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, 3 insertions, 0 deletions

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 66be04013048..259cb211a338 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -842,6 +842,9 @@ attribute-sets:
       -
         name: tx-err
         type: uint
+      -
+        name: tx-onestep-pkts-unconfirmed
+        type: uint
   -
     name: ts-hwtstamp-provider
     attr-cnt-name: __ethtool-a-ts-hwtstamp-provider-cnt