[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250116104628.123555-2-vladimir.oltean@nxp.com>
Date: Thu, 16 Jan 2025 12:46:25 +0200
From: Vladimir Oltean <vladimir.oltean@....com>
To: netdev@...r.kernel.org
Cc: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Andrew Lunn <andrew@...n.ch>,
Claudiu Manoil <claudiu.manoil@....com>,
Alexandre Belloni <alexandre.belloni@...tlin.com>,
Horatiu Vultur <horatiu.vultur@...rochip.com>,
Daniel Machon <daniel.machon@...rochip.com>,
UNGLinuxDriver@...rochip.com,
Xiaoliang Yang <xiaoliang.yang_1@....com>,
Yangbo Lu <yangbo.lu@....com>,
Richard Cochran <richardcochran@...il.com>
Subject: [PATCH v2 net-next 1/4] 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@....com>
Reviewed-by: Jakub Kicinski <kuba@...nel.org>
---
v1->v2: rebase
Documentation/netlink/specs/ethtool.yaml | 3 +++
Documentation/networking/ethtool-netlink.rst | 16 +++++++++++-----
include/linux/ethtool.h | 7 +++++++
include/uapi/linux/ethtool_netlink_generated.h | 1 +
net/ethtool/tsinfo.c | 2 ++
5 files changed, 24 insertions(+), 5 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
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index f70c0249860c..3770a2294509 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1281,11 +1281,17 @@ would be empty (no bit set).
Additional hardware timestamping statistics response contents:
- ===================================== ====== ===================================
- ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx HW timestamps
- ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp not arrived count
- ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request Tx timestamp count
- ===================================== ====== ===================================
+ ================================================== ====== =====================
+ ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx
+ HW timestamps
+ ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp
+ not arrived count
+ ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request
+ Tx timestamp count
+ ``ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED`` uint Packets with one-step
+ HW TX timestamps with
+ unconfirmed delivery
+ ================================================== ====== =====================
CABLE_TEST
==========
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;
);
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 2e17ff348f89..fe24c3459ac0 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -382,6 +382,7 @@ enum {
ETHTOOL_A_TS_STAT_TX_PKTS,
ETHTOOL_A_TS_STAT_TX_LOST,
ETHTOOL_A_TS_STAT_TX_ERR,
+ ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED,
__ETHTOOL_A_TS_STAT_CNT,
ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1)
diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 7e495a41aeec..691be6c445b3 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -186,6 +186,8 @@ static int tsinfo_put_stats(struct sk_buff *skb,
if (tsinfo_put_stat(skb, stats->tx_stats.pkts,
ETHTOOL_A_TS_STAT_TX_PKTS) ||
+ tsinfo_put_stat(skb, stats->tx_stats.onestep_pkts_unconfirmed,
+ ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED) ||
tsinfo_put_stat(skb, stats->tx_stats.lost,
ETHTOOL_A_TS_STAT_TX_LOST) ||
tsinfo_put_stat(skb, stats->tx_stats.err,
--
2.43.0
Powered by blists - more mailing lists