Am Montag 30 März 2009 17:58:28 schrieb Larry Finger:

Oliver Neukum wrote:

quoted

Thanks for this report and the patch. I think, however that it introduces
unneeded locking. It seems to me that we should be fine if we fix
kaweth_start_xmit(). That code assumes that it is called with interrupts
off and under a spinlock. Is that incorrect?

You are correct in that only the locking in kaweth_start_xmit() needs to be
changed to lock out the other CPU's. In my testing under extreme conditions

Very good.

(X server over the network), the interface stalled with no logged messages.

Do you get something with sysrq-t ?

	Regards
		Oliver