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

Re: [PATCH v2] xen/arm: implement GICD_I[S/C]ACTIVER reads

On 03/04/2020 11:43, George Dunlap wrote:

On Apr 3, 2020, at 9:47 AM, Marc Zyngier <maz@xxxxxxxxxx> wrote:

On 2020-04-02 19:52, Julien Grall wrote:

Thanks for looping me in. Definitely an interesting read, but also a very
puzzling one.


No. Low latency is a very desirable thing, but it doesn't matter at all when
you don't even have functional correctness. To use my favourite car analogy,
having a bigger engine doesn't help when you're about to hit the wall and
have no breaks... You just hit the wall faster.


s/imprecise/massively incorrect/


There is just no way I'll ever accept a change to the GIC interrupt state
machine for Linux. Feel free to try and convince other OS maintainers.


If I was someone developing a product using Xen/ARM, I'd be very worried
about what you have written above. Because it really reads "we don't care
about reliability as long as we can show amazing numbers". I really hope
it isn't what you mean.

What's puzzling to me, is that what everyone else in this thread is that what 
Stefano is trying to do is to get Xen to be have like KVM.

This reads to me as "bugs don't exist".

As I actually said in a previous e-mail, our vGIC is significantly different compare to KVM. It *might* be possible they are not affected because the may trap when a guest is deactivating an interrupt *or* by other means.

I didn't look in the details their implementation, but this suggests you or Stefano may have. Why do you think Stefano's implementation is following what KVM does? If the behavior is the same, was the problem reported to KVM ML? What was the answer from the maintainers?

I suspect this was never discussed on KVM ML. So that should really be the first step.


Julien Grall



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