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>

tcp.c

@@ -373,6 +373,9 @@ static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
 
 char		tcp_buf_discard		[MAX_WINDOW];
 
+/* Does the kernel support TCP_PEEK_OFF? */
+bool peek_offset_cap;
+
 /* sendmsg() to socket */
 static struct iovec	tcp_iov			[UIO_MAXIOV];
 
@@ -388,6 +391,25 @@ static_assert(ARRAY_SIZE(tc_hash) >= FLOW_MAX,
 int init_sock_pool4		[TCP_SOCK_POOL_SIZE];
 int init_sock_pool6		[TCP_SOCK_POOL_SIZE];
 
+/**
+ * tcp_set_peek_offset() - Set SO_PEEK_OFF offset on a socket if supported
+ * @s:          Socket to update
+ * @offset:     Offset in bytes
+ *
+ * Return:      -1 when it fails, 0 otherwise.
+ */
+int tcp_set_peek_offset(int s, int offset)
+{
+	if (!peek_offset_cap)
+		return 0;
+
+	if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset))) {
+		err("Failed to set SO_PEEK_OFF to %i in socket %i", offset, s);
+		return -1;
+	}
+	return 0;
+}
+
 /**
  * tcp_conn_epoll_events() - epoll events mask for given connection state
  * @events:	Current connection events
@@ -1947,6 +1969,10 @@ static int tcp_data_from_tap(struct ctx *c, struct tcp_tap_conn *conn,
 			   "fast re-transmit, ACK: %u, previous sequence: %u",
 			   max_ack_seq, conn->seq_to_tap);
 		conn->seq_to_tap = max_ack_seq;
+		if (tcp_set_peek_offset(conn->sock, 0)) {
+			tcp_rst(c, conn);
+			return -1;
+		}
 		tcp_data_from_sock(c, conn);
 	}
 
@@ -2039,6 +2065,10 @@ static void tcp_conn_from_sock_finish(struct ctx *c, struct tcp_tap_conn *conn,
 	conn->seq_ack_to_tap = conn->seq_from_tap;
 
 	conn_event(c, conn, ESTABLISHED);
+	if (tcp_set_peek_offset(conn->sock, 0)) {
+		tcp_rst(c, conn);
+		return;
+	}
 
 	/* The client might have sent data already, which we didn't
 	 * dequeue waiting for SYN,ACK from tap -- check now.
@@ -2119,6 +2149,8 @@ int tcp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af,
 			goto reset;
 
 		conn_event(c, conn, ESTABLISHED);
+		if (tcp_set_peek_offset(conn->sock, 0))
+			goto reset;
 
 		if (th->fin) {
 			conn->seq_from_tap++;
@@ -2367,8 +2399,12 @@ void tcp_timer_handler(struct ctx *c, union epoll_ref ref)
 			flow_dbg(conn, "ACK timeout, retry");
 			conn->retrans++;
 			conn->seq_to_tap = conn->seq_ack_from_tap;
-			tcp_data_from_sock(c, conn);
-			tcp_timer_ctl(c, conn);
+			if (tcp_set_peek_offset(conn->sock, 0)) {
+				tcp_rst(c, conn);
+			} else {
+				tcp_data_from_sock(c, conn);
+				tcp_timer_ctl(c, conn);
+			}
 		}
 	} else {
 		struct itimerspec new = { { 0 }, { ACT_TIMEOUT, 0 } };
@@ -2659,7 +2695,8 @@ static void tcp_sock_refill_init(const struct ctx *c)
  */
 int tcp_init(struct ctx *c)
 {
-	unsigned b;
+	unsigned int b, optv = 0;
+	int s;
 
 	for (b = 0; b < TCP_HASH_TABLE_SIZE; b++)
 		tc_hash[b] = FLOW_SIDX_NONE;
@@ -2683,6 +2720,17 @@ int tcp_init(struct ctx *c)
 		NS_CALL(tcp_ns_socks_init, c);
 	}
 
+	/* Probe for SO_PEEK_OFF support */
+	s = socket(AF_INET, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
+	if (s < 0) {
+		warn_perror("Temporary TCP socket creation failed");
+	} else {
+		if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int)))
+			peek_offset_cap = true;
+		close(s);
+	}
+	info("SO_PEEK_OFF%ssupported", peek_offset_cap ? " " : " not ");
+
 	return 0;
 }
 

tcp.h

@@ -24,6 +24,9 @@ void tcp_timer(struct ctx *c, const struct timespec *now);
 void tcp_defer_handler(struct ctx *c);
 
 void tcp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s);
+int tcp_set_peek_offset(int s, int offset);
+
+extern bool peek_offset_cap;
 
 /**
  * union tcp_epoll_ref - epoll reference portion for TCP connections

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;