diff options
Diffstat (limited to 'net/netfilter/nf_conntrack_proto_tcp.c')
-rw-r--r-- | net/netfilter/nf_conntrack_proto_tcp.c | 140 |
1 files changed, 80 insertions, 60 deletions
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 97a6e93d742..33fc0a443f3 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -29,9 +29,6 @@ #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> -/* Protects ct->proto.tcp */ -static DEFINE_RWLOCK(tcp_lock); - /* "Be conservative in what you do, be liberal in what you accept from others." If it's non-zero, we mark only out of window RST segments as INVALID. */ @@ -59,7 +56,7 @@ static const char *const tcp_conntrack_names[] = { "LAST_ACK", "TIME_WAIT", "CLOSE", - "LISTEN" + "SYN_SENT2", }; #define SECS * HZ @@ -82,6 +79,7 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { [TCP_CONNTRACK_LAST_ACK] = 30 SECS, [TCP_CONNTRACK_TIME_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE] = 10 SECS, + [TCP_CONNTRACK_SYN_SENT2] = 2 MINS, }; #define sNO TCP_CONNTRACK_NONE @@ -93,7 +91,7 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { #define sLA TCP_CONNTRACK_LAST_ACK #define sTW TCP_CONNTRACK_TIME_WAIT #define sCL TCP_CONNTRACK_CLOSE -#define sLI TCP_CONNTRACK_LISTEN +#define sS2 TCP_CONNTRACK_SYN_SENT2 #define sIV TCP_CONNTRACK_MAX #define sIG TCP_CONNTRACK_IGNORE @@ -123,6 +121,7 @@ enum tcp_bit_set { * * NONE: initial state * SYN_SENT: SYN-only packet seen + * SYN_SENT2: SYN-only packet seen from reply dir, simultaneous open * SYN_RECV: SYN-ACK packet seen * ESTABLISHED: ACK packet seen * FIN_WAIT: FIN packet seen @@ -131,26 +130,24 @@ enum tcp_bit_set { * TIME_WAIT: last ACK seen * CLOSE: closed connection (RST) * - * LISTEN state is not used. - * * Packets marked as IGNORED (sIG): * if they may be either invalid or valid * and the receiver may send back a connection * closing RST or a SYN/ACK. * * Packets marked as INVALID (sIV): - * if they are invalid - * or we do not support the request (simultaneous open) + * if we regard them as truly invalid packets */ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sS2 }, /* * sNO -> sSS Initialize a new connection * sSS -> sSS Retransmitted SYN - * sSR -> sIG Late retransmitted SYN? + * sS2 -> sS2 Late retransmitted SYN + * sSR -> sIG * sES -> sIG Error: SYNs in window outside the SYN_SENT state * are errors. Receiver will reply with RST * and close the connection. @@ -161,22 +158,30 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sSS Reopened connection (RFC 1122). * sCL -> sSS */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*synack*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*synack*/ { sIV, sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR }, /* - * A SYN/ACK from the client is always invalid: - * - either it tries to set up a simultaneous open, which is - * not supported; - * - or the firewall has just been inserted between the two hosts - * during the session set-up. The SYN will be retransmitted - * by the true client (or it'll time out). + * sNO -> sIV Too late and no reason to do anything + * sSS -> sIV Client can't send SYN and then SYN/ACK + * sS2 -> sSR SYN/ACK sent to SYN2 in simultaneous open + * sSR -> sIG + * sES -> sIG Error: SYNs in window outside the SYN_SENT state + * are errors. Receiver will reply with RST + * and close the connection. + * Or we are not in sync and hold a dead connection. + * sFW -> sIG + * sCW -> sIG + * sLA -> sIG + * sTW -> sIG + * sCL -> sIG */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sNO -> sIV Too late and no reason to do anything... * sSS -> sIV Client migth not send FIN in this state: * we enforce waiting for a SYN/ACK reply first. + * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions, waiting for @@ -187,11 +192,12 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*ack*/ { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV }, /* * sNO -> sES Assumed. * sSS -> sIV ACK is invalid: we haven't seen a SYN/ACK yet. + * sS2 -> sIV * sSR -> sES Established state is reached. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. @@ -200,29 +206,31 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } }, { /* REPLY */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*syn*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*syn*/ { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sS2 }, /* * sNO -> sIV Never reached. - * sSS -> sIV Simultaneous open, not supported - * sSR -> sIV Simultaneous open, not supported. - * sES -> sIV Server may not initiate a connection. + * sSS -> sS2 Simultaneous open + * sS2 -> sS2 Retransmitted simultaneous SYN + * sSR -> sIV Invalid SYN packets sent by the server + * sES -> sIV * sFW -> sIV * sCW -> sIV * sLA -> sIV * sTW -> sIV Reopened connection, but server may not do it. * sCL -> sIV */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sSR }, /* * sSS -> sSR Standard open. + * sS2 -> sSR Simultaneous open * sSR -> sSR Retransmitted SYN/ACK. * sES -> sIG Late retransmitted SYN/ACK? * sFW -> sIG Might be SYN/ACK answering ignored SYN @@ -231,10 +239,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sIG * sCL -> sIG */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sSS -> sIV Server might not send FIN in this state. + * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions. @@ -243,10 +252,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIG }, /* * sSS -> sIG Might be a half-open connection. + * sS2 -> sIG * sSR -> sSR Might answer late resent SYN. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. @@ -255,8 +265,8 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } } }; @@ -296,13 +306,13 @@ static int tcp_print_tuple(struct seq_file *s, } /* Print out the private part of the conntrack. */ -static int tcp_print_conntrack(struct seq_file *s, const struct nf_conn *ct) +static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { enum tcp_conntrack state; - read_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); state = ct->proto.tcp.state; - read_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return seq_printf(s, "%s ", tcp_conntrack_names[state]); } @@ -521,13 +531,14 @@ static bool tcp_in_window(const struct nf_conn *ct, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); - if (sender->td_end == 0) { + if (sender->td_maxwin == 0) { /* * Initialize sender data. */ - if (tcph->syn && tcph->ack) { + if (tcph->syn) { /* - * Outgoing SYN-ACK in reply to a SYN. + * SYN-ACK in reply to a SYN + * or SYN from reply direction in simultaneous open. */ sender->td_end = sender->td_maxend = end; @@ -543,6 +554,9 @@ static bool tcp_in_window(const struct nf_conn *ct, && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) sender->td_scale = receiver->td_scale = 0; + if (!tcph->ack) + /* Simultaneous open */ + return true; } else { /* * We are in the middle of a connection, @@ -716,14 +730,14 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb, end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph); - write_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); /* * We have to worry for the ack in the reply packet only... */ if (after(end, ct->proto.tcp.seen[dir].td_end)) ct->proto.tcp.seen[dir].td_end = end; ct->proto.tcp.last_end = end; - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); pr_debug("tcp_update: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, @@ -832,7 +846,7 @@ static int tcp_packet(struct nf_conn *ct, th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph); BUG_ON(th == NULL); - write_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); old_state = ct->proto.tcp.state; dir = CTINFO2DIR(ctinfo); index = get_conntrack_index(th); @@ -862,7 +876,7 @@ static int tcp_packet(struct nf_conn *ct, && ct->proto.tcp.last_index == TCP_RST_SET)) { /* Attempt to reopen a closed/aborted connection. * Delete this connection and look up again. */ - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); /* Only repeat if we can actually remove the timer. * Destruction may already be in progress in process @@ -898,7 +912,7 @@ static int tcp_packet(struct nf_conn *ct, * that the client cannot but retransmit its SYN and * thus initiate a clean new session. */ - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: killing out of sync session "); @@ -911,7 +925,7 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid packet ignored "); @@ -920,7 +934,7 @@ static int tcp_packet(struct nf_conn *ct, /* Invalid packet */ pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid state "); @@ -930,7 +944,7 @@ static int tcp_packet(struct nf_conn *ct, && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid RST "); @@ -961,7 +975,7 @@ static int tcp_packet(struct nf_conn *ct, if (!tcp_in_window(ct, &ct->proto.tcp, dir, index, skb, dataoff, th, pf)) { - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return -NF_ACCEPT; } in_window: @@ -990,9 +1004,8 @@ static int tcp_packet(struct nf_conn *ct, timeout = nf_ct_tcp_timeout_unacknowledged; else timeout = tcp_timeouts[new_state]; - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); - nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); @@ -1086,7 +1099,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[1].td_end = 0; ct->proto.tcp.seen[1].td_maxend = 0; - ct->proto.tcp.seen[1].td_maxwin = 1; + ct->proto.tcp.seen[1].td_maxwin = 0; ct->proto.tcp.seen[1].td_scale = 0; /* tcp_packet will set them */ @@ -1108,12 +1121,12 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, #include <linux/netfilter/nfnetlink_conntrack.h> static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, - const struct nf_conn *ct) + struct nf_conn *ct) { struct nlattr *nest_parms; struct nf_ct_tcp_flags tmp = {}; - read_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; @@ -1133,14 +1146,14 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, tmp.flags = ct->proto.tcp.seen[1].flags; NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY, sizeof(struct nf_ct_tcp_flags), &tmp); - read_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); return 0; nla_put_failure: - read_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return -1; } @@ -1171,7 +1184,7 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX) return -EINVAL; - write_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); if (tb[CTA_PROTOINFO_TCP_STATE]) ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]); @@ -1198,7 +1211,7 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) ct->proto.tcp.seen[1].td_scale = nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]); } - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return 0; } @@ -1328,6 +1341,13 @@ static struct ctl_table tcp_compat_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { + .procname = "ip_conntrack_tcp_timeout_syn_sent2", + .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT2], + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "ip_conntrack_tcp_timeout_syn_recv", .data = &tcp_timeouts[TCP_CONNTRACK_SYN_RECV], .maxlen = sizeof(unsigned int), |