Merge branch 'tcp-oom-probe'

Menglong Dong says:

====================
net: tcp: support probing OOM

In this series, we make some small changes to make the tcp
retransmission become zero-window probes if the receiver drops the skb
because of memory pressure.

In the 1st patch, we reply a zero-window ACK if the skb is dropped
because out of memory, instead of dropping the skb silently.

In the 2nd patch, we allow a zero-window ACK to update the window.

In the 3rd patch, fix unexcepted socket die when snd_wnd is 0 in
tcp_retransmit_timer().

In the 4th patch, we refactor the debug message in
tcp_retransmit_timer() to make it more correct.

After these changes, the tcp can probe the OOM of the receiver forever.

Changes since v3:
- make the timeout "2 * TCP_RTO_MAX" in the 3rd patch
- tp->retrans_stamp is not based on jiffies and can't be compared with
  icsk->icsk_timeout in the 3rd patch. Fix it.
- introduce the 4th patch

Changes since v2:
- refactor the code to avoid code duplication in the 1st patch
- use after() instead of max() in tcp_rtx_probe0_timed_out()

Changes since v1:
- send 0 rwin ACK for the receive queue empty case when necessary in the
  1st patch
- send the ACK immediately by using the ICSK_ACK_NOW flag in the 1st
  patch
- consider the case of the connection restart from idle, as Neal comment,
  in the 3rd patch
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/inet_connection_sock.h

@@ -164,7 +164,8 @@ enum inet_csk_ack_state_t {
 	ICSK_ACK_TIMER  = 2,
 	ICSK_ACK_PUSHED = 4,
 	ICSK_ACK_PUSHED2 = 8,
-	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOW = 16,	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOMEM = 32,
 };
 
 void inet_csk_init_xmit_timers(struct sock *sk,

net/ipv4/tcp_input.c

@@ -3525,7 +3525,7 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 {
 	return	after(ack, tp->snd_una) ||
 		after(ack_seq, tp->snd_wl1) ||
-		(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
+		(ack_seq == tp->snd_wl1 && (nwin > tp->snd_wnd || !nwin));
 }
 
 /* If we update tp->snd_una, also update tp->bytes_acked */
@@ -5059,14 +5059,20 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 
 		/* Ok. In sequence. In window. */
 queue_and_out:
-		if (skb_queue_len(&sk->sk_receive_queue) == 0)
-			sk_forced_mem_schedule(sk, skb->truesize);
-		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+		if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			/* TODO: maybe ratelimit these WIN 0 ACK ? */
+			inet_csk(sk)->icsk_ack.pending |=
+					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
+			inet_csk_schedule_ack(sk);
+			sk->sk_data_ready(sk);
+
+			if (skb_queue_len(&sk->sk_receive_queue)) {
 				reason = SKB_DROP_REASON_PROTO_MEM;
 				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
-			sk->sk_data_ready(sk);
 				goto drop;
 			}
+			sk_forced_mem_schedule(sk, skb->truesize);
+		}
 
 		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 		if (skb->len)

net/ipv4/tcp_output.c

@@ -257,11 +257,19 @@ EXPORT_SYMBOL(tcp_select_initial_window);
 static u16 tcp_select_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 old_win = tp->rcv_wnd;
-	u32 cur_win = tcp_receive_window(tp);
-	u32 new_win = __tcp_select_window(sk);
 	struct net *net = sock_net(sk);
+	u32 old_win = tp->rcv_wnd;
+	u32 cur_win, new_win;
+
+	/* Make the window 0 if we failed to queue the data because we
+	 * are out of memory. The window is temporary, so we don't store
+	 * it on the socket.
+	 */
+	if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM))
+		return 0;
 
+	cur_win = tcp_receive_window(tp);
+	new_win = __tcp_select_window(sk);
 	if (new_win < cur_win) {
 		/* Danger Will Robinson!
 		 * Don't update rcv_wup/rcv_wnd here or else

net/ipv4/tcp_timer.c

@@ -454,6 +454,22 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 			  req->timeout << req->num_timeout, TCP_RTO_MAX);
 }
 
+static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
+				     const struct sk_buff *skb)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	const int timeout = TCP_RTO_MAX * 2;
+	u32 rcv_delta, rtx_delta;
+
+	rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+	if (rcv_delta <= timeout)
+		return false;
+
+	rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) -
+			(tp->retrans_stamp ?: tcp_skb_timestamp(skb)));
+
+	return rtx_delta > timeout;
+}
 
 /**
  *  tcp_retransmit_timer() - The TCP retransmit timeout handler
@@ -503,23 +519,26 @@ void tcp_retransmit_timer(struct sock *sk)
 		 * we cannot allow such beasts to hang infinitely.
 		 */
 		struct inet_sock *inet = inet_sk(sk);
+		u32 rtx_delta;
+
+		rtx_delta = tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb));
 		if (sk->sk_family == AF_INET) {
-			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
-					    &inet->inet_daddr,
-					    ntohs(inet->inet_dport),
-					    inet->inet_num,
-					    tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n",
+				&inet->inet_daddr, ntohs(inet->inet_dport),
+				inet->inet_num, tp->snd_una, tp->snd_nxt,
+				jiffies_to_msecs(jiffies - tp->rcv_tstamp),
+				rtx_delta);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
-					    &sk->sk_v6_daddr,
-					    ntohs(inet->inet_dport),
-					    inet->inet_num,
-					    tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Probing zero-window on %pI6:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n",
+				&sk->sk_v6_daddr, ntohs(inet->inet_dport),
+				inet->inet_num, tp->snd_una, tp->snd_nxt,
+				jiffies_to_msecs(jiffies - tp->rcv_tstamp),
+				rtx_delta);
 		}
 #endif
-		if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) {
+		if (tcp_rtx_probe0_timed_out(sk, skb)) {
 			tcp_write_err(sk);
 			goto out;
 		}