AMD eGPU and Passthrough in Ubuntu 18.04

Hi all, I’m trying to get an R9 390x in an Akitio Node working with Ubuntu 18.04 and a Thinkpad T470 but I’m pretty new to this stuff. At first I tested it by booting into Windows 10, where everything worked fine. Trying Ubuntu, the card showed up under lspci but didn’t seem to work. I tried passing it through to a VirtualBox Windows 10 VM, where it showed up under Device Manager but with a “This device cannot start. (Code 10)” error. Poking around a little bit more, Here’s the output from a couple of commands in Ubuntu (without running the VM) which seem useful:

Relevant section of sudo lspci -v

0a:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Hawaii XT / Grenada XT [Radeon R9 290X/390X] (rev 80) (prog-if 00 [VGA controller])
    Subsystem: PC Partner Limited / Sapphire Technology Grenada XT2 [Radeon R9 390X]
    Flags: fast devsel, IRQ 18
    Memory at b0000000 (64-bit, prefetchable) [size=256M]
    Memory at c0000000 (64-bit, prefetchable) [size=8M]
    I/O ports at 3000 [size=256]
    Memory at d4000000 (32-bit, non-prefetchable) [size=256K]
    Expansion ROM at d4060000 [disabled] [size=128K]
    Capabilities: [48] Vendor Specific Information: Len=08 <?>
    Capabilities: [50] Power Management version 3
    Capabilities: [58] Express Legacy Endpoint, MSI 00
    Capabilities: [a0] MSI: Enable- Count=1/1 Maskable- 64bit+
    Capabilities: [100] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?>
    Capabilities: [150] Advanced Error Reporting
    Capabilities: [200] #15
    Capabilities: [270] #19
    Capabilities: [2b0] Address Translation Service (ATS)
    Capabilities: [2c0] Page Request Interface (PRI)
    Capabilities: [2d0] Process Address Space ID (PASID)
    Kernel modules: radeon, amdgpu

0a:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] Hawaii HDMI Audio [Radeon R9 290/290X / 390/390X]
    Subsystem: PC Partner Limited / Sapphire Technology Hawaii HDMI Audio [Radeon R9 290/290X / 390/390X]
    Flags: bus master, fast devsel, latency 0, IRQ 148
    Memory at d4040000 (64-bit, non-prefetchable) [size=16K]
    Capabilities: [48] Vendor Specific Information: Len=08 <?>
    Capabilities: [50] Power Management version 3
    Capabilities: [58] Express Legacy Endpoint, MSI 00
    Capabilities: [a0] MSI: Enable+ Count=1/1 Maskable- 64bit+
    Capabilities: [100] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?>
    Capabilities: [150] Advanced Error Reporting
    Kernel driver in use: snd_hda_intel
    Kernel modules: snd_hda_intel

dmesg | egrep ‘drm|radeon’

[    5.329773] [drm] Memory usable by graphics device = 4096M
[    5.329775] fb: switching to inteldrmfb from VESA VGA
[    5.329888] [drm] Replacing VGA console driver
[    5.336090] [drm] Supports vblank timestamp caching Rev 2 (21.10.2013).
[    5.336091] [drm] Driver supports precise vblank timestamp query.
[    5.338949] [drm] Finished loading DMC firmware i915/skl_dmc_ver1_26.bin (v1.26)
[    5.358427] [drm] Initialized i915 1.6.0 20171023 for 0000:00:02.0 on minor 0
[    5.637364] fbcon: inteldrmfb (fb0) is primary device
[    5.637444] i915 0000:00:02.0: fb0: inteldrmfb frame buffer device
[    6.784672] [drm] RC6 on
[    8.011735] [drm] radeon kernel modesetting enabled.
[    8.011865] radeon 0000:0a:00.0: enabling device (0006 -> 0007)
[    8.012455] [drm] initializing kernel modesetting (HAWAII 0x1002:0x67B0 0x174B:0xE324 0x80).
[    8.012493] [drm] doorbell mmio base: 0xC0000000
[    8.012493] [drm] doorbell mmio size: 8388608
[    8.708745] [drm] GPU not posted. posting now...
[   13.744052] [drm:atom_op_jump [radeon]] *ERROR* atombios stuck in loop for more than 5secs aborting
[   13.744088] [drm:atom_execute_table_locked [radeon]] *ERROR* atombios stuck executing E30E (len 417, WS 0, PS 4) @ 0xE35A
[   13.744102] [drm:atom_execute_table_locked [radeon]] *ERROR* atombios stuck executing B2D8 (len 138, WS 0, PS 8) @ 0xB32D
[   13.744352] radeon 0000:0a:00.0: VRAM: 0M 0x0000000000000000 - 0xFFFFFFFFFFFFFFFF (0M used)
[   13.744354] radeon 0000:0a:00.0: GTT: 2048M 0x0000000000000000 - 0x000000007FFFFFFF
[   13.744365] [drm] Detected VRAM RAM=0M, BAR=256M
[   13.744366] [drm] RAM width 32bits DDR
[   13.744592] radeon 0000:0a:00.0: Fatal error during GPU init
[   13.744595] [drm] radeon: finishing device.
[   13.753070] [drm] radeon: ttm finalized
[   13.753735] radeon: probe of 0000:0a:00.0 failed with error -12
[   13.805692] [drm] amdgpu kernel modesetting enabled.
[   13.814505] amdgpu 0000:0a:00.0: CIK support provided by radeon.
[   13.814507] amdgpu 0000:0a:00.0: Use radeon.cik_support=0 amdgpu.cik_support=1 to override.

Thanks for any help!