svn commit: r278473 - in head/sys: amd64/amd64 amd64/include amd64/vmm contrib/dev/acpica/include i386/i386 i386/include x86/acpica x86/include x86/x86 x86/xen

[Bryan Venteicher]

On Wed, Feb 11, 2015 at 9:20 AM, John Baldwin <jhb at freebsd.org> wrote:

> On Wednesday, February 11, 2015 10:32:00 AM Konstantin Belousov wrote:
> > On Wed, Feb 11, 2015 at 12:43:39AM +0000, Rui Paulo wrote:
> > > On Feb 09, 2015, at 01:01 PM, Konstantin Belousov <kib at FreeBSD.org>
> wrote:
> > >
> > > Author: kib
> > > Date: Mon Feb 9 21:00:56 2015
> > > New Revision: 278473
> > > URL: https://svnweb.freebsd.org/changeset/base/278473
> > >
> > > Log:
> > > Add x2APIC support. Enable it by default if CPU is capable. The
> > > hw.x2apic_enable tunable allows disabling it from the loader prompt.
> > >
> > > This breaks VMware Fusion when the host CPU has x2APIC support.  In
> > > my case, mpt(4) was unable to receive interrupts and USB was similarly
> > > broken.  It's possible that this is a VMware bug, but you might want to
> > > avoid turning this on when running under the VMware hypervisor.
> >
> > Neel pointed this out to me when the patch was reviewed.
> > He told me that x2APIC does not work in Fusion 5.x, while it seems
> > to be fixed in 7.x.
> > https://communities.vmware.com/message/2173695?tstart=0
> >
> > Upon further discussion with Neel and Peter, it was suggested that we
> > enable enable x2APIC unconditionally, which seems what is done for
> > Linux benchmarks.
> >
> > Is vmware 5.x is used while there is already at least version 7.x ?
> > I have no idea about vmware product nomenclature and lifecycle.
>
> I believe we can ask vmware what version it is when we notice we are
> running
> under it (which we already detect for TSC purposes).  We could quirk for
> that
> case, or even just disable for VM_GUEST_VMWARE for now.
>
>

I'm not too familiar with this stuff, but is this Linux commit [1]
relevant? If so, it might be something nice to wrap into my
projects/paravirt branch (I've been extremely busy recently, but I hope to
get the review comments addressed and merge it into HEAD soon).

[1] - https://lkml.org/lkml/2013/1/17/552

--
> John Baldwin
>
>