net: ethtool: ts: add separate counter for unconfirmed one-step TX timestamps

For packets with two-step timestamp requests, the hardware timestamp
comes back to the driver through a confirmation mechanism of sorts,
which allows the driver to confidently bump the successful "pkts"
counter.

For one-step PTP, the NIC is supposed to autonomously insert its
hardware TX timestamp in the packet headers while simultaneously
transmitting it. There may be a confirmation that this was done
successfully, or there may not.

None of the current drivers which implement ethtool_ops :: get_ts_stats()
also support HWTSTAMP_TX_ONESTEP_SYNC or HWTSTAMP_TX_ONESTEP_SYNC, so it
is a bit unclear which model to follow. But there are NICs, such as DSA,
where there is no transmit confirmation at all. Here, it would be wrong /
misleading to increment the successful "pkts" counter, because one-step
PTP packets can be dropped on TX just like any other packets.

So introduce a special counter which signifies "yes, an attempt was made,
but we don't know whether it also exited the port or not". I expect that
for one-step PTP packets where a confirmation is available, the "pkts"
counter would be bumped.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250116104628.123555-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 7 insertions, 0 deletions

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index e4136b0df892..64301ddf2f59 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -559,6 +559,12 @@ struct ethtool_rmon_stats {
 /**
  * struct ethtool_ts_stats - HW timestamping statistics
  * @pkts: Number of packets successfully timestamped by the hardware.
+ * @onestep_pkts_unconfirmed: Number of PTP packets with one-step TX
+ *			      timestamping that were sent, but for which the
+ *			      device offers no confirmation whether they made
+ *			      it onto the wire and the timestamp was inserted
+ *			      in the originTimestamp or correctionField, or
+ *			      not.
  * @lost: Number of hardware timestamping requests where the timestamping
  *	information from the hardware never arrived for submission with
  *	the skb.
@@ -571,6 +577,7 @@ struct ethtool_rmon_stats {
 struct ethtool_ts_stats {
 	struct_group(tx_stats,
 		u64 pkts;
+		u64 onestep_pkts_unconfirmed;
 		u64 lost;
 		u64 err;
 	);