// 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 <linux/sched.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, &addr_len);
}

/* 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_timewait_death_row *tcp_death_row;
        struct inet_sock *inet = inet_sk(sk);
        struct tcp_sock *tp = tcp_sk(sk);
        struct ip_options_rcu *inet_opt;
        struct net *net = sock_net(sk);
        __be16 orig_sport, orig_dport;
        __be32 daddr, nexthop;
        struct flowi4 *fl4;
        struct rtable *rt;
        int err;

        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,
                              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(net, 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;

        tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;

        if (!inet->inet_saddr) {
                err = inet_bhash2_update_saddr(sk,  &fl4->saddr, AF_INET);
                if (err) {
                        ip_rt_put(rt);
                        return err;
                }
        } else {
                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;
        }
        tp->tcp_usec_ts = dst_tcp_usec_ts(&rt->dst);
        /* 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));
                WRITE_ONCE(tp->tsoffset,
                           secure_tcp_ts_off(net, inet->inet_saddr,
                                             inet->inet_daddr));
        }

        atomic_set(&inet->inet_id, get_random_u16());

        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);
        inet_bhash2_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))
                WRITE_ONCE(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;
        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, net->ipv4.tcp_death_row.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) {
                /* To increase the counter of ignored icmps for TCP-AO */
                tcp_ao_ignore_icmp(sk, AF_INET, type, code);
                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;
        }

        if (tcp_ao_ignore_icmp(sk, AF_INET, type, code)) {
                sock_put(sk);
                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 (static_branch_unlikely(&ip4_min_ttl)) {
                /* min_ttl can be changed concurrently from do_ip_setsockopt() */
                if (unlikely(iph->ttl < READ_ONCE(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)) {
                        WRITE_ONCE(sk->sk_err, err);

                        sk_error_report(sk);

                        tcp_done(sk);
                } else {
                        WRITE_ONCE(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)
         */

        if (!sock_owned_by_user(sk) &&
            inet_test_bit(RECVERR, sk)) {
                WRITE_ONCE(sk->sk_err, err);
                sk_error_report(sk);
        } else  { /* Only an error on timeout */
                WRITE_ONCE(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);

#define REPLY_OPTIONS_LEN      (MAX_TCP_OPTION_SPACE / sizeof(__be32))

static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
                                 const struct tcp_ao_hdr *aoh,
                                 struct ip_reply_arg *arg, struct tcphdr *reply,
                                 __be32 reply_options[REPLY_OPTIONS_LEN])
{
#ifdef CONFIG_TCP_AO
        int sdif = tcp_v4_sdif(skb);
        int dif = inet_iif(skb);
        int l3index = sdif ? dif : 0;
        bool allocated_traffic_key;
        struct tcp_ao_key *key;
        char *traffic_key;
        bool drop = true;
        u32 ao_sne = 0;
        u8 keyid;

        rcu_read_lock();
        if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, ntohl(reply->seq),
                                 &key, &traffic_key, &allocated_traffic_key,
                                 &keyid, &ao_sne))
                goto out;

        reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) |
                                 (aoh->rnext_keyid << 8) | keyid);
        arg->iov[0].iov_len += tcp_ao_len_aligned(key);
        reply->doff = arg->iov[0].iov_len / 4;

        if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1],
                            key, traffic_key,
                            (union tcp_ao_addr *)&ip_hdr(skb)->saddr,
                            (union tcp_ao_addr *)&ip_hdr(skb)->daddr,
                            reply, ao_sne))
                goto out;
        drop = false;
out:
        rcu_read_unlock();
        if (allocated_traffic_key)
                kfree(traffic_key);
        return drop;
#else
        return true;
#endif
}

/*
 *      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;
                __be32 opt[REPLY_OPTIONS_LEN];
        } rep;
        const __u8 *md5_hash_location = NULL;
        const struct tcp_ao_hdr *aoh;
        struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
        struct tcp_md5sig_key *key = NULL;
        unsigned char newhash[16];
        struct sock *sk1 = NULL;
        int genhash;
#endif
        u64 transmit_time = 0;
        struct sock *ctl_sk;
        struct net *net;
        u32 txhash = 0;

        /* 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);

        /* Invalid TCP option size or twice included auth */
        if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh))
                return;

        if (aoh && tcp_v4_ao_sign_reset(sk, skb, aoh, &arg, &rep.th, rep.opt))
                return;

#ifdef CONFIG_TCP_MD5SIG
        rcu_read_lock();
        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 (md5_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, net->ipv4.tcp_death_row.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(md5_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
        /* Can't co-exist with TCPMD5, hence check rep.opt[0] */
        if (rep.opt[0] == 0) {
                __be32 mrst = mptcp_reset_option(skb);

                if (mrst) {
                        rep.opt[0] = mrst;
                        arg.iov[0].iov_len += sizeof(mrst);
                        rep.th.doff = arg.iov[0].iov_len / 4;
                }
        }

        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 : READ_ONCE(sk->sk_priority);
                transmit_time = tcp_transmit_time(sk);
                xfrm_sk_clone_policy(ctl_sk, sk);
                txhash = (sk->sk_state == TCP_TIME_WAIT) ?
                         inet_twsk(sk)->tw_txhash : sk->sk_txhash;
        } 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, txhash);

        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_key *key,
                            int reply_flags, u8 tos, u32 txhash)
{
        const struct tcphdr *th = tcp_hdr(skb);
        struct {
                struct tcphdr th;
                __be32 opt[(MAX_TCP_OPTION_SPACE  >> 2)];
        } 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 (tcp_key_is_md5(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->md5_key, ip_hdr(skb)->saddr,
                                    ip_hdr(skb)->daddr, &rep.th);
        }
#endif
#ifdef CONFIG_TCP_AO
        if (tcp_key_is_ao(key)) {
                int offset = (tsecr) ? 3 : 0;

                rep.opt[offset++] = htonl((TCPOPT_AO << 24) |
                                          (tcp_ao_len(key->ao_key) << 16) |
                                          (key->ao_key->sndid << 8) |
                                          key->rcv_next);
                arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key);
                rep.th.doff = arg.iov[0].iov_len / 4;

                tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],
                                key->ao_key, key->traffic_key,
                                (union tcp_ao_addr *)&ip_hdr(skb)->saddr,
                                (union tcp_ao_addr *)&ip_hdr(skb)->daddr,
                                &rep.th, key->sne);
        }
#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 : READ_ONCE(sk->sk_mark);
        ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
                           inet_twsk(sk)->tw_priority : READ_ONCE(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, txhash);

        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);
        struct tcp_key key = {};
#ifdef CONFIG_TCP_AO
        struct tcp_ao_info *ao_info;

        if (static_branch_unlikely(&tcp_ao_needed.key)) {
                /* FIXME: the segment to-be-acked is not verified yet */
                ao_info = rcu_dereference(tcptw->ao_info);
                if (ao_info) {
                        const struct tcp_ao_hdr *aoh;

                        if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) {
                                inet_twsk_put(tw);
                                return;
                        }

                        if (aoh)
                                key.ao_key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1);
                }
        }
        if (key.ao_key) {
                struct tcp_ao_key *rnext_key;

                key.traffic_key = snd_other_key(key.ao_key);
                key.sne = READ_ONCE(ao_info->snd_sne);
                rnext_key = READ_ONCE(ao_info->rnext_key);
                key.rcv_next = rnext_key->rcvid;
                key.type = TCP_KEY_AO;
#else
        if (0) {
#endif
#ifdef CONFIG_TCP_MD5SIG
        } else if (static_branch_unlikely(&tcp_md5_needed.key)) {
                key.md5_key = tcp_twsk_md5_key(tcptw);
                if (key.md5_key)
                        key.type = TCP_KEY_MD5;
#endif
        }

        tcp_v4_send_ack(sk, skb,
                        tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
                        tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
                        tcp_tw_tsval(tcptw),
                        tcptw->tw_ts_recent,
                        tw->tw_bound_dev_if, &key,
                        tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
                        tw->tw_tos,
                        tw->tw_txhash);

        inet_twsk_put(tw);
}

static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
                                  struct request_sock *req)
{
        struct tcp_key key = {};

        /* 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;

#ifdef CONFIG_TCP_AO
        if (static_branch_unlikely(&tcp_ao_needed.key) &&
            tcp_rsk_used_ao(req)) {
                const union tcp_md5_addr *addr;
                const struct tcp_ao_hdr *aoh;
                int l3index;

                /* Invalid TCP option size or twice included auth */
                if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
                        return;
                if (!aoh)
                        return;

                addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr;
                l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0;
                key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET,
                                              aoh->rnext_keyid, -1);
                if (unlikely(!key.ao_key)) {
                        /* Send ACK with any matching MKT for the peer */
                        key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, -1, -1);
                        /* Matching key disappeared (user removed the key?)
                         * let the handshake timeout.
                         */
                        if (!key.ao_key) {
                                net_info_ratelimited("TCP-AO key for (%pI4, %d)->(%pI4, %d) suddenly disappeared, won't ACK new connection\n",
                                                     addr,
                                                     ntohs(tcp_hdr(skb)->source),
                                                     &ip_hdr(skb)->daddr,
                                                     ntohs(tcp_hdr(skb)->dest));
                                return;
                        }
                }
                key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC);
                if (!key.traffic_key)
                        return;

                key.type = TCP_KEY_AO;
                key.rcv_next = aoh->keyid;
                tcp_v4_ao_calc_key_rsk(key.ao_key, key.traffic_key, req);
#else
        if (0) {
#endif
#ifdef CONFIG_TCP_MD5SIG
        } else if (static_branch_unlikely(&tcp_md5_needed.key)) {
                const union tcp_md5_addr *addr;
                int l3index;

                addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr;
                l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0;
                key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
                if (key.md5_key)
                        key.type = TCP_KEY_MD5;
#endif
        }

        /* 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:
         */
        tcp_v4_send_ack(sk, skb, seq,
                        tcp_rsk(req)->rcv_nxt,
                        req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
                        tcp_rsk_tsval(tcp_rsk(req)),
                        READ_ONCE(req->ts_recent),
                        0, &key,
                        inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
                        ip_hdr(skb)->tos,
                        READ_ONCE(tcp_rsk(req)->txhash));
        if (tcp_key_is_ao(&key))
                kfree(key.traffic_key);
}

/*
 *      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(inet_sk(sk)->tos);

                if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
                        tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
                              (tos & INET_ECN_MASK);

                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_DEFERRED_FALSE(tcp_md5_needed, HZ);
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, bool any_l3index)
{
        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 (!any_l3index && key->flags & TCP_MD5SIG_FLAG_IFINDEX &&
                    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, u8 flags)
{
        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->flags & TCP_MD5SIG_FLAG_IFINDEX) != (flags & TCP_MD5SIG_FLAG_IFINDEX))
                        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);

static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp)
{
        struct tcp_sock *tp = tcp_sk(sk);
        struct tcp_md5sig_info *md5sig;

        md5sig = kmalloc(sizeof(*md5sig), gfp);
        if (!md5sig)
                return -ENOMEM;

        sk_gso_disable(sk);
        INIT_HLIST_HEAD(&md5sig->head);
        rcu_assign_pointer(tp->md5sig_info, md5sig);
        return 0;
}

/* This can be called on a newly created socket, from other files */
static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
                            int family, u8 prefixlen, int l3index, u8 flags,
                            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, flags);
        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));

        key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO);
        if (!key)
                return -ENOMEM;

        memcpy(key->key, newkey, newkeylen);
        key->keylen = newkeylen;
        key->family = family;
        key->prefixlen = prefixlen;
        key->l3index = l3index;
        key->flags = flags;
        memcpy(&key->addr, addr,
               (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) ? sizeof(struct in6_addr) :
                                                                 sizeof(struct in_addr));
        hlist_add_head_rcu(&key->node, &md5sig->head);
        return 0;
}

int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
                   int family, u8 prefixlen, int l3index, u8 flags,
                   const u8 *newkey, u8 newkeylen)
{
        struct tcp_sock *tp = tcp_sk(sk);

        if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) {
                if (tcp_md5_alloc_sigpool())
                        return -ENOMEM;

                if (tcp_md5sig_info_add(sk, GFP_KERNEL)) {
                        tcp_md5_release_sigpool();
                        return -ENOMEM;
                }

                if (!static_branch_inc(&tcp_md5_needed.key)) {
                        struct tcp_md5sig_info *md5sig;

                        md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk));
                        rcu_assign_pointer(tp->md5sig_info, NULL);
                        kfree_rcu(md5sig, rcu);
                        tcp_md5_release_sigpool();
                        return -EUSERS;
                }
        }

        return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags,
                                newkey, newkeylen, GFP_KERNEL);
}
EXPORT_SYMBOL(tcp_md5_do_add);

int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr,
                     int family, u8 prefixlen, int l3index,
                     struct tcp_md5sig_key *key)
{
        struct tcp_sock *tp = tcp_sk(sk);

        if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) {
                tcp_md5_add_sigpool();

                if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) {
                        tcp_md5_release_sigpool();
                        return -ENOMEM;
                }

                if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) {
                        struct tcp_md5sig_info *md5sig;

                        md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk));
                        net_warn_ratelimited("Too many TCP-MD5 keys in the system\n");
                        rcu_assign_pointer(tp->md5sig_info, NULL);
                        kfree_rcu(md5sig, rcu);
                        tcp_md5_release_sigpool();
                        return -EUSERS;
                }
        }

        return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index,
                                key->flags, key->key, key->keylen,
                                sk_gfp_mask(sk, GFP_ATOMIC));
}
EXPORT_SYMBOL(tcp_md5_key_copy);

int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
                   u8 prefixlen, int l3index, u8 flags)
{
        struct tcp_md5sig_key *key;

        key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags);
        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);

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;
        bool l3flag;
        u8 flags;

        if (optlen < sizeof(cmd))
                return -EINVAL;

        if (copy_from_sockptr(&cmd, optval, sizeof(cmd)))
                return -EFAULT;

        if (sin->sin_family != AF_INET)
                return -EINVAL;

        flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
        l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;

        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_ifindex &&
            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, flags);

        if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
                return -EINVAL;

        /* Don't allow keys for peers that have a matching TCP-AO key.
         * See the comment in tcp_ao_add_cmd()
         */
        if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false))
                return -EKEYREJECTED;

        return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags,
                              cmd.tcpm_key, cmd.tcpm_keylen);
}

static int tcp_v4_md5_hash_headers(struct tcp_sigpool *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->req, &sg, NULL,
                                sizeof(*bp) + sizeof(*th));
        return crypto_ahash_update(hp->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_sigpool hp;

        if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp))
                goto clear_hash_nostart;

        if (crypto_ahash_init(hp.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(hp.req, NULL, md5_hash, 0);
        if (crypto_ahash_final(hp.req))
                goto clear_hash;

        tcp_sigpool_end(&hp);
        return 0;

clear_hash:
        tcp_sigpool_end(&hp);
clear_hash_nostart:
        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)
{
        const struct tcphdr *th = tcp_hdr(skb);
        struct tcp_sigpool hp;
        __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;
        }

        if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp))
                goto clear_hash_nostart;

        if (crypto_ahash_init(hp.req))
                goto clear_hash;

        if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, skb->len))
                goto clear_hash;
        if (tcp_sigpool_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(hp.req, NULL, md5_hash, 0);
        if (crypto_ahash_final(hp.req))
                goto clear_hash;

        tcp_sigpool_end(&hp);
        return 0;

clear_hash:
        tcp_sigpool_end(&hp);
clear_hash_nostart:
        memset(md5_hash, 0, 16);
        return 1;
}
EXPORT_SYMBOL(tcp_v4_md5_hash_skb);

#endif

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 sk_buff *skb,
                                          struct flowi *fl,
                                          struct request_sock *req)
{
        tcp_v4_init_req(req, sk, skb);

        if (security_inet_conn_request(sk, skb, req))
                return NULL;

        return inet_csk_route_req(sk, &fl->u.ip4, req);
}

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
#ifdef CONFIG_TCP_AO
        .ao_lookup      =       tcp_v4_ao_lookup_rsk,
        .ao_calc_key    =       tcp_v4_ao_calc_key_rsk,
        .ao_synack_hash =       tcp_v4_ao_synack_hash,
#endif
#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;
        atomic_set(&newinet->inet_id, get_random_u16());

        /* 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 && !tcp_rsk_used_ao(req)) {
                if (tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key))
                        goto put_and_exit;
                sk_gso_disable(newsk);
        }
#endif
#ifdef CONFIG_TCP_AO
        if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET))
                goto put_and_exit; /* OOM, release back memory */
#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;
}

INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
                                                           u32));
/* 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)
{
        enum skb_drop_reason reason;
        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 (sk->sk_rx_dst_ifindex != skb->skb_iif ||
                            !INDIRECT_CALL_1(dst->ops->check, ipv4_dst_check,
                                             dst, 0)) {
                                RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
                                dst_release(dst);
                        }
                }
                tcp_rcv_established(sk, skb);
                return 0;
        }

        reason = SKB_DROP_REASON_NOT_SPECIFIED;
        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_reason(skb, reason);
        /* 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:
        reason = SKB_DROP_REASON_TCP_CSUM;
        trace_tcp_bad_csum(skb);
        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)
{
        struct net *net = dev_net(skb->dev);
        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(net, net->ipv4.tcp_death_row.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 &&
                            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,
                     enum skb_drop_reason *reason)
{
        u32 limit, tail_gso_size, tail_gso_segs;
        struct skb_shared_info *shinfo;
        const struct tcphdr *th;
        struct tcphdr *thtail;