[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH 3/4 V3] X86: MPX IA32_BNDCFGS msr handle

>>> On 27.11.13 at 14:50, "Liu, Jinsong" <jinsong.liu@xxxxxxxxx> wrote:
> From 291adaf4ad6174c5641a7239c1801373e92e9975 Mon Sep 17 00:00:00 2001
> From: Liu Jinsong <jinsong.liu@xxxxxxxxx>
> Date: Thu, 28 Nov 2013 05:26:06 +0800
> Subject: [PATCH 3/4 V3] X86: MPX IA32_BNDCFGS msr handle
> When MPX supported, a new guest-state field for IA32_BNDCFGS
> is added to the VMCS. In addition, two new controls are added:
>  - a VM-exit control called "clear BNDCFGS"
>  - a VM-entry control called "load BNDCFGS."
> VM exits always save IA32_BNDCFGS into BNDCFGS field of VMCS.
> Signed-off-by: Xudong Hao <xudong.hao@xxxxxxxxx>
> Reviewed-by: Liu Jinsong <jinsong.liu@xxxxxxxxx>
> Unlikely, but in case VMX support is not available, not expose
> MPX to hvm guest.

Good. But this, thinking about it once more, still doesn't eliminate
the need to handle save/restore of the MSR - the VMCS itself
isn't part of the data that's being migrated, and hence the MSR
value needs to be pulled out of it just like vmx_save_vmcs_ctxt()
does for various other MSRs.

This, btw., would seem to also be missing for at least
MSR_CORE_PERF_GLOBAL_CTRL in case vPMU is enabled.


Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.