提交 d2a90036 编写于 作者: B broonie@sirena.org.uk 提交者: Jeff Garzik

natsemi: Avoid IntrStatus lossage if RX state machine resets.

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: NMark Brown <broonie@sirena.org.uk>
Signed-off-by: NJeff Garzik <jeff@garzik.org>
上级 069f8256
......@@ -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;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册