diff options
Diffstat (limited to '')
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 3034 |
1 files changed, 3034 insertions, 0 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c new file mode 100644 index 000000000..7a94acbd9 --- /dev/null +++ b/net/ipv4/tcp_ipv4.c @@ -0,0 +1,3034 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Implementation of the Transmission Control Protocol(TCP). + * + * IPv4 specific functions + * + * code split from: + * linux/ipv4/tcp.c + * linux/ipv4/tcp_input.c + * linux/ipv4/tcp_output.c + * + * See tcp.c for author information + */ + +/* + * Changes: + * David S. Miller : New socket lookup architecture. + * This code is dedicated to John Dyson. + * David S. Miller : Change semantics of established hash, + * half is devoted to TIME_WAIT sockets + * and the rest go in the other half. + * Andi Kleen : Add support for syncookies and fixed + * some bugs: ip options weren't passed to + * the TCP layer, missed a check for an + * ACK bit. + * Andi Kleen : Implemented fast path mtu discovery. + * Fixed many serious bugs in the + * request_sock handling and moved + * most of it into the af independent code. + * Added tail drop and some other bugfixes. + * Added new listen semantics. + * Mike McLagan : Routing by source + * Juan Jose Ciarlante: ip_dynaddr bits + * Andi Kleen: various fixes. + * Vitaly E. Lavrov : Transparent proxy revived after year + * coma. + * Andi Kleen : Fix new listen. + * Andi Kleen : Fix accept error reporting. + * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which + * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind + * 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> +#include <linux/random.h> +#include <linux/cache.h> +#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> +#include <net/inet_hashtables.h> +#include <net/tcp.h> +#include <net/transp_v6.h> +#include <net/ipv6.h> +#include <net/inet_common.h> +#include <net/timewait_sock.h> +#include <net/xfrm.h> +#include <net/secure_seq.h> +#include <net/busy_poll.h> + +#include <linux/inet.h> +#include <linux/ipv6.h> +#include <linux/stddef.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/inetdevice.h> +#include <linux/btf_ids.h> + +#include <crypto/hash.h> +#include <linux/scatterlist.h> + +#include <trace/events/tcp.h> + +#ifdef CONFIG_TCP_MD5SIG +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 tcp_hashinfo; +EXPORT_SYMBOL(tcp_hashinfo); + +static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); + +static u32 tcp_v4_init_seq(const struct sk_buff *skb) +{ + return secure_tcp_seq(ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); +} + +static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) +{ + return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); +} + +int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) +{ + int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); + const struct inet_timewait_sock *tw = inet_twsk(sktw); + const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); + struct tcp_sock *tp = tcp_sk(sk); + + if (reuse == 2) { + /* Still does not detect *everything* that goes through + * lo, since we require a loopback src or dst address + * or direct binding to 'lo' interface. + */ + bool loopback = false; + if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX) + loopback = true; +#if IS_ENABLED(CONFIG_IPV6) + if (tw->tw_family == AF_INET6) { + if (ipv6_addr_loopback(&tw->tw_v6_daddr) || + ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) || + ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || + ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr)) + loopback = true; + } else +#endif + { + if (ipv4_is_loopback(tw->tw_daddr) || + ipv4_is_loopback(tw->tw_rcv_saddr)) + loopback = true; + } + if (!loopback) + reuse = 0; + } + + /* With PAWS, it is safe from the viewpoint + of data integrity. Even without PAWS it is safe provided sequence + spaces do not overlap i.e. at data rates <= 80Mbit/sec. + + Actually, the idea is close to VJ's one, only timestamp cache is + held not per host, but per port pair and TW bucket is used as state + holder. + + If TW bucket has been already destroyed we fall back to VJ's scheme + and use initial timestamp retrieved from peer table. + */ + if (tcptw->tw_ts_recent_stamp && + (!twp || (reuse && time_after32(ktime_get_seconds(), + tcptw->tw_ts_recent_stamp)))) { + /* In case of repair and re-using TIME-WAIT sockets we still + * want to be sure that it is safe as above but honor the + * sequence numbers and time stamps set as part of the repair + * process. + * + * Without this check re-using a TIME-WAIT socket with TCP + * repair would accumulate a -1 on the repair assigned + * sequence number. The first time it is reused the sequence + * is -1, the second time -2, etc. This fixes that issue + * without appearing to create any others. + */ + if (likely(!tp->repair)) { + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + tp->rx_opt.ts_recent = tcptw->tw_ts_recent; + tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + } + sock_hold(sktw); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(tcp_twsk_unique); + +static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + /* This check is replicated from tcp_v4_connect() and intended to + * prevent BPF program called below from accessing bytes that are out + * of the bound specified by user in addr_len. + */ + if (addr_len < sizeof(struct sockaddr_in)) + return -EINVAL; + + sock_owned_by_me(sk); + + return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); +} + +/* 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); + __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; + struct flowi4 *fl4; + struct rtable *rt; + int err; + struct ip_options_rcu *inet_opt; + struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; + + if (addr_len < sizeof(struct sockaddr_in)) + return -EINVAL; + + if (usin->sin_family != AF_INET) + return -EAFNOSUPPORT; + + nexthop = daddr = usin->sin_addr.s_addr; + inet_opt = rcu_dereference_protected(inet->inet_opt, + lockdep_sock_is_held(sk)); + if (inet_opt && inet_opt->opt.srr) { + if (!daddr) + return -EINVAL; + nexthop = inet_opt->opt.faddr; + } + + 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)) { + ip_rt_put(rt); + return -ENETUNREACH; + } + + if (!inet_opt || !inet_opt->opt.srr) + daddr = fl4->daddr; + + if (!inet->inet_saddr) + inet->inet_saddr = fl4->saddr; + sk_rcv_saddr_set(sk, inet->inet_saddr); + + 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; + if (likely(!tp->repair)) + WRITE_ONCE(tp->write_seq, 0); + } + + inet->inet_dport = usin->sin_port; + sk_daddr_set(sk, daddr); + + inet_csk(sk)->icsk_ext_hdr_len = 0; + if (inet_opt) + inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; + + 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 + * lock select source port, enter ourselves into the hash tables and + * complete initialization after this. + */ + tcp_set_state(sk, TCP_SYN_SENT); + err = inet_hash_connect(tcp_death_row, sk); + if (err) + goto failure; + + sk_set_txhash(sk); + + 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->dst); + rt = NULL; + + if (likely(!tp->repair)) { + if (!tp->write_seq) + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); + tp->tsoffset = secure_tcp_ts_off(sock_net(sk), + inet->inet_saddr, + inet->inet_daddr); + } + + inet->inet_id = prandom_u32(); + + if (tcp_fastopen_defer_connect(sk, &err)) + return err; + if (err) + goto failure; + + err = tcp_connect(sk); + + if (err) + goto failure; + + return 0; + +failure: + /* + * This unhashes the socket and releases the local port, + * if necessary. + */ + tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); + ip_rt_put(rt); + sk->sk_route_caps = 0; + inet->inet_dport = 0; + return err; +} +EXPORT_SYMBOL(tcp_v4_connect); + +/* + * 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. + */ +void tcp_v4_mtu_reduced(struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + struct dst_entry *dst; + u32 mtu; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) + return; + + /* Something is about to be wrong... Remember soft error + * for the case, if this connection will not able to recover. + */ + if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst)) + sk->sk_err_soft = EMSGSIZE; + + 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); + + /* Resend the TCP packet because it's + * clear that the old packet has been + * dropped. This is the new "fast" path mtu + * discovery. + */ + tcp_simple_retransmit(sk); + } /* else let the usual retransmit timer handle it */ +} +EXPORT_SYMBOL(tcp_v4_mtu_reduced); + +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); +} + + +/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ +void tcp_req_err(struct sock *sk, u32 seq, bool abort) +{ + struct request_sock *req = inet_reqsk(sk); + struct net *net = sock_net(sk); + + /* ICMPs are not backlogged, hence we cannot get + * an established socket here. + */ + if (seq != tcp_rsk(req)->snt_isn) { + __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); + } else if (abort) { + /* + * Still in SYN_RECV, just remove it silently. + * There is no good way to pass the error to the newly + * created socket, and POSIX does not want network + * errors returned from accept(). + */ + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + tcp_listendrop(req->rsk_listener); + } + reqsk_put(req); +} +EXPORT_SYMBOL(tcp_req_err); + +/* TCP-LD (RFC 6069) logic */ +void tcp_ld_RTO_revert(struct sock *sk, u32 seq) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + s32 remaining; + u32 delta_us; + + if (sock_owned_by_user(sk)) + return; + + if (seq != tp->snd_una || !icsk->icsk_retransmits || + !icsk->icsk_backoff) + return; + + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + return; + + icsk->icsk_backoff--; + icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; + icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); + + tcp_mstamp_refresh(tp); + delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); + remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); + + if (remaining > 0) { + 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); + } +} +EXPORT_SYMBOL(tcp_ld_RTO_revert); + +/* + * This routine is called by the ICMP module when it gets some + * sort of error condition. If err < 0 then the socket should + * be closed and the error returned to the user. If err > 0 + * it's just the icmp type << 8 | icmp code. After adjustment + * header points to the first 8 bytes of the tcp header. We need + * to find the appropriate port. + * + * The locking strategy used here is very "optimistic". When + * someone else accesses the socket the ICMP is just dropped + * and for some paths there is no check at all. + * A more general error queue to queue errors for later handling + * is probably better. + * + */ + +int tcp_v4_err(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); + struct tcp_sock *tp; + struct inet_sock *inet; + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct sock *sk; + struct request_sock *fastopen; + u32 seq, snd_una; + int err; + struct net *net = dev_net(skb->dev); + + sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, + th->dest, iph->saddr, ntohs(th->source), + inet_iif(skb), 0); + if (!sk) { + __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); + return -ENOENT; + } + if (sk->sk_state == TCP_TIME_WAIT) { + inet_twsk_put(inet_twsk(sk)); + return 0; + } + seq = ntohl(th->seq); + if (sk->sk_state == TCP_NEW_SYN_RECV) { + tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB || + type == ICMP_TIME_EXCEEDED || + (type == ICMP_DEST_UNREACH && + (code == ICMP_NET_UNREACH || + code == ICMP_HOST_UNREACH))); + return 0; + } + + 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)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); + } + if (sk->sk_state == TCP_CLOSE) + goto out; + + if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { + __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); + goto out; + } + + tp = tcp_sk(sk); + /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ + fastopen = rcu_dereference(tp->fastopen_rsk); + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; + if (sk->sk_state != TCP_LISTEN && + !between(seq, snd_una, tp->snd_nxt)) { + __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); + goto out; + } + + switch (type) { + case ICMP_REDIRECT: + if (!sock_owned_by_user(sk)) + do_redirect(skb, sk); + goto out; + case ICMP_SOURCE_QUENCH: + /* Just silently ignore these. */ + goto out; + case ICMP_PARAMETERPROB: + err = EPROTO; + break; + case ICMP_DEST_UNREACH: + if (code > NR_ICMP_UNREACH) + goto out; + + if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ + /* 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; + + WRITE_ONCE(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, &sk->sk_tsq_flags)) + sock_hold(sk); + } + goto out; + } + + err = icmp_err_convert[code].errno; + /* check if this ICMP message allows revert of backoff. + * (see RFC 6069) + */ + if (!fastopen && + (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH)) + tcp_ld_RTO_revert(sk, seq); + break; + case ICMP_TIME_EXCEEDED: + err = EHOSTUNREACH; + break; + default: + goto out; + } + + switch (sk->sk_state) { + case TCP_SYN_SENT: + case TCP_SYN_RECV: + /* Only in fast or simultaneous open. If a fast open socket is + * already accepted it is treated as a connected one below. + */ + if (fastopen && !fastopen->sk) + break; + + ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); + + if (!sock_owned_by_user(sk)) { + sk->sk_err = err; + + sk->sk_error_report(sk); + + tcp_done(sk); + } else { + sk->sk_err_soft = err; + } + goto out; + } + + /* If we've already connected we will keep trying + * until we time out, or the user gives up. + * + * rfc1122 4.2.3.9 allows to consider as hard errors + * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, + * but it is obsoleted by pmtu discovery). + * + * Note, that in modern internet, where routing is unreliable + * and in each dark corner broken firewalls sit, sending random + * errors ordered by their masters even this two messages finally lose + * their original sense (even Linux sends invalid PORT_UNREACHs) + * + * Now we are in compliance with RFCs. + * --ANK (980905) + */ + + inet = inet_sk(sk); + if (!sock_owned_by_user(sk) && inet->recverr) { + sk->sk_err = err; + sk->sk_error_report(sk); + } else { /* Only an error on timeout */ + sk->sk_err_soft = err; + } + +out: + bh_unlock_sock(sk); + sock_put(sk); + return 0; +} + +void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) +{ + struct tcphdr *th = tcp_hdr(skb); + + 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); +} + +/* This routine computes an IPv4 TCP checksum. */ +void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) +{ + const struct inet_sock *inet = inet_sk(sk); + + __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. + * + * Someone asks: why I NEVER use socket parameters (TOS, TTL etc.) + * for reset. + * Answer: if a packet caused RST, it is not for a socket + * existing in our system, if it is matched to a socket, + * it is just duplicate segment or bug in other side's TCP. + * So that we build reply only basing on parameters + * arrived with segment. + * Exception: precedence violation. We do not implement it in any case. + */ + +static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) +{ + const struct tcphdr *th = tcp_hdr(skb); + struct { + struct tcphdr th; +#ifdef CONFIG_TCP_MD5SIG + __be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)]; +#endif + } rep; + struct ip_reply_arg arg; +#ifdef CONFIG_TCP_MD5SIG + struct tcp_md5sig_key *key = NULL; + const __u8 *hash_location = NULL; + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; +#endif + u64 transmit_time = 0; + struct sock *ctl_sk; + struct net *net; + + /* Never send a reset in response to a reset. */ + if (th->rst) + return; + + /* If sk not NULL, it means we did a successful lookup and incoming + * route had to be correct. prequeue might have dropped our dst. + */ + if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL) + return; + + /* Swap the send and the receive. */ + memset(&rep, 0, sizeof(rep)); + rep.th.dest = th->source; + rep.th.source = th->dest; + rep.th.doff = sizeof(struct tcphdr) / 4; + rep.th.rst = 1; + + if (th->ack) { + rep.th.seq = th->ack_seq; + } else { + rep.th.ack = 1; + rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin + + skb->len - (th->doff << 2)); + } + + memset(&arg, 0, sizeof(arg)); + arg.iov[0].iov_base = (unsigned char *)&rep; + arg.iov[0].iov_len = sizeof(rep.th); + + net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); +#ifdef CONFIG_TCP_MD5SIG + rcu_read_lock(); + hash_location = tcp_parse_md5sig_option(th); + if (sk && sk_fullsock(sk)) { + const union tcp_md5_addr *addr; + int l3index; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and inet_iif is set to it. + */ + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); + } else if (hash_location) { + const union tcp_md5_addr *addr; + int sdif = tcp_v4_sdif(skb); + int dif = inet_iif(skb); + int l3index; + + /* + * 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(net, &tcp_hashinfo, NULL, 0, + ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, + ntohs(th->source), dif, sdif); + /* don't send rst if it can't find key */ + if (!sk1) + goto out; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to it. + */ + l3index = sdif ? dif : 0; + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET); + if (!key) + goto out; + + + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto out; + + } + + if (key) { + rep.opt[0] = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + /* Update length and the length the header thinks exists */ + arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; + rep.th.doff = arg.iov[0].iov_len / 4; + + 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 */ + arg.iov[0].iov_len, IPPROTO_TCP, 0); + arg.csumoffset = offsetof(struct tcphdr, check) / 2; + arg.flags = (sk && inet_sk_transparent(sk)) ? 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; + if (sk_fullsock(sk)) + trace_tcp_send_reset(sk, skb); + } + + BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != + offsetof(struct inet_timewait_sock, tw_bound_dev_if)); + + arg.tos = ip_hdr(skb)->tos; + arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); + local_bh_disable(); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); + if (sk) { + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_priority : sk->sk_priority; + transmit_time = tcp_transmit_time(sk); + xfrm_sk_clone_policy(ctl_sk, sk); + } else { + ctl_sk->sk_mark = 0; + ctl_sk->sk_priority = 0; + } + ip_send_unicast_reply(ctl_sk, + skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + &arg, arg.iov[0].iov_len, + transmit_time); + + xfrm_sk_free_policy(ctl_sk); + sock_net_set(ctl_sk, &init_net); + __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); + local_bh_enable(); + +#ifdef CONFIG_TCP_MD5SIG +out: + rcu_read_unlock(); +#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(const struct sock *sk, + struct sk_buff *skb, u32 seq, u32 ack, + u32 win, u32 tsval, u32 tsecr, int oif, + struct tcp_md5sig_key *key, + int reply_flags, u8 tos) +{ + const struct tcphdr *th = tcp_hdr(skb); + struct { + struct tcphdr th; + __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2) +#ifdef CONFIG_TCP_MD5SIG + + (TCPOLEN_MD5SIG_ALIGNED >> 2) +#endif + ]; + } rep; + struct net *net = sock_net(sk); + struct ip_reply_arg arg; + struct sock *ctl_sk; + u64 transmit_time; + + 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 (tsecr) { + rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + rep.opt[1] = htonl(tsval); + rep.opt[2] = htonl(tsecr); + arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; + } + + /* Swap the send and the receive. */ + rep.th.dest = th->source; + rep.th.source = th->dest; + rep.th.doff = arg.iov[0].iov_len / 4; + rep.th.seq = htonl(seq); + rep.th.ack_seq = htonl(ack); + rep.th.ack = 1; + rep.th.window = htons(win); + +#ifdef CONFIG_TCP_MD5SIG + if (key) { + int offset = (tsecr) ? 3 : 0; + + rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; + rep.th.doff = arg.iov[0].iov_len/4; + + 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 (oif) + arg.bound_dev_if = oif; + arg.tos = tos; + arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); + local_bh_disable(); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_priority : sk->sk_priority; + transmit_time = tcp_transmit_time(sk); + ip_send_unicast_reply(ctl_sk, + skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + &arg, arg.iov[0].iov_len, + transmit_time); + + sock_net_set(ctl_sk, &init_net); + __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + local_bh_enable(); +} + +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(sk, skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, + 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(const struct sock *sk, struct sk_buff *skb, + struct request_sock *req) +{ + const union tcp_md5_addr *addr; + int l3index; + + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV + * sk->sk_state == TCP_SYN_RECV -> for Fast Open. + */ + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; + tcp_v4_send_ack(sk, skb, seq, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, + READ_ONCE(req->ts_recent), + 0, + tcp_md5_do_lookup(sk, l3index, addr, AF_INET), + inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, + ip_hdr(skb)->tos); +} + +/* + * Send a SYN-ACK after having received a SYN. + * This still operates on a request_sock only, not on a big + * socket. + */ +static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, + struct flowi *fl, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) +{ + const struct inet_request_sock *ireq = inet_rsk(req); + struct flowi4 fl4; + int err = -1; + struct sk_buff *skb; + u8 tos; + + /* First, grab a route. */ + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) + return -1; + + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); + + if (skb) { + __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + + tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (inet_sk(sk)->tos & INET_ECN_MASK) : + inet_sk(sk)->tos; + + if (!INET_ECN_is_capable(tos) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tos |= INET_ECN_ECT_0; + + rcu_read_lock(); + err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, + ireq->ir_rmt_addr, + rcu_dereference(ireq->ireq_opt), + tos); + rcu_read_unlock(); + err = net_xmit_eval(err); + } + + return err; +} + +/* + * IPv4 request_sock destructor. + */ +static void tcp_v4_reqsk_destructor(struct request_sock *req) +{ + kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); +} + +#ifdef CONFIG_TCP_MD5SIG +/* + * RFC2385 MD5 checksumming requires a mapping of + * IP address->MD5 Key. + * We need to maintain these in the sk structure. + */ + +DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); +EXPORT_SYMBOL(tcp_md5_needed); + +static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) +{ + if (!old) + return true; + + /* l3index always overrides non-l3index */ + if (old->l3index && new->l3index == 0) + return false; + if (old->l3index == 0 && new->l3index) + return true; + + return old->prefixlen < new->prefixlen; +} + +/* Find the Key structure for an address. */ +struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, + const union tcp_md5_addr *addr, + int family) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + const struct tcp_md5sig_info *md5sig; + __be32 mask; + struct tcp_md5sig_key *best_match = NULL; + bool match; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) + return NULL; + + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { + if (key->family != family) + continue; + if (key->l3index && key->l3index != l3index) + continue; + if (family == AF_INET) { + mask = inet_make_mask(key->prefixlen); + match = (key->addr.a4.s_addr & mask) == + (addr->a4.s_addr & mask); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, + key->prefixlen); +#endif + } else { + match = false; + } + + if (match && better_md5_match(best_match, key)) + best_match = key; + } + return best_match; +} +EXPORT_SYMBOL(__tcp_md5_do_lookup); + +static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, + const union tcp_md5_addr *addr, + int family, u8 prefixlen, + int l3index) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + unsigned int size = sizeof(struct in_addr); + const struct tcp_md5sig_info *md5sig; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) + return NULL; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + size = sizeof(struct in6_addr); +#endif + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { + if (key->family != family) + continue; + if (key->l3index != l3index) + continue; + if (!memcmp(&key->addr, addr, size) && + key->prefixlen == prefixlen) + return key; + } + return NULL; +} + +struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, + const struct sock *addr_sk) +{ + const union tcp_md5_addr *addr; + int l3index; + + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), + addr_sk->sk_bound_dev_if); + addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; + return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); +} +EXPORT_SYMBOL(tcp_v4_md5_lookup); + +/* This can be called on a newly created socket, from other files */ +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, + 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 tcp_md5sig_info *md5sig; + + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); + if (key) { + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + * data_race() is telling kcsan that we do not care of + * key mismatches, since changing MD5 key on live flows + * can lead to packet drops. + */ + data_race(memcpy(key->key, newkey, newkeylen)); + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + + return 0; + } + + md5sig = rcu_dereference_protected(tp->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) { + md5sig = kmalloc(sizeof(*md5sig), gfp); + if (!md5sig) + return -ENOMEM; + + sk_nocaps_add(sk, NETIF_F_GSO_MASK); + INIT_HLIST_HEAD(&md5sig->head); + rcu_assign_pointer(tp->md5sig_info, md5sig); + } + + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); + if (!key) + return -ENOMEM; + if (!tcp_alloc_md5sig_pool()) { + sock_kfree_s(sk, key, sizeof(*key)); + return -ENOMEM; + } + + memcpy(key->key, newkey, newkeylen); + key->keylen = newkeylen; + key->family = family; + key->prefixlen = prefixlen; + key->l3index = l3index; + 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); + +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, + u8 prefixlen, int l3index) +{ + struct tcp_md5sig_key *key; + + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); + 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); + +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; + + 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); + } +} + +static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, + sockptr_t optval, int optlen) +{ + struct tcp_md5sig cmd; + struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; + const union tcp_md5_addr *addr; + u8 prefixlen = 32; + int l3index = 0; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) + return -EFAULT; + + if (sin->sin_family != AF_INET) + return -EINVAL; + + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 32) + return -EINVAL; + } + + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); + if (dev && netif_is_l3_master(dev)) + l3index = dev->ifindex; + + rcu_read_unlock(); + + /* ok to reference set/not set outside of rcu; + * right now device MUST be an L3 master + */ + if (!dev || !l3index) + return -EINVAL; + } + + addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; + + if (!cmd.tcpm_keylen) + return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index); + + if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) + return -EINVAL; + + return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, + cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); +} + +static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, + __be32 daddr, __be32 saddr, + const struct tcphdr *th, int nbytes) +{ + struct tcp4_pseudohdr *bp; + struct scatterlist sg; + struct tcphdr *_th; + + bp = hp->scratch; + bp->saddr = saddr; + bp->daddr = daddr; + bp->pad = 0; + bp->protocol = IPPROTO_TCP; + bp->len = cpu_to_be16(nbytes); + + _th = (struct tcphdr *)(bp + 1); + memcpy(_th, th, sizeof(*th)); + _th->check = 0; + + sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, + sizeof(*bp) + sizeof(*th)); + return crypto_ahash_update(hp->md5_req); +} + +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th) +{ + struct tcp_md5sig_pool *hp; + struct ahash_request *req; + + hp = tcp_get_md5sig_pool(); + if (!hp) + goto clear_hash_noput; + req = hp->md5_req; + + if (crypto_ahash_init(req)) + goto clear_hash; + if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2)) + goto clear_hash; + if (tcp_md5_hash_key(hp, key)) + goto clear_hash; + ahash_request_set_crypt(req, NULL, md5_hash, 0); + if (crypto_ahash_final(req)) + 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; +} + +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, + const struct sk_buff *skb) +{ + struct tcp_md5sig_pool *hp; + struct ahash_request *req; + const struct tcphdr *th = tcp_hdr(skb); + __be32 saddr, daddr; + + if (sk) { /* valid for establish/request sockets */ + saddr = sk->sk_rcv_saddr; + daddr = sk->sk_daddr; + } else { + const struct iphdr *iph = ip_hdr(skb); + saddr = iph->saddr; + daddr = iph->daddr; + } + + hp = tcp_get_md5sig_pool(); + if (!hp) + goto clear_hash_noput; + req = hp->md5_req; + + if (crypto_ahash_init(req)) + goto clear_hash; + + if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len)) + goto clear_hash; + if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) + goto clear_hash; + if (tcp_md5_hash_key(hp, key)) + goto clear_hash; + ahash_request_set_crypt(req, NULL, md5_hash, 0); + if (crypto_ahash_final(req)) + 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); + +#endif + +/* Called with rcu_read_lock() */ +static bool tcp_v4_inbound_md5_hash(const struct sock *sk, + const struct sk_buff *skb, + int dif, int sdif) +{ +#ifdef CONFIG_TCP_MD5SIG + /* + * This gets called for each TCP segment that arrives + * so we want to be efficient. + * We have 3 drop cases: + * o No MD5 hash and one expected. + * o MD5 hash and we're not expecting one. + * o MD5 hash and its wrong. + */ + const __u8 *hash_location = NULL; + struct tcp_md5sig_key *hash_expected; + const struct iphdr *iph = ip_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); + const union tcp_md5_addr *addr; + unsigned char newhash[16]; + int genhash, l3index; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + addr = (union tcp_md5_addr *)&iph->saddr; + hash_expected = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); + hash_location = tcp_parse_md5sig_option(th); + + /* We've parsed the options - do we have a hash? */ + if (!hash_expected && !hash_location) + return false; + + if (hash_expected && !hash_location) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + return true; + } + + if (!hash_expected && hash_location) { + NET_INC_STATS(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_md5_hash_skb(newhash, + hash_expected, + NULL, skb); + + if (genhash || memcmp(hash_location, newhash, 16) != 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", + &iph->saddr, ntohs(th->source), + &iph->daddr, ntohs(th->dest), + genhash ? " tcp_v4_calc_md5_hash failed" + : "", l3index); + return true; + } + return false; +#endif + return false; +} + +static void tcp_v4_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct inet_request_sock *ireq = inet_rsk(req); + struct net *net = sock_net(sk_listener); + + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); + RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); +} + +static struct dst_entry *tcp_v4_route_req(const struct sock *sk, + struct flowi *fl, + const struct request_sock *req) +{ + return inet_csk_route_req(sk, &fl->u.ip4, req); +} + +struct request_sock_ops tcp_request_sock_ops __read_mostly = { + .family = PF_INET, + .obj_size = sizeof(struct tcp_request_sock), + .rtx_syn_ack = tcp_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, +}; + +const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { + .mss_clamp = TCP_MSS_DEFAULT, +#ifdef CONFIG_TCP_MD5SIG + .req_md5_lookup = tcp_v4_md5_lookup, + .calc_md5_hash = tcp_v4_md5_hash_skb, +#endif + .init_req = tcp_v4_init_req, +#ifdef CONFIG_SYN_COOKIES + .cookie_init_seq = cookie_v4_init_sequence, +#endif + .route_req = tcp_v4_route_req, + .init_seq = tcp_v4_init_seq, + .init_ts_off = tcp_v4_init_ts_off, + .send_synack = tcp_v4_send_synack, +}; + +int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) +{ + /* Never answer to SYNs send to broadcast or multicast */ + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + goto drop; + + return tcp_conn_request(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); + +drop: + tcp_listendrop(sk); + return 0; +} +EXPORT_SYMBOL(tcp_v4_conn_request); + + +/* + * The three way handshake has completed - we got a valid synack - + * now create the new socket. + */ +struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req) +{ + struct inet_request_sock *ireq; + bool found_dup_sk = false; + struct inet_sock *newinet; + struct tcp_sock *newtp; + struct sock *newsk; +#ifdef CONFIG_TCP_MD5SIG + const union tcp_md5_addr *addr; + struct tcp_md5sig_key *key; + int l3index; +#endif + struct ip_options_rcu *inet_opt; + + if (sk_acceptq_is_full(sk)) + goto exit_overflow; + + newsk = tcp_create_openreq_child(sk, req, skb); + if (!newsk) + goto exit_nonewsk; + + newsk->sk_gso_type = SKB_GSO_TCPV4; + inet_sk_rx_dst_set(newsk, skb); + + newtp = tcp_sk(newsk); + newinet = inet_sk(newsk); + ireq = inet_rsk(req); + sk_daddr_set(newsk, ireq->ir_rmt_addr); + sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); + newsk->sk_bound_dev_if = ireq->ir_iif; + newinet->inet_saddr = ireq->ir_loc_addr; + inet_opt = rcu_dereference(ireq->ireq_opt); + RCU_INIT_POINTER(newinet->inet_opt, inet_opt); + 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 (inet_opt) + inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; + newinet->inet_id = prandom_u32(); + + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) + newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; + + 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_ca_openreq_child(newsk, dst); + + tcp_sync_mss(newsk, dst_mtu(dst)); + newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); + + tcp_initialize_rcv_mss(newsk); + +#ifdef CONFIG_TCP_MD5SIG + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); + /* Copy over the MD5 key from the original socket */ + addr = (union tcp_md5_addr *)&newinet->inet_daddr; + key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); + if (key) { + /* + * 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. + */ + tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, + key->key, key->keylen, GFP_ATOMIC); + sk_nocaps_add(newsk, NETIF_F_GSO_MASK); + } +#endif + + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); + if (likely(*own_req)) { + tcp_move_syn(newtp, req); + ireq->ireq_opt = NULL; + } else { + newinet->inet_opt = NULL; + + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } + } + return newsk; + +exit_overflow: + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +exit_nonewsk: + dst_release(dst); +exit: + tcp_listendrop(sk); + return NULL; +put_and_exit: + newinet->inet_opt = NULL; + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); + goto exit; +} +EXPORT_SYMBOL(tcp_v4_syn_recv_sock); + +static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) +{ +#ifdef CONFIG_SYN_COOKIES + const struct tcphdr *th = tcp_hdr(skb); + + if (!th->syn) + sk = cookie_v4_check(sk, skb); +#endif + return sk; +} + +u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, + struct tcphdr *th, u32 *cookie) +{ + u16 mss = 0; +#ifdef CONFIG_SYN_COOKIES + mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, th); + if (mss) { + *cookie = __cookie_v4_init_sequence(iph, th, &mss); + tcp_synq_overflow(sk); + } +#endif + return mss; +} + +/* The socket must have it's spinlock held when we get + * here, unless it is a TCP_LISTEN socket. + * + * We have a potential double-lock case here, so even when + * doing backlog processing we use the BH locking scheme. + * This is because we cannot sleep with the original spinlock + * held. + */ +int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct sock *rsk; + + if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); + + sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + !dst->ops->check(dst, 0)) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); + dst_release(dst); + } + } + tcp_rcv_established(sk, skb); + return 0; + } + + if (tcp_checksum_complete(skb)) + goto csum_err; + + if (sk->sk_state == TCP_LISTEN) { + struct sock *nsk = tcp_v4_cookie_check(sk, skb); + + if (!nsk) + goto discard; + if (nsk != sk) { + if (tcp_child_process(sk, nsk, skb)) { + rsk = nsk; + goto reset; + } + return 0; + } + } else + sock_rps_save_rxhash(sk, skb); + + if (tcp_rcv_state_process(sk, skb)) { + rsk = sk; + goto reset; + } + return 0; + +reset: + tcp_v4_send_reset(rsk, skb); +discard: + kfree_skb(skb); + /* Be careful here. If this function gets more complicated and + * gcc suffers from register pressure on the x86, sk (in %ebx) + * might be destroyed here. This current version compiles correctly, + * but you have been warned. + */ + return 0; + +csum_err: + TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + goto discard; +} +EXPORT_SYMBOL(tcp_v4_do_rcv); + +int 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 0; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return 0; + + iph = ip_hdr(skb); + th = tcp_hdr(skb); + + if (th->doff < sizeof(struct tcphdr) / 4) + return 0; + + sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, + iph->daddr, ntohs(th->dest), + skb->skb_iif, inet_sdif(skb)); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk_fullsock(sk)) { + struct dst_entry *dst = rcu_dereference(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); + } + } + return 0; +} + +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) +{ + u32 limit, tail_gso_size, tail_gso_segs; + struct skb_shared_info *shinfo; + const struct tcphdr *th; + struct tcphdr *thtail; + struct sk_buff *tail; + unsigned int hdrlen; + bool fragstolen; + u32 gso_segs; + u32 gso_size; + int delta; + + /* In case all data was pulled from skb frags (in __pskb_pull_tail()), + * we can fix skb->truesize to its real value to avoid future drops. + * This is valid because skb is not yet charged to the socket. + * It has been noticed pure SACK packets were sometimes dropped + * (if cooked by drivers without copybreak feature). + */ + skb_condense(skb); + + skb_dst_drop(skb); + + if (unlikely(tcp_checksum_complete(skb))) { + bh_unlock_sock(sk); + __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); + __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + return true; + } + + /* Attempt coalescing to last skb in backlog, even if we are + * above the limits. + * This is okay because skb capacity is limited to MAX_SKB_FRAGS. + */ + th = (const struct tcphdr *)skb->data; + hdrlen = th->doff * 4; + + tail = sk->sk_backlog.tail; + if (!tail) + goto no_coalesce; + thtail = (struct tcphdr *)tail->data; + + if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq || + TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield || + ((TCP_SKB_CB(tail)->tcp_flags | + TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) || + !((TCP_SKB_CB(tail)->tcp_flags & + TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || + ((TCP_SKB_CB(tail)->tcp_flags ^ + TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || +#ifdef CONFIG_TLS_DEVICE + tail->decrypted != skb->decrypted || +#endif + !mptcp_skb_can_collapse(tail, skb) || + thtail->doff != th->doff || + memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) + goto no_coalesce; + + __skb_pull(skb, hdrlen); + + shinfo = skb_shinfo(skb); + gso_size = shinfo->gso_size ?: skb->len; + gso_segs = shinfo->gso_segs ?: 1; + + shinfo = skb_shinfo(tail); + tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen); + tail_gso_segs = shinfo->gso_segs ?: 1; + + if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { + TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; + + if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { + TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; + thtail->window = th->window; + } + + /* We have to update both TCP_SKB_CB(tail)->tcp_flags and + * thtail->fin, so that the fast path in tcp_rcv_established() + * is not entered if we append a packet with a FIN. + * SYN, RST, URG are not present. + * ACK is set on both packets. + * PSH : we do not really care in TCP stack, + * at least for 'GRO' packets. + */ + thtail->fin |= th->fin; + TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + + if (TCP_SKB_CB(skb)->has_rxtstamp) { + TCP_SKB_CB(tail)->has_rxtstamp = true; + tail->tstamp = skb->tstamp; + skb_hwtstamps(tail)->hwtstamp = skb_hwtstamps(skb)->hwtstamp; + } + + /* Not as strict as GRO. We only need to carry mss max value */ + shinfo->gso_size = max(gso_size, tail_gso_size); + shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF); + + sk->sk_backlog.len += delta; + __NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPBACKLOGCOALESCE); + kfree_skb_partial(skb, fragstolen); + return false; + } + __skb_push(skb, hdrlen); + +no_coalesce: + limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + + /* Only socket owner can try to collapse/prune rx queues + * to reduce memory overhead, so add a little headroom here. + * Few sockets backlog are possibly concurrently non empty. + */ + limit += 64 * 1024; + + if (unlikely(sk_add_backlog(sk, skb, limit))) { + bh_unlock_sock(sk); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + return true; + } + return false; +} +EXPORT_SYMBOL(tcp_add_backlog); + +int tcp_filter(struct sock *sk, struct sk_buff *skb) +{ + struct tcphdr *th = (struct tcphdr *)skb->data; + + return sk_filter_trim_cap(sk, skb, th->doff * 4); +} +EXPORT_SYMBOL(tcp_filter); + +static void tcp_v4_restore_cb(struct sk_buff *skb) +{ + memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, + sizeof(struct inet_skb_parm)); +} + +static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, + const struct tcphdr *th) +{ + /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() + * barrier() makes sure compiler wont play fool^Waliasing games. + */ + memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), + sizeof(struct inet_skb_parm)); + barrier(); + + TCP_SKB_CB(skb)->seq = ntohl(th->seq); + TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + + skb->len - th->doff * 4); + TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); + TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_tw_isn = 0; + TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); + TCP_SKB_CB(skb)->sacked = 0; + TCP_SKB_CB(skb)->has_rxtstamp = + skb->tstamp || skb_hwtstamps(skb)->hwtstamp; +} + +/* + * From tcp_input.c + */ + +int tcp_v4_rcv(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sk_buff *skb_to_free; + int sdif = inet_sdif(skb); + int dif = inet_iif(skb); + const struct iphdr *iph; + const struct tcphdr *th; + bool refcounted; + struct sock *sk; + int ret; + + if (skb->pkt_type != PACKET_HOST) + goto discard_it; + + /* Count it even if it's bad */ + __TCP_INC_STATS(net, TCP_MIB_INSEGS); + + if (!pskb_may_pull(skb, sizeof(struct tcphdr))) + goto discard_it; + + th = (const struct tcphdr *)skb->data; + + if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) + goto bad_packet; + if (!pskb_may_pull(skb, th->doff * 4)) + goto discard_it; + + /* An explanation is required here, I think. + * Packet length and doff are validated by header prediction, + * provided case of th->doff==0 is eliminated. + * So, we defer the checks. */ + + if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) + goto csum_error; + + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); +lookup: + sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, + th->dest, sdif, &refcounted); + if (!sk) + goto no_tcp_socket; + +process: + if (sk->sk_state == TCP_TIME_WAIT) + goto do_time_wait; + + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; + struct sock *nsk; + + sk = req->rsk_listener; + if (unlikely(!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb) || + tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) { + sk_drops_add(sk, skb); + reqsk_put(req); + goto discard_it; + } + if (tcp_checksum_complete(skb)) { + reqsk_put(req); + goto csum_error; + } + if (unlikely(sk->sk_state != TCP_LISTEN)) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + /* We own a reference on the listener, increase it again + * as we might lose it too soon. + */ + sock_hold(sk); + refcounted = true; + nsk = NULL; + if (!tcp_filter(sk, skb)) { + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); + tcp_v4_fill_cb(skb, iph, th); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); + } + if (!nsk) { + reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v4_restore_cb(skb); + sock_put(sk); + goto lookup; + } + goto discard_and_relse; + } + nf_reset_ct(skb); + if (nsk == sk) { + reqsk_put(req); + tcp_v4_restore_cb(skb); + } else if (tcp_child_process(sk, nsk, skb)) { + tcp_v4_send_reset(nsk, skb); + goto discard_and_relse; + } else { + sock_put(sk); + return 0; + } + } + if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { + __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); + goto discard_and_relse; + } + + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + goto discard_and_relse; + + if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) + goto discard_and_relse; + + nf_reset_ct(skb); + + if (tcp_filter(sk, skb)) + goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); + tcp_v4_fill_cb(skb, iph, th); + + skb->dev = NULL; + + if (sk->sk_state == TCP_LISTEN) { + ret = tcp_v4_do_rcv(sk, skb); + goto put_and_return; + } + + sk_incoming_cpu_update(sk); + + bh_lock_sock_nested(sk); + tcp_segs_in(tcp_sk(sk), skb); + ret = 0; + if (!sock_owned_by_user(sk)) { + skb_to_free = sk->sk_rx_skb_cache; + sk->sk_rx_skb_cache = NULL; + ret = tcp_v4_do_rcv(sk, skb); + } else { + if (tcp_add_backlog(sk, skb)) + goto discard_and_relse; + skb_to_free = NULL; + } + bh_unlock_sock(sk); + if (skb_to_free) + __kfree_skb(skb_to_free); + +put_and_return: + if (refcounted) + sock_put(sk); + + return ret; + +no_tcp_socket: + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto discard_it; + + tcp_v4_fill_cb(skb, iph, th); + + if (tcp_checksum_complete(skb)) { +csum_error: + __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); +bad_packet: + __TCP_INC_STATS(net, TCP_MIB_INERRS); + } else { + tcp_v4_send_reset(NULL, skb); + } + +discard_it: + /* Discard frame. */ + kfree_skb(skb); + return 0; + +discard_and_relse: + sk_drops_add(sk, skb); + if (refcounted) + sock_put(sk); + goto discard_it; + +do_time_wait: + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { + inet_twsk_put(inet_twsk(sk)); + goto discard_it; + } + + tcp_v4_fill_cb(skb, iph, th); + + 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(dev_net(skb->dev), + &tcp_hashinfo, skb, + __tcp_hdrlen(th), + iph->saddr, th->source, + iph->daddr, th->dest, + inet_iif(skb), + sdif); + if (sk2) { + inet_twsk_deschedule_put(inet_twsk(sk)); + sk = sk2; + tcp_v4_restore_cb(skb); + refcounted = false; + goto process; + } + } + /* to ACK */ + fallthrough; + case TCP_TW_ACK: + tcp_v4_timewait_ack(sk, skb); + break; + case TCP_TW_RST: + tcp_v4_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; + case TCP_TW_SUCCESS:; + } + goto discard_it; +} + +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, +}; + +void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst_hold_safe(dst)) { + rcu_assign_pointer(sk->sk_rx_dst, dst); + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + } +} +EXPORT_SYMBOL(inet_sk_rx_dst_set); + +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, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ip_setsockopt, + .getsockopt = ip_getsockopt, + .addr2sockaddr = inet_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in), + .mtu_reduced = tcp_v4_mtu_reduced, +}; +EXPORT_SYMBOL(ipv4_specific); + +#ifdef CONFIG_TCP_MD5SIG +static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { + .md5_lookup = tcp_v4_md5_lookup, + .calc_md5_hash = tcp_v4_md5_hash_skb, + .md5_parse = tcp_v4_parse_md5_keys, +}; +#endif + +/* NOTE: A lot of things set to zero explicitly by call to + * sk_alloc() so need not be done here. + */ +static int tcp_v4_init_sock(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_init_sock(sk); + + icsk->icsk_af_ops = &ipv4_specific; + +#ifdef CONFIG_TCP_MD5SIG + tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; +#endif + + return 0; +} + +void tcp_v4_destroy_sock(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + trace_tcp_destroy_sock(sk); + + tcp_clear_xmit_timers(sk); + + tcp_cleanup_congestion_control(sk); + + tcp_cleanup_ulp(sk); + + /* Cleanup up the write buffer. */ + tcp_write_queue_purge(sk); + + /* Check if we want to disable active TFO */ + tcp_fastopen_active_disable_ofo_check(sk); + + /* Cleans up our, hopefully empty, out_of_order_queue. */ + skb_rbtree_purge(&tp->out_of_order_queue); + +#ifdef CONFIG_TCP_MD5SIG + /* Clean up the MD5 key list, if any */ + if (tp->md5sig_info) { + tcp_clear_md5_list(sk); + kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); + tp->md5sig_info = NULL; + } +#endif + + /* Clean up a referenced TCP bind bucket. */ + if (inet_csk(sk)->icsk_bind_hash) + inet_put_port(sk); + + BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); + + /* If socket is aborted during connect operation */ + tcp_free_fastopen_req(tp); + tcp_fastopen_destroy_cipher(sk); + tcp_saved_syn_free(tp); + + sk_sockets_allocated_dec(sk); +} +EXPORT_SYMBOL(tcp_v4_destroy_sock); + +#ifdef CONFIG_PROC_FS +/* Proc filesystem TCP sock list dumping. */ + +/* + * 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 tcp_seq_afinfo *afinfo; + struct tcp_iter_state *st = seq->private; + struct net *net = seq_file_net(seq); + struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; + struct sock *sk = cur; + + if (st->bpf_seq_afinfo) + afinfo = st->bpf_seq_afinfo; + else + afinfo = PDE_DATA(file_inode(seq->file)); + + if (!sk) { +get_head: + ilb = &tcp_hashinfo.listening_hash[st->bucket]; + spin_lock(&ilb->lock); + sk = sk_nulls_head(&ilb->nulls_head); + st->offset = 0; + goto get_sk; + } + ilb = &tcp_hashinfo.listening_hash[st->bucket]; + ++st->num; + ++st->offset; + + sk = sk_nulls_next(sk); +get_sk: + sk_nulls_for_each_from(sk, node) { + if (!net_eq(sock_net(sk), net)) + continue; + if (afinfo->family == AF_UNSPEC || + sk->sk_family == afinfo->family) + return sk; + } + spin_unlock(&ilb->lock); + st->offset = 0; + if (++st->bucket < INET_LHTABLE_SIZE) + goto get_head; + return NULL; +} + +static void *listening_get_idx(struct seq_file *seq, loff_t *pos) +{ + 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); + --*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_seq_afinfo *afinfo; + struct tcp_iter_state *st = seq->private; + struct net *net = seq_file_net(seq); + void *rc = NULL; + + if (st->bpf_seq_afinfo) + afinfo = st->bpf_seq_afinfo; + else + afinfo = PDE_DATA(file_inode(seq->file)); + + st->offset = 0; + for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { + struct sock *sk; + 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; + + spin_lock_bh(lock); + sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { + if ((afinfo->family != AF_UNSPEC && + sk->sk_family != afinfo->family) || + !net_eq(sock_net(sk), net)) { + continue; + } + rc = sk; + goto out; + } + spin_unlock_bh(lock); + } +out: + return rc; +} + +static void *established_get_next(struct seq_file *seq, void *cur) +{ + struct tcp_seq_afinfo *afinfo; + struct sock *sk = cur; + struct hlist_nulls_node *node; + struct tcp_iter_state *st = seq->private; + struct net *net = seq_file_net(seq); + + if (st->bpf_seq_afinfo) + afinfo = st->bpf_seq_afinfo; + else + afinfo = PDE_DATA(file_inode(seq->file)); + + ++st->num; + ++st->offset; + + sk = sk_nulls_next(sk); + + sk_nulls_for_each_from(sk, node) { + if ((afinfo->family == AF_UNSPEC || + sk->sk_family == afinfo->family) && + net_eq(sock_net(sk), net)) + return sk; + } + + 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) +{ + 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); + --pos; + } + return rc; +} + +static void *tcp_get_idx(struct seq_file *seq, loff_t pos) +{ + void *rc; + struct tcp_iter_state *st = seq->private; + + st->state = TCP_SEQ_STATE_LISTENING; + rc = listening_get_idx(seq, &pos); + + if (!rc) { + st->state = TCP_SEQ_STATE_ESTABLISHED; + rc = established_get_idx(seq, pos); + } + + return rc; +} + +static void *tcp_seek_last_pos(struct seq_file *seq) +{ + struct tcp_iter_state *st = seq->private; + int bucket = st->bucket; + int offset = st->offset; + int orig_num = st->num; + void *rc = NULL; + + switch (st->state) { + 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 && bucket == st->bucket) + 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 && bucket == st->bucket) + rc = established_get_next(seq, rc); + } + + st->num = orig_num; + + return rc; +} + +void *tcp_seq_start(struct seq_file *seq, loff_t *pos) +{ + 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; + st->bucket = 0; + st->offset = 0; + rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + +out: + st->last_pos = *pos; + return rc; +} +EXPORT_SYMBOL(tcp_seq_start); + +void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct tcp_iter_state *st = seq->private; + void *rc = NULL; + + if (v == SEQ_START_TOKEN) { + rc = tcp_get_idx(seq, 0); + goto out; + } + + switch (st->state) { + case TCP_SEQ_STATE_LISTENING: + rc = listening_get_next(seq, v); + if (!rc) { + st->state = TCP_SEQ_STATE_ESTABLISHED; + st->bucket = 0; + st->offset = 0; + rc = established_get_first(seq); + } + break; + case TCP_SEQ_STATE_ESTABLISHED: + rc = established_get_next(seq, v); + break; + } +out: + ++*pos; + st->last_pos = *pos; + return rc; +} +EXPORT_SYMBOL(tcp_seq_next); + +void tcp_seq_stop(struct seq_file *seq, void *v) +{ + struct tcp_iter_state *st = seq->private; + + switch (st->state) { + case TCP_SEQ_STATE_LISTENING: + if (v != SEQ_START_TOKEN) + spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock); + break; + case TCP_SEQ_STATE_ESTABLISHED: + if (v) + spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + break; + } +} +EXPORT_SYMBOL(tcp_seq_stop); + +static void get_openreq4(const struct request_sock *req, + struct seq_file *f, int i) +{ + const struct inet_request_sock *ireq = inet_rsk(req); + long delta = req->rsk_timer.expires - jiffies; + + seq_printf(f, "%4d: %08X:%04X %08X:%04X" + " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", + i, + ireq->ir_loc_addr, + ireq->ir_num, + 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_delta_to_clock_t(delta), + req->num_timeout, + from_kuid_munged(seq_user_ns(f), + sock_i_uid(req->rsk_listener)), + 0, /* non standard timer */ + 0, /* open_requests have no inode */ + 0, + req); +} + +static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) +{ + int timer_active; + unsigned long timer_expires; + 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); + const 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; + int state; + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sk->sk_timer)) { + timer_active = 2; + timer_expires = sk->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = jiffies; + } + + state = inet_sk_state_load(sk); + if (state == TCP_LISTEN) + rx_queue = READ_ONCE(sk->sk_ack_backlog); + else + /* Because we don't lock the socket, + * we might find a transient negative value. + */ + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(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, state, + READ_ONCE(tp->write_seq) - tp->snd_una, + rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - jiffies), + icsk->icsk_retransmits, + from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), + icsk->icsk_probes_out, + sock_i_ino(sk), + refcount_read(&sk->sk_refcnt), sk, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), + tp->snd_cwnd, + state == TCP_LISTEN ? + fastopenq->max_qlen : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); +} + +static void get_timewait4_sock(const struct inet_timewait_sock *tw, + struct seq_file *f, int i) +{ + long delta = tw->tw_timer.expires - jiffies; + __be32 dest, src; + __u16 destp, srcp; + + dest = tw->tw_daddr; + src = tw->tw_rcv_saddr; + destp = ntohs(tw->tw_dport); + srcp = ntohs(tw->tw_sport); + + 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_delta_to_clock_t(delta), 0, 0, 0, 0, + refcount_read(&tw->tw_refcnt), tw); +} + +#define TMPSZ 150 + +static int tcp4_seq_show(struct seq_file *seq, void *v) +{ + struct tcp_iter_state *st; + struct sock *sk = v; + + seq_setwidth(seq, TMPSZ - 1); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, " sl local_address rem_address st tx_queue " + "rx_queue tr tm->when retrnsmt uid timeout " + "inode"); + goto out; + } + st = seq->private; + + if (sk->sk_state == TCP_TIME_WAIT) + get_timewait4_sock(v, seq, st->num); + else if (sk->sk_state == TCP_NEW_SYN_RECV) + get_openreq4(v, seq, st->num); + else + get_tcp4_sock(v, seq, st->num); +out: + seq_pad(seq, '\n'); + return 0; +} + +#ifdef CONFIG_BPF_SYSCALL +struct bpf_iter__tcp { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct sock_common *, sk_common); + uid_t uid __aligned(8); +}; + +static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, + struct sock_common *sk_common, uid_t uid) +{ + struct bpf_iter__tcp ctx; + + meta->seq_num--; /* skip SEQ_START_TOKEN */ + ctx.meta = meta; + ctx.sk_common = sk_common; + ctx.uid = uid; + return bpf_iter_run_prog(prog, &ctx); +} + +static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + struct sock *sk = v; + uid_t uid; + + if (v == SEQ_START_TOKEN) + return 0; + + if (sk->sk_state == TCP_TIME_WAIT) { + uid = 0; + } else if (sk->sk_state == TCP_NEW_SYN_RECV) { + const struct request_sock *req = v; + + uid = from_kuid_munged(seq_user_ns(seq), + sock_i_uid(req->rsk_listener)); + } else { + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + } + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + return tcp_prog_seq_show(prog, &meta, v, uid); +} + +static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + if (!v) { + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog) + (void)tcp_prog_seq_show(prog, &meta, v, 0); + } + + tcp_seq_stop(seq, v); +} + +static const struct seq_operations bpf_iter_tcp_seq_ops = { + .show = bpf_iter_tcp_seq_show, + .start = tcp_seq_start, + .next = tcp_seq_next, + .stop = bpf_iter_tcp_seq_stop, +}; +#endif + +static const struct seq_operations tcp4_seq_ops = { + .show = tcp4_seq_show, + .start = tcp_seq_start, + .next = tcp_seq_next, + .stop = tcp_seq_stop, +}; + +static struct tcp_seq_afinfo tcp4_seq_afinfo = { + .family = AF_INET, +}; + +static int __net_init tcp4_proc_init_net(struct net *net) +{ + if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops, + sizeof(struct tcp_iter_state), &tcp4_seq_afinfo)) + return -ENOMEM; + return 0; +} + +static void __net_exit tcp4_proc_exit_net(struct net *net) +{ + remove_proc_entry("tcp", net->proc_net); +} + +static struct pernet_operations tcp4_net_ops = { + .init = tcp4_proc_init_net, + .exit = tcp4_proc_exit_net, +}; + +int __init tcp4_proc_init(void) +{ + return register_pernet_subsys(&tcp4_net_ops); +} + +void tcp4_proc_exit(void) +{ + unregister_pernet_subsys(&tcp4_net_ops); +} +#endif /* CONFIG_PROC_FS */ + +struct proto tcp_prot = { + .name = "TCP", + .owner = THIS_MODULE, + .close = tcp_close, + .pre_connect = tcp_v4_pre_connect, + .connect = tcp_v4_connect, + .disconnect = tcp_disconnect, + .accept = inet_csk_accept, + .ioctl = tcp_ioctl, + .init = tcp_v4_init_sock, + .destroy = tcp_v4_destroy_sock, + .shutdown = tcp_shutdown, + .setsockopt = tcp_setsockopt, + .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, + .keepalive = tcp_set_keepalive, + .recvmsg = tcp_recvmsg, + .sendmsg = tcp_sendmsg, + .sendpage = tcp_sendpage, + .backlog_rcv = tcp_v4_do_rcv, + .release_cb = tcp_release_cb, + .hash = inet_hash, + .unhash = inet_unhash, + .get_port = inet_csk_get_port, + .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, + .sockets_allocated = &tcp_sockets_allocated, + .orphan_count = &tcp_orphan_count, + .memory_allocated = &tcp_memory_allocated, + .memory_pressure = &tcp_memory_pressure, + .sysctl_mem = sysctl_tcp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), + .max_header = MAX_TCP_HEADER, + .obj_size = sizeof(struct tcp_sock), + .slab_flags = SLAB_TYPESAFE_BY_RCU, + .twsk_prot = &tcp_timewait_sock_ops, + .rsk_prot = &tcp_request_sock_ops, + .h.hashinfo = &tcp_hashinfo, + .no_autobind = true, + .diag_destroy = tcp_abort, +}; +EXPORT_SYMBOL(tcp_prot); + +static void __net_exit tcp_sk_exit(struct net *net) +{ + if (net->ipv4.tcp_congestion_control) + bpf_module_put(net->ipv4.tcp_congestion_control, + net->ipv4.tcp_congestion_control->owner); +} + +static int __net_init tcp_sk_init(struct net *net) +{ + int cnt; + + net->ipv4.sysctl_tcp_ecn = 2; + net->ipv4.sysctl_tcp_ecn_fallback = 1; + + net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; + net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; + net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; + net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; + + net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; + net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; + net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; + + net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; + net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; + net->ipv4.sysctl_tcp_syncookies = 1; + net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; + net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; + net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; + net->ipv4.sysctl_tcp_orphan_retries = 0; + net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; + net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; + net->ipv4.sysctl_tcp_tw_reuse = 2; + net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; + + cnt = tcp_hashinfo.ehash_mask + 1; + net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; + net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; + + net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); + net->ipv4.sysctl_tcp_sack = 1; + net->ipv4.sysctl_tcp_window_scaling = 1; + net->ipv4.sysctl_tcp_timestamps = 1; + net->ipv4.sysctl_tcp_early_retrans = 3; + net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION; + net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */ + net->ipv4.sysctl_tcp_retrans_collapse = 1; + net->ipv4.sysctl_tcp_max_reordering = 300; + net->ipv4.sysctl_tcp_dsack = 1; + net->ipv4.sysctl_tcp_app_win = 31; + net->ipv4.sysctl_tcp_adv_win_scale = 1; + net->ipv4.sysctl_tcp_frto = 2; + net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; + /* This limits the percentage of the congestion window which we + * will allow a single TSO frame to consume. Building TSO frames + * which are too large can cause TCP streams to be bursty. + */ + net->ipv4.sysctl_tcp_tso_win_divisor = 3; + /* Default TSQ limit of 16 TSO segments */ + net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536; + /* rfc5961 challenge ack rate limiting */ + net->ipv4.sysctl_tcp_challenge_ack_limit = 1000; + net->ipv4.sysctl_tcp_min_tso_segs = 2; + net->ipv4.sysctl_tcp_min_rtt_wlen = 300; + net->ipv4.sysctl_tcp_autocorking = 1; + net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; + net->ipv4.sysctl_tcp_pacing_ss_ratio = 200; + net->ipv4.sysctl_tcp_pacing_ca_ratio = 120; + if (net != &init_net) { + memcpy(net->ipv4.sysctl_tcp_rmem, + init_net.ipv4.sysctl_tcp_rmem, + sizeof(init_net.ipv4.sysctl_tcp_rmem)); + memcpy(net->ipv4.sysctl_tcp_wmem, + init_net.ipv4.sysctl_tcp_wmem, + sizeof(init_net.ipv4.sysctl_tcp_wmem)); + } + net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; + net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; + net->ipv4.sysctl_tcp_comp_sack_nr = 44; + net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; + spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; + atomic_set(&net->ipv4.tfo_active_disable_times, 0); + + /* Reno is always built in */ + if (!net_eq(net, &init_net) && + bpf_try_module_get(init_net.ipv4.tcp_congestion_control, + init_net.ipv4.tcp_congestion_control->owner)) + net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; + else + net->ipv4.tcp_congestion_control = &tcp_reno; + + return 0; +} + +static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) +{ + struct net *net; + + inet_twsk_purge(&tcp_hashinfo, AF_INET); + + list_for_each_entry(net, net_exit_list, exit_list) + tcp_fastopen_ctx_destroy(net); +} + +static struct pernet_operations __net_initdata tcp_sk_ops = { + .init = tcp_sk_init, + .exit = tcp_sk_exit, + .exit_batch = tcp_sk_exit_batch, +}; + +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta, + struct sock_common *sk_common, uid_t uid) + +static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct tcp_iter_state *st = priv_data; + struct tcp_seq_afinfo *afinfo; + int ret; + + afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); + if (!afinfo) + return -ENOMEM; + + afinfo->family = AF_UNSPEC; + st->bpf_seq_afinfo = afinfo; + ret = bpf_iter_init_seq_net(priv_data, aux); + if (ret) + kfree(afinfo); + return ret; +} + +static void bpf_iter_fini_tcp(void *priv_data) +{ + struct tcp_iter_state *st = priv_data; + + kfree(st->bpf_seq_afinfo); + bpf_iter_fini_seq_net(priv_data); +} + +static const struct bpf_iter_seq_info tcp_seq_info = { + .seq_ops = &bpf_iter_tcp_seq_ops, + .init_seq_private = bpf_iter_init_tcp, + .fini_seq_private = bpf_iter_fini_tcp, + .seq_priv_size = sizeof(struct tcp_iter_state), +}; + +static struct bpf_iter_reg tcp_reg_info = { + .target = "tcp", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__tcp, sk_common), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &tcp_seq_info, +}; + +static void __init bpf_iter_register(void) +{ + tcp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON]; + if (bpf_iter_reg_target(&tcp_reg_info)) + pr_warn("Warning: could not register bpf iterator tcp\n"); +} + +#endif + +void __init tcp_v4_init(void) +{ + int cpu, res; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, &init_net); + if (res) + panic("Failed to create the TCP control socket.\n"); + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + + per_cpu(ipv4_tcp_sk, cpu) = sk; + } + if (register_pernet_subsys(&tcp_sk_ops)) + panic("Failed to create the TCP control socket.\n"); + +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) + bpf_iter_register(); +#endif +} |