Commit c0a11493 authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski
Browse files

tcp: annotate data-races around tcptw->tw_rcv_nxt



No lock protects tcp tw fields.

tcptw->tw_rcv_nxt can be changed from twsk_rcv_nxt_update()
while other threads might read this field.

Add READ_ONCE()/WRITE_ONCE() annotations, and make sure
tcp_timewait_state_process() reads tcptw->tw_rcv_nxt only once.

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarJason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20240827015250.3509197-3-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 3e5cbbb1
Loading
Loading
Loading
Loading
+1 −1
Original line number Diff line number Diff line
@@ -1073,7 +1073,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
	}

	tcp_v4_send_ack(sk, skb,
			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
			tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt),
			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
			tcp_tw_tsval(tcptw),
			READ_ONCE(tcptw->tw_ts_recent),
+15 −12
Original line number Diff line number Diff line
@@ -52,16 +52,17 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
	return TCP_TW_SUCCESS;
}

static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq)
static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq,
				u32 rcv_nxt)
{
#ifdef CONFIG_TCP_AO
	struct tcp_ao_info *ao;

	ao = rcu_dereference(tcptw->ao_info);
	if (unlikely(ao && seq < tcptw->tw_rcv_nxt))
	if (unlikely(ao && seq < rcv_nxt))
		WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1);
#endif
	tcptw->tw_rcv_nxt = seq;
	WRITE_ONCE(tcptw->tw_rcv_nxt, seq);
}

/*
@@ -98,8 +99,9 @@ enum tcp_tw_status
tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
			   const struct tcphdr *th, u32 *tw_isn)
{
	struct tcp_options_received tmp_opt;
	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
	u32 rcv_nxt = READ_ONCE(tcptw->tw_rcv_nxt);
	struct tcp_options_received tmp_opt;
	bool paws_reject = false;
	int ts_recent_stamp;

@@ -123,20 +125,20 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
		/* Out of window, send ACK */
		if (paws_reject ||
		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
				   tcptw->tw_rcv_nxt,
				   tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
				   rcv_nxt,
				   rcv_nxt + tcptw->tw_rcv_wnd))
			return tcp_timewait_check_oow_rate_limit(
				tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2);

		if (th->rst)
			goto kill;

		if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt))
		if (th->syn && !before(TCP_SKB_CB(skb)->seq, rcv_nxt))
			return TCP_TW_RST;

		/* Dup ACK? */
		if (!th->ack ||
		    !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
		    !after(TCP_SKB_CB(skb)->end_seq, rcv_nxt) ||
		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) {
			inet_twsk_put(tw);
			return TCP_TW_SUCCESS;
@@ -146,12 +148,13 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
		 * reset.
		 */
		if (!th->fin ||
		    TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1)
		    TCP_SKB_CB(skb)->end_seq != rcv_nxt + 1)
			return TCP_TW_RST;

		/* FIN arrived, enter true time-wait state. */
		WRITE_ONCE(tw->tw_substate, TCP_TIME_WAIT);
		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq,
				    rcv_nxt);

		if (tmp_opt.saw_tstamp) {
			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
@@ -182,7 +185,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
	 */

	if (!paws_reject &&
	    (TCP_SKB_CB(skb)->seq == tcptw->tw_rcv_nxt &&
	    (TCP_SKB_CB(skb)->seq == rcv_nxt &&
	     (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) {
		/* In window segment, it may be only reset or bare ack. */

@@ -229,7 +232,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
	 */

	if (th->syn && !th->rst && !th->ack && !paws_reject &&
	    (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) ||
	    (after(TCP_SKB_CB(skb)->seq, rcv_nxt) ||
	     (tmp_opt.saw_tstamp &&
	      (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) {
		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
+2 −1
Original line number Diff line number Diff line
@@ -1193,7 +1193,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
#endif
	}

	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt,
			READ_ONCE(tcptw->tw_rcv_nxt),
			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
			tcp_tw_tsval(tcptw),
			READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,