[vfio-users] vfio corruption?

[Ivan Volosyuk]

A bit more detail.
I do VM restarts because I switch between Win8.1 and Win10 VMs a lot.
I was using this host machine configuration without hardware changes
for a few years without any problems. I do periodic software updates,
but nothing suspicious recently.

On Kernel 4.19.82 I was using the VM / restarting it multiple times a
day for 1 month. On Kernel 4.19.86 I've got this problem after a few
VM restarts. It worked without any issues before that. Than it kept
giving me this errors and I also had a lot of problems with my X
session on my host: shells not starting. Root session seemed to work
fine. After restarting the machine everything went back to normal.

Host hardware configuration:
00:00.0 Host bridge: Intel Corporation 4th Gen Core Processor DRAM
Controller (rev 06)
00:01.0 PCI bridge: Intel Corporation Xeon E3-1200 v3/4th Gen Core
Processor PCI Express x16 Controller (rev 06)
00:02.0 VGA compatible controller: Intel Corporation Xeon E3-1200
v3/4th Gen Core Processor Integrated Graphics Controller (rev 06)
00:03.0 Audio device: Intel Corporation Xeon E3-1200 v3/4th Gen Core
Processor HD Audio Controller (rev 06)
00:14.0 USB controller: Intel Corporation 9 Series Chipset Family USB
xHCI Controller
00:16.0 Communication controller: Intel Corporation 9 Series Chipset
Family ME Interface #1
00:1a.0 USB controller: Intel Corporation 9 Series Chipset Family USB
EHCI Controller #2
00:1b.0 Audio device: Intel Corporation 9 Series Chipset Family HD
Audio Controller
00:1c.0 PCI bridge: Intel Corporation 9 Series Chipset Family PCI
Express Root Port 1 (rev d0)
00:1c.2 PCI bridge: Intel Corporation 9 Series Chipset Family PCI
Express Root Port 3 (rev d0)
00:1c.3 PCI bridge: Intel Corporation 82801 PCI Bridge (rev d0)
00:1d.0 USB controller: Intel Corporation 9 Series Chipset Family USB
EHCI Controller #1
00:1f.0 ISA bridge: Intel Corporation Z97 Chipset LPC Controller
00:1f.2 SATA controller: Intel Corporation 9 Series Chipset Family
SATA Controller [AHCI Mode]
00:1f.3 SMBus: Intel Corporation 9 Series Chipset Family SMBus Controller
01:00.0 VGA compatible controller: NVIDIA Corporation TU102 [GeForce
RTX 2080 Ti Rev. A] (rev a1)
01:00.1 Audio device: NVIDIA Corporation TU102 High Definition Audio
Controller (rev a1)
01:00.2 USB controller: NVIDIA Corporation TU102 USB 3.1 Controller (rev a1)
01:00.3 Serial bus controller [0c80]: NVIDIA Corporation TU102 UCSI
Controller (rev a1)
03:00.0 Ethernet controller: Qualcomm Atheros Killer E220x Gigabit
Ethernet Controller (rev 13)
04:00.0 PCI bridge: ASMedia Technology Inc. ASM1083/1085 PCIe to PCI
Bridge (rev 03)

On Sat, Dec 14, 2019 at 10:08 PM Ivan Volosyuk <ivan.volosyuk at gmail.com> wrote:
>
> Kernel version: 4.19.86-gentoo
> Qemu: 4.0.0
> Command line:
> + /home/ivan/opt/bin/qemu-system-x86_64 -enable-kvm -m 8192 -mem-path
> /dev/qemu-mem -cpu host,kvm=off,hv_r
> elaxed,hv_spinlocks=0x1fff,hv_vapic,hv_time,hv-vendor-id=servo,hv-vpindex,hv-reset,hv-runtime,hv-crash,-hy
> pervisor -smp 4,sockets=1,cores=4,threads=1 -vcpu 0,affinity=4 -vcpu
> 1,affinity=5 -vcpu 2,affinity=6 -vcpu
> 3,affinity=7 -device virtio-net-pci,netdev=eth0,mac=DE:AD:BE:EF:CE:B9
> -netdev bridge,br=brkvm,id=eth0 -no
> graphic -monitor telnet:127.0.0.1:1234,server,nowait -usb -device
> usb-host,vendorid=0x0461,productid=0x4d1
> 5,bus=usb-bus.0 -usb -device
> usb-host,vendorid=0x0b38,productid=0x0010,bus=usb-bus.0 -vga none
> -device vfi
> o-pci,host=01:00.0,addr=6.0,multifunction=on -device
> vfio-pci,host=01:00.1,addr=6.1 -device vfio-pci,host=
> 01:00.2,addr=6.2 -soundhw ac97 -rtc base=utc,driftfix=slew -no-hpet
> -global kvm-pit.lost_tick_policy=disca
> rd -device ahci,id=ahci -device virtio-scsi-pci,id=scsi0 -drive
> file=/ssd/win81/win81f.raw,id=disk,if=none
> ,format=raw,cache=none,aio=threads,discard=unmap -device
> scsi-hd,bus=scsi0.0,drive=disk -drive file=/archi
> ve/system/qemu/games/games.raw,format=raw,id=games_disk,if=none,cache=none,aio=threads,discard=unmap
> -devi
> ce scsi-hd,drive=games_disk -drive
> file=/ssd/games_300/games_300.raw,format=raw,id=games_ssd_zfs_disk,if=n
> one,cache=none,aio=threads,discard=unmap -device
> scsi-hd,drive=games_ssd_zfs_disk -drive if=pflash,format=
> raw,readonly,file=/home/ivan/qemu/edk2-ovmf-git-20190219/OVMF_CODE.fd,format=raw
> -drive if=pflash,format=r
> aw,file=/home/ivan/qemu/win81.vars,format=raw
> ++ pidof pulseaudio
> + for pid in $(pidof pulseaudio)
> + gdb --pid 7740 --batch -x /home/vm-images/scripts/mlockall
> [New LWP 7827]
> [New LWP 7835]
> [New LWP 7836]
> [New LWP 7837]
>
> warning: .dynamic section for "/lib64/ld-linux-x86-64.so.2" is not at
> the expected address (wrong library
> or version mismatch?)
> qemu-system-x86_64: -device
> vfio-pci,host=01:00.0,addr=6.0,multifunction=on: VFIO_MAP_DMA: -14
> qemu-system-x86_64: -device
> vfio-pci,host=01:00.0,addr=6.0,multifunction=on:
> vfio_dma_map(0x556d1f02b3d0,
> 0x100000, 0xbff00000, 0x7f75fc0ff000) = -14 (Bad address)
> qemu-system-x86_64: -device
> vfio-pci,host=01:00.0,addr=6.0,multifunction=on: VFIO_MAP_DMA: -14
> qemu-system-x86_64: -device
> vfio-pci,host=01:00.0,addr=6.0,multifunction=on:
> vfio_dma_map(0x556d1f02b3d0,
> 0x100000000, 0x140000000, 0x7f76bbfff000) = -14 (Bad address)
> qemu-system-x86_64: -device
> vfio-pci,host=01:00.0,addr=6.0,multifunction=on: vfio 0000:01:00.0:
> failed to
> setup container for group 1: memory listener initialization failed for
> container: Bad address
>
> I wonder what's the errors mean? Is this some sort of kernel memory
> corruption, which causes this?