net: add new control message for incoming HW-timestamped packets

Add SOF_TIMESTAMPING_OPT_PKTINFO option to request a new control message
for incoming packets with hardware timestamps. It contains the index of
the real interface which received the packet and the length of the
packet at layer 2.

The index is useful with bonding, bridges and other interfaces, where
IP_PKTINFO doesn't allow applications to determine which PHC made the
timestamp. With the L2 length (and link speed) it is possible to
transpose preamble timestamps to trailer timestamps, which are used in
the NTP protocol.

While this information could be provided by two new socket options
independently from timestamping, it doesn't look like they would be very
useful. With this option any performance impact is limited to hardware
timestamping.

Use dev_get_by_napi_id() to get the device and its index. On kernels
with disabled CONFIG_NET_RX_BUSY_POLL or drivers not using NAPI, a zero
index will be returned in the control message.

CC: Richard Cochran <richardcochran@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 26 insertions, 1 deletions

diff --git a/net/socket.c b/net/socket.c
index c2564eb..67db7d8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -662,6 +662,27 @@ static bool skb_is_err_queue(const struct sk_buff *skb)
 	return skb->pkt_type == PACKET_OUTGOING;
 }
 
+static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
+{
+	struct scm_ts_pktinfo ts_pktinfo;
+	struct net_device *orig_dev;
+
+	if (!skb_mac_header_was_set(skb))
+		return;
+
+	memset(&ts_pktinfo, 0, sizeof(ts_pktinfo));
+
+	rcu_read_lock();
+	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
+	if (orig_dev)
+		ts_pktinfo.if_index = orig_dev->ifindex;
+	rcu_read_unlock();
+
+	ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb);
+	put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO,
+		 sizeof(ts_pktinfo), &ts_pktinfo);
+}
+
 /*
  * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
  */
@@ -699,8 +720,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 		empty = 0;
 	if (shhwtstamps &&
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
-	    ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2))
+	    ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) {
 		empty = 0;
+		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+		    !skb_is_err_queue(skb))
+			put_ts_pktinfo(msg, skb);
+	}
 	if (!empty) {
 		put_cmsg(msg, SOL_SOCKET,
 			 SCM_TIMESTAMPING, sizeof(tss), &tss);