Commit e887a196 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'tcp-annotate-data-races-around-icsk_retransmits-and-icsk_probes_out' 

Eric Dumazet says:

====================
tcp: annotate data-races around icsk_retransmits and icsk_probes_out

icsk->icsk_retransmits is read locklessly from inet_sk_diag_fill(),
tcp_get_timestamping_opt_stats, get_tcp4_sock() and get_tcp6_sock().

icsk->icsk_probes_out is read locklessly from inet_sk_diag_fill(),
get_tcp4_sock() and get_tcp6_sock().

Add corresponding READ_ONCE()/WRITE_ONCE() annotations.
====================

Link: https://patch.msgid.link/20250822091727.835869-1-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 3ad96554 9bd999eb

net/ipv4/inet_diag.c

+3 −3
Original line number Diff line number Diff line
@@ -313,17 +313,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, 
	    icsk_pending == ICSK_TIME_REO_TIMEOUT ||

	    icsk_pending == ICSK_TIME_LOSS_PROBE) {

		r->idiag_timer = 1;

		r->idiag_retrans = icsk->icsk_retransmits;

		r->idiag_retrans = READ_ONCE(icsk->icsk_retransmits);

		r->idiag_expires =

			jiffies_delta_to_msecs(icsk_timeout(icsk) - jiffies);

	} else if (icsk_pending == ICSK_TIME_PROBE0) {

		r->idiag_timer = 4;

		r->idiag_retrans = icsk->icsk_probes_out;

		r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out);

		r->idiag_expires =

			jiffies_delta_to_msecs(icsk_timeout(icsk) - jiffies);

	} else if (timer_pending(&sk->sk_timer)) {

		r->idiag_timer = 2;

		r->idiag_retrans = icsk->icsk_probes_out;

		r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out);

		r->idiag_expires =

			jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);

	}

net/ipv4/tcp.c

+3 −2
Original line number Diff line number Diff line
@@ -3376,7 +3376,7 @@ int tcp_disconnect(struct sock *sk, int flags) 
	WRITE_ONCE(tp->write_seq, seq);



	icsk->icsk_backoff = 0;

	icsk->icsk_probes_out = 0;

	WRITE_ONCE(icsk->icsk_probes_out, 0);

	icsk->icsk_probes_tstamp = 0;

	icsk->icsk_rto = TCP_TIMEOUT_INIT;

	WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
@@ -4346,7 +4346,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, 
	nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering);

	nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp));



	nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits);

	nla_put_u8(stats, TCP_NLA_RECUR_RETRANS,

		   READ_ONCE(inet_csk(sk)->icsk_retransmits));

	nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited);

	nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh);

	nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered);

net/ipv4/tcp_input.c

+4 −4
Original line number Diff line number Diff line
@@ -2569,7 +2569,7 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) 
		if (frto_undo)

			NET_INC_STATS(sock_net(sk),

					LINUX_MIB_TCPSPURIOUSRTOS);

		inet_csk(sk)->icsk_retransmits = 0;

		WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0);

		if (tcp_is_non_sack_preventing_reopen(sk))

			return true;

		if (frto_undo || tcp_is_sack(tp)) {
@@ -3851,7 +3851,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) 


	if (after(ack, prior_snd_una)) {

		flag |= FLAG_SND_UNA_ADVANCED;

		icsk->icsk_retransmits = 0;

		WRITE_ONCE(icsk->icsk_retransmits, 0);



#if IS_ENABLED(CONFIG_TLS_DEVICE)

		if (static_branch_unlikely(&clean_acked_data_enabled.key))
@@ -3913,7 +3913,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) 
	 * log. Something worked...

	 */

	WRITE_ONCE(sk->sk_err_soft, 0);

	icsk->icsk_probes_out = 0;

	WRITE_ONCE(icsk->icsk_probes_out, 0);

	tp->rcv_tstamp = tcp_jiffies32;

	if (!prior_packets)

		goto no_queue;
@@ -6636,7 +6636,7 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) 
		tcp_try_undo_recovery(sk);



	tcp_update_rto_time(tp);

	inet_csk(sk)->icsk_retransmits = 0;

	WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0);

	/* In tcp_fastopen_synack_timer() on the first SYNACK RTO we set

	 * retrans_stamp but don't enter CA_Loss, so in case that happened we

	 * need to zero retrans_stamp here to prevent spurious

net/ipv4/tcp_ipv4.c

+2 −2
Original line number Diff line number Diff line
@@ -2958,9 +2958,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) 
		rx_queue,

		timer_active,

		jiffies_delta_to_clock_t(timer_expires - jiffies),

		icsk->icsk_retransmits,

		READ_ONCE(icsk->icsk_retransmits),

		from_kuid_munged(seq_user_ns(f), sk_uid(sk)),

		icsk->icsk_probes_out,

		READ_ONCE(icsk->icsk_probes_out),

		sock_i_ino(sk),

		refcount_read(&sk->sk_refcnt), sk,

		jiffies_to_clock_t(icsk->icsk_rto),

net/ipv4/tcp_output.c

+3 −3
Original line number Diff line number Diff line
@@ -3956,7 +3956,7 @@ static void tcp_connect_init(struct sock *sk) 
	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);



	inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);

	inet_csk(sk)->icsk_retransmits = 0;

	WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0);

	tcp_clear_retrans(tp);

}
@@ -4394,13 +4394,13 @@ void tcp_send_probe0(struct sock *sk) 


	if (tp->packets_out || tcp_write_queue_empty(sk)) {

		/* Cancel probe timer, if it is not required. */

		icsk->icsk_probes_out = 0;

		WRITE_ONCE(icsk->icsk_probes_out, 0);

		icsk->icsk_backoff = 0;

		icsk->icsk_probes_tstamp = 0;

		return;

	}



	icsk->icsk_probes_out++;

	WRITE_ONCE(icsk->icsk_probes_out, icsk->icsk_probes_out + 1);

	if (err <= 0) {

		if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))

			icsk->icsk_backoff++;