Virtualization - Feb 2017 - [PATCH 2/2] x86/vdso: Add VCLOCK_HVCLOCK vDSO clock read method

Since sequence count algorithm is done by hypervisor, better to not reuse
seqcount.
Still concerned that the code is racy.

-----Original Message-----
From: Thomas Gleixner [mailto:tglx at linutronix.de] 
Sent: Friday, February 10, 2017 4:28 AM
To: Vitaly Kuznetsov <vkuznets at redhat.com>
Cc: Stephen Hemminger <sthemmin at microsoft.com>; x86 at kernel.org; Andy
Lutomirski <luto at amacapital.net>; Ingo Molnar <mingo at
redhat.com>; H. Peter Anvin <hpa at zytor.com>; KY Srinivasan <kys
at microsoft.com>; Haiyang Zhang <haiyangz at microsoft.com>; Dexuan
Cui <decui at microsoft.com>; linux-kernel at vger.kernel.org; devel at
linuxdriverproject.org; virtualization at lists.linux-foundation.org
Subject: Re: [PATCH 2/2] x86/vdso: Add VCLOCK_HVCLOCK vDSO clock read method

On Fri, 10 Feb 2017, Vitaly Kuznetsov wrote:
> Stephen Hemminger <sthemmin at microsoft.com> writes:
> 
> > Why not use existing seqlock's?
> >
> 
> To be honest I don't quite understand how we could use it -- the 
> sequence locking here is done against the page updated by the 
> hypersior, we're not creating new structures (so I don't understand
> how we could use struct seqcount which we don't have) but I may be 
> misunderstanding something.
You can't use seqlock, but you might be able to use seqcount. Though I doubt
it given the 0 check ....

Thanks,

	tglx

On Fri, 10 Feb 2017, Stephen Hemminger wrote:
> Since sequence count algorithm is done by hypervisor, better to not reuse
seqcount.
> Still concerned that the code is racy.
That's a different question and can only be answered by the hypervisor
folks. Dunno, whether they have barrier requirements. The seqcount stuff
relies on:

do {
	seq = READ_ONCE(s->sequence);

	smp_rmb();

	sample_data();
  
	smp_rmb();
} while (s->sequence != seq);

which pairs with the writer side:

       s->sequence++;
       
       smp_wmb();

       update_data();

       smp_wmb();

       s->sequence++;

That's important if the stuff happens cross CPU. If the update happens on
the same CPU then this is a different story and as there are VMexits
involved they might provide the required ordering already. But I can't tell
as I have no idea how that host side thing is done.

Thanks,

	tglx

> From: Thomas Gleixner [mailto:tglx at linutronix.de]
> Sent: Saturday, February 11, 2017 02:02
>  ...
> That's important if the stuff happens cross CPU. If the update happens
on
> the same CPU then this is a different story and as there are VMexits
> involved they might provide the required ordering already. But I can't
tell
> as I have no idea how that host side thing is done.
> 
> 	tglx
IMO Hyper-V TSC page clocksource here seems pretty similar to KVM's pvclock,
So I would guess "the structure is only updated just before reentering the
guest
after some VM event" (https://rwmj.wordpress.com/2010/10/15/kvm-pvclock/),
that is, the update should happen on the same CPU, I guess.

Thanks,
-- Dexuan