tcp: leverage support of SO_PEEK_OFF socket option when available

>From linux-6.9.0 the kernel will contain
commit 05ea491641d3 ("tcp: add support for SO_PEEK_OFF socket option").

This new feature makes is possible to call recv_msg(MSG_PEEK) and make
it start reading data from a given offset set by the SO_PEEK_OFF socket
option. This way, we can avoid repeated reading of already read bytes of
a received message, hence saving read cycles when forwarding TCP
messages in the host->name space direction.

In this commit, we add functionality to leverage this feature when
available, while we fall back to the previous behavior when not.

Measurements with iperf3 shows that throughput increases with 15-20
percent in the host->namespace direction when this feature is used.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

1 files changed, 19 insertions, 6 deletions

diff --git a/tcp_buf.c b/tcp_buf.c
index ff9f797..11dce02 100644
--- a/tcp_buf.c
+++ b/tcp_buf.c
@@ -408,6 +408,7 @@ int tcp_buf_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
 	uint32_t already_sent, seq;
 	struct iovec *iov;
 
+	/* How much have we read/sent since last received ack ? */
 	already_sent = conn->seq_to_tap - conn->seq_ack_from_tap;
 
 	if (SEQ_LT(already_sent, 0)) {
@@ -416,6 +417,10 @@ int tcp_buf_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
 			   conn->seq_ack_from_tap, conn->seq_to_tap);
 		conn->seq_to_tap = conn->seq_ack_from_tap;
 		already_sent = 0;
+		if (tcp_set_peek_offset(s, 0)) {
+			tcp_rst(c, conn);
+			return -1;
+		}
 	}
 
 	if (!wnd_scaled || already_sent >= wnd_scaled) {
@@ -433,11 +438,16 @@ int tcp_buf_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
 		iov_rem = (wnd_scaled - already_sent) % mss;
 	}
 
-	mh_sock.msg_iov = iov_sock;
-	mh_sock.msg_iovlen = fill_bufs + 1;
-
-	iov_sock[0].iov_base = tcp_buf_discard;
-	iov_sock[0].iov_len = already_sent;
+	/* Prepare iov according to kernel capability */
+	if (!peek_offset_cap) {
+		mh_sock.msg_iov = iov_sock;
+		iov_sock[0].iov_base = tcp_buf_discard;
+		iov_sock[0].iov_len = already_sent;
+		mh_sock.msg_iovlen = fill_bufs + 1;
+	} else {
+		mh_sock.msg_iov = &iov_sock[1];
+		mh_sock.msg_iovlen = fill_bufs;
+	}
 
 	if (( v4 && tcp4_payload_used + fill_bufs > TCP_FRAMES_MEM) ||
 	    (!v4 && tcp6_payload_used + fill_bufs > TCP_FRAMES_MEM)) {
@@ -478,7 +488,10 @@ int tcp_buf_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
 		return 0;
 	}
 
-	sendlen = len - already_sent;
+	sendlen = len;
+	if (!peek_offset_cap)
+		sendlen -= already_sent;
+
 	if (sendlen <= 0) {
 		conn_flag(c, conn, STALLED);
 		return 0;