DPDK-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Rajesh Kumar <rajesh3.kumar@intel.com>
To: dev@dpdk.org
Cc: thomas@monjalon.net, bruce.richardson@intel.com,
	andrew.rybchenko@oktetlabs.ru, stephen@networkplumber.org,
	aman.deep.singh@intel.com, Rajesh Kumar <rajesh3.kumar@intel.com>
Subject: [RFC PATCH v5 2/5] doc: describe ethdev timesync clock and Rx timestamp API
Date: Tue,  8 Sep 2026 13:02:03 +0530	[thread overview]
Message-ID: <20260908073206.1236372-3-rajesh3.kumar@intel.com> (raw)
In-Reply-To: <20260908073206.1236372-1-rajesh3.kumar@intel.com>

Add a programming guide page for the ethdev IEEE 1588 / PTP timesync
API, covering PHC clock management and receive timestamp extraction.

This describes existing, previously undocumented API and does not
introduce any new functionality.

Signed-off-by: Rajesh Kumar <rajesh3.kumar@intel.com>
---
 doc/guides/prog_guide/ethdev/index.rst    |  1 +
 doc/guides/prog_guide/ethdev/timesync.rst | 72 +++++++++++++++++++++++
 2 files changed, 73 insertions(+)
 create mode 100644 doc/guides/prog_guide/ethdev/timesync.rst

diff --git a/doc/guides/prog_guide/ethdev/index.rst b/doc/guides/prog_guide/ethdev/index.rst
index 392ced0a2e..bc21f28091 100644
--- a/doc/guides/prog_guide/ethdev/index.rst
+++ b/doc/guides/prog_guide/ethdev/index.rst
@@ -13,3 +13,4 @@ Ethernet Device Library
     traffic_metering_and_policing
     traffic_management
     qos_framework
+    timesync
diff --git a/doc/guides/prog_guide/ethdev/timesync.rst b/doc/guides/prog_guide/ethdev/timesync.rst
new file mode 100644
index 0000000000..59d660eba8
--- /dev/null
+++ b/doc/guides/prog_guide/ethdev/timesync.rst
@@ -0,0 +1,72 @@
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright(c) 2026 Intel Corporation.
+
+IEEE 1588 / PTP Timesync API
+============================
+
+Overview
+--------
+
+The DPDK IEEE 1588 / Precision Time Protocol (PTP) Timesync API provides
+a standardized framework for managing PTP Hardware Clocks (PHCs) and retrieving
+precise hardware transmit (Tx) and receive (Rx) timestamps.
+
+The Timesync framework encompasses three core capabilities:
+
+1. **Clock Control & Adjustment**: Enabling/disabling hardware timestamping, reading/setting clock time, and adjusting phase/frequency.
+2. **Receive Timestamping**: Hardware capture of incoming PTP packet arrival timestamps.
+3. **Transmit Timestamping**: Hardware capture of outbound PTP packet departure timestamps.
+
+
+Clock Management & Control
+--------------------------
+
+To initialize and discipline a port's PTP Hardware Clock (PHC), the API provides:
+
+Enable / Disable
+   ``rte_eth_timesync_enable(port_id)`` enables hardware timestamping on the specified port.
+   ``rte_eth_timesync_disable(port_id)`` disables timesync offloads.
+   The application must ensure no Tx timestamp operations are in flight before disabling timesync, unless the PMD explicitly supports concurrent disable and Tx timestamp operations.
+   This does not make the PMD hardware lifecycle safe by itself.
+
+Clock Time Read / Write
+   ``rte_eth_timesync_read_time(port_id, &ts)`` reads the current PHC wall-clock time as a ``struct timespec``.
+   ``rte_eth_timesync_write_time(port_id, &ts)`` sets the PHC wall-clock time.
+
+Clock Adjustments
+   ``rte_eth_timesync_adjust_time(port_id, delta_ns)`` adjusts the clock phase by a delta offset in nanoseconds.
+   ``rte_eth_timesync_adjust_freq(port_id, scaled_ppm)`` adjusts the clock frequency in scaled parts-per-million (1 ppm = 1 << 16).
+
+
+Receive (Rx) Timestamping
+-------------------------
+
+When receive timestamping is enabled, the hardware identifies incoming PTP packets and latches their arrival time.
+
+Rx Timestamp Extraction Workflow
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+1. On packet reception via ``rte_eth_rx_burst()``, the PMD checks if the received mbuf represents a PTP packet.
+2. The PMD sets the ``RTE_MBUF_F_RX_IEEE1588_PTP`` flag in ``mbuf->ol_flags``.
+3. Depending on the PMD and hardware capability, the Rx timestamp is either:
+
+   Extracted via API
+      Application calls ``rte_eth_timesync_read_rx_timestamp(port_id, &ts, flags)``.
+
+   Inlined in Mbuf
+      Stored in a registered mbuf dynamic field (e.g. ``rte_mbuf_dyn_rx_timestamp_register()``).
+
+
+PMD Implementation Requirements
+-------------------------------
+
+To support full timesync capabilities, a Poll Mode Driver (PMD) implements the following driver contract:
+
+1. Clock Operations
+   (``timesync_enable``, ``timesync_disable``, ``timesync_read_time``, ``timesync_write_time``, ``timesync_adjust_time``, ``timesync_adjust_freq``)
+
+   Controls hardware timestamp generation and disciplines the hardware clock registers.
+
+2. Rx Timestamping (``timesync_read_rx_timestamp``)
+
+   Configures Rx filters to latch incoming PTP arrival times and flags received mbufs with ``RTE_MBUF_F_RX_IEEE1588_PTP``.
-- 
2.55.0


  parent reply	other threads:[~2026-09-08  7:32 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-17 19:24 [RFC 0/1] ethdev: per-packet Tx timestamp slot management Rajesh Kumar
2026-08-17 19:24 ` [RFC 1/1] ethdev: add per-packet Tx timestamp slot APIs Rajesh Kumar
2026-08-20  4:51   ` Naga Harish K, S V
2026-08-18  2:23 ` [RFC 0/1] ethdev: per-packet Tx timestamp slot management Stephen Hemminger
2026-08-20  4:41 ` Naga Harish K, S V
2026-08-27 11:09   ` Kumar, Rajesh
2026-08-27 12:13 ` [RFC PATCH v2 0/1] ethdev: add Tx timestamp slot APIs Rajesh Kumar
2026-08-27 12:13   ` [RFC PATCH v3 1/1] ethdev: add Tx timestamp slot management APIs Rajesh Kumar
2026-08-27 12:18 ` [RFC PATCH v3 0/1] ethdev: add Tx timestamp slot APIs Rajesh Kumar
2026-08-27 12:21 ` Rajesh Kumar
2026-08-27 12:21   ` [RFC PATCH v3 1/1] ethdev: add Tx timestamp slot management APIs Rajesh Kumar
2026-08-27 21:45     ` Stephen Hemminger
2026-09-02  5:51     ` [RFC PATCH v4 0/3] ethdev: add Tx timestamp slot APIs Rajesh Kumar
2026-09-02  5:51       ` [RFC PATCH v4 1/3] ethdev: add Tx timestamp slot management APIs Rajesh Kumar
2026-09-02 14:13         ` Stephen Hemminger
2026-09-08  7:25           ` Kumar, Rajesh
2026-09-02  5:51       ` [RFC PATCH v4 2/3] net/ice: support per-packet Tx timestamp slots Rajesh Kumar
2026-09-02  5:51       ` [RFC PATCH v4 3/3] app/testpmd: add Tx timestamp capabilities command Rajesh Kumar
2026-09-08  7:32     ` [RFC PATCH v5 0/5] ethdev: add Tx timestamp slot APIs Rajesh Kumar
2026-09-08  7:32       ` [RFC PATCH v5 1/5] ethdev: add Tx timestamp slot management APIs Rajesh Kumar
2026-09-08  7:32       ` Rajesh Kumar [this message]
2026-09-08  7:32       ` [RFC PATCH v5 3/5] doc: describe ethdev Tx timestamp slot API Rajesh Kumar
2026-09-08  7:32       ` [RFC PATCH v5 4/5] net/ice: support per-packet Tx timestamp slots Rajesh Kumar
2026-09-08  7:32       ` [RFC PATCH v5 5/5] app/testpmd: add Tx timestamp capabilities command Rajesh Kumar
2026-08-27 12:34 ` [RFC PATCH v2 0/1] ethdev: add Tx timestamp slot APIs Rajesh Kumar
2026-08-27 12:34   ` [RFC PATCH v2 1/1] ethdev: add Tx timestamp slot management APIs Rajesh Kumar
2026-09-02 14:16   ` [RFC PATCH v2 0/1] ethdev: add Tx timestamp slot APIs Stephen Hemminger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260908073206.1236372-3-rajesh3.kumar@intel.com \
    --to=rajesh3.kumar@intel.com \
    --cc=aman.deep.singh@intel.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=stephen@networkplumber.org \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox