RE: [RFC PATCH 0/2] KVM: VMX: Fix VM entry failure on PT_MODE_HOST_GUEST while host is using PT

From: "Wang, Wei W" <wei.w.wang@intel.com>
To: "Liang, Kan" <kan.liang@linux.intel.com>,
	"Li, Xiaoyao" <xiaoyao.li@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	"Arnaldo Carvalho de Melo" <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	"Christopherson,, Sean" <seanjc@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	"Liang, Kan" <kan.liang@intel.com>,
	"Kleen, Andi" <andi.kleen@intel.com>
Cc: "linux-perf-users@vger.kernel.org"
	<linux-perf-users@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>
Subject: RE: [RFC PATCH 0/2] KVM: VMX: Fix VM entry failure on PT_MODE_HOST_GUEST while host is using PT
Date: Thu, 15 Sep 2022 14:39:36 +0000	[thread overview]
Message-ID: <CY5PR11MB636535BE57F8CC07B1B2770DDC499@CY5PR11MB6365.namprd11.prod.outlook.com> (raw)
In-Reply-To: <ef391316-cde5-3cda-ff0d-980e8ecc9aef@linux.intel.com>

On Thursday, September 15, 2022 9:55 PM Liang, Kan wrote:
> On 2022-09-14 10:46 p.m., Wang, Wei W wrote:
> > On Thursday, September 15, 2022 4:26 AM, Liang, Kan wrote:
> >> The perf_event_disable() eventually invokes the intel_pt_stop().
> >> We already expose the intel_pt_stop()/cpu_emergency_stop_pt() to
> >> other modules. I don't think we have to use the perf_event_disable().
> >> Also, the
> >> perf_event_disable() requires extra codes.
> >>
> >> I went through the discussions. I agree with Sean's suggestion.
> >> We should only put the logic in the KVM but all the MSR access
> >> details into the PT driver.
> >
> > Even the driver itself doesn’t drive the save/restore of the MSRs, it is drived
> by perf.
> 
> It through perf_event, not driven by perf_event. The perf_event generic code
> never knows when should invokes each driver to save/restore information. It
> should be driven by the other subsystem e.g., scheduler.

Yes. The cpu scheduler does this via the perf subsystem, though.

> 
> For this case, KVM should drive the save/restore, and the PT driver eventually
> does all the MSR access details.
> 
> > 1. If we make KVM a user of perf, we should do this via
> perf_event_disable/enable_*.
> > 2. If we make KVM an alternative to perf (i.e. have direct control
> > over PMU HW), we can do this via driver interfaces like perf.
> > Per my experience, we should go for 1. Probably need Peter's opinions on
> this.
> >
> 
> For 1, the perf_event_disable/enable_* are not enough. They don't
> save/restore MSRs. 

perf_event_disable will go through perf to call pt_event_stop which saves the related MSRs, right?
(if so, what large changes did you mean?)

> If we go to this way, we have to introduce a new generic
> interface to ask each driver to save/restore their MSRs when the guest is
> entering/exiting. We'd better combine the new interface with the existing
> perf_guest_get_msrs() of the core driver.
> I think that's an ideal solution, but requires big changes in the code.
> 
> 2 is the current KVM implementation. See pt_save_msr()/pt_load_msr(). I don't
> think it's a right way. We'd better fix it.
> 
> The suggestion should be 3. The KVM notify the PT driver via the interface
> provided by PT. The PT driver save/restore all the registers.
> I think it's an acceptable solution with small code changes.

This looks like we just relocate the save/restore functions to the PT driver and KVM still directly call them - still not going through perf's management. Imagine every user operates on the pmu h/w directly like this, things would be a mess.

Thanks,
Wei