[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87k18mfj0v.fsf@ashishki-desk.ger.corp.intel.com>
Date: Wed, 30 Oct 2019 15:41:04 +0200
From: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>,
"Kang\, Luwei" <luwei.kang@...el.com>
Cc: "kvm\@vger.kernel.org" <kvm@...r.kernel.org>,
"linux-kernel\@vger.kernel.org" <linux-kernel@...r.kernel.org>,
"pbonzini\@redhat.com" <pbonzini@...hat.com>,
"rkrcmar\@redhat.com" <rkrcmar@...hat.com>,
"Christopherson\, Sean J" <sean.j.christopherson@...el.com>,
"vkuznets\@redhat.com" <vkuznets@...hat.com>,
"wanpengli\@tencent.com" <wanpengli@...cent.com>,
"jmattson\@google.com" <jmattson@...gle.com>,
"joro\@8bytes.org" <joro@...tes.org>,
"tglx\@linutronix.de" <tglx@...utronix.de>,
"mingo\@redhat.com" <mingo@...hat.com>,
"bp\@alien8.de" <bp@...en8.de>, "hpa\@zytor.com" <hpa@...or.com>,
"x86\@kernel.org" <x86@...nel.org>,
"ak\@linux.intel.com" <ak@...ux.intel.com>,
"thomas.lendacky\@amd.com" <thomas.lendacky@....com>,
"acme\@kernel.org" <acme@...nel.org>,
"mark.rutland\@arm.com" <mark.rutland@....com>,
"jolsa\@redhat.com" <jolsa@...hat.com>,
"namhyung\@kernel.org" <namhyung@...nel.org>,
alexander.shishkin@...ux.intel.com
Subject: Re: [PATCH v1 3/8] KVM: x86: Allocate performance counter for PEBS event
Peter Zijlstra <peterz@...radead.org> writes:
> On Wed, Oct 30, 2019 at 04:06:36AM +0000, Kang, Luwei wrote:
>> > > static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
>> > > unsigned config, bool exclude_user,
>> > > bool exclude_kernel, bool intr,
>> > > - bool in_tx, bool in_tx_cp)
>> > > + bool in_tx, bool in_tx_cp, bool pebs)
>> > > {
>> > > struct perf_event *event;
>> > > struct perf_event_attr attr = {
>> > > @@ -111,9 +111,12 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
>> > > .exclude_user = exclude_user,
>> > > .exclude_kernel = exclude_kernel,
>> > > .config = config,
>> > > + .precise_ip = pebs ? 1 : 0,
>> > > + .aux_output = pebs ? 1 : 0,
>> >
>> > srsly?
>>
>> Hi Peter,
>> Thanks for review. For aux_output, I think it should be set 1 when the guest wants to enabled PEBS by Intel PT.
>> For precise_ip, it is the precise level in perf and set by perf command line in KVM guest, this may not reflect the accurate value (can be 0~3) here. Here set to 1 is used to allocate a counter for PEBS event and set the MSR_IA32_PEBS_ENABLE register. For PMU virtualization, KVM will trap the guest's write operation to PMU registers and allocate/free event counter from host if a counter enable/disable in guest. We can't always deduce the exact parameter of perf command line from the value of the guest writers to the register.
>
> Please, teach your MUA to wrap on 78 chars.
>
> The thing I really fell over is the gratuitous 'bool ? 1 : 0'. But yes,
Notice the .exclude_kernel assignment above that does the same thing the
other way around.
Regards,
--
Alex
Powered by blists - more mailing lists