Re: [Xen-devel] [PATCH v4 0/3] VT-d Device-TLB flush issue

["Xu, Quan" <quan.xu@xxxxxxxxx>]

> On 25.12.2015 at 9:54am, <Tian, Kevin> wrote:
> > From: Xu, Quan
> > Sent: Wednesday, December 23, 2015 4:26 PM
> >
> > This patches are based on Kevin Tian's previous discussion 'Revisit
> > VT-d asynchronous flush issue'.
> > Fix current timeout concern and also allow limited ATS support in a light 
> > way:
> >
> > 1. Check VT-d Device-TLB flush error.
> >    This patch checks all kinds of error and all the way up the call
> > trees of VT-d Device-TLB flush.
> >
> > 2. Reduce spin timeout to 1ms, which can be boot-time changed with
> > 'iommu_qi_timeout_ms'.
> >    For example:
> >            multiboot /boot/xen.gz ats=1 iommu_qi_timeout_ms=100
> >
> > 3. Fix vt-d Device-TLB flush timeout issue.
> >     Now if IOTLB/Context/IETC flush is timeout, panic hypervisor. The
> coming patch
> >     set will fix it.
> 
> remove above sentence which is not related to this patch.
>

Agreed. I did NOT introduce these panics.


> >
> >     If Device-TLB flush is timeout, we'll hide the target ATS
> >     device and crash the domain owning this ATS device.
> >
> >     If impacted domain is hardware domain, just throw out a warning.
> >
> >     The hided Device will be disallowed to be further assigned to
> >     any domain.
> 
> hided -> hidden. Device -> device.
> 

Agreed. 


> >
> > --
> >
> >  * DMAR_OPERATION_TIMEOUT should be also chopped down to a low
> number
> > of milliseconds.
> >    As Kevin Tian mentioned in 'Revisit VT-d asynchronous flush issue',
> > We also confirmed with hardware team
> >    that 1ms is large enough for IOMMU internal flush. So I can change
> > DMAR_OPERATION_TIMEOUT from 1000 ms to 1 ms.
> >
> >    IOMMU_WAIT_OP() is only for VT-d registers read/write, and there is
> > also a panic. We need a further discussion
> >    whether or how to remove this panic in next patch set.
> >
> >  * if IOTLB/Context/IETC flush is timeout, panic hypervisor. The
> > coming patch set will fix it.
> 
> for all above, enough to say TODO tasks based on your summary earlier:
> 
>    - context/iotlb flush error. (need 2 ~ 3 weeks)
>    - iec flush error. (need 3 ~ 4 weeks)
> 
> as I commented in another thread, let's discuss them when you have new code
> ready.
> 

Thanks, I will speed up this process.

Merry Christmas!
-Quan


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