natsemi: Avoid IntrStatus lossage if RX state machine resets. (d2a90036) · Commits · 戴 / test

This patch fixes the poll routine for the natsemi driver so that if the driver detects an RX state machine lockup then no interrupts will be lost while the driver recovers from that. Signed-Off-By:

Mark Brown <broonie@sirena.org.uk> Signed-off-by:

Jeff Garzik <jeff@garzik.org>

drivers/net/natsemi.c

+8 −6

Original line number	Diff line number	Diff line
		@@ -2169,6 +2169,14 @@ static int natsemi_poll(struct net_device dev, int budget)
		dev->name, np->intr_status,
		readl(ioaddr + IntrMask));

		/* netdev_rx() may read IntrStatus again if the RX state
		* machine falls over so do it first. */
		if (np->intr_status &
		(IntrRxDone \| IntrRxIntr \| RxStatusFIFOOver \|
		IntrRxErr \| IntrRxOverrun)) {
		netdev_rx(dev, &work_done, work_to_do);
		}

		if (np->intr_status &
		(IntrTxDone \| IntrTxIntr \| IntrTxIdle \| IntrTxErr)) {
		spin_lock(&np->lock);
		@@ -2180,12 +2188,6 @@ static int natsemi_poll(struct net_device dev, int budget)
		if (np->intr_status & IntrAbnormalSummary)
		netdev_error(dev, np->intr_status);

		if (np->intr_status &
		(IntrRxDone \| IntrRxIntr \| RxStatusFIFOOver \|
		IntrRxErr \| IntrRxOverrun)) {
		netdev_rx(dev, &work_done, work_to_do);
		}

		*budget -= work_done;
		dev->quota -= work_done;

Admin message