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 <[email protected]>
Acked-by: Willem de Bruijn <[email protected]>
Signed-off-by: Miroslav Lichvar <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Documentation/networking/timestamping.txt

@@ -193,6 +193,16 @@ SOF_TIMESTAMPING_OPT_STATS:
   the transmit timestamps, such as how long a certain block of
   data was limited by peer's receiver window.
 
+SOF_TIMESTAMPING_OPT_PKTINFO:
+
+  Enable the SCM_TIMESTAMPING_PKTINFO control message for incoming
+  packets with hardware timestamps. The message contains struct
+  scm_ts_pktinfo, which supplies the index of the real interface which
+  received the packet and its length at layer 2. A valid (non-zero)
+  interface index will be returned only if CONFIG_NET_RX_BUSY_POLL is
+  enabled and the driver is using NAPI. The struct contains also two
+  other fields, but they are reserved and undefined.
+
 New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to
 disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate
 regardless of the setting of sysctl net.core.tstamp_allow_data.

include/uapi/asm-generic/socket.h

@@ -100,4 +100,6 @@
 
 #define SO_COOKIE		57
 
+#define SCM_TIMESTAMPING_PKTINFO	58
+
 #endif /* __ASM_GENERIC_SOCKET_H */

include/uapi/linux/net_tstamp.h

@@ -9,6 +9,7 @@
 #ifndef _NET_TIMESTAMPING_H
 #define _NET_TIMESTAMPING_H
 
+#include <linux/types.h>
 #include <linux/socket.h>   /* for SO_TIMESTAMPING */
 
 /* SO_TIMESTAMPING gets an integer bit field comprised of these values */
@@ -26,8 +27,9 @@ enum {
 	SOF_TIMESTAMPING_OPT_CMSG = (1<<10),
 	SOF_TIMESTAMPING_OPT_TSONLY = (1<<11),
 	SOF_TIMESTAMPING_OPT_STATS = (1<<12),
+	SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_STATS,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_PKTINFO,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };
@@ -130,4 +132,11 @@ enum hwtstamp_rx_filters {
 	HWTSTAMP_FILTER_NTP_ALL,
 };
 
+/* SCM_TIMESTAMPING_PKTINFO control message */
+struct scm_ts_pktinfo {
+	__u32 if_index;
+	__u32 pkt_length;
+	__u32 reserved[2];
+};
+
 #endif /* _NET_TIMESTAMPING_H */

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);