usbnet: ipheth: fix racing condition

Fix a racing condition in ipheth.c that can lead to slow performance.

Bug: In ipheth_tx(), netif_wake_queue() may be called on the callback
ipheth_sndbulk_callback(), _before_ netif_stop_queue() is called.
When this happens, the queue is stopped longer than it needs to be,
thus reducing network performance.

Fix: Move netif_stop_queue() in front of usb_submit_urb(). Now the order
is always correct. In case, usb_submit_urb() fails, the queue is woken up
again as callback will not fire.

Testing: This racing condition is usually not noticeable, as it has to
occur very frequently to slowdown the network. The callback from the USB
is usually triggered slow enough, so the situation does not appear.
However, on a Ubuntu Linux on VMWare Workstation, running on Windows 10,
the we loose the race quite often and the following speedup can be noticed:

Without this patch: Download:  4.10 Mbit/s, Upload:  4.01 Mbit/s
With this patch:    Download: 36.23 Mbit/s, Upload: 17.61 Mbit/s

Signed-off-by: Oliver Zweigle <Oliver.Zweigle@faro.com>
Signed-off-by: Bernd Eckstein <3ernd.Eckstein@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Bernd Eckstein 2019-05-20 17:31:09 +02:00 committed by David S. Miller
parent af8f3fb7fb
commit 94d250fae4
1 changed files with 2 additions and 1 deletions

View File

@ -383,17 +383,18 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
dev); dev);
dev->tx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; dev->tx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
netif_stop_queue(net);
retval = usb_submit_urb(dev->tx_urb, GFP_ATOMIC); retval = usb_submit_urb(dev->tx_urb, GFP_ATOMIC);
if (retval) { if (retval) {
dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n", dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n",
__func__, retval); __func__, retval);
dev->net->stats.tx_errors++; dev->net->stats.tx_errors++;
dev_kfree_skb_any(skb); dev_kfree_skb_any(skb);
netif_wake_queue(net);
} else { } else {
dev->net->stats.tx_packets++; dev->net->stats.tx_packets++;
dev->net->stats.tx_bytes += skb->len; dev->net->stats.tx_bytes += skb->len;
dev_consume_skb_any(skb); dev_consume_skb_any(skb);
netif_stop_queue(net);
} }
return NETDEV_TX_OK; return NETDEV_TX_OK;