[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH] IOMMU: don't disable bus mastering on faults for devices used by Xen or Dom0



At 15:29 +0100 on 06 Nov (1352215760), Dario Faggioli wrote:
> On Tue, 2012-11-06 at 14:17 +0000, Jan Beulich wrote:
> > > Indeed.  (Intel) IOMMU interrupts are suppressed until the softirq
> > > handler acknowledges the error, but if the softirq handler doesn't
> > > disable the device, it will take another IOMMU interrupt immediately.
> > > I thought the AMD side behaved eth same but clearly not -- I'll try to
> > > take a look at that later in the week.
> > 
> > I don't think AMD's behaves much different, it's just that for the
> > PPR case nothing is being done in that regard (and it's unclear
> > whether or under what circumstances a high rate of these could
> > occur).
> > 
> Indeed. I just double checked the code and yes, both faults and PPRs are
> handled that way, and new interrupts are disabled until the tasklet
> handles the request and re-enables them.
> 
> The difference, as Jan is saying, is there is no PPR equivalent of
> disabling bus mastering that can ensure livelock safeness when it comes
> to them.

Right, I see.  We could always disable the card entirely. 

Tim.


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.