Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0 is loaded

From	Paolo Bonzini <pbonzini@redhat.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0 is loaded
Date	2016-03-14 14:20 +0100
Message-ID	<rcAzD-4e2-9@gated-at.bofh.it> (permalink)
References	<rbCat-3jh-1@gated-at.bofh.it> <rbCau-3jh-3@gated-at.bofh.it> <rbCDw-3NU-23@gated-at.bofh.it> <rbCWR-3YT-1@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On 11/03/2016 22:33, David Matlack wrote:
> > Is this better than just always keeping the host's XCR0 loaded outside
> > if the KVM interrupts-disabled region?
> 
> Probably not. AFAICT KVM does not rely on it being loaded outside that
> region. xsetbv isn't insanely expensive, is it? Maybe to minimize the
> time spent with interrupts disabled it was put outside.
> 
> I do like that your solution would be contained to KVM.

I agree with Andy.  We do want a fix for recent kernels because of the
!eager_fpu case that Guangrong mentioned.

Paolo

ps: while Andy is planning to kill lazy FPU, I want to benchmark it with
KVM...  Remember that with a single pre-xsave host in your cluster, your
virt management might happily default your VMs to a Westmere or Nehalem
CPU model.  GCC might be a pretty good testbench for this (e.g. a kernel
compile with very high make -j), because outside of the lexer (which
plays SIMD games) it never uses the FPU.

Thread

[PATCH 0/1] KVM: x86: using the fpu in interrupt context with a guest's xcr0 David Matlack <dmatlack@google.com> - 2016-03-11 21:50 +0100
  [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0 is loaded David Matlack <dmatlack@google.com> - 2016-03-11 21:50 +0100
    Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded Andy Lutomirski <luto@amacapital.net> - 2016-03-11 22:20 +0100
      Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded David Matlack <dmatlack@google.com> - 2016-03-11 22:40 +0100
        Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded Paolo Bonzini <pbonzini@redhat.com> - 2016-03-14 14:20 +0100
          Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded Andy Lutomirski <luto@amacapital.net> - 2016-03-15 19:30 +0100
            Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded Paolo Bonzini <pbonzini@redhat.com> - 2016-03-15 20:40 +0100
              Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2016-03-16 05:00 +0100
                Re: [PATCH 1/1] KVM: don't allow irq_fpu_usable when the VCPU's XCR0  is loaded Paolo Bonzini <pbonzini@redhat.com> - 2016-03-16 13:10 +0100
  Re: [PATCH 0/1] KVM: x86: using the fpu in interrupt context with a  guest's xcr0 Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2016-03-14 08:50 +0100
    Re: [PATCH 0/1] KVM: x86: using the fpu in interrupt context with a  guest's xcr0 David Matlack <dmatlack@google.com> - 2016-03-15 20:10 +0100
      Re: [PATCH 0/1] KVM: x86: using the fpu in interrupt context with a  guest's xcr0 Xiao Guangrong <guangrong.xiao@linux.intel.com> - 2016-03-16 04:50 +0100
        Re: [PATCH 0/1] KVM: x86: using the fpu in interrupt context with a  guest's xcr0 Andy Lutomirski <luto@amacapital.net> - 2016-03-16 04:50 +0100
          Re: [PATCH 0/1] KVM: x86: using the fpu in interrupt context with a  guest's xcr0 David Matlack <dmatlack@google.com> - 2016-03-16 18:20 +0100
        Re: [PATCH 0/1] KVM: x86: using the fpu in interrupt context with a  guest's xcr0 David Matlack <dmatlack@google.com> - 2016-03-16 18:10 +0100

csiph-web