wrmsr to register 0x49(0x1) on vcpu x

[edenist]

Hi Frank,

While the changelog from Asus is rather lean, I would wager it has to do
with spectre mitigations introduced by AMD.
Last month they announced that they had prepared a microcode update to
address variant 2, and had handed the microcode to motherboard vendors
to supply as a BIOS update.

Most of my systems are AMD, though I've yet to see this microcode update
personally yet due to lazy vendors. That said, it appears they have
followed intel and introduced an IBRS feature.

https://developer.amd.com/wp-content/resources/Architecture_Guidelines_Update_Indirect_Branch_Control.pdf

According to that document, sure enough msr 49 is for IBPB.

If you check your CPU features in your kernel logs, if the CPU has the
IBRS feature, both IBPB and STIBP will appear under Structured Extended
Features.
On an intel system I have with updated microcode, it shows the following:
Structured Extended Features3=0xc000000<IBPB,STIBP>

I'd then check the hw.ibrs_active sysctl to see if it is in use. If so,
it can be disabled with hw.ibrs_disable.

Someone more knowledgeable on the inner workings of bhyve can likely
give more info on the error itself, but I'm unsure if these features
have even been exposed to guests yet.

Josh


On 08/05/18 15:18, Frank Ebert wrote:
> Hi,
> 
> since the last bios-update (AMD Ryzen Threadripper 1950X on Asus ROG
> STRIX x399-E) I get the following message when starting a Windows 10
> Guest on FreeBSD 11.1/amd64: 
> 
> wrmsr to register 0x49(0x1) on vcpu x
> wrmsr to register 0x49(0x1) on vcpu x
> wrmsr to register 0x49(0x1) on vcpu x
> wrmsr to register 0x49(0x1) on vcpu x
> 
> The message will be repeated endless (x is the number of the vcpu).
> 
> Despite this message, the guest is running fine. I don't have any
> performance issues at the moment. Prior to this bios-update the message
> appears only once (or twice?) for every vcpu.
> 
> Attached you find the way I start bhyve:
> 
> bhyve -c8 -m 16G -H -w \
> -s 0,amd_hostbridge \
> -s 3,ahci-cd,/home/frank/bhyve/null_dvd.iso \
> -s 4,ahci-hd,/dev/zvol/zroot/win10disk0 \
> -s 10,virtio-net,tap0 \
> -s11,fbuf,tcp=0.0.0.0:5900,w=1600,h=900 \
> -s 30,xhci,tablet \
> -s31,lpc \
> -lbootrom,/usr/local/share/uefi-firmware/BHYVE_UEFI.fd win10
> 
> I use "hw.vmm.topology.cores_per_package=4" in /boot/loader.conf and a
> "custom" vmm.ko (https://reviews.freebsd.org/D13780) since January.
> 
> When starting bhyve without "-w", the guest freezes while booting. But
> I think this has to do with another issue
> https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=219343
> 
> The changelog from Asus says:
> 
> Update AGESA 1.0.0.5
> recommend to keep C-state [enable]
> 
> Does anyone have an idea how to solve this issue?
> 
> Thanx Frank
>