1 files changed, 89 insertions, 51 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d1ad20ce1c8c..e4c616bbd727 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,10 +22,11 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <net/tcp.h>
+#include <net/rstreason.h>
 
 static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	u32 elapsed, user_timeout;
 	s32 remaining;
@@ -47,7 +48,7 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 
 u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 remaining, user_timeout;
 	s32 elapsed;
 
@@ -73,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
 
 static void tcp_write_err(struct sock *sk)
 {
-	WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
-	sk_error_report(sk);
-
-	tcp_write_queue_purge(sk);
-	tcp_done(sk);
+	tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
 
@@ -112,7 +109,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
-	if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
+	if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset)
 		shift++;
 
 	/* If some dubious ICMP arrived, penalize even more. */
@@ -127,7 +124,8 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 		    (!tp->snd_wnd && !tp->packets_out))
 			do_reset = true;
 		if (do_reset)
-			tcp_send_active_reset(sk, GFP_ATOMIC);
+			tcp_send_active_reset(sk, GFP_ATOMIC,
+					      SK_RST_REASON_TCP_ABORT_ON_MEMORY);
 		tcp_done(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
@@ -191,12 +189,12 @@ static unsigned int tcp_model_timeout(struct sock *sk,
 {
 	unsigned int linear_backoff_thresh, timeout;
 
-	linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base);
+	linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base);
 	if (boundary <= linear_backoff_thresh)
 		timeout = ((2 << boundary) - 1) * rto_base;
 	else
 		timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
-			(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+			(boundary - linear_backoff_thresh) * tcp_rto_max(sk);
 	return jiffies_to_msecs(timeout);
 }
 /**
@@ -270,7 +268,7 @@ static int tcp_write_timeout(struct sock *sk)
 
 		retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
 		if (sock_flag(sk, SOCK_DEAD)) {
-			const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
+			const bool alive = icsk->icsk_rto < tcp_rto_max(sk);
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
@@ -284,6 +282,7 @@ static int tcp_write_timeout(struct sock *sk)
 		expired = retransmits_timed_out(sk, retry_until,
 						READ_ONCE(icsk->icsk_user_timeout));
 	tcp_fastopen_active_detect_blackhole(sk, expired);
+	mptcp_active_detect_blackhole(sk, expired);
 
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
 		tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
@@ -323,8 +322,9 @@ void tcp_delack_timer_handler(struct sock *sk)
 	if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		return;
 
-	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
-		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
+	if (time_after(icsk_delack_timeout(icsk), jiffies)) {
+		sk_reset_timer(sk, &icsk->icsk_delack_timer,
+			       icsk_delack_timeout(icsk));
 		return;
 	}
 	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
@@ -362,6 +362,14 @@ static void tcp_delack_timer(struct timer_list *t)
 			from_timer(icsk, t, icsk_delack_timer);
 	struct sock *sk = &icsk->icsk_inet.sk;
 
+	/* Avoid taking socket spinlock if there is no ACK to send.
+	 * The compressed_ack check is racy, but a separate hrtimer
+	 * will take care of it eventually.
+	 */
+	if (!(smp_load_acquire(&icsk->icsk_ack.pending) & ICSK_ACK_TIMER) &&
+	    !READ_ONCE(tcp_sk(sk)->compressed_ack))
+		goto out;
+
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
@@ -372,6 +380,7 @@ static void tcp_delack_timer(struct timer_list *t)
 			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
+out:
 	sock_put(sk);
 }
 
@@ -408,7 +417,8 @@ static void tcp_probe_timer(struct sock *sk)
 	}
 	max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
 	if (sock_flag(sk, SOCK_DEAD)) {
-		const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
+		unsigned int rto_max = tcp_rto_max(sk);
+		const bool alive = inet_csk_rto_backoff(icsk, rto_max) < rto_max;
 
 		max_probes = tcp_orphan_retries(sk, alive);
 		if (!alive && icsk->icsk_backoff >= max_probes)
@@ -473,19 +483,34 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 	tcp_update_rto_stats(sk);
 	if (!tp->retrans_stamp)
 		tp->retrans_stamp = tcp_time_stamp_ts(tp);
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-			  req->timeout << req->num_timeout, TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+			  req->timeout << req->num_timeout, false);
 }
 
 static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
 				     const struct sk_buff *skb,
 				     u32 rtx_delta)
 {
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	const int timeout = TCP_RTO_MAX * 2;
-	u32 rcv_delta;
+	int timeout = tcp_rto_max(sk) * 2;
+	s32 rcv_delta;
 
-	rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+	if (user_timeout) {
+		/* If user application specified a TCP_USER_TIMEOUT,
+		 * it does not want win 0 packets to 'reset the timer'
+		 * while retransmits are not making progress.
+		 */
+		if (rtx_delta > user_timeout)
+			return true;
+		timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout));
+	}
+	/* Note: timer interrupt might have been delayed by at least one jiffy,
+	 * and tp->rcv_tstamp might very well have been written recently.
+	 * rcv_delta can thus be negative.
+	 */
+	rcv_delta = icsk_timeout(icsk) - tp->rcv_tstamp;
 	if (rcv_delta <= timeout)
 		return false;
 
@@ -530,8 +555,6 @@ void tcp_retransmit_timer(struct sock *sk)
 	if (WARN_ON_ONCE(!skb))
 		return;
 
-	tp->tlp_high_seq = 0;
-
 	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
 	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
 		/* Receiver dastardly shrinks window. Our retransmits
@@ -605,9 +628,9 @@ void tcp_retransmit_timer(struct sock *sk)
 		/* Retransmission failed because of local congestion,
 		 * Let senders fight for local resources conservatively.
 		 */
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  TCP_RESOURCE_PROBE_INTERVAL,
-					  TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+				     TCP_RESOURCE_PROBE_INTERVAL,
+				     false);
 		goto out;
 	}
 
@@ -644,7 +667,7 @@ out_reset_timer:
 		icsk->icsk_backoff = 0;
 		icsk->icsk_rto = clamp(__tcp_set_rto(tp),
 				       tcp_rto_min(sk),
-				       TCP_RTO_MAX);
+				       tcp_rto_max(sk));
 	} else if (sk->sk_state != TCP_SYN_SENT ||
 		   tp->total_rto >
 		   READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
@@ -652,10 +675,10 @@ out_reset_timer:
 		 * activated.
 		 */
 		icsk->icsk_backoff++;
-		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+		icsk->icsk_rto = min(icsk->icsk_rto << 1, tcp_rto_max(sk));
 	}
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				  tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+			     tcp_clamp_rto_to_user_timeout(sk), false);
 	if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
 		__sk_dst_reset(sk);
 
@@ -663,7 +686,8 @@ out:;
 }
 
 /* Called with bottom-half processing disabled.
-   Called by tcp_write_timer() */
+ * Called by tcp_write_timer() and tcp_release_cb().
+ */
 void tcp_write_timer_handler(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -673,11 +697,11 @@ void tcp_write_timer_handler(struct sock *sk)
 	    !icsk->icsk_pending)
 		return;
 
-	if (time_after(icsk->icsk_timeout, jiffies)) {
-		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
+	if (time_after(icsk_timeout(icsk), jiffies)) {
+		sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
+			       icsk_timeout(icsk));
 		return;
 	}
-
 	tcp_mstamp_refresh(tcp_sk(sk));
 	event = icsk->icsk_pending;
 
@@ -689,11 +713,11 @@ void tcp_write_timer_handler(struct sock *sk)
 		tcp_send_loss_probe(sk);
 		break;
 	case ICSK_TIME_RETRANS:
-		icsk->icsk_pending = 0;
+		smp_store_release(&icsk->icsk_pending, 0);
 		tcp_retransmit_timer(sk);
 		break;
 	case ICSK_TIME_PROBE0:
-		icsk->icsk_pending = 0;
+		smp_store_release(&icsk->icsk_pending, 0);
 		tcp_probe_timer(sk);
 		break;
 	}
@@ -705,6 +729,10 @@ static void tcp_write_timer(struct timer_list *t)
 			from_timer(icsk, t, icsk_retransmit_timer);
 	struct sock *sk = &icsk->icsk_inet.sk;
 
+	/* Avoid locking the socket when there is no pending event. */
+	if (!smp_load_acquire(&icsk->icsk_pending))
+		goto out;
+
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
 		tcp_write_timer_handler(sk);
@@ -714,6 +742,7 @@ static void tcp_write_timer(struct timer_list *t)
 			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
+out:
 	sock_put(sk);
 }
 
@@ -723,7 +752,17 @@ void tcp_syn_ack_timeout(const struct request_sock *req)
 
 	__NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS);
 }
-EXPORT_SYMBOL(tcp_syn_ack_timeout);
+EXPORT_IPV6_MOD(tcp_syn_ack_timeout);
+
+void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len)
+{
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+}
+
+static void tcp_delete_keepalive_timer(struct sock *sk)
+{
+	sk_stop_timer(sk, &sk->sk_timer);
+}
 
 void tcp_set_keepalive(struct sock *sk, int val)
 {
@@ -731,14 +770,13 @@ void tcp_set_keepalive(struct sock *sk, int val)
 		return;
 
 	if (val && !sock_flag(sk, SOCK_KEEPOPEN))
-		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
+		tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
 	else if (!val)
-		inet_csk_delete_keepalive_timer(sk);
+		tcp_delete_keepalive_timer(sk);
 }
-EXPORT_SYMBOL_GPL(tcp_set_keepalive);
-
+EXPORT_IPV6_MOD_GPL(tcp_set_keepalive);
 
-static void tcp_keepalive_timer (struct timer_list *t)
+static void tcp_keepalive_timer(struct timer_list *t)
 {
 	struct sock *sk = from_timer(sk, t, sk_timer);
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -749,7 +787,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
-		inet_csk_reset_keepalive_timer (sk, HZ/20);
+		tcp_reset_keepalive_timer(sk, HZ/20);
 		goto out;
 	}
 
@@ -768,7 +806,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 				goto out;
 			}
 		}
-		tcp_send_active_reset(sk, GFP_ATOMIC);
+		tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE);
 		goto death;
 	}
 
@@ -795,7 +833,8 @@ static void tcp_keepalive_timer (struct timer_list *t)
 		    icsk->icsk_probes_out > 0) ||
 		    (user_timeout == 0 &&
 		    icsk->icsk_probes_out >= keepalive_probes(tp))) {
-			tcp_send_active_reset(sk, GFP_ATOMIC);
+			tcp_send_active_reset(sk, GFP_ATOMIC,
+					      SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT);
 			tcp_write_err(sk);
 			goto out;
 		}
@@ -814,7 +853,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 	}
 
 resched:
-	inet_csk_reset_keepalive_timer (sk, elapsed);
+	tcp_reset_keepalive_timer(sk, elapsed);
 	goto out;
 
 death:
@@ -838,6 +877,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
 			 * LINUX_MIB_TCPACKCOMPRESSED accurate.
 			 */
 			tp->compressed_ack--;
+			tcp_mstamp_refresh(tp);
 			tcp_send_ack(sk);
 		}
 	} else {
@@ -856,11 +896,9 @@ void tcp_init_xmit_timers(struct sock *sk)
 {
 	inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
 				  &tcp_keepalive_timer);
-	hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED_SOFT);
-	tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
+	hrtimer_setup(&tcp_sk(sk)->pacing_timer, tcp_pace_kick, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED_SOFT);
 
-	hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_PINNED_SOFT);
-	tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick;
+	hrtimer_setup(&tcp_sk(sk)->compressed_ack_timer, tcp_compressed_ack_kick, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL_PINNED_SOFT);
 }