[PATCH v4 7/8] tcp: Fast re-transmit if half-closed, make TAP_FIN_RCVD path consistent

[Stefano Brivio <sbrivio@redhat.com>]

We currently have a number of discrepancies in the tcp_tap_handler()
path between the half-closed connection path and the regular one, and
they are mostly a result of code duplication, which comes in turn from
the fact that tcp_data_from_tap() deals with data transfers as well as
general connection bookkeeping, so we can't use it for half-closed
connections.

This suggests that we should probably rework it into two or more
functions, in the long term, but for the moment being I'm just fixing
one obvious issue, which is the lack of fast retransmissions in the
TAP_FIN_RCVD path, and a potential one, which is the fact we don't
handle socket flush failures.

Add fast re-transmit for half-closed connections, and handle the case
of socket flush (tcp_sock_consume()) flush failure in the same way as
tcp_data_from_tap() handles it.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tcp.c | 42 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/tcp.c b/tcp.c
index 9c70a25..5163dbf 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1652,6 +1652,23 @@ static int tcp_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
 	return tcp_buf_data_from_sock(c, conn);
 }
 
+/**
+ * tcp_packet_data_len() - Get data (TCP payload) length for a TCP packet
+ * @th:		Pointer to TCP header
+ * @l4len:	TCP packet length, including TCP header
+ *
+ * Return: data length of TCP packet, -1 on invalid value of Data Offset field
+ */
+static ssize_t tcp_packet_data_len(const struct tcphdr *th, size_t l4len)
+{
+	size_t off = th->doff * 4UL;
+
+	if (off < sizeof(*th) || off > l4len)
+		return -1;
+
+	return l4len - off;
+}
+
 /**
  * tcp_data_from_tap() - tap/guest data for established connection
  * @c:		Execution context
@@ -2113,9 +2130,28 @@ int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
 
 	/* Established connections not accepting data from tap */
 	if (conn->events & TAP_FIN_RCVD) {
-		tcp_sock_consume(conn, ntohl(th->ack_seq));
-		tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));
-		if (tcp_tap_window_update(c, conn, ntohs(th->window)))
+		bool retr;
+
+		retr = th->ack && !tcp_packet_data_len(th, l4len) && !th->fin &&
+		       ntohl(th->ack_seq) == conn->seq_ack_from_tap &&
+		       ntohs(th->window) == conn->wnd_from_tap;
+
+		/* On socket flush failure, pretend there was no ACK, try again
+		 * later
+		 */
+		if (th->ack && !tcp_sock_consume(conn, ntohl(th->ack_seq)))
+			tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));
+
+		if (retr) {
+			flow_trace(conn,
+				   "fast re-transmit, ACK: %u, previous sequence: %u",
+				   ntohl(th->ack_seq), conn->seq_to_tap);
+
+			if (tcp_rewind_seq(c, conn))
+				return -1;
+		}
+
+		if (tcp_tap_window_update(c, conn, ntohs(th->window)) || retr)
 			tcp_data_from_sock(c, conn);
 
 		if (conn->seq_ack_from_tap == conn->seq_to_tap) {
-- 
@@ -1652,6 +1652,23 @@ static int tcp_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
 	return tcp_buf_data_from_sock(c, conn);
 }
 
+/**
+ * tcp_packet_data_len() - Get data (TCP payload) length for a TCP packet
+ * @th:		Pointer to TCP header
+ * @l4len:	TCP packet length, including TCP header
+ *
+ * Return: data length of TCP packet, -1 on invalid value of Data Offset field
+ */
+static ssize_t tcp_packet_data_len(const struct tcphdr *th, size_t l4len)
+{
+	size_t off = th->doff * 4UL;
+
+	if (off < sizeof(*th) || off > l4len)
+		return -1;
+
+	return l4len - off;
+}
+
 /**
  * tcp_data_from_tap() - tap/guest data for established connection
  * @c:		Execution context
@@ -2113,9 +2130,28 @@ int tcp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
 
 	/* Established connections not accepting data from tap */
 	if (conn->events & TAP_FIN_RCVD) {
-		tcp_sock_consume(conn, ntohl(th->ack_seq));
-		tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));
-		if (tcp_tap_window_update(c, conn, ntohs(th->window)))
+		bool retr;
+
+		retr = th->ack && !tcp_packet_data_len(th, l4len) && !th->fin &&
+		       ntohl(th->ack_seq) == conn->seq_ack_from_tap &&
+		       ntohs(th->window) == conn->wnd_from_tap;
+
+		/* On socket flush failure, pretend there was no ACK, try again
+		 * later
+		 */
+		if (th->ack && !tcp_sock_consume(conn, ntohl(th->ack_seq)))
+			tcp_update_seqack_from_tap(c, conn, ntohl(th->ack_seq));
+
+		if (retr) {
+			flow_trace(conn,
+				   "fast re-transmit, ACK: %u, previous sequence: %u",
+				   ntohl(th->ack_seq), conn->seq_to_tap);
+
+			if (tcp_rewind_seq(c, conn))
+				return -1;
+		}
+
+		if (tcp_tap_window_update(c, conn, ntohs(th->window)) || retr)
 			tcp_data_from_sock(c, conn);
 
 		if (conn->seq_ack_from_tap == conn->seq_to_tap) {
-- 
2.43.0