[PATCH v4 3/3] tcp: allow retransmit when peer receive window is zero

[Jon Maloy <jmaloy@redhat.com>]

A bug in kernel TCP may lead to a deadlock where a zero window is sent
from the peer, while it is unable to send out window updates even after
reads have freed up enough buffer space to permit a larger window.
In this situation, new window advertisemnts from the peer can only be
triggered by packets arriving from this side.

However, such packets are never sent, because the zero-window condition
currently prevents this side from sending out any packets whatsoever
to the peer.

We notice that the above bug is triggered *only* after the peer has
dropped an arriving packet because of severe memory squeeze, and that we
hence always enter a retransmission situation when this occurs. This
also means that it goes against the RFC 9293 recommendation that a
previously advertised window never should shrink.

RFC 9293 gives the solution to this situation. In chapter 3.6.1 we find
the following statement:
"A TCP receiver SHOULD NOT shrink the window, i.e., move the right
window edge to the left (SHLD-14). However, a sending TCP peer MUST
be robust against window shrinking, which may cause the
"usable window" (see Section 3.8.6.2.1) to become negative (MUST-34).

If this happens, the sender SHOULD NOT send new data (SHLD-15), but
SHOULD retransmit normally the old unacknowledged data between SND.UNA
and SND.UNA+SND.WND (SHLD-16). The sender MAY also retransmit old data
beyond SND.UNA+SND.WND (MAY-7)"

We never see the window become negative, but we interpret this as a
recommendation to use the previously available window during
retransmission even when the currently advertised window is zero.

We use the above mechanism only at timer-induced retransmits.
In the case we receive duplicate ack and a zero window, but
still know we have outstanding data acks waiting, we send out an
empty "fast probe" instead of doing fast retransmit. This averts
the risk of overwhelming a memory squeezed peer with retransmits,
while still forcing it to send out a new window update when the
probe is received. This entails a theoretical risk of redundant
retransmits from the peer, but that is a risk worth taking.

In case of a zero-window non-retransmission situation where there
is no new data to be sent, we also add a simple zero-window probing
feature. By sending an empty packet at regular timeout events we
resolve the situation described above, since the peer receives the
necessary trigger to advertise its window once it becomes non-zero
again.

It should be noted that although this solves the problem we have at
hand, it is not a genuine solution to the kernel bug. There may well
be TCP stacks around in other OS-es which don't do this, nor have
keep-alive probing as an alternatve way to solve the situation.

Signed-off-by: Jon Maloy <jmaloy@redhat.com>

---
v2: - Using previously advertised window during retransmission, instead
      highest send sequencece number in the cycle.
v3: - Rebased to newest code
    - Changes based on feedback from PASST team
    - Sending out empty probe message at timer expiration when
      we are not in retransmit situation.
v4: - Some small changes based on feedback from PASST team.
    - Replaced fast retransmit with a one-time 'fast probe' when
      window is zero.
---
 tcp.c      | 32 +++++++++++++++++++++++++++-----
 tcp_conn.h |  2 ++
 2 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/tcp.c b/tcp.c
index 4163bf9..a33f494 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1761,9 +1761,15 @@ static void tcp_get_tap_ws(struct tcp_tap_conn *conn,
  */
 static void tcp_tap_window_update(struct tcp_tap_conn *conn, unsigned wnd)
 {
+	uint32_t wnd_edge;
+
 	wnd = MIN(MAX_WINDOW, wnd << conn->ws_from_tap);
 	conn->wnd_from_tap = MIN(wnd >> conn->ws_from_tap, USHRT_MAX);
 
+	wnd_edge = conn->seq_ack_from_tap + wnd;
+	if (wnd && SEQ_GT(wnd_edge, conn->seq_wnd_edge_from_tap))
+		conn->seq_wnd_edge_from_tap = wnd_edge;
+
 	/* FIXME: reflect the tap-side receiver's window back to the sock-side
 	 * sender by adjusting SO_RCVBUF? */
 }
@@ -1796,6 +1802,7 @@ static void tcp_seq_init(const struct ctx *c, struct tcp_tap_conn *conn,
 	ns = (now->tv_sec * 1000000000 + now->tv_nsec) >> 5;
 
 	conn->seq_to_tap = ((uint32_t)(hash >> 32) ^ (uint32_t)hash) + ns;
+	conn->seq_wnd_edge_from_tap = conn->seq_to_tap;
 }
 
 /**
@@ -2205,13 +2212,12 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
  */
 static int tcp_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
 {
-	uint32_t wnd_scaled = conn->wnd_from_tap << conn->ws_from_tap;
 	int fill_bufs, send_bufs = 0, last_len, iov_rem = 0;
 	int sendlen, len, dlen, v4 = CONN_V4(conn);
+	uint32_t already_sent, max_send, seq;
 	int s = conn->sock, i, ret = 0;
 	struct msghdr mh_sock = { 0 };
 	uint16_t mss = MSS_GET(conn);
-	uint32_t already_sent, seq;
 	struct iovec *iov;
 
 	/* How much have we read/sent since last received ack ? */
@@ -2225,19 +2231,24 @@ static int tcp_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
 		tcp_set_peek_offset(s, 0);
 	}
 
-	if (!wnd_scaled || already_sent >= wnd_scaled) {
+	/* How much are we still allowed to send within current window ? */
+	max_send = conn->seq_wnd_edge_from_tap - conn->seq_to_tap;
+	if (SEQ_LE(max_send, 0)) {
+		flow_trace(conn, "Empty window: win_upper: %u, sent: %u",
+			   conn->seq_wnd_edge_from_tap, conn->seq_to_tap);
+		conn->seq_wnd_edge_from_tap = conn->seq_to_tap;
 		conn_flag(c, conn, STALLED);
 		conn_flag(c, conn, ACK_FROM_TAP_DUE);
 		return 0;
 	}
 
 	/* Set up buffer descriptors we'll fill completely and partially. */
-	fill_bufs = DIV_ROUND_UP(wnd_scaled - already_sent, mss);
+	fill_bufs = DIV_ROUND_UP(max_send,  mss);
 	if (fill_bufs > TCP_FRAMES) {
 		fill_bufs = TCP_FRAMES;
 		iov_rem = 0;
 	} else {
-		iov_rem = (wnd_scaled - already_sent) % mss;
+		iov_rem = max_send % mss;
 	}
 
 	/* Prepare iov according to kernel capability */
@@ -2466,6 +2477,13 @@ static int tcp_data_from_tap(struct ctx *c, struct tcp_tap_conn *conn,
 		conn->seq_to_tap = max_ack_seq;
 		tcp_set_peek_offset(conn->sock, 0);
 		tcp_data_from_sock(c, conn);
+	} else if (!max_ack_seq_wnd && SEQ_GT(conn->seq_to_tap, max_ack_seq)) {
+		/* Force peer to send new advertisement now, but only once */
+		flow_trace(conn, "fast probe, ACK: %u, previous sequence: %u",
+			   max_ack_seq, conn->seq_to_tap);
+		tcp_send_flag(c, conn, ACK);
+		conn->seq_to_tap = max_ack_seq;
+		tcp_set_peek_offset(conn->sock, 0);
 	}
 
 	if (!iov_i)
@@ -2911,6 +2929,10 @@ void tcp_timer_handler(struct ctx *c, union epoll_ref ref)
 			flow_dbg(conn, "activity timeout");
 			tcp_rst(c, conn);
 		}
+		/* No data exchanged recently? Keep connection alive. */
+		if (conn->seq_to_tap == conn->seq_ack_from_tap &&
+		    conn->seq_from_tap == conn->seq_ack_to_tap)
+			tcp_send_flag(c, conn, ACK);
 	}
 }
 
diff --git a/tcp_conn.h b/tcp_conn.h
index d280b22..5cbad2a 100644
--- a/tcp_conn.h
+++ b/tcp_conn.h
@@ -30,6 +30,7 @@
  * @wnd_to_tap:		Sending window advertised to tap, unscaled (as sent)
  * @seq_to_tap:		Next sequence for packets to tap
  * @seq_ack_from_tap:	Last ACK number received from tap
+ * @seq_wnd_edge_from_tap: Right edge of last non-zero window from tap
  * @seq_from_tap:	Next sequence for packets from tap (not actually sent)
  * @seq_ack_to_tap:	Last ACK number sent to tap
  * @seq_init_from_tap:	Initial sequence number from tap
@@ -101,6 +102,7 @@ struct tcp_tap_conn {
 
 	uint32_t	seq_to_tap;
 	uint32_t	seq_ack_from_tap;
+	uint32_t	seq_wnd_edge_from_tap;
 	uint32_t	seq_from_tap;
 	uint32_t	seq_ack_to_tap;
 	uint32_t	seq_init_from_tap;
-- 
@@ -30,6 +30,7 @@
  * @wnd_to_tap:		Sending window advertised to tap, unscaled (as sent)
  * @seq_to_tap:		Next sequence for packets to tap
  * @seq_ack_from_tap:	Last ACK number received from tap
+ * @seq_wnd_edge_from_tap: Right edge of last non-zero window from tap
  * @seq_from_tap:	Next sequence for packets from tap (not actually sent)
  * @seq_ack_to_tap:	Last ACK number sent to tap
  * @seq_init_from_tap:	Initial sequence number from tap
@@ -101,6 +102,7 @@ struct tcp_tap_conn {
 
 	uint32_t	seq_to_tap;
 	uint32_t	seq_ack_from_tap;
+	uint32_t	seq_wnd_edge_from_tap;
 	uint32_t	seq_from_tap;
 	uint32_t	seq_ack_to_tap;
 	uint32_t	seq_init_from_tap;
-- 
2.42.0