/* consumes sk */ void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { /* assigning tw sockets complicates things; most * skb->sk->X checks would have to test sk->sk_state first */ if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } skb_orphan(skb); skb->sk = sk; skb->destructor = nf_tproxy_destructor; }
int bastet_sync_prop_start(struct bst_set_sock_sync_prop *set_prop) { int err = 0; struct sock *sk; struct bastet_sock *bsk; struct bst_sock_comm_prop *guide = &set_prop->guide; sk = get_sock_by_comm_prop(guide); if (NULL == sk) { BASTET_LOGE("can not find sock by lport: %d, lIp: %pI4, rport: %d, rIp: %pI4", guide->local_port, &guide->local_ip, guide->remote_port, &guide->remote_ip); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { BASTET_LOGE("sk: %p not expected time wait sock", sk); inet_twsk_put(inet_twsk(sk)); return -EPERM; } bsk = sk->bastet; if (NULL == bsk) { BASTET_LOGE("sk: %p not expected bastet null", sk); err = -EPERM; goto out_put; } BASTET_LOGI("sk: %p", sk); if (NULL != bsk->sync_p) { BASTET_LOGE("sk: %p has a pending sock set", sk); err = -EPERM; goto out; } sock_set_internal(sk, &set_prop->sync_prop); bastet_sync_prop_cancel(sk); bsk->flag = true; BASTET_LOGI("wake up bastet wq"); wake_up_interruptible(&bsk->wq); out: adjust_traffic_flow_by_sock(sk, set_prop->sync_prop.tx, set_prop->sync_prop.rx); out_put: sock_put(sk); return err; }
/******************************************************************************* 函数名称: sslvpn_data_packet 功能描述: 判断sslvpn报文类型 输入参数: skb 输出参数: 无 返 回 值: 0 非sslvpn 报文 1 sslvpn 报文 -------------------------------------------------------------------------------- 最近一次修改记录: 修改作者: 谢永超 修改目的: 创建新函数 修改日期: 2010年8月9日 ********************************************************************************/ s32 sslvpn_data_packet(struct sk_buff *skb) { s32 ret = 0; #ifdef CONFIG_KSSL if(skb->nh.iph->protocol == IPPROTO_TCP) { int ihl = 0; struct tcphdr *th = NULL; struct iphdr *iph = NULL; struct sock *sk = NULL; ihl =skb->nh.iph->ihl * 4; th = (struct tcphdr *)(skb->nh.raw + ihl); iph = skb->nh.iph; sk = __inet_lookup(&init_vrf, 0, &tcp_hashinfo,iph->saddr,th->source,iph->daddr,th->dest,inet_iif(skb)); if (sk) { if (sk->ssl) { ret = 1; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); } else { sock_put(sk); } } } #endif return ret; }
static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { struct sock *sk; sk = xt_socket_get4_sk(skb, par); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY, * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return (sk != NULL); }
static bool socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6hdr *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; struct in6_addr *daddr, *saddr; __be16 dport, sport; int thoff = 0, tproto; const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); return NF_DROP; } if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) { hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; saddr = &iph->saddr; sport = hp->source; daddr = &iph->daddr; dport = hp->dest; } else if (tproto == IPPROTO_ICMPV6) { if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport)) return false; } else { return false; } sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); if (sk != NULL) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY */ wildcard = (sk->sk_state != TCP_TIME_WAIT && ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ if (info && info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; } pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " "(orig %pI6:%hu) sock %p\n", tproto, saddr, ntohs(sport), daddr, ntohs(dport), &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return (sk != NULL); }
static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; __be32 daddr, saddr; __be16 dport, sport; u8 protocol; #ifdef XT_SOCKET_HAVE_CONNTRACK struct nf_conn const *ct; enum ip_conntrack_info ctinfo; #endif if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) return false; protocol = iph->protocol; saddr = iph->saddr; sport = hp->source; daddr = iph->daddr; dport = hp->dest; } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, &sport, &dport)) return false; } else { return false; } #ifdef XT_SOCKET_HAVE_CONNTRACK /* Do the lookup with the original socket address in case this is a * reply packet of an established SNAT-ted connection. */ ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && ctinfo == IP_CT_ESTABLISHED_REPLY) || (iph->protocol == IPPROTO_ICMP && ctinfo == IP_CT_RELATED_REPLY)) && (ct->status & IPS_SRC_NAT_DONE)) { daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; dport = (iph->protocol == IPPROTO_TCP) ? ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port : ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; } #endif sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); if (sk != NULL) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY */ wildcard = (sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ if (info && info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; } pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", protocol, &saddr, ntohs(sport), &daddr, ntohs(dport), &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return (sk != NULL); }
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { const struct inet_sock *inet = inet_sk(sk); const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; int ext = req->idiag_ext; struct inet_diag_msg *r; struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; handler = inet_diag_table[req->sdiag_protocol]; BUG_ON(!handler); nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); BUG_ON(!sk_fullsock(sk)); inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) goto errout; /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, * hence this needs to be included regardless of socket family. */ if (ext & (1 << (INET_DIAG_TOS - 1))) if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0) goto errout; #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { if (ext & (1 << (INET_DIAG_TCLASS - 1))) if (nla_put_u8(skb, INET_DIAG_TCLASS, inet6_sk(sk)->tclass) < 0) goto errout; if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk))) goto errout; } #endif r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), .idiag_wmem = sk->sk_wmem_queued, .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0) goto errout; } if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) goto errout; if (!icsk) { handler->idiag_get_info(sk, r, NULL); goto out; } #define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ) if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { r->idiag_timer = 1; r->idiag_retrans = icsk->icsk_retransmits; r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout); } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { r->idiag_timer = 4; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout); } else if (timer_pending(&sk->sk_timer)) { r->idiag_timer = 2; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires); } else { r->idiag_timer = 0; r->idiag_expires = 0; } #undef EXPIRES_IN_MS if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { attr = nla_reserve(skb, INET_DIAG_INFO, handler->idiag_info_size); if (!attr) goto errout; info = nla_data(attr); } if (ext & (1 << (INET_DIAG_CONG - 1))) { int err = 0; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops) err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name); rcu_read_unlock(); if (err < 0) goto errout; } handler->idiag_get_info(sk, r, info); if (sk->sk_state < TCP_TIME_WAIT) { union tcp_cc_info info; size_t sz = 0; int attr; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ext, &attr, &info); rcu_read_unlock(); if (sz && nla_put(skb, attr, sz, &info) < 0) goto errout; } out: nlmsg_end(skb, nlh); return 0; errout: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_csk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, portid, seq, nlmsg_flags, unlh); } static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); BUG_ON(tw->tw_state != TCP_TIME_WAIT); tmo = tw->tw_timer.expires - jiffies; if (tmo < 0) tmo = 0; inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; r->idiag_state = tw->tw_substate; r->idiag_timer = 3; r->idiag_expires = jiffies_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; nlmsg_end(skb, nlh); return 0; } static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; r->idiag_retrans = inet_reqsk(sk)->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0; r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; nlmsg_end(skb, nlh); return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, portid, seq, nlmsg_flags, unlh); if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, portid, seq, nlmsg_flags, unlh); return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh); } struct sock *inet_diag_find_one_icsk(struct net *net, struct inet_hashinfo *hashinfo, const struct inet_diag_req_v2 *req) { struct sock *sk; if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if); else sk = inet6_lookup(net, hashinfo, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if); } #endif else return ERR_PTR(-EINVAL); if (!sk) return ERR_PTR(-ENOENT); if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_gen_put(sk); return ERR_PTR(-ENOENT); } return sk; } EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { struct net *net = sock_net(in_skb->sk); struct sk_buff *rep; struct sock *sk; int err; sk = inet_diag_find_one_icsk(net, hashinfo, req); if (IS_ERR(sk)) return PTR_ERR(sk); rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; } err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); goto out; } err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); if (err > 0) err = 0; out: if (sk) sock_gen_put(sk); return err; } EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { const struct inet_diag_handler *handler; int err; handler = inet_diag_lock_handler(req->sdiag_protocol); if (IS_ERR(handler)) err = PTR_ERR(handler); else if (cmd == SOCK_DIAG_BY_FAMILY) err = handler->dump_one(in_skb, nlh, req); else if (cmd == SOCK_DESTROY_BACKPORT && handler->destroy) err = handler->destroy(in_skb, req); else err = -EOPNOTSUPP; inet_diag_unlock_handler(handler); return err; } static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits) { int words = bits >> 5; bits &= 0x1f; if (words) { if (memcmp(a1, a2, words << 2)) return 0; } if (bits) { __be32 w1, w2; __be32 mask; w1 = a1[words]; w2 = a2[words]; mask = htonl((0xffffffff) << (32 - bits)); if ((w1 ^ w2) & mask) return 0; } return 1; }
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; struct net *net = dev_net(skb->dev); if (skb->len < offset + sizeof(*dh) || skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } sk = inet6_lookup(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); if (sk == NULL) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == NDISC_REDIRECT) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); goto out; } if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (!ip6_sk_accept_pmtu(sk)) goto out; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; dst = inet6_csk_update_pmtu(sk, ntohl(info)); if (!dst) goto out; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { struct request_sock *req, **prev; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (req == NULL) goto out; /* * ICMPs are not backlogged, hence we cannot get an established * socket here. */ WARN_ON(req->sk != NULL); if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; /* * Wake people up to see the error * (see connect in sock.c) */ sk->sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; goto out; } if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }
static int dccp_v6_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; struct sock *sk; int min_cov; /* Step 1: Check header basics */ if (dccp_invalid_packet(skb)) goto discard_it; /* Step 1: If header checksum is incorrect, drop packet and return. */ if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr)) { DCCP_WARN("dropped packet with invalid checksum\n"); goto discard_it; } dh = dccp_hdr(skb); DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; if (dccp_packet_without_ack(skb)) DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; else DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); /* Step 2: * Look up flow ID in table and get corresponding socket */ sk = __inet6_lookup_skb(&dccp_hashinfo, skb, dh->dccph_sport, dh->dccph_dport); /* * Step 2: * If no socket ... */ if (sk == NULL) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; } /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (sk->sk_state == DCCP_TIME_WAIT) { dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n"); inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov */ min_cov = dccp_sk(sk)->dccps_pcrlen; if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) { dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n", dh->dccph_cscov, min_cov); /* FIXME: send Data Dropped option (see also dccp_v4_rcv) */ goto discard_and_relse; } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; return sk_receive_skb(sk, skb, 1) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; dccp_v6_ctl_send_reset(sk, skb); } discard_it: kfree_skb(skb); return 0; discard_and_relse: sock_put(sk); goto discard_it; }
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; struct net *net = dev_net(skb->dev); if (skb->len < offset + sizeof(*dh) || skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } sk = inet6_lookup(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); if (sk == NULL) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; /* icmp should have updated the destination cache entry */ dst = __sk_dst_check(sk, np->dst_cookie); if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); struct flowi fl; /* BUGGG_FUTURE: Again, it is not clear how to handle rthdr case. Ignore this complexity for now. */ memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_DCCP; ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; security_sk_classify_flow(sk, &fl); err = ip6_dst_lookup(sk, &dst, &fl); if (err) { sk->sk_err_soft = -err; goto out; } err = xfrm_lookup(net, &dst, &fl, sk, 0); if (err < 0) { sk->sk_err_soft = -err; goto out; } } else dst_hold(dst); if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { dccp_sync_mss(sk, dst_mtu(dst)); } /* else let the usual retransmit timer handle it */ dst_release(dst); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { struct request_sock *req, **prev; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (req == NULL) goto out; /* * ICMPs are not backlogged, hence we cannot get an established * socket here. */ WARN_ON(req->sk != NULL); if (seq != dccp_rsk(req)->dreq_iss) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; /* * Wake people up to see the error * (see connect in sock.c) */ sk->sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; goto out; } if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }
static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; __u64 seq; int err; struct net *net = dev_net(skb->dev); if (skb->len < offset + sizeof(*dh) || skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } sk = inet_lookup(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, iph->saddr, dh->dccph_sport, inet_iif(skb)); if (sk == NULL) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_SOURCE_QUENCH: goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { if (!sock_owned_by_user(sk)) dccp_do_pmtu_discovery(sk, iph, info); goto out; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { struct request_sock *req , **prev; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet_csk_search_req(sk, &prev, dh->dccph_dport, iph->daddr, iph->saddr); if (!req) goto out; WARN_ON(req->sk); if (seq != dccp_rsk(req)->dreq_iss) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; goto out; } inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }
/* * 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. */ static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; __u64 seq; int err; struct net *net = dev_net(skb->dev); if (skb->len < offset + sizeof(*dh) || skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } sk = __inet_lookup_established(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, iph->saddr, ntohs(dh->dccph_sport), inet_iif(skb)); if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } seq = dccp_hdr_seq(dh); if (sk->sk_state == DCCP_NEW_SYN_RECV) return dccp_req_err(sk, seq); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_REDIRECT: dccp_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) */ if (!sock_owned_by_user(sk)) dccp_do_pmtu_discovery(sk, iph, info); goto out; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); dccp_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); }
/* * 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. */ static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + (iph->ihl << 2)); struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; __u64 seq; int err; if (skb->len < (iph->ihl << 2) + 8) { ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); return; } sk = inet_lookup(&dccp_hashinfo, iph->daddr, dh->dccph_dport, iph->saddr, dh->dccph_sport, inet_iif(skb)); if (sk == NULL) { ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); seq = dccp_hdr_seq(skb); if (sk->sk_state != DCCP_LISTEN && !between48(seq, dp->dccps_swl, dp->dccps_swh)) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { 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) */ if (!sock_owned_by_user(sk)) dccp_do_pmtu_discovery(sk, iph, info); goto out; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { struct request_sock *req , **prev; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet_csk_search_req(sk, &prev, dh->dccph_dport, iph->daddr, iph->saddr); if (!req) goto out; /* * ICMPs are not backlogged, hence we cannot get an established * socket here. */ WARN_ON(req->sk); if (seq != dccp_rsk(req)->dreq_iss) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } /* * Still in RESPOND, 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(sk, req, prev); goto out; case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); dccp_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); }
static bool socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { static struct xt_socket_mtinfo1 xt_info_v0 = { .flags = 0, }; return socket_match(skb, par, &xt_info_v0); } static bool socket_mt4_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } #ifdef XT_SOCKET_HAVE_IPV6 static int extract_icmp6_fields(const struct sk_buff *skb, unsigned int outside_hdrlen, int *protocol, const struct in6_addr **raddr, const struct in6_addr **laddr, __be16 *rport, __be16 *lport, struct ipv6hdr *ipv6_var) { const struct ipv6hdr *inside_iph; struct icmp6hdr *icmph, _icmph; __be16 *ports, _ports[2]; u8 inside_nexthdr; __be16 inside_fragoff; int inside_hdrlen; icmph = skb_header_pointer(skb, outside_hdrlen, sizeof(_icmph), &_icmph); if (icmph == NULL) return 1; if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK) return 1; inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), sizeof(*ipv6_var), ipv6_var); if (inside_iph == NULL) return 1; inside_nexthdr = inside_iph->nexthdr; inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(*ipv6_var), &inside_nexthdr, &inside_fragoff); if (inside_hdrlen < 0) return 1; /* hjm: Packet has no/incomplete transport layer headers. */ if (inside_nexthdr != IPPROTO_TCP && inside_nexthdr != IPPROTO_UDP) return 1; ports = skb_header_pointer(skb, inside_hdrlen, sizeof(_ports), &_ports); if (ports == NULL) return 1; /* the inside IP packet is the one quoted from our side, thus * its saddr is the local address */ *protocol = inside_nexthdr; *laddr = &inside_iph->saddr; *lport = ports[0]; *raddr = &inside_iph->daddr; *rport = ports[1]; return 0; } static struct sock * xt_socket_get_sock_v6(struct net *net, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, const struct net_device *in) { switch (protocol) { case IPPROTO_TCP: return inet6_lookup(net, &tcp_hashinfo, saddr, sport, daddr, dport, in->ifindex); case IPPROTO_UDP: return udp6_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); } return NULL; } static bool socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6hdr ipv6_var, *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk = skb->sk; const struct in6_addr *daddr = NULL, *saddr = NULL; __be16 uninitialized_var(dport), uninitialized_var(sport); int thoff = 0, uninitialized_var(tproto); const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); return NF_DROP; } if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) { hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; saddr = &iph->saddr; sport = hp->source; daddr = &iph->daddr; dport = hp->dest; } else if (tproto == IPPROTO_ICMPV6) { if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport, &ipv6_var)) return false; } else { return false; } if (!sk) sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, sport, dport, par->in); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk->sk_state != TCP_TIME_WAIT && ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " "(orig %pI6:%hu) sock %p\n", tproto, saddr, ntohs(sport), daddr, ntohs(dport), &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return (sk != NULL); } #endif static int socket_mt_v1_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; if (info->flags & ~XT_SOCKET_FLAGS_V1) { pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); return -EINVAL; } return 0; } static int socket_mt_v2_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo; if (info->flags & ~XT_SOCKET_FLAGS_V2) { pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); return -EINVAL; } return 0; } static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", .revision = 0, .family = NFPROTO_IPV4, .match = socket_mt4_v0, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #ifdef XT_SOCKET_HAVE_IPV6 { .name = "socket",
static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; struct net *net = dev_net(skb->dev); /* Only need dccph_dport & dccph_sport which are the first * 4 bytes in dccp header. * Our caller (icmpv6_notify()) already pulled 8 bytes for us. */ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, ntohs(dh->dccph_sport), inet6_iif(skb), 0); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return 0; } seq = dccp_hdr_seq(dh); if (sk->sk_state == DCCP_NEW_SYN_RECV) { dccp_req_err(sk, seq); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (!ip6_sk_accept_pmtu(sk)) goto out; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; dst = inet6_csk_update_pmtu(sk, ntohl(info)); if (!dst) goto out; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; /* * Wake people up to see the error * (see connect in sock.c) */ sk->sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; goto out; } if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); return 0; }
static int dccp_v6_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; bool refcounted; struct sock *sk; int min_cov; /* Step 1: Check header basics */ if (dccp_invalid_packet(skb)) goto discard_it; /* Step 1: If header checksum is incorrect, drop packet and return. */ if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr)) { DCCP_WARN("dropped packet with invalid checksum\n"); goto discard_it; } dh = dccp_hdr(skb); DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; if (dccp_packet_without_ack(skb)) DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; else DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); lookup: sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, inet6_iif(skb), 0, &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; } /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (sk->sk_state == DCCP_TIME_WAIT) { dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n"); inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); struct sock *nsk; sk = req->rsk_listener; if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sock_hold(sk); refcounted = true; nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); goto discard_and_relse; } else { sock_put(sk); return 0; } } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov */ min_cov = dccp_sk(sk)->dccps_pcrlen; if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) { dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n", dh->dccph_cscov, min_cov); /* FIXME: send Data Dropped option (see also dccp_v4_rcv) */ goto discard_and_relse; } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; dccp_v6_ctl_send_reset(sk, skb); } discard_it: kfree_skb(skb); return 0; discard_and_relse: if (refcounted) sock_put(sk); goto discard_it; }
/* Similar to: tcp_v4_do_rcv * We only process join requests here. (either the SYN or the final ACK) */ int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); struct sock *child, *rsk = NULL, *sk; int ret; sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (!sk) goto new_subflow; if (is_meta_sk(sk)) { WARN("%s Did not find a sub-sk - did found the meta!\n", __func__); sock_put(sk); goto discard; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); goto discard; } if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen; if (!mptcp_can_new_subflow(meta_sk)) goto reset_and_discard; local_bh_disable(); child = tcp_check_req(meta_sk, skb, req, false, &req_stolen); if (!child) { reqsk_put(req); local_bh_enable(); goto discard; } if (child != meta_sk) { ret = mptcp_finish_handshake(child, skb); if (ret) { rsk = child; local_bh_enable(); goto reset_and_discard; } local_bh_enable(); return 0; } /* tcp_check_req failed */ reqsk_put(req); local_bh_enable(); goto discard; } ret = tcp_v4_do_rcv(sk, skb); sock_put(sk); return ret; new_subflow: if (!mptcp_can_new_subflow(meta_sk)) goto reset_and_discard; child = tcp_v4_cookie_check(meta_sk, skb); if (!child) goto discard; if (child != meta_sk) { ret = mptcp_finish_handshake(child, skb); if (ret) { rsk = child; goto reset_and_discard; } } if (tcp_hdr(skb)->syn) { local_bh_disable(); mptcp_v4_join_request(meta_sk, skb); local_bh_enable(); } discard: kfree_skb(skb); return 0; reset_and_discard: tcp_v4_send_reset(rsk, skb); goto discard; }
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct ipv6_pinfo *np; struct sock *sk; int err; struct tcp_sock *tp; __u32 seq; struct net *net = dev_net(skb->dev); sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr, th->source, skb->dev->ifindex); if (sk == NULL) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) { NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); goto out; } tp = tcp_sk(sk); seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && !between(seq, tp->snd_una, tp->snd_nxt)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto out; dst = __sk_dst_check(sk, np->dst_cookie); if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = np->daddr; fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; fl6.flowi6_uid = sock_i_uid(sk); security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false); if (IS_ERR(dst)) { sk->sk_err_soft = -PTR_ERR(dst); goto out; } } else dst_hold(dst); if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { tcp_sync_mss(sk, dst_mtu(dst)); tcp_simple_retransmit(sk); } dst_release(dst); goto out; } icmpv6_err_convert(type, code, &err); switch (sk->sk_state) { struct request_sock *req, **prev; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (!req) goto out; WARN_ON(req->sk != NULL); if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case TCP_SYN_SENT: case TCP_SYN_RECV: 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 (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh, bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; int ext = req->idiag_ext; struct inet_diag_msg *r; struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; handler = inet_diag_table[req->sdiag_protocol]; BUG_ON(!handler); nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); BUG_ON(!sk_fullsock(sk)); inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), .idiag_wmem = sk->sk_wmem_queued, .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0) goto errout; } if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) goto errout; /* * RAW sockets might have user-defined protocols assigned, * so report the one supplied on socket creation. */ if (sk->sk_type == SOCK_RAW) { if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol)) goto errout; } if (!icsk) { handler->idiag_get_info(sk, r, NULL); goto out; } if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { r->idiag_timer = 1; r->idiag_retrans = icsk->icsk_retransmits; r->idiag_expires = jiffies_to_msecs(icsk->icsk_timeout - jiffies); } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { r->idiag_timer = 4; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = jiffies_to_msecs(icsk->icsk_timeout - jiffies); } else if (timer_pending(&sk->sk_timer)) { r->idiag_timer = 2; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = jiffies_to_msecs(sk->sk_timer.expires - jiffies); } else { r->idiag_timer = 0; r->idiag_expires = 0; } if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { attr = nla_reserve_64bit(skb, INET_DIAG_INFO, handler->idiag_info_size, INET_DIAG_PAD); if (!attr) goto errout; info = nla_data(attr); } if (ext & (1 << (INET_DIAG_CONG - 1))) { int err = 0; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops) err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name); rcu_read_unlock(); if (err < 0) goto errout; } handler->idiag_get_info(sk, r, info); if (ext & (1 << (INET_DIAG_INFO - 1)) && handler->idiag_get_aux) if (handler->idiag_get_aux(sk, net_admin, skb) < 0) goto errout; if (sk->sk_state < TCP_TIME_WAIT) { union tcp_cc_info info; size_t sz = 0; int attr; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ext, &attr, &info); rcu_read_unlock(); if (sz && nla_put(skb, attr, sz, &info) < 0) goto errout; } if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { u32 classid = 0; #ifdef CONFIG_SOCK_CGROUP_DATA classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; } out: nlmsg_end(skb, nlh); return 0; errout: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_csk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh, bool net_admin) { return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, portid, seq, nlmsg_flags, unlh, net_admin); } static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); BUG_ON(tw->tw_state != TCP_TIME_WAIT); tmo = tw->tw_timer.expires - jiffies; if (tmo < 0) tmo = 0; inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; r->idiag_state = tw->tw_substate; r->idiag_timer = 3; r->idiag_expires = jiffies_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; nlmsg_end(skb, nlh); return 0; } static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh, bool net_admin) { struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; r->idiag_retrans = reqsk->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0; r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, inet_rsk(reqsk)->ir_mark)) return -EMSGSIZE; nlmsg_end(skb, nlh); return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, portid, seq, nlmsg_flags, unlh); if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, portid, seq, nlmsg_flags, unlh, net_admin); return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh, net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, struct inet_hashinfo *hashinfo, const struct inet_diag_req_v2 *req) { struct sock *sk; rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if); else sk = inet6_lookup(net, hashinfo, NULL, 0, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if); } #endif else { rcu_read_unlock(); return ERR_PTR(-EINVAL); } rcu_read_unlock(); if (!sk) return ERR_PTR(-ENOENT); if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_gen_put(sk); return ERR_PTR(-ENOENT); } return sk; } EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN); struct net *net = sock_net(in_skb->sk); struct sk_buff *rep; struct sock *sk; int err; sk = inet_diag_find_one_icsk(net, hashinfo, req); if (IS_ERR(sk)) return PTR_ERR(sk); rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; } err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, nlh, net_admin); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); goto out; } err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); if (err > 0) err = 0; out: if (sk) sock_gen_put(sk); return err; }
/* this is called when real data arrives */ static int dccp_v4_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; const struct iphdr *iph; struct sock *sk; int min_cov; /* Step 1: Check header basics */ if (dccp_invalid_packet(skb)) goto discard_it; iph = ip_hdr(skb); /* Step 1: If header checksum is incorrect, drop packet and return */ if (dccp_v4_csum_finish(skb, iph->saddr, iph->daddr)) { DCCP_WARN("dropped packet with invalid checksum\n"); goto discard_it; } dh = dccp_hdr(skb); DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; dccp_pr_debug("%8.8s src=%pI4@%-5d dst=%pI4@%-5d seq=%llu", dccp_packet_name(dh->dccph_type), &iph->saddr, ntohs(dh->dccph_sport), &iph->daddr, ntohs(dh->dccph_dport), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); if (dccp_packet_without_ack(skb)) { DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; dccp_pr_debug_cat("\n"); } else { DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); dccp_pr_debug_cat(", ack=%llu\n", (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); } lookup: sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; } /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (sk->sk_state == DCCP_TIME_WAIT) { dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n"); inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); struct sock *nsk; sk = req->rsk_listener; if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sock_hold(sk); nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb); goto discard_and_relse; } else { sock_put(sk); return 0; } } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov */ min_cov = dccp_sk(sk)->dccps_pcrlen; if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) { dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n", dh->dccph_cscov, min_cov); /* FIXME: "Such packets SHOULD be reported using Data Dropped * options (Section 11.7) with Drop Code 0, Protocol * Constraints." */ goto discard_and_relse; } if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; nf_reset(skb); return sk_receive_skb(sk, skb, 1); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; dccp_v4_ctl_send_reset(sk, skb); } discard_it: kfree_skb(skb); return 0; discard_and_relse: sock_put(sk); goto discard_it; }
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __u32 info) { struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct ipv6_pinfo *np; struct sock *sk; int err; struct tcp_sock *tp; __u32 seq; sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr, th->source, skb->dev->ifindex); if (sk == NULL) { ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; tp = tcp_sk(sk); seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && !between(seq, tp->snd_una, tp->snd_nxt)) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto out; /* icmp should have updated the destination cache entry */ dst = __sk_dst_check(sk, np->dst_cookie); if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); struct flowi fl; /* BUGGG_FUTURE: Again, it is not clear how to handle rthdr case. Ignore this complexity for now. */ memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; security_skb_classify_flow(skb, &fl); if ((err = ip6_dst_lookup(sk, &dst, &fl))) { sk->sk_err_soft = -err; goto out; } if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { sk->sk_err_soft = -err; goto out; } } else dst_hold(dst); if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { tcp_sync_mss(sk, dst_mtu(dst)); tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ dst_release(dst); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { struct request_sock *req, **prev; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (!req) goto out; /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ BUG_TRAP(req->sk == NULL); if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case TCP_SYN_SENT: case TCP_SYN_RECV: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { sk->sk_err = err; sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ tcp_done(sk); } else sk->sk_err_soft = err; goto out; } if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }