[PATCH v7 2/3] tcp: leverage support of SO_PEEK_OFF socket option when available

[Jon Maloy <jmaloy@redhat.com>]

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.

Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
 tcp.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 51 insertions(+), 8 deletions(-)

diff --git a/tcp.c b/tcp.c
index 146ab8f..01898f1 100644
--- a/tcp.c
+++ b/tcp.c
@@ -509,6 +509,9 @@ static struct iovec	tcp6_l2_iov		[TCP_FRAMES_MEM][TCP_NUM_IOVS];
 static struct iovec	tcp4_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
 static struct iovec	tcp6_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
 
+/* Does the kernel support TCP_PEEK_OFF? */
+static bool peek_offset_cap;
+
 /* sendmsg() to socket */
 static struct iovec	tcp_iov			[UIO_MAXIOV];
 
@@ -524,6 +527,20 @@ 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
+ */
+static void tcp_set_peek_offset(int s, int offset)
+{
+	if (!peek_offset_cap)
+		return;
+
+	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);
+}
+
 /**
  * tcp_conn_epoll_events() - epoll events mask for given connection state
  * @events:	Current connection events
@@ -1269,6 +1286,7 @@ static void tcp_revert_seq(struct tcp_tap_conn **conns, struct iovec (*frames)[T
 			continue;
 
 		conn->seq_to_tap = seq;
+		tcp_set_peek_offset(conn->sock, seq - conn->seq_ack_from_tap);
 	}
 }
 
@@ -2199,14 +2217,15 @@ static int tcp_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)) {
 		/* RFC 761, section 2.1. */
 		flow_trace(conn, "ACK sequence gap: ACK for %u, sent: %u",
 			   conn->seq_ack_from_tap, conn->seq_to_tap);
 		conn->seq_to_tap = conn->seq_ack_from_tap;
 		already_sent = 0;
+		tcp_set_peek_offset(s, 0);
 	}
 
 	if (!wnd_scaled || already_sent >= wnd_scaled) {
@@ -2224,11 +2243,16 @@ static int tcp_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)) {
@@ -2269,7 +2293,10 @@ static int tcp_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;
@@ -2440,6 +2467,7 @@ 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;
+		tcp_set_peek_offset(conn->sock, 0);
 		tcp_data_from_sock(c, conn);
 	}
 
@@ -2532,6 +2560,7 @@ 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);
+	tcp_set_peek_offset(conn->sock, 0);
 
 	/* The client might have sent data already, which we didn't
 	 * dequeue waiting for SYN,ACK from tap -- check now.
@@ -2612,6 +2641,7 @@ int tcp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af,
 			goto reset;
 
 		conn_event(c, conn, ESTABLISHED);
+		tcp_set_peek_offset(conn->sock, 0);
 
 		if (th->fin) {
 			conn->seq_from_tap++;
@@ -2860,6 +2890,7 @@ 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_set_peek_offset(conn->sock, 0);
 			tcp_data_from_sock(c, conn);
 			tcp_timer_ctl(c, conn);
 		}
@@ -3151,7 +3182,8 @@ 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;
@@ -3175,6 +3207,17 @@ 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("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;
 }
 
-- 
@@ -509,6 +509,9 @@ static struct iovec	tcp6_l2_iov		[TCP_FRAMES_MEM][TCP_NUM_IOVS];
 static struct iovec	tcp4_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
 static struct iovec	tcp6_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
 
+/* Does the kernel support TCP_PEEK_OFF? */
+static bool peek_offset_cap;
+
 /* sendmsg() to socket */
 static struct iovec	tcp_iov			[UIO_MAXIOV];
 
@@ -524,6 +527,20 @@ 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
+ */
+static void tcp_set_peek_offset(int s, int offset)
+{
+	if (!peek_offset_cap)
+		return;
+
+	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);
+}
+
 /**
  * tcp_conn_epoll_events() - epoll events mask for given connection state
  * @events:	Current connection events
@@ -1269,6 +1286,7 @@ static void tcp_revert_seq(struct tcp_tap_conn **conns, struct iovec (*frames)[T
 			continue;
 
 		conn->seq_to_tap = seq;
+		tcp_set_peek_offset(conn->sock, seq - conn->seq_ack_from_tap);
 	}
 }
 
@@ -2199,14 +2217,15 @@ static int tcp_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)) {
 		/* RFC 761, section 2.1. */
 		flow_trace(conn, "ACK sequence gap: ACK for %u, sent: %u",
 			   conn->seq_ack_from_tap, conn->seq_to_tap);
 		conn->seq_to_tap = conn->seq_ack_from_tap;
 		already_sent = 0;
+		tcp_set_peek_offset(s, 0);
 	}
 
 	if (!wnd_scaled || already_sent >= wnd_scaled) {
@@ -2224,11 +2243,16 @@ static int tcp_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)) {
@@ -2269,7 +2293,10 @@ static int tcp_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;
@@ -2440,6 +2467,7 @@ 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;
+		tcp_set_peek_offset(conn->sock, 0);
 		tcp_data_from_sock(c, conn);
 	}
 
@@ -2532,6 +2560,7 @@ 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);
+	tcp_set_peek_offset(conn->sock, 0);
 
 	/* The client might have sent data already, which we didn't
 	 * dequeue waiting for SYN,ACK from tap -- check now.
@@ -2612,6 +2641,7 @@ int tcp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af,
 			goto reset;
 
 		conn_event(c, conn, ESTABLISHED);
+		tcp_set_peek_offset(conn->sock, 0);
 
 		if (th->fin) {
 			conn->seq_from_tap++;
@@ -2860,6 +2890,7 @@ 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_set_peek_offset(conn->sock, 0);
 			tcp_data_from_sock(c, conn);
 			tcp_timer_ctl(c, conn);
 		}
@@ -3151,7 +3182,8 @@ 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;
@@ -3175,6 +3207,17 @@ 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("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;
 }
 
-- 
2.45.0