Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Fri, 7 Aug 2020 11:02:32 +0200
From:   peterz@infradead.org
To:     "Jin, Yao" <yao.jin@linux.intel.com>
Cc:     mingo@redhat.com, oleg@redhat.com, acme@kernel.org,
        jolsa@kernel.org, Linux-kernel@vger.kernel.org, ak@linux.intel.com,
        kan.liang@intel.com, yao.jin@intel.com,
        alexander.shishkin@linux.intel.com, mark.rutland@arm.com
Subject: Re: [PATCH v1 2/2] perf/core: Fake regs for leaked kernel samples
Message-ID: <20200807090232.GE2674@hirez.programming.kicks-ass.net>
References: <20200731025617.16243-1-yao.jin@linux.intel.com>
 <20200731025617.16243-2-yao.jin@linux.intel.com>
 <20200804114900.GI2657@hirez.programming.kicks-ass.net>
 <4c958d61-11a7-9f3e-9e7d-d733270144a1@linux.intel.com>
 <20200805124454.GP2657@hirez.programming.kicks-ass.net>
 <797aa4de-c618-f340-ad7b-cef38c96b035@linux.intel.com>
 <20200806091827.GY2674@hirez.programming.kicks-ass.net>
 <20200806110046.GF35926@hirez.programming.kicks-ass.net>
 <1d03d443-b187-bc1f-2601-a54037a64eff@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1d03d443-b187-bc1f-2601-a54037a64eff@linux.intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, Aug 07, 2020 at 02:24:30PM +0800, Jin, Yao wrote:
> Hi Peter,
> 
> On 8/6/2020 7:00 PM, peterz@infradead.org wrote:
> > On Thu, Aug 06, 2020 at 11:18:27AM +0200, peterz@infradead.org wrote:
> > 
> > > Suppose we have nested virt:
> > > 
> > > 	L0-hv
> > > 	|
> > > 	G0/L1-hv
> > > 	   |
> > > 	   G1
> > > 
> > > And we're running in G0, then:
> > > 
> > >   - 'exclude_hv' would exclude L0 events
> > >   - 'exclude_host' would ... exclude L1-hv events?
> > >   - 'exclude_guest' would ... exclude G1 events?
> > 
> > So in arch/x86/events/intel/core.c we have:
> > 
> > static inline void intel_set_masks(struct perf_event *event, int idx)
> > {
> > 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
> > 
> > 	if (event->attr.exclude_host)
> > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
> > 	if (event->attr.exclude_guest)
> > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
> > 	if (event_is_checkpointed(event))
> > 		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
> > }
> > 
> 
> exclude_host is now set by guest (pmc_reprogram_counter,
> arch/x86/kvm/pmu.c). When enabling the event, we can check exclude_host to
> know if it's a guest.
> 
> Otherwise we may need more flags in event->attr to indicate the status.
> 
> > which is, afaict, just plain wrong. Should that not be something like:
> > 
> > 	if (!event->attr.exclude_host)
> > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
> > 	if (!event->attr.exclude_guest)
> > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
> > 
> > 
> 
> How can we know it's guest or host even if exclude_host is set in guest?

I'm not following you, consider:

	xh	xg	h	g	h'	g'
	0	0	0	0	1	1
	0	1	1	0	1	0
	1	0	0	1	0	1
	1	1	1	1	0	0


So the 0,0 and 1,1 cases get flipped. I have a suspicion, but this
_really_ should have fat comments all over :-(

What a sodding trainwreck..