctx) { + crypto_cipher_encrypt_one(ctx->tfm, + foc->val, + (__u8 *)peer_addr); + foc->len = TCP_FASTOPEN_COOKIE_SIZE; + } + rcu_read_unlock(); +} static int __init tcp_fastopen_init(void) { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + + get_random_bytes(key, sizeof(key)); + tcp_fastopen_reset_cipher(key, sizeof(key)); return 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bcfccc5..8c304a4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -378,7 +378,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk) /* 4. Try to fixup all. It is made immediately after connection enters * established state. */ -static void tcp_init_buffer_space(struct sock *sk) +void tcp_init_buffer_space(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int maxwin; @@ -2930,13 +2930,14 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int newly_acked_sacked, bool is_dupack, + int prior_sacked, bool is_dupack, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); + int newly_acked_sacked = 0; int fast_rexmit = 0; if (WARN_ON(!tp->packets_out && tp->sacked_out)) @@ -2996,6 +2997,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_add_reno_sack(sk); } else do_lost = tcp_try_undo_partial(sk, pkts_acked); + newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; break; case TCP_CA_Loss: if (flag & FLAG_DATA_ACKED) @@ -3017,6 +3019,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (is_dupack) tcp_add_reno_sack(sk); } + newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); @@ -3124,6 +3127,12 @@ void tcp_rearm_rto(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + /* If the retrans timer is currently being used by Fast Open + * for SYN-ACK retrans purpose, stay put. + */ + if (tp->fastopen_rsk) + return; + if (!tp->packets_out) { inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); } else { @@ -3594,7 +3603,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_packets; int prior_sacked = tp->sacked_out; int pkts_acked = 0; - int newly_acked_sacked = 0; bool frto_cwnd = false; /* If the ack is older than previous acks @@ -3670,8 +3678,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); pkts_acked = prior_packets - tp->packets_out; - newly_acked_sacked = (prior_packets - prior_sacked) - - (tp->packets_out - tp->sacked_out); if (tp->frto_counter) frto_cwnd = tcp_process_frto(sk, flag); @@ -3685,7 +3691,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); - tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) @@ -3702,7 +3708,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) - tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than @@ -3722,8 +3728,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); - newly_acked_sacked = tp->sacked_out - prior_sacked; - tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); } @@ -4039,7 +4044,7 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) } /* When we get a reset we do this. */ -static void tcp_reset(struct sock *sk) +void tcp_reset(struct sock *sk) { /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { @@ -5896,7 +5901,9 @@ discard: tcp_send_synack(sk); #if 0 /* Note, we could accept data and URG from this segment. - * There are no obstacles to make this. + * There are no obstacles to make this (except that we must + * either change tcp_recvmsg() to prevent it from returning data + * before 3WHS completes per RFC793, or employ TCP Fast Open). * * However, if we ignore data in ACKless segments sometimes, * we have no reasons to accept it sometimes. @@ -5936,6 +5943,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; int queued = 0; tp->rx_opt.saw_tstamp = 0; @@ -5991,7 +5999,14 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 0; } - if (!tcp_validate_incoming(sk, skb, th, 0)) + req = tp->fastopen_rsk; + if (req != NULL) { + BUG_ON(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); + + if (tcp_check_req(sk, skb, req, NULL, true) == NULL) + goto discard; + } else if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; /* step 5: check the ACK field */ @@ -6001,7 +6016,22 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, switch (sk->sk_state) { case TCP_SYN_RECV: if (acceptable) { - tp->copied_seq = tp->rcv_nxt; + /* Once we leave TCP_SYN_RECV, we no longer + * need req so release it. + */ + if (req) { + reqsk_fastopen_remove(sk, req, false); + } else { + /* Make sure socket is routed, for + * correct metrics. + */ + icsk->icsk_af_ops->rebuild_header(sk); + tcp_init_congestion_control(sk); + + tcp_mtup_init(sk); + tcp_init_buffer_space(sk); + tp->copied_seq = tp->rcv_nxt; + } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); @@ -6023,23 +6053,27 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - /* Make sure socket is routed, for - * correct metrics. - */ - icsk->icsk_af_ops->rebuild_header(sk); - - tcp_init_metrics(sk); - - tcp_init_congestion_control(sk); + if (req) { + /* Re-arm the timer because data may + * have been sent out. This is similar + * to the regular data transmission case + * when new data has just been ack'ed. + * + * (TFO) - we could try to be more + * aggressive and retranmitting any data + * sooner based on when they were sent + * out. + */ + tcp_rearm_rto(sk); + } else + tcp_init_metrics(sk); /* Prevent spurious tcp_cwnd_restart() on * first data packet. */ tp->lsndtime = tcp_time_stamp; - tcp_mtup_init(sk); tcp_initialize_rcv_mss(sk); - tcp_init_buffer_space(sk); tcp_fast_path_on(tp); } else { return 1; @@ -6047,6 +6081,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, break; case TCP_FIN_WAIT1: + /* If we enter the TCP_FIN_WAIT1 state and we are a + * Fast Open socket and this is the first acceptable + * ACK we have received, this would have acknowledged + * our SYNACK so stop the SYNACK timer. + */ + if (acceptable && req != NULL) { + /* We no longer need the request sock. */ + reqsk_fastopen_remove(sk, req, false); + tcp_rearm_rto(sk); + } if (tp->snd_una == tp->write_seq) { struct dst_entry *dst; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e15c5b..e64abed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -352,6 +352,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) const int code = icmp_hdr(icmp_skb)->code; struct sock *sk; struct sk_buff *skb; + struct request_sock *req; __u32 seq; __u32 remaining; int err; @@ -394,9 +395,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); + req = tp->fastopen_rsk; seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt)) { + !between(seq, tp->snd_una, tp->snd_nxt) && + (req == NULL || seq != tcp_rsk(req)->snt_isn)) { + /* For a Fast Open socket, allow seq to be snt_isn. */ NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -435,6 +439,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) !icsk->icsk_backoff) break; + /* XXX (TFO) - revisit the following logic for TFO */ + if (sock_owned_by_user(sk)) break; @@ -466,6 +472,14 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; } + /* XXX (TFO) - if it's a TFO socket and has been accepted, rather + * than following the TCP_SYN_RECV case and closing the socket, + * we ignore the ICMP error and keep trying like a fully established + * socket. Is this the right thing to do? + */ + if (req && req->sk == NULL) + goto out; + switch (sk->sk_state) { struct request_sock *req, **prev; case TCP_LISTEN: @@ -498,7 +512,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) case TCP_SYN_SENT: case TCP_SYN_RECV: /* Cannot happen. - It can f.e. if SYNs crossed. + It can f.e. if SYNs crossed, + or Fast Open. */ if (!sock_owned_by_user(sk)) { sk->sk_err = err; @@ -809,8 +824,12 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, - tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV + * sk->sk_state == TCP_SYN_RECV -> for Fast Open. + */ + tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? + tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + tcp_rsk(req)->rcv_nxt, req->rcv_wnd, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, @@ -839,7 +858,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, rvp); + skb = tcp_make_synack(sk, dst, req, rvp, NULL); if (skb) { __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); @@ -1272,6 +1291,178 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { }; #endif +static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct tcp_fastopen_cookie *valid_foc) +{ + bool skip_cookie = false; + struct fastopen_queue *fastopenq; + + if (likely(!fastopen_cookie_present(foc))) { + /* See include/net/tcp.h for the meaning of these knobs */ + if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) || + ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) && + (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1))) + skip_cookie = true; /* no cookie to validate */ + else + return false; + } + fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; + /* A FO option is present; bump the counter. */ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); + + /* Make sure the listener has enabled fastopen, and we don't + * exceed the max # of pending TFO requests allowed before trying + * to validating the cookie in order to avoid burning CPU cycles + * unnecessarily. + * + * XXX (TFO) - The implication of checking the max_qlen before + * processing a cookie request is that clients can't differentiate + * between qlen overflow causing Fast Open to be disabled + * temporarily vs a server not supporting Fast Open at all. + */ + if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 || + fastopenq == NULL || fastopenq->max_qlen == 0) + return false; + + if (fastopenq->qlen >= fastopenq->max_qlen) { + struct request_sock *req1; + spin_lock(&fastopenq->lock); + req1 = fastopenq->rskq_rst_head; + if ((req1 == NULL) || time_after(req1->expires, jiffies)) { + spin_unlock(&fastopenq->lock); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); + /* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/ + foc->len = -1; + return false; + } + fastopenq->rskq_rst_head = req1->dl_next; + fastopenq->qlen--; + spin_unlock(&fastopenq->lock); + reqsk_free(req1); + } + if (skip_cookie) { + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + return true; + } + if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) { + if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) { + tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc); + if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) || + memcmp(&foc->val[0], &valid_foc->val[0], + TCP_FASTOPEN_COOKIE_SIZE) != 0) + return false; + valid_foc->len = -1; + } + /* Acknowledge the data received from the peer. */ + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + return true; + } else if (foc->len == 0) { /* Client requesting a cookie */ + tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENCOOKIEREQD); + } else { + /* Client sent a cookie with wrong size. Treat it + * the same as invalid and return a valid one. + */ + tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc); + } + return false; +} + +static int tcp_v4_conn_req_fastopen(struct sock *sk, + struct sk_buff *skb, + struct sk_buff *skb_synack, + struct request_sock *req, + struct request_values *rvp) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + const struct inet_request_sock *ireq = inet_rsk(req); + struct sock *child; + + req->retrans = 0; + req->sk = NULL; + + child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); + if (child == NULL) { + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + kfree_skb(skb_synack); + return -1; + } + ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr, + ireq->rmt_addr, ireq->opt); + /* XXX (TFO) - is it ok to ignore error and continue? */ + + spin_lock(&queue->fastopenq->lock); + queue->fastopenq->qlen++; + spin_unlock(&queue->fastopenq->lock); + + /* Initialize the child socket. Have to fix some values to take + * into account the child is a Fast Open socket and is created + * only out of the bits carried in the SYN packet. + */ + tp = tcp_sk(child); + + tp->fastopen_rsk = req; + /* Do a hold on the listner sk so that if the listener is being + * closed, the child that has been accepted can live on and still + * access listen_lock. + */ + sock_hold(sk); + tcp_rsk(req)->listener = sk; + + /* RFC1323: The window in SYN & SYN/ACK segments is never + * scaled. So correct it appropriately. + */ + tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + + /* Activate the retrans timer so that SYNACK can be retransmitted. + * The request socket is not added to the SYN table of the parent + * because it's been added to the accept queue directly. + */ + inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, + TCP_TIMEOUT_INIT, TCP_RTO_MAX); + + /* Add the child socket directly into the accept queue */ + inet_csk_reqsk_queue_add(sk, req, child); + + /* Now finish processing the fastopen child socket. */ + inet_csk(child)->icsk_af_ops->rebuild_header(child); + tcp_init_congestion_control(child); + tcp_mtup_init(child); + tcp_init_buffer_space(child); + tcp_init_metrics(child); + + /* Queue the data carried in the SYN packet. We need to first + * bump skb's refcnt because the caller will attempt to free it. + * + * XXX (TFO) - we honor a zero-payload TFO request for now. + * (Any reason not to?) + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) { + /* Don't queue the skb if there is no payload in SYN. + * XXX (TFO) - How about SYN+FIN? + */ + tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + } else { + skb = skb_get(skb); + skb_dst_drop(skb); + __skb_pull(skb, tcp_hdr(skb)->doff * 4); + skb_set_owner_r(skb, child); + __skb_queue_tail(&child->sk_receive_queue, skb); + tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + } + sk->sk_data_ready(sk, 0); + bh_unlock_sock(child); + sock_put(child); + WARN_ON(req->sk == NULL); + return 0; +} + int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; @@ -1285,6 +1476,11 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; bool want_cookie = false; + struct flowi4 fl4; + struct tcp_fastopen_cookie foc = { .len = -1 }; + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; + struct sk_buff *skb_synack; + int do_fastopen; /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -1319,7 +1515,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, + want_cookie ? NULL : &foc); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1377,8 +1574,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = cookie_v4_init_sequence(sk, skb, &req->mss); req->cookie_ts = tmp_opt.tstamp_ok; } else if (!isn) { - struct flowi4 fl4; - /* VJ's idea. We save last timestamp seen * from the destination in peer table, when entering * state TIME-WAIT, and check against it before @@ -1419,14 +1614,52 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->snt_synack = tcp_time_stamp; - if (tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext, - skb_get_queue_mapping(skb), - want_cookie) || - want_cookie) + if (dst == NULL) { + dst = inet_csk_route_req(sk, &fl4, req); + if (dst == NULL) + goto drop_and_free; + } + do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc); + + /* We don't call tcp_v4_send_synack() directly because we need + * to make sure a child socket can be created successfully before + * sending back synack! + * + * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack() + * (or better yet, call tcp_send_synack() in the child context + * directly, but will have to fix bunch of other code first) + * after syn_recv_sock() except one will need to first fix the + * latter to remove its dependency on the current implementation + * of tcp_v4_send_synack()->tcp_select_initial_window(). + */ + skb_synack = tcp_make_synack(sk, dst, req, + (struct request_values *)&tmp_ext, + fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL); + + if (skb_synack) { + __tcp_v4_send_check(skb_synack, ireq->loc_addr, ireq->rmt_addr); + skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb)); + } else + goto drop_and_free; + + if (likely(!do_fastopen)) { + int err; + err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr, + ireq->rmt_addr, ireq->opt); + err = net_xmit_eval(err); + if (err || want_cookie) + goto drop_and_free; + + tcp_rsk(req)->listener = NULL; + /* Add the request_sock to the SYN table */ + inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + if (fastopen_cookie_present(&foc) && foc.len != 0) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req, + (struct request_values *)&tmp_ext)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; drop_and_release: @@ -1554,7 +1787,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) struct request_sock *req = inet_csk_search_req(sk, &prev, th->source, iph->saddr, iph->daddr); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); @@ -1977,6 +2210,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cookie_values_release); tp->cookie_values = NULL; } + BUG_ON(tp->fastopen_rsk != NULL); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2393,7 +2627,7 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) EXPORT_SYMBOL(tcp_proc_unregister); static void get_openreq4(const struct sock *sk, const struct request_sock *req, - struct seq_file *f, int i, int uid, int *len) + struct seq_file *f, int i, kuid_t uid, int *len) { const struct inet_request_sock *ireq = inet_rsk(req); long delta = req->expires - jiffies; @@ -2410,7 +2644,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), req->retrans, - uid, + from_kuid_munged(seq_user_ns(f), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ atomic_read(&sk->sk_refcnt), @@ -2425,6 +2659,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); + struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); @@ -2461,7 +2696,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, - sock_i_uid(sk), + from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), atomic_read(&sk->sk_refcnt), sk, @@ -2469,7 +2704,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh, + sk->sk_state == TCP_LISTEN ? + (fastopenq ? fastopenq->max_qlen : 0) : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh), len); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6ff7f10..e965319 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -507,6 +507,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; TCP_ECN_openreq_child(newtp, req); + newtp->fastopen_rsk = NULL; TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS); } @@ -515,13 +516,18 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, EXPORT_SYMBOL(tcp_create_openreq_child); /* - * Process an incoming packet for SYN_RECV sockets represented - * as a request_sock. + * Process an incoming packet for SYN_RECV sockets represented as a + * request_sock. Normally sk is the listener socket but for TFO it + * points to the child socket. + * + * XXX (TFO) - The current impl contains a special check for ack + * validation and inside tcp_v4_reqsk_send_ack(). Can we do better? */ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct request_sock **prev) + struct request_sock **prev, + bool fastopen) { struct tcp_options_received tmp_opt; const u8 *hash_location; @@ -530,6 +536,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); bool paws_reject = false; + BUG_ON(fastopen == (sk->sk_state == TCP_LISTEN)); + tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); @@ -565,6 +573,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. + * + * Note that even if there is new data in the SYN packet + * they will be thrown away too. */ req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; @@ -622,9 +633,12 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * sent (the segment carries an unacceptable ACK) ... * a reset is sent." * - * Invalid ACK: reset will be sent by listening socket + * Invalid ACK: reset will be sent by listening socket. + * Note that the ACK validity check for a Fast Open socket is done + * elsewhere and is checked directly against the child socket rather + * than req because user data may have been sent out. */ - if ((flg & TCP_FLAG_ACK) && + if ((flg & TCP_FLAG_ACK) && !fastopen && (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk)))) return sk; @@ -637,7 +651,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) { + tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) req->rsk_ops->send_ack(sk, skb, req); @@ -648,7 +662,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1)) + if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) req->ts_recent = tmp_opt.rcv_tsval; if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { @@ -667,10 +681,19 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* ACK sequence verified above, just make sure ACK is * set. If ACK not set, just silently drop the packet. + * + * XXX (TFO) - if we ever allow "data after SYN", the + * following check needs to be removed. */ if (!(flg & TCP_FLAG_ACK)) return NULL; + /* For Fast Open no more processing is needed (sk is the + * child socket). + */ + if (fastopen) + return sk; + /* While TCP_DEFER_ACCEPT is active, drop bare ACK. */ if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { @@ -706,11 +729,21 @@ listen_overflow: } embryonic_reset: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); - if (!(flg & TCP_FLAG_RST)) + if (!(flg & TCP_FLAG_RST)) { + /* Received a bad SYN pkt - for TFO We try not to reset + * the local connection unless it's really necessary to + * avoid becoming vulnerable to outside attack aiming at + * resetting legit local connections. + */ req->rsk_ops->send_reset(sk, skb); - - inet_csk_reqsk_queue_drop(sk, req, prev); + } else if (fastopen) { /* received a valid RST pkt */ + reqsk_fastopen_remove(sk, req, true); + tcp_reset(sk); + } + if (!fastopen) { + inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + } return NULL; } EXPORT_SYMBOL(tcp_check_req); @@ -719,6 +752,12 @@ EXPORT_SYMBOL(tcp_check_req); * Queue segment on the new socket if the new socket is active, * otherwise we just shortcircuit this and continue with * the new socket. + * + * For the vast majority of cases child->sk_state will be TCP_SYN_RECV + * when entering. But other states are possible due to a race condition + * where after __inet_lookup_established() fails but before the listener + * locked is obtained, other packets cause the same connection to + * be created. */ int tcp_child_process(struct sock *parent, struct sock *child, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d046326..9383b51 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -702,7 +702,8 @@ static unsigned int tcp_synack_options(struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5, - struct tcp_extend_values *xvp) + struct tcp_extend_values *xvp, + struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -747,7 +748,15 @@ static unsigned int tcp_synack_options(struct sock *sk, if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } - + if (foc != NULL) { + u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + need = (need + 3) & ~3U; /* Align to 32 bits */ + if (remaining >= need) { + opts->options |= OPTION_FAST_OPEN_COOKIE; + opts->fastopen_cookie = foc; + remaining -= need; + } + } /* Similar rationale to tcp_syn_options() applies here, too. * If the <SYN> options fit, the same options should fit now! */ @@ -2658,7 +2667,8 @@ int tcp_send_synack(struct sock *sk) */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp, + struct tcp_fastopen_cookie *foc) { struct tcp_out_options opts; struct tcp_extend_values *xvp = tcp_xv(rvp); @@ -2718,7 +2728,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #endif TCP_SKB_CB(skb)->when = tcp_time_stamp; tcp_header_size = tcp_synack_options(sk, req, mss, - skb, &opts, &md5, xvp) + skb, &opts, &md5, xvp, foc) + sizeof(*th); skb_push(skb, tcp_header_size); @@ -2772,7 +2782,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } th->seq = htonl(TCP_SKB_CB(skb)->seq); - th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); + /* XXX data is queued and acked as is. No buffer/window check */ + th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b774a03..fc04711 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -305,6 +305,35 @@ static void tcp_probe_timer(struct sock *sk) } /* + * Timer for Fast Open socket to retransmit SYNACK. Note that the + * sk here is the child socket, not the parent (listener) socket. + */ +static void tcp_fastopen_synack_timer(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + int max_retries = icsk->icsk_syn_retries ? : + sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ + struct request_sock *req; + + req = tcp_sk(sk)->fastopen_rsk; + req->rsk_ops->syn_ack_timeout(sk, req); + + if (req->retrans >= max_retries) { + tcp_write_err(sk); + return; + } + /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error + * returned from rtx_syn_ack() to make it more persistent like + * regular retransmit because if the child socket has been accepted + * it's not good to give up too easily. + */ + req->rsk_ops->rtx_syn_ack(sk, req, NULL); + req->retrans++; + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_TIMEOUT_INIT << req->retrans, TCP_RTO_MAX); +} + +/* * The TCP retransmit timer. */ @@ -317,7 +346,15 @@ void tcp_retransmit_timer(struct sock *sk) tcp_resume_early_retransmit(sk); return; } - + if (tp->fastopen_rsk) { + BUG_ON(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); + tcp_fastopen_synack_timer(sk); + /* Before we receive ACK to our SYN-ACK don't retransmit + * anything else (e.g., data or FIN segments). + */ + return; + } if (!tp->packets_out) goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6f6d1ac..c4e6432 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2110,7 +2110,9 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), - 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), + 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops), len); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 16d0960..d2f336e 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -24,7 +24,9 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, if (!inet_diag_bc_sk(bc, sk)) return 0; - return inet_sk_diag_fill(sk, NULL, skb, req, NETLINK_CB(cb->skb).pid, + return inet_sk_diag_fill(sk, NULL, skb, req, + sk_user_ns(NETLINK_CB(cb->skb).ssk), + NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } @@ -69,6 +71,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out; err = inet_sk_diag_fill(sk, NULL, rep, req, + sk_user_ns(NETLINK_CB(in_skb).ssk), NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { |