From: David Ahern <dsahern@gmail.com>
To: Gleb Natapov <gleb@redhat.com>
Cc: kvm@vger.kernel.org, avi@redhat.com, mtosatti@redhat.com,
linux-kernel@redhat.com, mingo@elte.hu, a.p.zijlstra@chello.nl,
acme@ghostprotocols.net
Subject: Re: [PATCH 7/9] KVM: Expose the architectural performance monitoring CPUID leaf
Date: Tue, 01 Nov 2011 10:24:41 -0600 [thread overview]
Message-ID: <4EB01D49.6010309@gmail.com> (raw)
In-Reply-To: <20111101161815.GB16539@redhat.com>
On 11/01/2011 10:18 AM, Gleb Natapov wrote:
> On Tue, Nov 01, 2011 at 09:49:27AM -0600, David Ahern wrote:
>> On 10/30/2011 10:53 AM, Gleb Natapov wrote:
>>> From: Avi Kivity <avi@redhat.com>
>>>
>>> Provide a CPUID leaf that describes the emulated PMU.
>>>
>>> Signed-off-by: Avi Kivity <avi@redhat.com>
>>> Signed-off-by: Gleb Natapov <gleb@redhat.com>
>>> ---
>>> arch/x86/kvm/x86.c | 23 ++++++++++++++++++++++-
>>> 1 files changed, 22 insertions(+), 1 deletions(-)
>>>
>>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>>> index 5ea4cb8..56153a9 100644
>>> --- a/arch/x86/kvm/x86.c
>>> +++ b/arch/x86/kvm/x86.c
>>> @@ -2543,6 +2543,28 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
>>> }
>>> case 9:
>>> break;
>>> + case 0xa: { /* Architectural Performance Monitoring */
>>> + struct x86_pmu_capability cap;
>>> +
>>> + perf_get_x86_pmu_capability(&cap);
>>> +
>>> + /*
>>> + * Only support guest architectural pmu on a host
>>> + * with architectural pmu.
>>> + */
>>> + if (!cap.version)
>>> + memset(&cap, 0, sizeof(cap));
>>> +
>>> + entry->eax = min(cap.version, 2)
>>> + | (cap.num_counters_gp << 8)
>>> + | (cap.bit_width_gp << 16)
>>> + | (cap.events_mask_len << 24);
>>> + entry->ebx = cap.events_mask;
>>> + entry->ecx = 0;
>>> + entry->edx = cap.num_counters_fixed
>>> + | (cap.bit_width_fixed << 5);
>>> + break;
>>> + }
>>
>> If PERF_EVENTS is disabled in the host kernel will KVM return the right
>> thing for the guest that might have PERF_EVENTS enabled?
>>
> With correct implementation of perf_get_x86_pmu_capability() it should.
> PERF_EVENTS disable version should set cap.version to zero, so guest will
> find that vcpu does not provide architectural PMU.
Ok.
I was also thinking about kvm-kmod where newer KVM source is compiled
against older kernels - which at one point had PERF_EVENTS as a
configurable parameter. In this case it is possible to have perf events
disabled host side yet enabled guest side.
David
next prev parent reply other threads:[~2011-11-01 16:24 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-10-30 16:53 [PATCH 0/9] KVM in-guest performance monitoring Gleb Natapov
2011-10-30 16:53 ` [PATCH 1/9] KVM: Expose kvm_lapic_local_deliver() Gleb Natapov
2011-10-30 16:53 ` [PATCH 2/9] KVM: Expose a version 2 architectural PMU to a guests Gleb Natapov
2011-11-01 10:47 ` Avi Kivity
2011-11-01 12:30 ` Gleb Natapov
2011-11-01 13:57 ` Gleb Natapov
2011-11-02 9:54 ` Avi Kivity
2011-11-02 9:56 ` Gleb Natapov
2011-11-02 10:01 ` Avi Kivity
2011-11-02 11:09 ` Gleb Natapov
2011-11-02 12:03 ` Gleb Natapov
2011-11-03 8:31 ` Gleb Natapov
2011-12-15 12:04 ` [PATCH] KVM: x86: Fix build breakage due to anonymous field initialization Jan Kiszka
2011-12-15 12:08 ` Peter Zijlstra
2011-12-15 12:16 ` Jan Kiszka
2011-12-26 12:38 ` Avi Kivity
2011-10-30 16:53 ` [PATCH 3/9] KVM: Add generic RDPMC support Gleb Natapov
2011-10-30 16:53 ` [PATCH 4/9] KVM: SVM: Intercept RDPMC Gleb Natapov
2011-10-30 16:53 ` [PATCH 5/9] KVM: VMX: " Gleb Natapov
2011-10-30 16:53 ` [PATCH 6/9] perf: expose perf capability to other modules Gleb Natapov
2011-11-01 10:49 ` Avi Kivity
2011-11-01 15:49 ` David Ahern
2011-11-01 16:13 ` Gleb Natapov
2011-11-01 16:20 ` David Ahern
2011-11-01 16:41 ` Gleb Natapov
2011-11-02 7:42 ` Frederic Weisbecker
2011-11-07 14:45 ` Will Deacon
2011-11-10 8:58 ` Frederic Weisbecker
2011-11-10 12:12 ` Jason Wessel
2011-11-15 18:34 ` Frederic Weisbecker
2011-10-30 16:53 ` [PATCH 7/9] KVM: Expose the architectural performance monitoring CPUID leaf Gleb Natapov
2011-11-01 10:51 ` Avi Kivity
2011-11-01 11:25 ` Gleb Natapov
2011-11-01 15:49 ` David Ahern
2011-11-01 16:18 ` Gleb Natapov
2011-11-01 16:24 ` David Ahern [this message]
2011-11-01 16:40 ` Gleb Natapov
2011-11-01 17:43 ` David Ahern
2011-11-02 11:18 ` Gleb Natapov
2011-10-30 16:53 ` [PATCH 8/9] KVM: x86 emulator: fix RDPMC privilege check Gleb Natapov
2011-10-30 16:53 ` [PATCH 9/9] KVM: x86 emulator: implement RDPMC (0F 33) Gleb Natapov
2011-10-30 16:57 ` [PATCH 0/9] KVM in-guest performance monitoring Gleb Natapov
-- strict thread matches above, loose matches on Subject: below --
2011-11-03 12:31 Gleb Natapov
2011-11-03 12:31 ` [PATCH 7/9] KVM: Expose the architectural performance monitoring CPUID leaf Gleb Natapov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4EB01D49.6010309@gmail.com \
--to=dsahern@gmail.com \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@ghostprotocols.net \
--cc=avi@redhat.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@redhat.com \
--cc=mingo@elte.hu \
--cc=mtosatti@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).