From 6a128cdf1926b20a94d6af7d7d03b76ba19a4f8b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 16 Jan 2025 12:46:25 +0200 Subject: 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 Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20250116104628.123555-2-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') 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; ); -- cgit v1.2.3