[lkml]   [2018]   [Feb]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [9/8] KVM: x86: limit MSR_IA32_SPEC_CTRL access based on CPUID availability

* Paolo Bonzini <> wrote:

> On 30/01/2018 12:45, Thomas Gleixner wrote:
> > On Tue, 30 Jan 2018, David Woodhouse wrote:
> >
> >> On Tue, 2018-01-30 at 08:57 -0800, Jim Mattson wrote:
> >>> It's really hard to tell which patches are being proposed for which
> >>> repositories, but assuming that everything else is correct, I don't
> >>> think your condition is adequate. What if the physical CPU and the
> >>> virtual CPU both have CPUID.(EAX=7H,ECX=0):EDX[26], but only the
> >>> physical CPU has CPUID.(EAX=7H,ECX=0):EDX[27]? If the guest has write
> >>> access to MSR_IA32_SPEC_CTRL, it can set MSR_IA32_SPEC_CTRL[1]
> >>> (STIBP), even though setting that bit in the guest should raise #GP.
> >>
> >> Everything we're talking about here is for tip/x86/pti. Which I note
> >> has just updated to be 4.15-based, although I thought it was going to
> >> stay on 4.14 for now. So I've updated my tree at
> >>
> >> accordingly.
> >
> > Yes, we tried to stay on 4.14 base but this started to created nasty merge
> > conflicts for no value. Merging in v4.15 turned out to resolve those issues
> > while still serving as the feed branch for Gregs stable work. For the time
> > being we try to make stable backporting at least for 4.14/15 as painless as
> > possible.
> Great, then the "per-VCPU MSR bitmaps" branch
> (git:// refs/heads/msr-bitmaps)
> that I created last weekend can be pulled directly in tip/x86/pti.

Can this branch still be rebased, to fix the SoB chain of:

de3a0021a606 ("KVM: nVMX: Eliminate vmcs02 pool")


I'm not sure what workflow resulted in this commit, but it is missing your SoB:

commit de3a0021a60635de96aa92713c1a31a96747d72c
Author: Jim Mattson <>
AuthorDate: Mon Nov 27 17:22:25 2017 -0600
Commit: Paolo Bonzini <>
CommitDate: Sat Jan 27 09:43:03 2018 +0100

KVM: nVMX: Eliminate vmcs02 pool

The potential performance advantages of a vmcs02 pool have never been
realized. To simplify the code, eliminate the pool. Instead, a single
vmcs02 is allocated per VCPU when the VCPU enters VMX operation.

Cc: # prereq for Spectre mitigation
Signed-off-by: Jim Mattson <>
Signed-off-by: Mark Kanda <>
Reviewed-by: Ameya More <>
Reviewed-by: David Hildenbrand <>
Reviewed-by: Paolo Bonzini <>
Signed-off-by: Radim Krčmář <>

You probably rebased Radim'm tree?

If this tree can still be rebased I'd like to re-pull it into tip:x86/pti, as
those bits are not yet upstream.



 \ /
  Last update: 2018-02-05 12:12    [W:0.094 / U:20.636 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site