Commit d82bae12 authored by Soheil Hassas Yeganeh's avatar Soheil Hassas Yeganeh Committed by David S. Miller
Browse files

tcp: remove per-destination timestamp cache 



Commit 8a5bd45f6616 (tcp: randomize tcp timestamp offsets for each connection)
randomizes TCP timestamps per connection. After this commit,
there is no guarantee that the timestamps received from the
same destination are monotonically increasing. As a result,
the per-destination timestamp cache in TCP metrics (i.e., tcpm_ts
in struct tcp_metrics_block) is broken and cannot be relied upon.

Remove the per-destination timestamp cache and all related code
paths.

Note that this cache was already broken for caching timestamps of
multiple machines behind a NAT sharing the same address.

Signed-off-by: default avatarSoheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Signed-off-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarYuchung Cheng <ycheng@google.com>
Cc: Lutz Vieweg <lvml@5t9.de>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 8b705f52

include/net/tcp.h

+1 −5
Original line number Diff line number Diff line
@@ -406,11 +406,7 @@ void tcp_clear_retrans(struct tcp_sock *tp); 
void tcp_update_metrics(struct sock *sk);

void tcp_init_metrics(struct sock *sk);

void tcp_metrics_init(void);

bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,

			bool paws_check, bool timestamps);

bool tcp_remember_stamp(struct sock *sk);

bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);

void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);

bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);

void tcp_disable_fack(struct tcp_sock *tp);

void tcp_close(struct sock *sk, long timeout);

void tcp_init_sock(struct sock *sk);

net/ipv4/tcp_input.c

+2 −4
Original line number Diff line number Diff line
@@ -6342,8 +6342,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, 
			dst = af_ops->route_req(sk, &fl, req, &strict);



			if (dst && strict &&

			    !tcp_peer_is_proven(req, dst, true,

						tmp_opt.saw_tstamp)) {

			    !tcp_peer_is_proven(req, dst)) {

				NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);

				goto drop_and_release;

			}
@@ -6352,8 +6351,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, 
		else if (!net->ipv4.sysctl_tcp_syncookies &&

			 (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <

			  (net->ipv4.sysctl_max_syn_backlog >> 2)) &&

			 !tcp_peer_is_proven(req, dst, false,

					     tmp_opt.saw_tstamp)) {

			 !tcp_peer_is_proven(req, dst)) {

			/* Without syncookies last quarter of

			 * backlog is filled with destinations,

			 * proven to be alive.

net/ipv4/tcp_ipv4.c

+0 −4
Original line number Diff line number Diff line
@@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) 
			tp->write_seq	   = 0;

	}



	if (tcp_death_row->sysctl_tw_recycle &&

	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)

		tcp_fetch_timewait_stamp(sk, &rt->dst);



	inet->inet_dport = usin->sin_port;

	sk_daddr_set(sk, daddr);

net/ipv4/tcp_metrics.c

+4 −143
Original line number Diff line number Diff line
@@ -45,8 +45,6 @@ struct tcp_metrics_block { 
	struct inetpeer_addr		tcpm_saddr;

	struct inetpeer_addr		tcpm_daddr;

	unsigned long			tcpm_stamp;

	u32				tcpm_ts;

	u32				tcpm_ts_stamp;

	u32				tcpm_lock;

	u32				tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];

	struct tcp_fastopen_metrics	tcpm_fastopen;
@@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, 
	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);

	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);

	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);

	tm->tcpm_ts = 0;

	tm->tcpm_ts_stamp = 0;

	if (fastopen_clear) {

		tm->tcpm_fastopen.mss = 0;

		tm->tcpm_fastopen.syn_loss = 0;
@@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, 
	return tm;

}



static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)

{

	struct tcp_metrics_block *tm;

	struct inetpeer_addr saddr, daddr;

	unsigned int hash;

	struct net *net;



	if (tw->tw_family == AF_INET) {

		inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);

		inetpeer_set_addr_v4(&daddr, tw->tw_daddr);

		hash = ipv4_addr_hash(tw->tw_daddr);

	}

#if IS_ENABLED(CONFIG_IPV6)

	else if (tw->tw_family == AF_INET6) {

		if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {

			inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);

			inetpeer_set_addr_v4(&daddr, tw->tw_daddr);

			hash = ipv4_addr_hash(tw->tw_daddr);

		} else {

			inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr);

			inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr);

			hash = ipv6_addr_hash(&tw->tw_v6_daddr);

		}

	}

#endif

	else

		return NULL;



	net = twsk_net(tw);

	hash ^= net_hash_mix(net);

	hash = hash_32(hash, tcp_metrics_hash_log);



	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;

	     tm = rcu_dereference(tm->tcpm_next)) {

		if (addr_same(&tm->tcpm_saddr, &saddr) &&

		    addr_same(&tm->tcpm_daddr, &daddr) &&

		    net_eq(tm_net(tm), net))

			break;

	}

	return tm;

}



static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,

						 struct dst_entry *dst,

						 bool create)
@@ -573,8 +527,7 @@ reset: 
	tp->snd_cwnd_stamp = tcp_time_stamp;

}



bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,

			bool paws_check, bool timestamps)

bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)

{

	struct tcp_metrics_block *tm;

	bool ret;
@@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, 


	rcu_read_lock();

	tm = __tcp_get_metrics_req(req, dst);

	if (paws_check) {

		if (tm &&

		    (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&

		    ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW ||

		     !timestamps))

			ret = false;

		else

			ret = true;

	} else {

		if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp)

	if (tm && tcp_metric_get(tm, TCP_METRIC_RTT))

		ret = true;

	else

		ret = false;

	}

	rcu_read_unlock();



	return ret;

}



void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst)

{

	struct tcp_metrics_block *tm;



	rcu_read_lock();

	tm = tcp_get_metrics(sk, dst, true);

	if (tm) {

		struct tcp_sock *tp = tcp_sk(sk);



		if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) {

			tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp;

			tp->rx_opt.ts_recent = tm->tcpm_ts;

		}

	}

	rcu_read_unlock();

}

EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp);



/* VJ's idea. Save last timestamp seen from this destination and hold

 * it at least for normal timewait interval to use for duplicate

 * segment detection in subsequent connections, before they enter

 * synchronized state.

 */

bool tcp_remember_stamp(struct sock *sk)

{

	struct dst_entry *dst = __sk_dst_get(sk);

	bool ret = false;



	if (dst) {

		struct tcp_metrics_block *tm;



		rcu_read_lock();

		tm = tcp_get_metrics(sk, dst, true);

		if (tm) {

			struct tcp_sock *tp = tcp_sk(sk);



			if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 ||

			    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&

			     tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {

				tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;

				tm->tcpm_ts = tp->rx_opt.ts_recent;

			}

			ret = true;

		}

		rcu_read_unlock();

	}

	return ret;

}



bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)

{

	struct tcp_metrics_block *tm;

	bool ret = false;



	rcu_read_lock();

	tm = __tcp_get_metrics_tw(tw);

	if (tm) {

		const struct tcp_timewait_sock *tcptw;

		struct sock *sk = (struct sock *) tw;



		tcptw = tcp_twsk(sk);

		if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 ||

		    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&

		     tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {

			tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;

			tm->tcpm_ts	   = tcptw->tw_ts_recent;

		}

		ret = true;

	}

	rcu_read_unlock();



	return ret;
@@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, 
			  jiffies - tm->tcpm_stamp,

			  TCP_METRICS_ATTR_PAD) < 0)

		goto nla_put_failure;

	if (tm->tcpm_ts_stamp) {

		if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP,

				(s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0)

			goto nla_put_failure;

		if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL,

				tm->tcpm_ts) < 0)

			goto nla_put_failure;

	}



	{

		int n = 0;

net/ipv4/tcp_minisocks.c

+4 −18
Original line number Diff line number Diff line
@@ -94,7 +94,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, 
	struct tcp_options_received tmp_opt;

	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);

	bool paws_reject = false;

	struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row;



	tmp_opt.saw_tstamp = 0;

	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
@@ -149,11 +148,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, 
			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;

		}



		if (tcp_death_row->sysctl_tw_recycle &&

		    tcptw->tw_ts_recent_stamp &&

		    tcp_tw_remember_stamp(tw))

			inet_twsk_reschedule(tw, tw->tw_timeout);

		else

		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);

		return TCP_TW_ACK;

	}
@@ -259,12 +253,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) 
	const struct inet_connection_sock *icsk = inet_csk(sk);

	const struct tcp_sock *tp = tcp_sk(sk);

	struct inet_timewait_sock *tw;

	bool recycle_ok = false;

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



	if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)

		recycle_ok = tcp_remember_stamp(sk);



	tw = inet_twsk_alloc(sk, tcp_death_row, state);



	if (tw) {
@@ -317,13 +307,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) 
		if (timeo < rto)

			timeo = rto;



		if (recycle_ok) {

			tw->tw_timeout = rto;

		} else {

		tw->tw_timeout = TCP_TIMEWAIT_LEN;

		if (state == TCP_TIME_WAIT)

			timeo = TCP_TIMEWAIT_LEN;

		}



		inet_twsk_schedule(tw, timeo);

		/* Linkage updates. */

CRA Git | Maintained and supported by SUSTech CRA and CCSE