On Mon, Jun 01, 2026 at 03:22:18PM +0800, Jiawen Wu wrote:

Implement .ndo_tx_timeout to handle Tx side timeout event. When a Tx
timeout event occur, it will trigger driver into reset process.

The WX_HANG_CHECK_ARMED bit is set to indicate a potential hang. It will
be cleared if a pause frame is received to avoid false hang detection
caused by pause frames.

In general, logic seems sound, below 1 small nit.
There is also a seemingly sensible comment from Sashiko (pasted below), which I 
agree with. If you not schedule NAPI every time to check for hang, then without 
Rx you are relying on dev_watchdog anyway, so maybe internal hang detection is 
not that necessary?

This driver does not generally use pr_err().

+		return -ENOMEM;
+	}
+
+	INIT_WORK(&wx->reset_task, wx_reset_task);
+	return 0;
+}
+EXPORT_SYMBOL(wx_init_err_task);
+
+static bool wx_ring_tx_pending(struct wx *wx)
+{
+	int i;
+
+	for (i = 0; i < wx->num_tx_queues; i++) {
+		struct wx_ring *tx_ring = wx->tx_ring[i];
+
+		if (tx_ring->next_to_use != tx_ring->next_to_clean)
+			return true;
+	}
+
+	return false;
+}
+
+static bool wx_vf_tx_pending(struct wx *wx)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
+	u32 i, j;
+
+	if (!wx->num_vfs)
+		return false;
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		for (j = 0; j < q_per_pool; j++) {
+			u32 h, t;
+
+			h = rd32(wx, WX_PX_TR_RP_PV(q_per_pool, i, j));
+			t = rd32(wx, WX_PX_TR_WP_PV(q_per_pool, i, j));
+
+			if (h != t)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static void wx_watchdog_flush_tx(struct wx *wx)
+{
+	if (!netif_running(wx->netdev))
+		return;
+	if (netif_carrier_ok(wx->netdev))
+		return;
+
+	if (wx_ring_tx_pending(wx) || wx_vf_tx_pending(wx)) {
+		/* We've lost link, so the controller stops DMA,
+		 * but we've got queued Tx work that's never going
+		 * to get done, so reset controller to flush Tx.
+		 * (Do the reset outside of interrupt context).
+		 */
+		wx_warn(wx, "initiating reset due to lost link with pending Tx work\n");
+		set_bit(WX_FLAG_NEED_PF_RESET, wx->flags);
+	}
+}
+
+static void wx_check_tx_hang(struct wx *wx)
+{
+	int i;
+
+	/* If we're down or resetting, just bail */
+	if (!netif_running(wx->netdev) ||
+	    test_bit(WX_STATE_RESETTING, wx->state))
+		return;
+
+	/* Force detection of hung controller */
+	if (netif_carrier_ok(wx->netdev)) {
+		for (i = 0; i < wx->num_tx_queues; i++)
+			set_bit(WX_TX_DETECT_HANG, wx->tx_ring[i]->state);

Sashiko says:

If a software interrupt is not triggered, wouldn't the evaluation of this
flag in wx_clean_tx_irq() fail to run unless incoming Rx traffic happens
to arrive on the same interrupt vector?

+	}
+}
+
+void wx_check_tx_hang_subtask(struct wx *wx)
+{
+	wx_watchdog_flush_tx(wx);
+	wx_check_tx_hang(wx);
+}
+EXPORT_SYMBOL(wx_check_tx_hang_subtask);
+
+static void wx_tx_timeout_reset(struct wx *wx)
+{
+	if (test_bit(WX_STATE_DOWN, wx->state))
+		return;
+
+	set_bit(WX_FLAG_NEED_PF_RESET, wx->flags);
+	wx_warn(wx, "initiating reset due to tx timeout\n");
+	wx_service_event_schedule(wx);
+}
+
+void wx_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	wx_tx_timeout_reset(wx);
+}
+EXPORT_SYMBOL(wx_tx_timeout);
+
+void wx_handle_tx_hang(struct wx_ring *tx_ring, unsigned int next)
+{
+	struct wx *wx = netdev_priv(tx_ring->netdev);
+
+	wx_warn(wx,
+		"Detected Tx Unit Hang: Queue %d, TDH %x, TDT %x, ntu %x, ntc %x, ntc.time_stamp %lx, jiffies %lx\n",
+		tx_ring->queue_index,
+		rd32(wx, WX_PX_TR_RP(tx_ring->reg_idx)),
+		rd32(wx, WX_PX_TR_WP(tx_ring->reg_idx)),
+		tx_ring->next_to_use, next,
+		tx_ring->tx_buffer_info[next].time_stamp, jiffies);
+
+	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+	wx_tx_timeout_reset(wx);
+}

[...]