Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset()

From	Jim Mattson <jmattson@google.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset()
Date	2016-09-20 00:20 +0200
Message-ID	<sjf4S-2Yf-17@gated-at.bofh.it> (permalink)
References	<si2jn-5SZ-3@gated-at.bofh.it> <si2jp-5SZ-55@gated-at.bofh.it> <sj8PL-7bp-5@gated-at.bofh.it> <sj8PL-7bp-3@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Hmmm. Yes, I think it does. With this patch series,
vcpu->arch.tsc_offset appears to contain L1's TSC offset (perhaps
making vmx->nested.vmcs01_tsc_offset redundant).

However, this unfortunately limits the newly added functionality to
merging host and *L1* guest traces. It doesn't work with L2 (or
deeper) guests. Or perhaps I'm missing something?

On Mon, Sep 19, 2016 at 8:34 AM, Paolo Bonzini <pbonzini@redhat.com> wrote:
>
>
> On 19/09/2016 17:30, Jim Mattson wrote:
>> vmx_read_tsc_offset has a bug when running nested VMs.  It should really be:
>>
>>        if (is_guest_mode(vcpu))
>>                return to_vmx(vcpu)->nested.vmcs01_tsc_offset;
>>        else
>>                return vmcs_read64(TSC_OFFSET);
>>
>> Perhaps a better name woulf be "vmx_get_l1_tsc_offset."
>
> I agree, but doesn't this patch fix the bug too?
>
> Paolo
>
>> In any case, this does not seem consistent with vcpu->arch.tsc_offset.
>

Thread

[PATCH v2 0/6] kvm: x86: export TSC information to user-space Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 16:30 +0200
  [PATCH 1/6] kvm: x86: add tsc_offset field to struct kvm_vcpu_arch Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 16:30 +0200
  [PATCH 3/6] kvm: kvm_destroy_vm_debugfs(): check debugfs_stat_data pointer Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 16:30 +0200
  [PATCH 4/6] kvm: add stubs for arch specific debugfs support Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 16:30 +0200
  [PATCH 2/6] kvm: x86: drop read_tsc_offset() Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 16:30 +0200
    Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Paolo Bonzini <pbonzini@redhat.com> - 2016-09-19 17:40 +0200
      Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Jim Mattson <jmattson@google.com> - 2016-09-20 00:20 +0200
        Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Paolo Bonzini <pbonzini@redhat.com> - 2016-09-20 07:40 +0200
          Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Paolo Bonzini <pbonzini@redhat.com> - 2016-09-21 17:30 +0200
            Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Jim Mattson <jmattson@google.com> - 2016-09-21 17:40 +0200
          Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Jim Mattson <jmattson@google.com> - 2016-09-21 17:30 +0200
    Re: [PATCH 2/6] kvm: x86: drop read_tsc_offset() Jim Mattson <jmattson@google.com> - 2016-09-19 17:40 +0200
  Re: [PATCH v2 0/6] kvm: x86: export TSC information to user-space Paolo Bonzini <pbonzini@redhat.com> - 2016-09-16 17:00 +0200
    Re: [PATCH v2 0/6] kvm: x86: export TSC information to user-space Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 17:00 +0200
      Re: [PATCH v2 0/6] kvm: x86: export TSC information to user-space Paolo Bonzini <pbonzini@redhat.com> - 2016-09-16 17:10 +0200
        Re: [PATCH v2 0/6] kvm: x86: export TSC information to user-space Luiz Capitulino <lcapitulino@redhat.com> - 2016-09-16 17:20 +0200

csiph-web