Re: [PATCH v6] kvm: better MWAIT emulation for guests

From: Jim Mattson <jmattson@google.com>
To: Alexander Graf <agraf@suse.de>
Cc: "kvm list" <kvm@vger.kernel.org>,
	"Radim Krčmář" <rkrcmar@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>,
	"Gabriel L. Somlo" <gsomlo@gmail.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Ingo Molnar" <mingo@redhat.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	"the arch/x86 maintainers" <x86@kernel.org>,
	"Joerg Roedel" <joro@8bytes.org>,
	linux-doc@vger.kernel.org, qemu-devel@nongnu.org
Subject: Re: [PATCH v6] kvm: better MWAIT emulation for guests
Date: Wed, 12 Apr 2017 08:20:21 -0700	[thread overview]
Message-ID: <CALMp9eRndxWDknB8ncmXB5DeK4KxO8Zcu+=4VVJNo6nqpA70Xw@mail.gmail.com> (raw)
In-Reply-To: <204f274d-697d-f9c6-8719-9bf91105f8b9@suse.de>

On Wed, Apr 12, 2017 at 7:54 AM, Alexander Graf <agraf@suse.de> wrote:
>
>
> On 12.04.17 16:34, Jim Mattson wrote:
>>
>> Actually, we have rejected commit 87c00572ba05aa8c ("kvm: x86: emulate
>> monitor and mwait instructions as nop"), so when we intercept
>> MONITOR/MWAIT, we synthesize #UD. Perhaps it is this difference from
>> vanilla kvm that motivates the following idea...
>
>
> So you're not running upstream kvm? In that case, you can just not take this
> patch either :).
This patch should be harmless. :-)
>
>> Since we're still not going to report MONITOR support in CPUID, the
>> only guests of consequence are paravirtual guests. What if a
>
>
> Only if someone actually implemented something for PV guests, yes.
>
> The real motivation is to allow user space to force set the MONITOR CPUID
> flag. That way an admin can - if he really wants to - dedicate pCPUs to the
> VM.
>
> I agree that we don't need the kvm pv flag for that. I'd be happy to drop
> that if everyone agrees.
>
>> paravirtual guest was aware of the fact that sometimes MONITOR/MWAIT
>> would work as architected, and sometimes they would raise #UD (or do
>> something else that's guest-visible, to indicate that the hypevisor is
>> intercepting the instructions). Such a guest could first try a
>> MONITOR/MWAIT-based idle loop and then fall back on a HLT-based idle
>> loop if the hypervisor rejected its use of MONITOR/MWAIT.
>
>
> How would that work? That guest would have to atomically notify all other
> vCPUs that wakeup notifications now go via IPIs instead of cache line
> dirtying.
>
> That's probably as much work to get right as it would be to just emulate
> MWAIT inside kvm ;).
True. I don't have an easy solution to that problem.
>
>> We already have the loose concept of "this pCPU has other things to
>> do," which is encoded in the variable-sized PLE window. With
>> MONITOR/MWAIT, the choice is binary, but a simple implementation could
>> tie the two together, by allowing the guest to use MONITOR/MWAIT
>> whenever the PLE window exceeds a certain threshold. Or the decision
>> could be left to the userspace agent.
>
>
> I agree, and that's basically the idea I mentioned earlier with MWAIT
> emulation. We could (for well behaved guests) switch between emulating MWAIT
> and running native MWAIT.
Yes, that would probably be the preferred solution.
>
>
>
> Alex