diff options
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 2036 |
1 files changed, 1064 insertions, 972 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 00156bf421c..77cccda1ad0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -5,8 +5,6 @@ * * Implementation of the Transmission Control Protocol(TCP). * - * Version: $Id: tcp_ipv4.c,v 1.240 2002/02/01 22:01:04 davem Exp $ - * * IPv4 specific functions * * @@ -52,7 +50,9 @@ * a single port at the same time. */ +#define pr_fmt(fmt) "TCP: " fmt +#include <linux/bottom_half.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> @@ -61,6 +61,7 @@ #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/icmp.h> @@ -72,6 +73,9 @@ #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/netdma.h> +#include <net/secure_seq.h> +#include <net/tcp_memcontrol.h> +#include <net/busy_poll.h> #include <linux/inet.h> #include <linux/ipv6.h> @@ -84,31 +88,18 @@ int sysctl_tcp_tw_reuse __read_mostly; int sysctl_tcp_low_latency __read_mostly; +EXPORT_SYMBOL(sysctl_tcp_low_latency); -/* Check TCP sequence numbers in ICMP packets. */ -#define ICMP_MIN_LENGTH 8 - -/* Socket used for sending RSTs */ -static struct socket *tcp_socket __read_mostly; - -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, - __be32 addr); -static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key, - __be32 saddr, __be32 daddr, - struct tcphdr *th, int protocol, - unsigned int tcplen); +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif -struct inet_hashinfo __cacheline_aligned tcp_hashinfo = { - .lhash_lock = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock), - .lhash_users = ATOMIC_INIT(0), - .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait), -}; +struct inet_hashinfo tcp_hashinfo; +EXPORT_SYMBOL(tcp_hashinfo); -static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb) +static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb) { return secure_tcp_sequence_number(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, @@ -146,19 +137,20 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) return 0; } - EXPORT_SYMBOL_GPL(tcp_twsk_unique); /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct rtable *rt; + __be16 orig_sport, orig_dport; __be32 daddr, nexthop; - int tmp; + struct flowi4 *fl4; + struct rtable *rt; int err; + struct ip_options_rcu *inet_opt; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; @@ -167,20 +159,26 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; - if (inet->opt && inet->opt->srr) { + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); + if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; - nexthop = inet->opt->faddr; + nexthop = inet_opt->opt.faddr; } - tmp = ip_route_connect(&rt, nexthop, inet->saddr, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, - IPPROTO_TCP, - inet->sport, usin->sin_port, sk, 1); - if (tmp < 0) { - if (tmp == -ENETUNREACH) - IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); - return tmp; + orig_sport = inet->inet_sport; + orig_dport = usin->sin_port; + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, + IPPROTO_TCP, + orig_sport, orig_dport, sk); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + if (err == -ENETUNREACH) + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + return err; } if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { @@ -188,44 +186,33 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -ENETUNREACH; } - if (!inet->opt || !inet->opt->srr) - daddr = rt->rt_dst; + if (!inet_opt || !inet_opt->opt.srr) + daddr = fl4->daddr; - if (!inet->saddr) - inet->saddr = rt->rt_src; - inet->rcv_saddr = inet->saddr; + if (!inet->inet_saddr) + inet->inet_saddr = fl4->saddr; + inet->inet_rcv_saddr = inet->inet_saddr; - if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) { + if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + if (likely(!tp->repair)) + tp->write_seq = 0; } if (tcp_death_row.sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) { - struct inet_peer *peer = rt_get_peer(rt); - /* - * VJ's idea. We save last timestamp seen from - * the destination in peer table, when entering state - * TIME-WAIT * and initialize rx_opt.ts_recent from it, - * when trying new connection. - */ - if (peer != NULL && - peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) { - tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp; - tp->rx_opt.ts_recent = peer->tcp_ts; - } - } + !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) + tcp_fetch_timewait_stamp(sk, &rt->dst); - inet->dport = usin->sin_port; - inet->daddr = daddr; + inet->inet_dport = usin->sin_port; + inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; - if (inet->opt) - inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; + if (inet_opt) + inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - tp->rx_opt.mss_clamp = 536; + tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket @@ -237,24 +224,27 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - err = ip_route_newports(&rt, IPPROTO_TCP, - inet->sport, inet->dport, sk); - if (err) + rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, + inet->inet_sport, inet->inet_dport, sk); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; goto failure; - + } /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); - if (!tp->write_seq) - tp->write_seq = secure_tcp_sequence_number(inet->saddr, - inet->daddr, - inet->sport, + if (!tp->write_seq && likely(!tp->repair)) + tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, usin->sin_port); - inet->id = tp->write_seq ^ jiffies; + inet->inet_id = tp->write_seq ^ jiffies; err = tcp_connect(sk); + rt = NULL; if (err) goto failure; @@ -269,36 +259,26 @@ failure: tcp_set_state(sk, TCP_CLOSE); ip_rt_put(rt); sk->sk_route_caps = 0; - inet->dport = 0; + inet->inet_dport = 0; return err; } +EXPORT_SYMBOL(tcp_v4_connect); /* - * This routine does path mtu discovery as defined in RFC1191. + * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. + * It can be called through tcp_release_cb() if socket was owned by user + * at the time tcp_v4_err() was called to handle ICMP message. */ -static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) +static void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); + u32 mtu = tcp_sk(sk)->mtu_info; - /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs - * send out by Linux are always <576bytes so they should go through - * unfragmented). - */ - if (sk->sk_state == TCP_LISTEN) - return; - - /* We don't check in the destentry if pmtu discovery is forbidden - * on this route. We just assume that no packet_to_big packets - * are send back when pmtu discovery is not active. - * There is a small race when the user changes this flag in the - * route, but I think that's acceptable. - */ - if ((dst = __sk_dst_check(sk, 0)) == NULL) + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) return; - dst->ops->update_pmtu(dst, mtu); - /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ @@ -308,6 +288,7 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && + ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { tcp_sync_mss(sk, mtu); @@ -320,6 +301,14 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) } /* else let the usual retransmit timer handle it */ } +static void do_redirect(struct sk_buff *skb, struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + + if (dst) + dst->ops->redirect(dst, sk, skb); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -336,27 +325,32 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) * */ -void tcp_v4_err(struct sk_buff *skb, u32 info) +void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) { - struct iphdr *iph = (struct iphdr *)skb->data; - struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); + const struct iphdr *iph = (const struct iphdr *)icmp_skb->data; + struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2)); + struct inet_connection_sock *icsk; struct tcp_sock *tp; struct inet_sock *inet; - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; + const int type = icmp_hdr(icmp_skb)->type; + const int code = icmp_hdr(icmp_skb)->code; struct sock *sk; - __u32 seq; + struct sk_buff *skb; + struct request_sock *fastopen; + __u32 seq, snd_una; + __u32 remaining; int err; + struct net *net = dev_net(icmp_skb->dev); - if (skb->len < (iph->ihl << 2) + 8) { - ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); + if (icmp_skb->len < (iph->ihl << 2) + 8) { + ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } - sk = inet_lookup(skb->dev->nd_net, &tcp_hashinfo, iph->daddr, th->dest, - iph->saddr, th->source, inet_iif(skb)); + sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest, + iph->saddr, th->source, inet_iif(icmp_skb)); if (!sk) { - ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); + ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } if (sk->sk_state == TCP_TIME_WAIT) { @@ -367,22 +361,37 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. + * We do take care of PMTU discovery (RFC1191) special case : + * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk)) - NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out; + if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto out; + } + + icsk = inet_csk(sk); tp = tcp_sk(sk); seq = ntohl(th->seq); + /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ + fastopen = tp->fastopen_rsk; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt)) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + !between(seq, snd_una, tp->snd_nxt)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { + case ICMP_REDIRECT: + do_redirect(icmp_skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; @@ -394,12 +403,55 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ - if (!sock_owned_by_user(sk)) - do_pmtu_discovery(sk, iph, info); + /* We are not interested in TCP_LISTEN and open_requests + * (SYN-ACKs send out by Linux are always <576bytes so + * they should go through unfragmented). + */ + if (sk->sk_state == TCP_LISTEN) + goto out; + + tp->mtu_info = info; + if (!sock_owned_by_user(sk)) { + tcp_v4_mtu_reduced(sk); + } else { + if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags)) + sock_hold(sk); + } goto out; } err = icmp_err_convert[code].errno; + /* check if icmp_skb allows revert of backoff + * (see draft-zimmermann-tcp-lcd) */ + if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH) + break; + if (seq != tp->snd_una || !icsk->icsk_retransmits || + !icsk->icsk_backoff || fastopen) + break; + + if (sock_owned_by_user(sk)) + break; + + icsk->icsk_backoff--; + inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : + TCP_TIMEOUT_INIT) << icsk->icsk_backoff; + tcp_bound_rto(sk); + + skb = tcp_write_queue_head(sk); + BUG_ON(!skb); + + remaining = icsk->icsk_rto - min(icsk->icsk_rto, + tcp_time_stamp - TCP_SKB_CB(skb)->when); + + if (remaining) { + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + remaining, TCP_RTO_MAX); + } else { + /* RTO revert clocked out retransmission. + * Will retransmit now */ + tcp_retransmit_timer(sk); + } + break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; @@ -422,10 +474,10 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) /* ICMPs are not backlogged, hence we cannot get an established socket here. */ - BUG_TRAP(!req->sk); + WARN_ON(req->sk); if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -436,12 +488,17 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: - case TCP_SYN_RECV: /* Cannot happen. - It can f.e. if SYNs crossed. - */ + case TCP_SYN_RECV: + /* Only in fast or simultaneous open. If a fast open socket is + * is already accepted it is treated as a connected one below. + */ + if (fastopen && fastopen->sk == NULL) + break; + if (!sock_owned_by_user(sk)) { sk->sk_err = err; @@ -483,43 +540,30 @@ out: sock_put(sk); } -/* This routine computes an IPv4 TCP checksum. */ -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { - struct inet_sock *inet = inet_sk(sk); struct tcphdr *th = tcp_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(len, inet->saddr, - inet->daddr, 0); + th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = tcp_v4_check(len, inet->saddr, inet->daddr, - csum_partial((char *)th, + th->check = tcp_v4_check(skb->len, saddr, daddr, + csum_partial(th, th->doff << 2, skb->csum)); } } -int tcp_v4_gso_send_check(struct sk_buff *skb) +/* This routine computes an IPv4 TCP checksum. */ +void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { - const struct iphdr *iph; - struct tcphdr *th; - - if (!pskb_may_pull(skb, sizeof(*th))) - return -EINVAL; + const struct inet_sock *inet = inet_sk(sk); - iph = ip_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; - return 0; + __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } +EXPORT_SYMBOL(tcp_v4_send_check); /* * This routine will send an RST to the other tcp. @@ -536,7 +580,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; #ifdef CONFIG_TCP_MD5SIG @@ -546,13 +590,18 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; + const __u8 *hash_location = NULL; + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; #endif + struct net *net; /* Never send a reset in response to a reset. */ if (th->rst) return; - if (((struct rtable *)skb->dst)->rt_type != RTN_LOCAL) + if (skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ @@ -575,7 +624,37 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len = sizeof(rep.th); #ifdef CONFIG_TCP_MD5SIG - key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL; + hash_location = tcp_parse_md5sig_option(th); + if (!sk && hash_location) { + /* + * active side is lost. Try to find listening socket through + * source port, and then find md5 key through listening socket. + * we are not loose security here: + * Incoming packet is checked with md5 hash with finding key, + * no RST generated if md5 hash doesn't match. + */ + sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), + &tcp_hashinfo, ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, + ntohs(th->source), inet_iif(skb)); + /* don't send rst if it can't find key */ + if (!sk1) + return; + rcu_read_lock(); + key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, AF_INET); + if (!key) + goto release_sk1; + + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto release_sk1; + } else { + key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, + AF_INET) : NULL; + } + if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -585,34 +664,50 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len / 4; - tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[1], - key, - ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - &rep.th, IPPROTO_TCP, - arg.iov[0].iov_len); + tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1], + key, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &rep.th); } #endif arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ - sizeof(struct tcphdr), IPPROTO_TCP, 0); + arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; + arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. + * routing might fail in this case. No choice here, if we choose to force + * input interface, we will misroute in case of asymmetric route. + */ + if (sk) + arg.bound_dev_if = sk->sk_bound_dev_if; + + net = dev_net(skb_dst(skb)->dev); + arg.tos = ip_hdr(skb)->tos; + ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); - ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len); + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); - TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(TCP_MIB_OUTRSTS); +#ifdef CONFIG_TCP_MD5SIG +release_sk1: + if (sk1) { + rcu_read_unlock(); + sock_put(sk1); + } +#endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk, - struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 ts) +static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, + u32 win, u32 tsval, u32 tsecr, int oif, + struct tcp_md5sig_key *key, + int reply_flags, u8 tos) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2) @@ -622,22 +717,19 @@ static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk, ]; } rep; struct ip_reply_arg arg; -#ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; - struct tcp_md5sig_key tw_key; -#endif + struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); - if (ts) { + if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - rep.opt[1] = htonl(tcp_time_stamp); - rep.opt[2] = htonl(ts); + rep.opt[1] = htonl(tsval); + rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } @@ -651,25 +743,8 @@ static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk, rep.th.window = htons(win); #ifdef CONFIG_TCP_MD5SIG - /* - * The SKB holds an imcoming packet, but may not have a valid ->sk - * pointer. This is especially the case when we're dealing with a - * TIME_WAIT ack, because the sk structure is long gone, and only - * the tcp_timewait_sock remains. So the md5 key is stashed in that - * structure, and we use it in preference. I believe that (twsk || - * skb->sk) holds true, but we program defensively. - */ - if (!twsk && skb->sk) { - key = tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr); - } else if (twsk && twsk->tw_md5_keylen) { - tw_key.key = twsk->tw_md5_key; - tw_key.keylen = twsk->tw_md5_keylen; - key = &tw_key; - } else - key = NULL; - if (key) { - int offset = (ts) ? 3 : 0; + int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -678,24 +753,23 @@ static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk, arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len/4; - tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[offset], - key, - ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - &rep.th, IPPROTO_TCP, - arg.iov[0].iov_len); + tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], + key, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &rep.th); } #endif + arg.flags = reply_flags; arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; - if (twsk) - arg.bound_dev_if = twsk->tw_sk.tw_bound_dev_if; - - ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len); + if (oif) + arg.bound_dev_if = oif; + arg.tos = tos; + ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); - TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); } static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -703,19 +777,35 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(tcptw, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcptw->tw_ts_recent); + tcp_time_stamp + tcptw->tw_ts_offset, + tcptw->tw_ts_recent, + tw->tw_bound_dev_if, + tcp_twsk_md5_key(tcptw), + tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, + tw->tw_tos + ); inet_twsk_put(tw); } -static void tcp_v4_reqsk_send_ack(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(NULL, skb, tcp_rsk(req)->snt_isn + 1, - tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, - req->ts_recent); + /* 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, + tcp_time_stamp, + req->ts_recent, + 0, + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + AF_INET), + inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, + ip_hdr(skb)->tos); } /* @@ -723,39 +813,48 @@ static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + u16 queue_mapping, + struct tcp_fastopen_cookie *foc) { const struct inet_request_sock *ireq = inet_rsk(req); + struct flowi4 fl4; int err = -1; - struct sk_buff * skb; + struct sk_buff *skb; /* First, grab a route. */ - if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) - goto out; + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) + return -1; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, foc); if (skb) { - struct tcphdr *th = tcp_hdr(skb); - - th->check = tcp_v4_check(skb->len, - ireq->loc_addr, - ireq->rmt_addr, - csum_partial((char *)th, skb->len, - skb->csum)); + __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); - err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, - ireq->rmt_addr, + skb_set_queue_mapping(skb, queue_mapping); + err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, + ireq->ir_rmt_addr, ireq->opt); err = net_xmit_eval(err); + if (!tcp_rsk(req)->snt_synack && !err) + tcp_rsk(req)->snt_synack = tcp_time_stamp; } -out: - dst_release(dst); return err; } +static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) +{ + int res = tcp_v4_send_synack(sk, NULL, req, 0, NULL); + + if (!res) { + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } + return res; +} + /* * IPv4 request_sock destructor. */ @@ -764,34 +863,50 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -#ifdef CONFIG_SYN_COOKIES -static void syn_flood_warning(struct sk_buff *skb) +/* + * Return true if a syncookie should be sent + */ +bool tcp_syn_flood_action(struct sock *sk, + const struct sk_buff *skb, + const char *proto) { - static unsigned long warntime; + const char *msg = "Dropping request"; + bool want_cookie = false; + struct listen_sock *lopt; + +#ifdef CONFIG_SYN_COOKIES + if (sysctl_tcp_syncookies) { + msg = "Sending cookies"; + want_cookie = true; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); + } else +#endif + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (time_after(jiffies, (warntime + HZ * 60))) { - warntime = jiffies; - printk(KERN_INFO - "possible SYN flooding on port %d. Sending cookies.\n", - ntohs(tcp_hdr(skb)->dest)); + lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; + if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { + lopt->synflood_warned = 1; + pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); } + return want_cookie; } -#endif +EXPORT_SYMBOL(tcp_syn_flood_action); /* * Save and compile IPv4 options into the request_sock if needed. */ -static struct ip_options *tcp_v4_save_options(struct sock *sk, - struct sk_buff *skb) +static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb) { - struct ip_options *opt = &(IPCB(skb)->opt); - struct ip_options *dopt = NULL; + const struct ip_options *opt = &(IPCB(skb)->opt); + struct ip_options_rcu *dopt = NULL; if (opt && opt->optlen) { - int opt_size = optlength(opt); + int opt_size = sizeof(*dopt) + opt->optlen; + dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt) { - if (ip_options_echo(dopt, skb)) { + if (ip_options_echo(&dopt->opt, skb)) { kfree(dopt); dopt = NULL; } @@ -808,153 +923,129 @@ static struct ip_options *tcp_v4_save_options(struct sock *sk, */ /* Find the Key structure for an address. */ -static struct tcp_md5sig_key * - tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) +struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, + const union tcp_md5_addr *addr, + int family) { struct tcp_sock *tp = tcp_sk(sk); - int i; - - if (!tp->md5sig_info || !tp->md5sig_info->entries4) + struct tcp_md5sig_key *key; + unsigned int size = sizeof(struct in_addr); + struct tcp_md5sig_info *md5sig; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); + if (!md5sig) return NULL; - for (i = 0; i < tp->md5sig_info->entries4; i++) { - if (tp->md5sig_info->keys4[i].addr == addr) - return &tp->md5sig_info->keys4[i].base; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + size = sizeof(struct in6_addr); +#endif + hlist_for_each_entry_rcu(key, &md5sig->head, node) { + if (key->family != family) + continue; + if (!memcmp(&key->addr, addr, size)) + return key; } return NULL; } +EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->daddr); -} + union tcp_md5_addr *addr; + addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr; + return tcp_md5_do_lookup(sk, addr, AF_INET); +} EXPORT_SYMBOL(tcp_v4_md5_lookup); static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk, struct request_sock *req) { - return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr); + union tcp_md5_addr *addr; + + addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr; + return tcp_md5_do_lookup(sk, addr, AF_INET); } /* This can be called on a newly created socket, from other files */ -int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, - u8 *newkey, u8 newkeylen) +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); - struct tcp4_md5sig_key *keys; + struct tcp_md5sig_info *md5sig; - key = tcp_v4_md5_do_lookup(sk, addr); + key = tcp_md5_do_lookup(sk, addr, family); if (key) { /* Pre-existing entry - just update that one. */ - kfree(key->key); - key->key = newkey; + memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; - } else { - struct tcp_md5sig_info *md5sig; - - if (!tp->md5sig_info) { - tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), - GFP_ATOMIC); - if (!tp->md5sig_info) { - kfree(newkey); - return -ENOMEM; - } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - } - if (tcp_alloc_md5sig_pool() == NULL) { - kfree(newkey); + return 0; + } + + md5sig = rcu_dereference_protected(tp->md5sig_info, + sock_owned_by_user(sk)); + if (!md5sig) { + md5sig = kmalloc(sizeof(*md5sig), gfp); + if (!md5sig) return -ENOMEM; - } - md5sig = tp->md5sig_info; - - if (md5sig->alloced4 == md5sig->entries4) { - keys = kmalloc((sizeof(*keys) * - (md5sig->entries4 + 1)), GFP_ATOMIC); - if (!keys) { - kfree(newkey); - tcp_free_md5sig_pool(); - return -ENOMEM; - } - if (md5sig->entries4) - memcpy(keys, md5sig->keys4, - sizeof(*keys) * md5sig->entries4); + sk_nocaps_add(sk, NETIF_F_GSO_MASK); + INIT_HLIST_HEAD(&md5sig->head); + rcu_assign_pointer(tp->md5sig_info, md5sig); + } - /* Free old key list, and reference new one */ - kfree(md5sig->keys4); - md5sig->keys4 = keys; - md5sig->alloced4++; - } - md5sig->entries4++; - md5sig->keys4[md5sig->entries4 - 1].addr = addr; - md5sig->keys4[md5sig->entries4 - 1].base.key = newkey; - md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen; + key = sock_kmalloc(sk, sizeof(*key), gfp); + if (!key) + return -ENOMEM; + if (!tcp_alloc_md5sig_pool()) { + sock_kfree_s(sk, key, sizeof(*key)); + return -ENOMEM; } + + memcpy(key->key, newkey, newkeylen); + key->keylen = newkeylen; + key->family = family; + memcpy(&key->addr, addr, + (family == AF_INET6) ? sizeof(struct in6_addr) : + sizeof(struct in_addr)); + hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } +EXPORT_SYMBOL(tcp_md5_do_add); -EXPORT_SYMBOL(tcp_v4_md5_do_add); - -static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk, - u8 *newkey, u8 newkeylen) +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) { - return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->daddr, - newkey, newkeylen); -} + struct tcp_md5sig_key *key; -int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) -{ - struct tcp_sock *tp = tcp_sk(sk); - int i; - - for (i = 0; i < tp->md5sig_info->entries4; i++) { - if (tp->md5sig_info->keys4[i].addr == addr) { - /* Free the key */ - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4--; - - if (tp->md5sig_info->entries4 == 0) { - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; - } else if (tp->md5sig_info->entries4 != i) { - /* Need to do some manipulation */ - memmove(&tp->md5sig_info->keys4[i], - &tp->md5sig_info->keys4[i+1], - (tp->md5sig_info->entries4 - i) * - sizeof(struct tcp4_md5sig_key)); - } - tcp_free_md5sig_pool(); - return 0; - } - } - return -ENOENT; + key = tcp_md5_do_lookup(sk, addr, family); + if (!key) + return -ENOENT; + hlist_del_rcu(&key->node); + atomic_sub(sizeof(*key), &sk->sk_omem_alloc); + kfree_rcu(key, rcu); + return 0; } +EXPORT_SYMBOL(tcp_md5_do_del); -EXPORT_SYMBOL(tcp_v4_md5_do_del); - -static void tcp_v4_clear_md5_list(struct sock *sk) +static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + struct hlist_node *n; + struct tcp_md5sig_info *md5sig; - /* Free each key, then the set of key keys, - * the crypto element, and then decrement our - * hold on the last resort crypto. - */ - if (tp->md5sig_info->entries4) { - int i; - for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4 = 0; - tcp_free_md5sig_pool(); - } - if (tp->md5sig_info->keys4) { - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; + md5sig = rcu_dereference_protected(tp->md5sig_info, 1); + + hlist_for_each_entry_safe(key, n, &md5sig->head, node) { + hlist_del_rcu(&key->node); + atomic_sub(sizeof(*key), &sk->sk_omem_alloc); + kfree_rcu(key, rcu); } } @@ -963,7 +1054,6 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; - u8 *newkey; if (optlen < sizeof(cmd)) return -EINVAL; @@ -974,59 +1064,25 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; - if (!cmd.tcpm_key || !cmd.tcpm_keylen) { - if (!tcp_sk(sk)->md5sig_info) - return -ENOENT; - return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr); - } + if (!cmd.tcpm_key || !cmd.tcpm_keylen) + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, + AF_INET); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - if (!tcp_sk(sk)->md5sig_info) { - struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_info *p = kzalloc(sizeof(*p), GFP_KERNEL); - - if (!p) - return -EINVAL; - - tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - } - - newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); - if (!newkey) - return -ENOMEM; - return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr, - newkey, cmd.tcpm_keylen); + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, + AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, + GFP_KERNEL); } -static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key, - __be32 saddr, __be32 daddr, - struct tcphdr *th, int protocol, - unsigned int tcplen) +static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, + __be32 daddr, __be32 saddr, int nbytes) { - struct scatterlist sg[4]; - __u16 data_len; - int block = 0; - __sum16 old_checksum; - struct tcp_md5sig_pool *hp; struct tcp4_pseudohdr *bp; - struct hash_desc *desc; - int err; - unsigned int nbytes = 0; - - /* - * Okay, so RFC2385 is turned on for this connection, - * so we need to generate the MD5 hash for the packet now. - */ - - hp = tcp_get_md5sig_pool(); - if (!hp) - goto clear_hash_noput; + struct scatterlist sg; bp = &hp->md5_blk.ip4; - desc = &hp->md5_desc; /* * 1. the TCP pseudo-header (in the order: source IP address, @@ -1036,88 +1092,97 @@ static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key, bp->saddr = saddr; bp->daddr = daddr; bp->pad = 0; - bp->protocol = protocol; - bp->len = htons(tcplen); - - sg_init_table(sg, 4); - - sg_set_buf(&sg[block++], bp, sizeof(*bp)); - nbytes += sizeof(*bp); + bp->protocol = IPPROTO_TCP; + bp->len = cpu_to_be16(nbytes); - /* 2. the TCP header, excluding options, and assuming a - * checksum of zero/ - */ - old_checksum = th->check; - th->check = 0; - sg_set_buf(&sg[block++], th, sizeof(struct tcphdr)); - nbytes += sizeof(struct tcphdr); - - /* 3. the TCP segment data (if any) */ - data_len = tcplen - (th->doff << 2); - if (data_len > 0) { - unsigned char *data = (unsigned char *)th + (th->doff << 2); - sg_set_buf(&sg[block++], data, data_len); - nbytes += data_len; - } + sg_init_one(&sg, bp, sizeof(*bp)); + return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp)); +} - /* 4. an independently-specified key or password, known to both - * TCPs and presumably connection-specific - */ - sg_set_buf(&sg[block++], key->key, key->keylen); - nbytes += key->keylen; +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th) +{ + struct tcp_md5sig_pool *hp; + struct hash_desc *desc; - sg_mark_end(&sg[block - 1]); + hp = tcp_get_md5sig_pool(); + if (!hp) + goto clear_hash_noput; + desc = &hp->md5_desc; - /* Now store the Hash into the packet */ - err = crypto_hash_init(desc); - if (err) + if (crypto_hash_init(desc)) goto clear_hash; - err = crypto_hash_update(desc, sg, nbytes); - if (err) + if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2)) goto clear_hash; - err = crypto_hash_final(desc, md5_hash); - if (err) + if (tcp_md5_hash_header(hp, th)) + goto clear_hash; + if (tcp_md5_hash_key(hp, key)) + goto clear_hash; + if (crypto_hash_final(desc, md5_hash)) goto clear_hash; - /* Reset header, and free up the crypto */ tcp_put_md5sig_pool(); - th->check = old_checksum; - -out: return 0; + clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); - goto out; + return 1; } -int tcp_v4_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key, - struct sock *sk, - struct dst_entry *dst, - struct request_sock *req, - struct tcphdr *th, int protocol, - unsigned int tcplen) +int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, + const struct sock *sk, const struct request_sock *req, + const struct sk_buff *skb) { + struct tcp_md5sig_pool *hp; + struct hash_desc *desc; + const struct tcphdr *th = tcp_hdr(skb); __be32 saddr, daddr; if (sk) { - saddr = inet_sk(sk)->saddr; - daddr = inet_sk(sk)->daddr; + saddr = inet_sk(sk)->inet_saddr; + daddr = inet_sk(sk)->inet_daddr; + } else if (req) { + saddr = inet_rsk(req)->ir_loc_addr; + daddr = inet_rsk(req)->ir_rmt_addr; } else { - struct rtable *rt = (struct rtable *)dst; - BUG_ON(!rt); - saddr = rt->rt_src; - daddr = rt->rt_dst; + const struct iphdr *iph = ip_hdr(skb); + saddr = iph->saddr; + daddr = iph->daddr; } - return tcp_v4_do_calc_md5_hash(md5_hash, key, - saddr, daddr, - th, protocol, tcplen); -} -EXPORT_SYMBOL(tcp_v4_calc_md5_hash); + hp = tcp_get_md5sig_pool(); + if (!hp) + goto clear_hash_noput; + desc = &hp->md5_desc; + + if (crypto_hash_init(desc)) + goto clear_hash; -static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) + if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len)) + goto clear_hash; + if (tcp_md5_hash_header(hp, th)) + goto clear_hash; + if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) + goto clear_hash; + if (tcp_md5_hash_key(hp, key)) + goto clear_hash; + if (crypto_hash_final(desc, md5_hash)) + goto clear_hash; + + tcp_put_md5sig_pool(); + return 0; + +clear_hash: + tcp_put_md5sig_pool(); +clear_hash_noput: + memset(md5_hash, 0, 16); + return 1; +} +EXPORT_SYMBOL(tcp_v4_md5_hash_skb); + +static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { /* * This gets called for each TCP segment that arrives @@ -1127,96 +1192,47 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ - __u8 *hash_location = NULL; + const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct iphdr *iph = ip_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); - int length = (th->doff << 2) - sizeof(struct tcphdr); + const struct tcphdr *th = tcp_hdr(skb); int genhash; - unsigned char *ptr; unsigned char newhash[16]; - hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr); - - /* - * If the TCP option length is less than the TCP_MD5SIG - * option length, then we can shortcut - */ - if (length < TCPOLEN_MD5SIG) { - if (hash_expected) - return 1; - else - return 0; - } - - /* Okay, we can't shortcut - we have to grub through the options */ - ptr = (unsigned char *)(th + 1); - while (length > 0) { - int opcode = *ptr++; - int opsize; + hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr, + AF_INET); + hash_location = tcp_parse_md5sig_option(th); - switch (opcode) { - case TCPOPT_EOL: - goto done_opts; - case TCPOPT_NOP: - length--; - continue; - default: - opsize = *ptr++; - if (opsize < 2) - goto done_opts; - if (opsize > length) - goto done_opts; - - if (opcode == TCPOPT_MD5SIG) { - hash_location = ptr; - goto done_opts; - } - } - ptr += opsize-2; - length -= opsize; - } -done_opts: /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) - return 0; + return false; if (hash_expected && !hash_location) { - LIMIT_NETDEBUG(KERN_INFO "MD5 Hash expected but NOT found " - "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n", - NIPQUAD(iph->saddr), ntohs(th->source), - NIPQUAD(iph->daddr), ntohs(th->dest)); - return 1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + return true; } if (!hash_expected && hash_location) { - LIMIT_NETDEBUG(KERN_INFO "MD5 Hash NOT expected but found " - "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n", - NIPQUAD(iph->saddr), ntohs(th->source), - NIPQUAD(iph->daddr), ntohs(th->dest)); - return 1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); + return true; } /* Okay, so this is hash_expected and hash_location - * so we need to calculate the checksum. */ - genhash = tcp_v4_do_calc_md5_hash(newhash, - hash_expected, - iph->saddr, iph->daddr, - th, sk->sk_protocol, - skb->len); + genhash = tcp_v4_md5_hash_skb(newhash, + hash_expected, + NULL, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { - if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash failed for " - "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)%s\n", - NIPQUAD(iph->saddr), ntohs(th->source), - NIPQUAD(iph->daddr), ntohs(th->dest), - genhash ? " tcp_v4_calc_md5_hash failed" : ""); - } - return 1; - } - return 0; + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", + &iph->saddr, ntohs(th->source), + &iph->daddr, ntohs(th->dest), + genhash ? " tcp_v4_calc_md5_hash failed" + : ""); + return true; + } + return false; } #endif @@ -1224,55 +1240,48 @@ done_opts: struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), - .rtx_syn_ack = tcp_v4_send_synack, + .rtx_syn_ack = tcp_v4_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { +static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .md5_lookup = tcp_v4_reqsk_md5_lookup, + .calc_md5_hash = tcp_v4_md5_hash_skb, }; #endif -static struct timewait_sock_ops tcp_timewait_sock_ops = { - .twsk_obj_size = sizeof(struct tcp_timewait_sock), - .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, -}; - int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { - struct inet_request_sock *ireq; struct tcp_options_received tmp_opt; struct request_sock *req; + struct inet_request_sock *ireq; + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = NULL; __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; -#ifdef CONFIG_SYN_COOKIES - int want_cookie = 0; -#else -#define want_cookie 0 /* Argh, why doesn't gcc optimize this :( */ -#endif + bool want_cookie = false, fastopen; + struct flowi4 fl4; + struct tcp_fastopen_cookie foc = { .len = -1 }; + int err; /* Never answer to SYNs send to broadcast or multicast */ - if (((struct rtable *)skb->dst)->rt_flags & - (RTCF_BROADCAST | RTCF_MULTICAST)) + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; /* TW buckets are converted to open requests without * limitations, they conserve resources and peer is * evidently real one. */ - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) { - want_cookie = 1; - } else -#endif - goto drop; + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { + want_cookie = tcp_syn_flood_action(sk, skb, "TCP"); + if (!want_cookie) + goto drop; } /* Accept backlog is full. If we have already queued enough @@ -1280,10 +1289,12 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * clogging syn queue with openreqs with exponentially increasing * timeout. */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } - req = reqsk_alloc(&tcp_request_sock_ops); + req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) goto drop; @@ -1292,47 +1303,33 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) #endif tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = 536; - tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss; - - tcp_parse_options(skb, &tmp_opt, 0); + tmp_opt.mss_clamp = TCP_MSS_DEFAULT; + tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); - if (want_cookie) { + if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); - tmp_opt.saw_tstamp = 0; - } - if (tmp_opt.saw_tstamp && !tmp_opt.rcv_tsval) { - /* Some OSes (unknown ones, but I see them on web server, which - * contains information interesting only for windows' - * users) do not send their stamp in SYN. It is easy case. - * We simply do not advertise TS support. - */ - tmp_opt.saw_tstamp = 0; - tmp_opt.tstamp_ok = 0; - } tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); + ireq = inet_rsk(req); + ireq->ir_loc_addr = daddr; + ireq->ir_rmt_addr = saddr; + ireq->no_srccheck = inet_sk(sk)->transparent; + ireq->opt = tcp_v4_save_options(skb); + ireq->ir_mark = inet_request_mark(sk, skb); + if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; - ireq = inet_rsk(req); - ireq->loc_addr = daddr; - ireq->rmt_addr = saddr; - ireq->opt = tcp_v4_save_options(sk, skb); - if (!want_cookie) - TCP_ECN_create_request(req, tcp_hdr(skb)); + if (!want_cookie || tmp_opt.tstamp_ok) + TCP_ECN_create_request(req, skb, sock_net(sk)); if (want_cookie) { -#ifdef CONFIG_SYN_COOKIES - syn_flood_warning(skb); -#endif isn = cookie_v4_init_sequence(sk, skb, &req->mss); + req->cookie_ts = tmp_opt.tstamp_ok; } else if (!isn) { - struct inet_peer *peer = NULL; - /* VJ's idea. We save last timestamp seen * from the destination in peer table, when entering * state TIME-WAIT, and check against it before @@ -1344,23 +1341,18 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, req)) != NULL && - (peer = rt_get_peer((struct rtable *)dst)) != NULL && - peer->v4daddr == saddr) { - if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL && - (s32)(peer->tcp_ts - req->ts_recent) > - TCP_PAWS_WINDOW) { - NET_INC_STATS_BH(LINUX_MIB_PAWSPASSIVEREJECTED); - dst_release(dst); - goto drop_and_free; + (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && + fl4.daddr == saddr) { + if (!tcp_peer_is_proven(req, dst, true)) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); + goto drop_and_release; } } /* Kill the following clause, if you dislike this way. */ else if (!sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && - (!peer || !peer->tcp_ts_stamp) && - (!dst || !dst_metric(dst, RTAX_RTT))) { + !tcp_peer_is_proven(req, dst, false)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -1368,33 +1360,43 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * to destinations, already remembered * to the moment of synflood. */ - LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open " - "request from %u.%u.%u.%u/%u\n", - NIPQUAD(saddr), - ntohs(tcp_hdr(skb)->source)); - dst_release(dst); - goto drop_and_free; + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"), + &saddr, ntohs(tcp_hdr(skb)->source)); + goto drop_and_release; } isn = tcp_v4_init_sequence(skb); } - tcp_rsk(req)->snt_isn = isn; - - if (tcp_v4_send_synack(sk, req, dst)) + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) goto drop_and_free; - if (want_cookie) { - reqsk_free(req); - } else { + tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_openreq_init_rwin(req, sk, dst); + fastopen = !want_cookie && + tcp_try_fastopen(sk, skb, req, &foc, dst); + err = tcp_v4_send_synack(sk, dst, req, + skb_get_queue_mapping(skb), &foc); + if (!fastopen) { + if (err || want_cookie) + goto drop_and_free; + + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_rsk(req)->listener = NULL; inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } + return 0; +drop_and_release: + dst_release(dst); drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; } +EXPORT_SYMBOL(tcp_v4_conn_request); /* @@ -1412,68 +1414,88 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif + struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; - if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) - goto exit; - newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) - goto exit; + goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; - sk_setup_caps(newsk, dst); + inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->daddr = ireq->rmt_addr; - newinet->rcv_saddr = ireq->loc_addr; - newinet->saddr = ireq->loc_addr; - newinet->opt = ireq->opt; + newinet->inet_daddr = ireq->ir_rmt_addr; + newinet->inet_rcv_saddr = ireq->ir_loc_addr; + newinet->inet_saddr = ireq->ir_loc_addr; + inet_opt = ireq->opt; + rcu_assign_pointer(newinet->inet_opt, inet_opt); ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; + newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newinet->opt) - inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen; - newinet->id = newtp->write_seq ^ jiffies; + if (inet_opt) + inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; + newinet->inet_id = newtp->write_seq ^ jiffies; + + if (!dst) { + dst = inet_csk_route_child_sock(sk, newsk, req); + if (!dst) + goto put_and_exit; + } else { + /* syncookie case : see end of cookie_v4_check() */ + } + sk_setup_caps(newsk, dst); - tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); - newtp->advmss = dst_metric(dst, RTAX_ADVMSS); + newtp->advmss = dst_metric_advmss(dst); + if (tcp_sk(sk)->rx_opt.user_mss && + tcp_sk(sk)->rx_opt.user_mss < newtp->advmss) + newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; + tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v4_md5_do_lookup(sk, newinet->daddr)) != NULL) { + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, + AF_INET); + if (key != NULL) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ - char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); - if (newkey != NULL) - tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr, - newkey, key->keylen); + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, + AF_INET, key->key, key->keylen, GFP_ATOMIC); + sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif - __inet_hash_nolisten(newsk); - __inet_inherit_port(sk, newsk); + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; + __inet_hash_nolisten(newsk, NULL); return newsk; exit_overflow: - NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); -exit: - NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +exit_nonewsk: dst_release(dst); +exit: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; +put_and_exit: + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); + goto exit; } +EXPORT_SYMBOL(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) { @@ -1485,9 +1507,9 @@ 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(sk->sk_net, &tcp_hashinfo, iph->saddr, + nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (nsk) { @@ -1500,34 +1522,12 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) } #ifdef CONFIG_SYN_COOKIES - if (!th->rst && !th->syn && th->ack) + if (!th->syn) sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt)); #endif return sk; } -static __sum16 tcp_v4_checksum_init(struct sk_buff *skb) -{ - const struct iphdr *iph = ip_hdr(skb); - - if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!tcp_v4_check(skb->len, iph->saddr, - iph->daddr, skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - return 0; - } - } - - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb->len, IPPROTO_TCP, 0); - - if (skb->len <= 76) { - return __skb_checksum_complete(skb); - } - return 0; -} - - /* The socket must have it's spinlock held when we get * here. * @@ -1551,12 +1551,17 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - TCP_CHECK_TIMER(sk); - if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { - rsk = sk; - goto reset; + struct dst_entry *dst = sk->sk_rx_dst; + + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, 0) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } } - TCP_CHECK_TIMER(sk); + tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len); return 0; } @@ -1569,20 +1574,20 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; } return 0; } - } + } else + sock_rps_save_rxhash(sk, skb); - TCP_CHECK_TIMER(sk); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; } - TCP_CHECK_TIMER(sk); return 0; reset: @@ -1597,9 +1602,93 @@ discard: return 0; csum_err: - TCP_INC_STATS_BH(TCP_MIB_INERRS); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); goto discard; } +EXPORT_SYMBOL(tcp_v4_do_rcv); + +void tcp_v4_early_demux(struct sk_buff *skb) +{ + const struct iphdr *iph; + const struct tcphdr *th; + struct sock *sk; + + if (skb->pkt_type != PACKET_HOST) + return; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return; + + iph = ip_hdr(skb); + th = tcp_hdr(skb); + + if (th->doff < sizeof(struct tcphdr) / 4) + return; + + sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, + iph->daddr, ntohs(th->dest), + skb->skb_iif); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + + if (dst) + dst = dst_check(dst, 0); + if (dst && + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) + skb_dst_set_noref(skb, dst); + } + } +} + +/* Packet is added to VJ-style prequeue for processing in process + * context, if a reader task is waiting. Apparently, this exciting + * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93) + * failed somewhere. Latency? Burstiness? Well, at least now we will + * see, why it failed. 8)8) --ANK + * + */ +bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (sysctl_tcp_low_latency || !tp->ucopy.task) + return false; + + if (skb->len <= tcp_hdrlen(skb) && + skb_queue_len(&tp->ucopy.prequeue) == 0) + return false; + + skb_dst_force(skb); + __skb_queue_tail(&tp->ucopy.prequeue, skb); + tp->ucopy.memory += skb->truesize; + if (tp->ucopy.memory > sk->sk_rcvbuf) { + struct sk_buff *skb1; + + BUG_ON(sock_owned_by_user(sk)); + + while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) { + sk_backlog_rcv(sk, skb1); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPPREQUEUEDROPPED); + } + + tp->ucopy.memory = 0; + } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) { + wake_up_interruptible_sync_poll(sk_sleep(sk), + POLLIN | POLLRDNORM | POLLRDBAND); + if (!inet_csk_ack_scheduled(sk)) + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, + (3 * tcp_rto_min(sk)) / 4, + TCP_RTO_MAX); + } + return true; +} +EXPORT_SYMBOL(tcp_prequeue); /* * From tcp_input.c @@ -1608,15 +1697,16 @@ csum_err: int tcp_v4_rcv(struct sk_buff *skb) { const struct iphdr *iph; - struct tcphdr *th; + const struct tcphdr *th; struct sock *sk; int ret; + struct net *net = dev_net(skb->dev); if (skb->pkt_type != PACKET_HOST) goto discard_it; /* Count it even if it's bad */ - TCP_INC_STATS_BH(TCP_MIB_INSEGS); + TCP_INC_STATS_BH(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; @@ -1632,8 +1722,9 @@ int tcp_v4_rcv(struct sk_buff *skb) * Packet length and doff are validated by header prediction, * provided case of th->doff==0 is eliminated. * So, we defer the checks. */ - if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb)) - goto bad_packet; + + if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) + goto csum_error; th = tcp_hdr(skb); iph = ip_hdr(skb); @@ -1642,11 +1733,10 @@ int tcp_v4_rcv(struct sk_buff *skb) skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->when = 0; - TCP_SKB_CB(skb)->flags = iph->tos; + TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; - sk = __inet_lookup(skb->dev->nd_net, &tcp_hashinfo, iph->saddr, - th->source, iph->daddr, th->dest, inet_iif(skb)); + sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); if (!sk) goto no_tcp_socket; @@ -1654,6 +1744,11 @@ process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto discard_and_relse; + } + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; nf_reset(skb); @@ -1661,6 +1756,7 @@ process: if (sk_filter(sk, skb)) goto discard_and_relse; + sk_mark_napi_id(sk, skb); skb->dev = NULL; bh_lock_sock_nested(sk); @@ -1669,17 +1765,21 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = get_softnet_dma(); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v4_do_rcv(sk, skb); else #endif { if (!tcp_prequeue(sk, skb)) - ret = tcp_v4_do_rcv(sk, skb); + ret = tcp_v4_do_rcv(sk, skb); } - } else - sk_add_backlog(sk, skb); + } else if (unlikely(sk_add_backlog(sk, skb, + sk->sk_rcvbuf + sk->sk_sndbuf))) { + bh_unlock_sock(sk); + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); + goto discard_and_relse; + } bh_unlock_sock(sk); sock_put(sk); @@ -1691,8 +1791,10 @@ no_tcp_socket: goto discard_it; if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) { +csum_error: + TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: - TCP_INC_STATS_BH(TCP_MIB_INERRS); + TCP_INC_STATS_BH(net, TCP_MIB_INERRS); } else { tcp_v4_send_reset(NULL, skb); } @@ -1712,15 +1814,19 @@ do_time_wait: goto discard_it; } - if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) { - TCP_INC_STATS_BH(TCP_MIB_INERRS); + if (skb->len < (th->doff << 2)) { inet_twsk_put(inet_twsk(sk)); - goto discard_it; + goto bad_packet; + } + if (tcp_checksum_complete(skb)) { + inet_twsk_put(inet_twsk(sk)); + goto csum_error; } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { - struct sock *sk2 = inet_lookup_listener(skb->dev->nd_net, + struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (sk2) { @@ -1741,71 +1847,29 @@ do_time_wait: goto discard_it; } -/* VJ's idea. Save last timestamp seen from this destination - * and hold it at least for normal timewait interval to use for duplicate - * segment detection in subsequent connections, before they enter synchronized - * state. - */ - -int tcp_v4_remember_stamp(struct sock *sk) -{ - struct inet_sock *inet = inet_sk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct rtable *rt = (struct rtable *)__sk_dst_get(sk); - struct inet_peer *peer = NULL; - int release_it = 0; - - if (!rt || rt->rt_dst != inet->daddr) { - peer = inet_getpeer(inet->daddr, 1); - release_it = 1; - } else { - if (!rt->peer) - rt_bind_peer(rt, 1); - peer = rt->peer; - } - - if (peer) { - if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || - (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() && - peer->tcp_ts_stamp <= tp->rx_opt.ts_recent_stamp)) { - peer->tcp_ts_stamp = tp->rx_opt.ts_recent_stamp; - peer->tcp_ts = tp->rx_opt.ts_recent; - } - if (release_it) - inet_putpeer(peer); - return 1; - } - - return 0; -} +static struct timewait_sock_ops tcp_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct tcp_timewait_sock), + .twsk_unique = tcp_twsk_unique, + .twsk_destructor= tcp_twsk_destructor, +}; -int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) +void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { - struct inet_peer *peer = inet_getpeer(tw->tw_daddr, 1); - - if (peer) { - const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); - - if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || - (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() && - peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) { - peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp; - peer->tcp_ts = tcptw->tw_ts_recent; - } - inet_putpeer(peer); - return 1; - } + struct dst_entry *dst = skb_dst(skb); - return 0; + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } +EXPORT_SYMBOL(inet_sk_rx_dst_set); -struct inet_connection_sock_af_ops ipv4_specific = { +const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, - .remember_stamp = tcp_v4_remember_stamp, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, @@ -1817,12 +1881,12 @@ struct inet_connection_sock_af_ops ipv4_specific = { .compat_getsockopt = compat_ip_getsockopt, #endif }; +EXPORT_SYMBOL(ipv4_specific); #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv4_specific = { +static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .md5_lookup = tcp_v4_md5_lookup, - .calc_md5_hash = tcp_v4_calc_md5_hash, - .md5_add = tcp_v4_md5_add_func, + .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, }; #endif @@ -1833,52 +1897,19 @@ static struct tcp_sock_af_ops tcp_sock_ipv4_specific = { static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - - skb_queue_head_init(&tp->out_of_order_queue); - tcp_init_xmit_timers(sk); - tcp_prequeue_init(tp); - icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - tp->snd_cwnd = 2; - - /* See draft-stevens-tcpca-spec-01 for discussion of the - * initialization of these values. - */ - tp->snd_ssthresh = 0x7fffffff; /* Infinity */ - tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; - - tp->reordering = sysctl_tcp_reordering; - icsk->icsk_ca_ops = &tcp_init_congestion_ops; - - sk->sk_state = TCP_CLOSE; - - sk->sk_write_space = sk_stream_write_space; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; - icsk->icsk_sync_mss = tcp_sync_mss; + #ifdef CONFIG_TCP_MD5SIG - tp->af_specific = &tcp_sock_ipv4_specific; + tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - - atomic_inc(&tcp_sockets_allocated); - return 0; } -int tcp_v4_destroy_sock(struct sock *sk) +void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -1895,8 +1926,8 @@ int tcp_v4_destroy_sock(struct sock *sk) #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { - tcp_v4_clear_md5_list(sk); - kfree(tp->md5sig_info); + tcp_clear_md5_list(sk); + kfree_rcu(tp->md5sig_info, rcu); tp->md5sig_info = NULL; } #endif @@ -1913,50 +1944,43 @@ int tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - /* - * If sendmsg cached page exists, toss it. - */ - if (sk->sk_sndmsg_page) { - __free_page(sk->sk_sndmsg_page); - sk->sk_sndmsg_page = NULL; - } + BUG_ON(tp->fastopen_rsk != NULL); - atomic_dec(&tcp_sockets_allocated); + /* If socket is aborted during connect operation */ + tcp_free_fastopen_req(tp); - return 0; + sk_sockets_allocated_dec(sk); + sock_release_memcg(sk); } - EXPORT_SYMBOL(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ -static inline struct inet_timewait_sock *tw_head(struct hlist_head *head) -{ - return hlist_empty(head) ? NULL : - list_entry(head->first, struct inet_timewait_sock, tw_node); -} - -static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw) -{ - return tw->tw_node.next ? - hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL; -} - +/* + * Get next listener socket follow cur. If cur is NULL, get first socket + * starting from bucket given in st->bucket; when st->bucket is zero the + * very first socket in the hash table is returned. + */ static void *listening_get_next(struct seq_file *seq, void *cur) { struct inet_connection_sock *icsk; - struct hlist_node *node; + struct hlist_nulls_node *node; struct sock *sk = cur; - struct tcp_iter_state* st = seq->private; + struct inet_listen_hashbucket *ilb; + struct tcp_iter_state *st = seq->private; + struct net *net = seq_file_net(seq); if (!sk) { - st->bucket = 0; - sk = sk_head(&tcp_hashinfo.listening_hash[0]); + ilb = &tcp_hashinfo.listening_hash[st->bucket]; + spin_lock_bh(&ilb->lock); + sk = sk_nulls_head(&ilb->head); + st->offset = 0; goto get_sk; } - + ilb = &tcp_hashinfo.listening_hash[st->bucket]; ++st->num; + ++st->offset; if (st->state == TCP_SEQ_STATE_OPENREQ) { struct request_sock *req = cur; @@ -1976,7 +2000,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) get_req: req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket]; } - sk = sk_next(st->syn_wait_sk); + sk = sk_nulls_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } else { @@ -1985,10 +2009,12 @@ get_req: if (reqsk_queue_len(&icsk->icsk_accept_queue)) goto start_req; read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - sk = sk_next(sk); + sk = sk_nulls_next(sk); } get_sk: - sk_for_each_from(sk, node) { + sk_nulls_for_each_from(sk, node) { + if (!net_eq(sock_net(sk), net)) + continue; if (sk->sk_family == st->family) { cur = sk; goto out; @@ -2005,8 +2031,12 @@ start_req: } read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } + spin_unlock_bh(&ilb->lock); + st->offset = 0; if (++st->bucket < INET_LHTABLE_SIZE) { - sk = sk_head(&tcp_hashinfo.listening_hash[st->bucket]); + ilb = &tcp_hashinfo.listening_hash[st->bucket]; + spin_lock_bh(&ilb->lock); + sk = sk_nulls_head(&ilb->head); goto get_sk; } cur = NULL; @@ -2016,7 +2046,12 @@ out: static void *listening_get_idx(struct seq_file *seq, loff_t *pos) { - void *rc = listening_get_next(seq, NULL); + struct tcp_iter_state *st = seq->private; + void *rc; + + st->bucket = 0; + st->offset = 0; + rc = listening_get_next(seq, NULL); while (rc && *pos) { rc = listening_get_next(seq, rc); @@ -2025,36 +2060,41 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos) return rc; } +static inline bool empty_bucket(const struct tcp_iter_state *st) +{ + return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain); +} + +/* + * Get first established socket starting from bucket given in st->bucket. + * If st->bucket is zero, the very first socket in the hash is returned. + */ static void *established_get_first(struct seq_file *seq) { - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; + struct net *net = seq_file_net(seq); void *rc = NULL; - for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) { + st->offset = 0; + for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { struct sock *sk; - struct hlist_node *node; - struct inet_timewait_sock *tw; - rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); + struct hlist_nulls_node *node; + spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); + + /* Lockless fast path for the common case of empty buckets */ + if (empty_bucket(st)) + continue; - read_lock_bh(lock); - sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { - if (sk->sk_family != st->family) { + spin_lock_bh(lock); + sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { + if (sk->sk_family != st->family || + !net_eq(sock_net(sk), net)) { continue; } rc = sk; goto out; } - st->state = TCP_SEQ_STATE_TIME_WAIT; - inet_twsk_for_each(tw, node, - &tcp_hashinfo.ehash[st->bucket].twchain) { - if (tw->tw_family != st->family) { - continue; - } - rc = tw; - goto out; - } - read_unlock_bh(lock); - st->state = TCP_SEQ_STATE_ESTABLISHED; + spin_unlock_bh(lock); } out: return rc; @@ -2063,53 +2103,32 @@ out: static void *established_get_next(struct seq_file *seq, void *cur) { struct sock *sk = cur; - struct inet_timewait_sock *tw; - struct hlist_node *node; - struct tcp_iter_state* st = seq->private; + struct hlist_nulls_node *node; + struct tcp_iter_state *st = seq->private; + struct net *net = seq_file_net(seq); ++st->num; + ++st->offset; - if (st->state == TCP_SEQ_STATE_TIME_WAIT) { - tw = cur; - tw = tw_next(tw); -get_tw: - while (tw && tw->tw_family != st->family) { - tw = tw_next(tw); - } - if (tw) { - cur = tw; - goto out; - } - read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); - st->state = TCP_SEQ_STATE_ESTABLISHED; - - if (++st->bucket < tcp_hashinfo.ehash_size) { - read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); - sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain); - } else { - cur = NULL; - goto out; - } - } else - sk = sk_next(sk); + sk = sk_nulls_next(sk); - sk_for_each_from(sk, node) { - if (sk->sk_family == st->family) - goto found; + sk_nulls_for_each_from(sk, node) { + if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) + return sk; } - st->state = TCP_SEQ_STATE_TIME_WAIT; - tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain); - goto get_tw; -found: - cur = sk; -out: - return cur; + spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + ++st->bucket; + return established_get_first(seq); } static void *established_get_idx(struct seq_file *seq, loff_t pos) { - void *rc = established_get_first(seq); + struct tcp_iter_state *st = seq->private; + void *rc; + + st->bucket = 0; + rc = established_get_first(seq); while (rc && pos) { rc = established_get_next(seq, rc); @@ -2121,14 +2140,12 @@ static void *established_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_get_idx(struct seq_file *seq, loff_t pos) { void *rc; - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; - inet_listen_lock(&tcp_hashinfo); st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_idx(seq, &pos); if (!rc) { - inet_listen_unlock(&tcp_hashinfo); st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } @@ -2136,48 +2153,96 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) return rc; } +static void *tcp_seek_last_pos(struct seq_file *seq) +{ + struct tcp_iter_state *st = seq->private; + int offset = st->offset; + int orig_num = st->num; + void *rc = NULL; + + switch (st->state) { + case TCP_SEQ_STATE_OPENREQ: + case TCP_SEQ_STATE_LISTENING: + if (st->bucket >= INET_LHTABLE_SIZE) + break; + st->state = TCP_SEQ_STATE_LISTENING; + rc = listening_get_next(seq, NULL); + while (offset-- && rc) + rc = listening_get_next(seq, rc); + if (rc) + break; + st->bucket = 0; + st->state = TCP_SEQ_STATE_ESTABLISHED; + /* Fallthrough */ + case TCP_SEQ_STATE_ESTABLISHED: + if (st->bucket > tcp_hashinfo.ehash_mask) + break; + rc = established_get_first(seq); + while (offset-- && rc) + rc = established_get_next(seq, rc); + } + + st->num = orig_num; + + return rc; +} + static void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; + void *rc; + + if (*pos && *pos == st->last_pos) { + rc = tcp_seek_last_pos(seq); + if (rc) + goto out; + } + st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; - return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + st->bucket = 0; + st->offset = 0; + rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + +out: + st->last_pos = *pos; + return rc; } static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct tcp_iter_state *st = seq->private; void *rc = NULL; - struct tcp_iter_state* st; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); goto out; } - st = seq->private; switch (st->state) { case TCP_SEQ_STATE_OPENREQ: case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { - inet_listen_unlock(&tcp_hashinfo); st->state = TCP_SEQ_STATE_ESTABLISHED; + st->bucket = 0; + st->offset = 0; rc = established_get_first(seq); } break; case TCP_SEQ_STATE_ESTABLISHED: - case TCP_SEQ_STATE_TIME_WAIT: rc = established_get_next(seq, v); break; } out: ++*pos; + st->last_pos = *pos; return rc; } static void tcp_seq_stop(struct seq_file *seq, void *v) { - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_OPENREQ: @@ -2187,114 +2252,98 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) - inet_listen_unlock(&tcp_hashinfo); + spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock); break; - case TCP_SEQ_STATE_TIME_WAIT: case TCP_SEQ_STATE_ESTABLISHED: if (v) - read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); break; } } -static int tcp_seq_open(struct inode *inode, struct file *file) +int tcp_seq_open(struct inode *inode, struct file *file) { - struct tcp_seq_afinfo *afinfo = PDE(inode)->data; - struct seq_file *seq; + struct tcp_seq_afinfo *afinfo = PDE_DATA(inode); struct tcp_iter_state *s; - int rc; + int err; - if (unlikely(afinfo == NULL)) - return -EINVAL; + err = seq_open_net(inode, file, &afinfo->seq_ops, + sizeof(struct tcp_iter_state)); + if (err < 0) + return err; - s = kzalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; + s = ((struct seq_file *)file->private_data)->private; s->family = afinfo->family; - s->seq_ops.start = tcp_seq_start; - s->seq_ops.next = tcp_seq_next; - s->seq_ops.show = afinfo->seq_show; - s->seq_ops.stop = tcp_seq_stop; - - rc = seq_open(file, &s->seq_ops); - if (rc) - goto out_kfree; - seq = file->private_data; - seq->private = s; -out: - return rc; -out_kfree: - kfree(s); - goto out; + s->last_pos = 0; + return 0; } +EXPORT_SYMBOL(tcp_seq_open); -int tcp_proc_register(struct tcp_seq_afinfo *afinfo) +int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo) { int rc = 0; struct proc_dir_entry *p; - if (!afinfo) - return -EINVAL; - afinfo->seq_fops->owner = afinfo->owner; - afinfo->seq_fops->open = tcp_seq_open; - afinfo->seq_fops->read = seq_read; - afinfo->seq_fops->llseek = seq_lseek; - afinfo->seq_fops->release = seq_release_private; - - p = proc_net_fops_create(&init_net, afinfo->name, S_IRUGO, afinfo->seq_fops); - if (p) - p->data = afinfo; - else + afinfo->seq_ops.start = tcp_seq_start; + afinfo->seq_ops.next = tcp_seq_next; + afinfo->seq_ops.stop = tcp_seq_stop; + + p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, + afinfo->seq_fops, afinfo); + if (!p) rc = -ENOMEM; return rc; } +EXPORT_SYMBOL(tcp_proc_register); -void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo) +void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) { - if (!afinfo) - return; - proc_net_remove(&init_net, afinfo->name); - memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); + remove_proc_entry(afinfo->name, net->proc_net); } +EXPORT_SYMBOL(tcp_proc_unregister); -static void get_openreq4(struct sock *sk, struct request_sock *req, - char *tmpbuf, int i, int uid) +static void get_openreq4(const struct sock *sk, const struct request_sock *req, + struct seq_file *f, int i, kuid_t uid) { const struct inet_request_sock *ireq = inet_rsk(req); - int ttd = req->expires - jiffies; + long delta = req->expires - jiffies; - sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p", + seq_printf(f, "%4d: %08X:%04X %08X:%04X" + " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", i, - ireq->loc_addr, - ntohs(inet_sk(sk)->sport), - ireq->rmt_addr, - ntohs(ireq->rmt_port), + ireq->ir_loc_addr, + ntohs(inet_sk(sk)->inet_sport), + ireq->ir_rmt_addr, + ntohs(ireq->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ - jiffies_to_clock_t(ttd), - req->retrans, - uid, + jiffies_delta_to_clock_t(delta), + req->num_timeout, + from_kuid_munged(seq_user_ns(f), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ atomic_read(&sk->sk_refcnt), req); } -static void get_tcp4_sock(struct sock *sk, char *tmpbuf, int i) +static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) { int timer_active; unsigned long timer_expires; - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_sock *inet = inet_sk(sk); - __be32 dest = inet->daddr; - __be32 src = inet->rcv_saddr; - __u16 destp = ntohs(inet->dport); - __u16 srcp = ntohs(inet->sport); - - if (icsk->icsk_pending == ICSK_TIME_RETRANS) { + 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); + __u16 srcp = ntohs(inet->inet_sport); + int rx_queue; + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk->icsk_timeout; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { @@ -2308,45 +2357,51 @@ static void get_tcp4_sock(struct sock *sk, char *tmpbuf, int i) timer_expires = jiffies; } - sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " - "%08X %5d %8d %lu %d %p %u %u %u %u %d", + if (sk->sk_state == TCP_LISTEN) + rx_queue = sk->sk_ack_backlog; + else + /* + * because we dont lock socket, we might find a transient negative value + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + + seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " + "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, - sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog : - (tp->rcv_nxt - tp->copied_seq), + rx_queue, timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + 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, - icsk->icsk_rto, - icsk->icsk_ack.ato, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh); + sk->sk_state == TCP_LISTEN ? + (fastopenq ? fastopenq->max_qlen : 0) : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } -static void get_timewait4_sock(struct inet_timewait_sock *tw, - char *tmpbuf, int i) +static void get_timewait4_sock(const struct inet_timewait_sock *tw, + struct seq_file *f, int i) { __be32 dest, src; __u16 destp, srcp; - int ttd = tw->tw_ttd - jiffies; - - if (ttd < 0) - ttd = 0; + s32 delta = tw->tw_ttd - inet_tw_time_stamp(); dest = tw->tw_daddr; src = tw->tw_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); - sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p", + seq_printf(f, "%4d: %08X:%04X %08X:%04X" + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw); } @@ -2354,12 +2409,12 @@ static void get_timewait4_sock(struct inet_timewait_sock *tw, static int tcp4_seq_show(struct seq_file *seq, void *v) { - struct tcp_iter_state* st; - char tmpbuf[TMPSZ + 1]; + struct tcp_iter_state *st; + struct sock *sk = v; + seq_setwidth(seq, TMPSZ - 1); if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-*s\n", TMPSZ - 1, - " sl local_address rem_address st tx_queue " + seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode"); goto out; @@ -2369,42 +2424,63 @@ static int tcp4_seq_show(struct seq_file *seq, void *v) switch (st->state) { case TCP_SEQ_STATE_LISTENING: case TCP_SEQ_STATE_ESTABLISHED: - get_tcp4_sock(v, tmpbuf, st->num); + if (sk->sk_state == TCP_TIME_WAIT) + get_timewait4_sock(v, seq, st->num); + else + get_tcp4_sock(v, seq, st->num); break; case TCP_SEQ_STATE_OPENREQ: - get_openreq4(st->syn_wait_sk, v, tmpbuf, st->num, st->uid); - break; - case TCP_SEQ_STATE_TIME_WAIT: - get_timewait4_sock(v, tmpbuf, st->num); + get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid); break; } - seq_printf(seq, "%-*s\n", TMPSZ - 1, tmpbuf); out: + seq_pad(seq, '\n'); return 0; } -static struct file_operations tcp4_seq_fops; +static const struct file_operations tcp_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = tcp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct tcp_seq_afinfo tcp4_seq_afinfo = { - .owner = THIS_MODULE, .name = "tcp", .family = AF_INET, - .seq_show = tcp4_seq_show, - .seq_fops = &tcp4_seq_fops, + .seq_fops = &tcp_afinfo_seq_fops, + .seq_ops = { + .show = tcp4_seq_show, + }, +}; + +static int __net_init tcp4_proc_init_net(struct net *net) +{ + return tcp_proc_register(net, &tcp4_seq_afinfo); +} + +static void __net_exit tcp4_proc_exit_net(struct net *net) +{ + tcp_proc_unregister(net, &tcp4_seq_afinfo); +} + +static struct pernet_operations tcp4_net_ops = { + .init = tcp4_proc_init_net, + .exit = tcp4_proc_exit_net, }; int __init tcp4_proc_init(void) { - return tcp_proc_register(&tcp4_seq_afinfo); + return register_pernet_subsys(&tcp4_net_ops); } void tcp4_proc_exit(void) { - tcp_proc_unregister(&tcp4_seq_afinfo); + unregister_pernet_subsys(&tcp4_net_ops); } #endif /* CONFIG_PROC_FS */ -DEFINE_PROTO_INUSE(tcp) - struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, @@ -2419,11 +2495,16 @@ struct proto tcp_prot = { .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .recvmsg = tcp_recvmsg, + .sendmsg = tcp_sendmsg, + .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, + .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, @@ -2433,36 +2514,47 @@ struct proto tcp_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, - .hashinfo = &tcp_hashinfo, + .h.hashinfo = &tcp_hashinfo, + .no_autobind = true, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif - REF_PROTO_INUSE(tcp) +#ifdef CONFIG_MEMCG_KMEM + .init_cgroup = tcp_init_cgroup, + .destroy_cgroup = tcp_destroy_cgroup, + .proto_cgroup = tcp_proto_cgroup, +#endif }; +EXPORT_SYMBOL(tcp_prot); -void __init tcp_v4_init(struct net_proto_family *ops) +static int __net_init tcp_sk_init(struct net *net) { - if (inet_csk_ctl_sock_create(&tcp_socket, PF_INET, SOCK_RAW, - IPPROTO_TCP) < 0) - panic("Failed to create the TCP control socket.\n"); + net->ipv4.sysctl_tcp_ecn = 2; + return 0; } -EXPORT_SYMBOL(ipv4_specific); -EXPORT_SYMBOL(tcp_hashinfo); -EXPORT_SYMBOL(tcp_prot); -EXPORT_SYMBOL(tcp_v4_conn_request); -EXPORT_SYMBOL(tcp_v4_connect); -EXPORT_SYMBOL(tcp_v4_do_rcv); -EXPORT_SYMBOL(tcp_v4_remember_stamp); -EXPORT_SYMBOL(tcp_v4_send_check); -EXPORT_SYMBOL(tcp_v4_syn_recv_sock); +static void __net_exit tcp_sk_exit(struct net *net) +{ +} -#ifdef CONFIG_PROC_FS -EXPORT_SYMBOL(tcp_proc_register); -EXPORT_SYMBOL(tcp_proc_unregister); -#endif -EXPORT_SYMBOL(sysctl_tcp_low_latency); +static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET); +} + +static struct pernet_operations __net_initdata tcp_sk_ops = { + .init = tcp_sk_init, + .exit = tcp_sk_exit, + .exit_batch = tcp_sk_exit_batch, +}; +void __init tcp_v4_init(void) +{ + inet_hashinfo_init(&tcp_hashinfo); + if (register_pernet_subsys(&tcp_sk_ops)) + panic("Failed to create the TCP control socket.\n"); +} |