Re: [PATCH] KVM: arm64: Count guest exit due to various reasons

[Christoffer Dall <christoffer.dall@linaro.org>]

On Mon, Oct 26, 2015 at 05:44:42PM +0530, Amit Tomer wrote:
> Thanks for the Review.
> 
> 
> > I think it would be even more useful to distinguish between mmio exits
> > handled in the kernel vs. those going to userspace.
> 
> Ok, I would work on it.
> 
> 
> > why more exit stats on arm64 than on arm?
> 
> Intention is to just add these stats only for ARM64 but I had to do it for arm,
> so that things don't break.

please keep both architectures up to date as much as possible for these
kinds of changes.

> 
> > why u32?  Would it not make sense to make these u64 or just unsigned
> > long?
> 
> Ok, You mean to say, for ARM we should use u32 and for ARM64 we should
> u64, right?

loss of context here, so I'm not sure.  Is there a reason why you
cannot/shouldn't use u64?  I'm just thinking that overflows could happen
fairly easy on u32, but otoh. there are some existing defines using u32
for some reason...

> 
> > either you should use one called wfx_exit_stat or you should distinguish
> > between wfi and wfe; this is just a weird way of doing it.
> 
> Sorry, didn't just get your point here :(
> 
wfx means "either a wfi or wfe happened", so you either define two
separate trace points, one for wfi and one for wfe, or you define a
single tracepoint for wfx.

I'll look forward to v2.

-Christoffer