* [Bug 221699] New: PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4
@ 2026-06-28 7:21 bugzilla-daemon
2026-06-28 7:22 ` [Bug 221699] " bugzilla-daemon
` (3 more replies)
0 siblings, 4 replies; 5+ messages in thread
From: bugzilla-daemon @ 2026-06-28 7:21 UTC (permalink / raw)
To: linux-usb
https://bugzilla.kernel.org/show_bug.cgi?id=221699
Bug ID: 221699
Summary: PCIe link drops during GPU BAR2 init — Minisforum DEG2
eGPU dock over Thunderbolt 4
Product: Drivers
Version: 2.5
Hardware: All
OS: Linux
Status: NEW
Severity: normal
Priority: P3
Component: USB
Assignee: drivers_usb@kernel-bugs.kernel.org
Reporter: artiom@flexlabs.org
Regression: No
Created attachment 310385
--> https://bugzilla.kernel.org/attachment.cgi?id=310385&action=edit
dmesg logs: Connecting the dock with the GPU attached, USB and NVMe
disconnected, using Nvidia driver
An RTX 3080 Ti connected via a Minisforum DEG2 Thunderbolt 5 eGPU dock to a
Thunderbolt-4 laptop running Linux enumerates correctly over the PCIe tunnel,
but the PCIe link then dies roughly 8–10 seconds later, while the GPU driver is
in its early BAR2 (instance-memory / page-table aperture) initialization phase.
This reproduces under both the proprietary NVIDIA driver and the in-tree
nouveau driver, which strongly suggests the fault is below the driver layer —
in the Thunderbolt/PCIe tunnel itself (the kernel thunderbolt/pciehp path, the
dock firmware, or the Intel Barlow Ridge-class controller).
The same dock, cable, and GPU work without issue under Windows, including under
a sustained 3D stress test.
## System configuration:
* Laptop: Lenovo ThinkPad, model 21VVCTO1WW, BIOS N4QET33W (1.12)
* CPU/platform: Intel Panther Lake, integrated Arc B390 iGPU (xe driver)
* Thunderbolt host: Intel Panther Lake Thunderbolt 4 NHI (USB4)
* OS / kernel: Fedora 44, 7.0.13-200.fc44.x86_64
* eGPU dock: Minisforum DEG2 in Thunderbolt mode. Enumerates over Thunderbolt
as "Micro Computer (HK) Tech. Ltd. TBGAA"
* GPU: NVIDIA RTX 3080 Ti
* Cable: DEG2-supplied TB5 cable (confirmed functional under Windows 3D load)
* Dock PSU: Corsair SF850
* Drivers tested: NVIDIA open kernel module 595.80 (GSP-based); nouveau
(in-tree, GSP/r535 path, firmware RM version 570.144)
## Reproducible symptom
1. Dock connected (reproduces on both cold-plug and hot-plug).
2. Thunderbolt/USB4 link authorizes; PCIe hotplug bridge reports pciehp:
Slot(10-2): Card present → Link Up.
3. Full PCIe enumeration succeeds: the Intel switch, the GPU (82:00.0) and its
audio function (82:00.1) appear, and BARs are assigned (BAR1 prefetchable 256
MB, BAR3 prefetchable 32 MB, BAR0 16 MB, etc.).
4. The GPU driver begins bring-up and reaches BAR2 initialization.
5. Within 5 seconds after connecting the cable, the OS becomes visually
unresponsive
6. Approximately 8–10 seconds after Link Up, the GPU stops responding on the
PCIe link:
* NVIDIA driver (~10 s): NVRM: Xid (PCI:0000:82:00): 79, GPU has fallen off
the bus, immediately followed by BAR2 setup failing as a consequence —
kbusInitVirtualBar2_HAL ... kern_bus.c:469, kbusInitBar2_HAL ...
kern_bus_gm107.c:332 — then pciehp: Slot(10-2): Link Down and RM resource-leak
assertions during teardown.
* nouveau driver (~8 s): the driver is actively performing BAR2 bring-up
(gf100_bar_oneinit_bar → nvkm_vmm_boot → nvkm_bar_bar2_init/r535_bar_bar2_init)
when MMIO accesses begin returning all-ones: nouveau: timer: stalled at
ffffffffffffffff in g84_bar_flush/tu102_vmm_flush, looping for several seconds,
then pciehp: pcie_do_write_cmd: no response from device.
7. Unplugging the dock immediately restores stability; replugging reproduces
the fault. Leaving it plugged keeps the system unresponsive, and it shortly
resets within 5 more seconds or so.
The key shared detail: under both drivers, the device falls off the bus during
early BAR2 initialization — NVIDIA's "fallen off the bus" detection and its
BAR2-init failure are interleaved in the same instant, and nouveau's hang is
literally inside the BAR2 flush. The two drivers share no relevant code here,
so this points away from a driver bug.
## Directly observed evidence
* Cross-driver reproduction at the same stage. Two independent drivers fail at
BAR2 init (function names above), with the link dropping ~8–10 s after
enumeration.
* GPU-presence is the determining variable. With the GPU removed from the riser
and only the dock's onboard NVMe SSD connected, the dock ran stably for ~37 s
(49 s → 86 s, ended by manual disconnect) with clean USB/UAS/SCSI enumeration
and no link drop or errors. The fault appears only when the GPU is present and
BAR2 init begins.
* Windows is unaffected. The same dock + cable + GPU sustained a 3D stress test
under Windows on a different host with no link loss, indicating the GPU, cable,
dock power delivery, and dock hardware are functional.
## Kernel parameters tried
* Default parameters: GPU enumerates fully, link dies at BAR2 init as described
above. (This is the failure being reported.)
* pcie_aspm=off: system boots, but the eGPU's PCIe link does not initialize —
the GPU does not reach the enumeration/BAR2 stage at all. This is a different
behavior from the default-parameter crash, not a reproduction of it.
## Other potential factors
* GPU, cable, dock power delivery: Functional, tested by sustained 3D stress
test on Windows
* BIOS configuration: All thunderbolt configuration turned on, including PCIe
tunneling
* DEG2 configuration: Verified that the mode switch is set to Thunderbolt
(tested with the Oculink setting, just to be safe, but also TB mode confirmed
working on Windows)
## Suspected root-cause area (hypothesis)
* A kernel thunderbolt/pciehp interaction specific to a discrete GPU's large
memory-mapped BAR2 traffic tunneled through this Barlow Ridge-class controller
over a TB4 host.
* DEG2 / controller firmware failing to sustain the PCIe tunnel once large
BAR-mapped GPU MMIO begins (vs. the lighter NVMe/USB traffic that runs fine).
* A Linux-specific gap in tunnel setup/maintenance that Windows handles
differently (Windows is unaffected under heavier load).
## Attached log files:
1. GPU only: Connecting the dock with the GPU attached, USB and NVMe
disconnected, using Nvidia driver
2. NVMe only: Connecting the dock with GPU removed, only NVMe drive attached
3. Nouveau driver: Connected the dock with the nvidia driver disabled in grub,
using Nouveau driver instead
--
You may reply to this email to add a comment.
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply [flat|nested] 5+ messages in thread* [Bug 221699] PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4
2026-06-28 7:21 [Bug 221699] New: PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4 bugzilla-daemon
@ 2026-06-28 7:22 ` bugzilla-daemon
2026-06-28 7:28 ` bugzilla-daemon
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: bugzilla-daemon @ 2026-06-28 7:22 UTC (permalink / raw)
To: linux-usb
https://bugzilla.kernel.org/show_bug.cgi?id=221699
--- Comment #1 from Artiom (artiom@flexlabs.org) ---
Created attachment 310386
--> https://bugzilla.kernel.org/attachment.cgi?id=310386&action=edit
dmesg logs: Connecting the dock with GPU removed, only NVMe drive attached
--
You may reply to this email to add a comment.
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply [flat|nested] 5+ messages in thread* [Bug 221699] PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4
2026-06-28 7:21 [Bug 221699] New: PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4 bugzilla-daemon
2026-06-28 7:22 ` [Bug 221699] " bugzilla-daemon
@ 2026-06-28 7:28 ` bugzilla-daemon
2026-07-10 23:32 ` bugzilla-daemon
2026-11-22 11:37 ` bugzilla-daemon
3 siblings, 0 replies; 5+ messages in thread
From: bugzilla-daemon @ 2026-06-28 7:28 UTC (permalink / raw)
To: linux-usb
https://bugzilla.kernel.org/show_bug.cgi?id=221699
--- Comment #2 from Artiom (artiom@flexlabs.org) ---
Created attachment 310387
--> https://bugzilla.kernel.org/attachment.cgi?id=310387&action=edit
dmesg logs: Connected the dock with the nvidia driver disabled in grub, using
Nouveau driver instead
--
You may reply to this email to add a comment.
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply [flat|nested] 5+ messages in thread
* [Bug 221699] PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4
2026-06-28 7:21 [Bug 221699] New: PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4 bugzilla-daemon
2026-06-28 7:22 ` [Bug 221699] " bugzilla-daemon
2026-06-28 7:28 ` bugzilla-daemon
@ 2026-07-10 23:32 ` bugzilla-daemon
2026-11-22 11:37 ` bugzilla-daemon
3 siblings, 0 replies; 5+ messages in thread
From: bugzilla-daemon @ 2026-07-10 23:32 UTC (permalink / raw)
To: linux-usb
https://bugzilla.kernel.org/show_bug.cgi?id=221699
Morgwai Kotarbinski (foss@morgwai.pl) changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |foss@morgwai.pl
--- Comment #3 from Morgwai Kotarbinski (foss@morgwai.pl) ---
Hello @Artiom,
Recently a semi-successful Intel host + TB5 + Nvidia + Linux build have been
posted on egpu.io:
https://egpu.io/forums/builds/2023-14-lenovo-thinkpad-x1-yoga-gen-8-13th10cu-rtx-5090-32gbps-tb4tb5-gigabyte-aorus-ai-box-linux-ubuntu-2404-lts/
It is a result of community work and investigation documented in this NV Github
issue:
https://github.com/NVIDIA/open-gpu-kernel-modules/issues/979
It required some drastic workarounds: reducing link speed to gen3 and only the
compute part is stable. Although these patches and workarounds were primarily
intended for Blackwell, we were wondering in the follow-up discussion if they
could possibly help in your case also (you would need to at least add PCI IDs
of your card to the patches, from what I understand).
Apart from the above, have you tried NV's proprietary flavour modules with
disabled GSP firmware? It drastically changes the situation in case of AMD
hosts and there was also a report from an Intel host user on egpu.io:
https://egpu.io/forums/thunderbolt-linux-setup/rtx-40-series-egpu-on-linux-mint-check-this-before-you-give-up/
Please consider creating a Work-In-Progress build on egpu.io, so that a wider
community can chime-in without spamming the kernel Bugzilla.
Cheers!
--
You may reply to this email to add a comment.
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply [flat|nested] 5+ messages in thread* [Bug 221699] PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4
2026-06-28 7:21 [Bug 221699] New: PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4 bugzilla-daemon
` (2 preceding siblings ...)
2026-07-10 23:32 ` bugzilla-daemon
@ 2026-11-22 11:37 ` bugzilla-daemon
3 siblings, 0 replies; 5+ messages in thread
From: bugzilla-daemon @ 2026-11-22 11:37 UTC (permalink / raw)
To: linux-usb
https://bugzilla.kernel.org/show_bug.cgi?id=221699
inwestygator@gmail.com changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |inwestygator@gmail.com
--- Comment #4 from inwestygator@gmail.com ---
Another Intel Panther Lake data point, with a working workaround.
Hardware:
- Laptop: Framework Laptop 13 Pro (Intel Core Ultra Series 3, Panther Lake, Arc
B390 iGPU on xe), BIOS 03.04
- eGPU: Razer Core X V2, Intel JHL9480 / Barlow Ridge (8086:5786), USB4 40 Gb/s
(2 x 20)
- GPU: NVIDIA RTX 3090 (10de:2204), PCIe 4.0 x4
- PCIe path: 00:07.0 (USB4 root port) -> 02:00.0 (switch upstream) -> 03:00.0
(switch downstream) -> 04:00.0 (GPU)
- Kernel 7.2.15 (Arch, Omarchy). NVIDIA open 615.78.08 and proprietary
580.178.04.
Symptom:
The GPU falls off the bus (Xid 79) at state changes: during the driver's start,
at the first
Vulkan use after idle, and when a workload stops. Steady load runs fine. After
a failure only a
power cycle of the enclosure recovers it. With the open driver it failed in 19
of 20 boots.
What I found:
- With the proprietary driver and NVreg_EnableGpuFirmware=0 (GSP firmware off)
the card is
stable, but it stays in P0 at about 105 W, so its link speed never changes.
- With GSP on, the same proprietary driver fails again (2 of 2 boots).
- Locking the link speed before the driver loads fixes it with GSP on, at full
16 GT/s
(the workaround from bug 221319 comment 58):
setpci -s 03:00.0 CAP_EXP+30.w=0024:002f # LnkCtl2: target 16 GT/s + HW
Autonomous Speed Disable
setpci -s 04:00.0 CAP_EXP+30.w=0024:002f # same on the GPU
setpci -s 03:00.0 CAP_EXP+10.w=0020:0020 # retrain, then load the driver
Results: 8 vulkaninfo runs with 20 s idle between them, no Xid (unlocked:
failed within one to
three runs). 13 runs of a compute workload started and stopped (a model
loaded on the
GPU, a request, the process exiting), most with 30 s idle after: no Xid. The
link stayed at 16 GT/s and the card idles normally in P8 at
about 7 W.
Then the same with the open driver 615.78.08 (unlocked it failed in 19 of 20
boots, often
already while loading): the driver loaded cleanly, 8 vulkaninfo runs with 20
s idle and 4
workloads started and stopped with 30 s idle, no Xid, link at 16 GT/s, idle
in P8.
So on this Intel host too, the failure follows the GPU changing its link speed,
which fits the
analysis in bug 221319. ASPM was already disabled on the link.
Related reports:
https://forums.developer.nvidia.com/t/gsp-firmware-triggering-xid-79-on-usb4-thunderbolt-egpu/389811
(with nvidia-bug-report.log.gz, GSP on, right after a failure) and
https://github.com/NVIDIA/open-gpu-kernel-modules/issues/979
--
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2026-11-22 11:37 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-28 7:21 [Bug 221699] New: PCIe link drops during GPU BAR2 init — Minisforum DEG2 eGPU dock over Thunderbolt 4 bugzilla-daemon
2026-06-28 7:22 ` [Bug 221699] " bugzilla-daemon
2026-06-28 7:28 ` bugzilla-daemon
2026-07-10 23:32 ` bugzilla-daemon
2026-11-22 11:37 ` bugzilla-daemon
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox