Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1350223

Re: [PATCH] KVM: x86: disable PEBS before a guest entry

From Radim Krčmář <rkrcmar@redhat.com>
Newsgroups linux.kernel
Subject Re: [PATCH] KVM: x86: disable PEBS before a guest entry
Date 2016-03-04 14:30 +0100
Message-ID <r8XXQ-7oV-5@gated-at.bofh.it> (permalink)
References <r8GDE-2P0-21@gated-at.bofh.it> <r8J8u-4LK-19@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


2016-03-03 13:32-0800, David Matlack:
> On Thu, Mar 3, 2016 at 10:53 AM, Radim Krčmář <rkrcmar@redhat.com> wrote:
>> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
>> @@ -1767,6 +1767,13 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
>>                         return;
>>                 }
>>                 break;
>> +       case MSR_IA32_PEBS_ENABLE:
>> +               /* PEBS needs a quiescent period after being disabled (to write
>> +                * a record).  Disabling PEBS through VMX MSR swapping doesn't
>> +                * provide that period, so a CPU could write host's record into
>> +                * guest's memory.
>> +                */
>> +               wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
> 
> Should this go in add_atomic_switch_msr instead of clear_atomic_switch_msr?

Yes, it could be cleared in both (in case guest PEBS can be non-zero),
but I wanted to have it only in add_atomic_switch_msr().

Thank you!

v2 underway.

(In case it makes you wonder how it was tested:
 I have a bad habit of trying whether a patch can be improved before
 posting and this one went awry, because I already returned the machine
 with reproducer and the change seemed simple enough.)

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread


Thread

[PATCH] KVM: x86: disable PEBS before a guest entry Radim Krčmář <rkrcmar@redhat.com> - 2016-03-03 20:00 +0100
  Re: [PATCH] KVM: x86: disable PEBS before a guest entry David Matlack <dmatlack@google.com> - 2016-03-03 22:40 +0100
    Re: [PATCH] KVM: x86: disable PEBS before a guest entry Radim Krčmář <rkrcmar@redhat.com> - 2016-03-04 14:30 +0100

csiph-web