[PATCH iwl-net v2 11/15] ice: wait for in-flight Tx timestamps before flushing the tracker

From
Jacob Keller <jacob.e.keller@intel.com>
Date
2026-09-22 18:08:37
Also in
intel-wired-lan
Reply to
Jacob Keller, 2026-09-22
From: Petr Oros <redacted>

ice_ptp_flush_tx_tracker() frees every tracked request, but a request
whose timestamp is still being captured by the PHY at that moment is
freed without touching the PHY entry. The ready bit published shortly
after has no tracked owner, and the PHY does not raise another Tx
timestamp interrupt until every outstanding ready bit is read, so
delivery for the whole quad degrades to the periodic work.

Wait up to 10 ms for in-flight captures to publish their ready bits
before flushing, so the flush clears them together with the rest.

Note that the ice_ptp_flush_tx_tracker() function was introduced along with
the original E810 support, but that device does not have a ready bitmap.
Only later devices (E822, E825, E830) have the bitmap and potential issues
with internal tracking. Thus, skip the wait for E810 by checking the
tx->has_ready_bitmap flag.

Fixes: 10e4b4a3a3e1 ("ice: check Tx timestamp memory register for ready timestamps")
Signed-off-by: Petr Oros <redacted>
Reviewed-by: Maciek Machnikowski <redacted>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 43 ++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 657cd78ec738..142d9e1c1f2e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -744,6 +744,47 @@ ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx)
 	return 0;
 }
 
+static bool
+ice_ptp_is_tracker_drained(struct ice_pf *pf, struct ice_ptp_tx *tx)
+{
+	struct ice_hw *hw = &pf->hw;
+	bool pending = false;
+	u64 tstamp_ready;
+	u8 idx;
+
+	/* If HW reset is ongoing, we can't access SBQ */
+	if (hw->reset_ongoing)
+		return true;
+
+	if (ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready))
+		return true;
+
+	for_each_set_bit(idx, tx->in_use, tx->len) {
+		if (!(tstamp_ready & BIT_ULL(idx + tx->offset)))
+			pending = true;
+	}
+
+	return !pending;
+}
+
+static void
+ice_ptp_wait_for_tracker_drain(struct ice_pf *pf, struct ice_ptp_tx *tx)
+{
+	bool drained;
+	int err;
+
+	if (!tx->has_ready_bitmap)
+		return;
+
+	err = read_poll_timeout(ice_ptp_is_tracker_drained,
+				drained, drained, 500, 10 * USEC_PER_MSEC, false,
+				pf, tx);
+	if (err) {
+		dev_dbg(ice_pf_to_dev(pf), "Timed out waiting for in-flight Tx timestamps on block %u\n",
+			tx->block);
+	}
+}
+
 /**
  * ice_ptp_flush_tx_tracker - Flush any remaining timestamps from the tracker
  * @pf: Board private structure
@@ -760,6 +801,8 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 	int err;
 	u8 idx;
 
+	ice_ptp_wait_for_tracker_drain(pf, tx);
+
 	err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready);
 	if (err) {
 		dev_dbg(ice_pf_to_dev(pf), "Failed to get the Tx tstamp ready bitmap for block %u, err %d\n",
-- 
2.56.0.rc0.395.gd1f3524e15dc
Thread (22 messages) 22 messages, 3 authors, last reply 2026-09-23
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help