Bug: nvidia_uvm causes kernel panic under heavy I/O and parallel compilation

NVIDIA Open GPU Kernel Modules Version

595.58.03-1

Please confirm this issue does not happen with the proprietary driver (of the same version). This issue tracker is only for bugs specific to the open kernel driver.

• I confirm that this does not happen with the proprietary driver package.

Operating System and Version

Arch Linux (rolling)

Kernel Release

6.18.22-1-lts #1 SMP PREEMPT_DYNAMIC Sat, 11 Apr 2026 17:16:25 +0000 x86_64

Please confirm you are running a stable release kernel (e.g. not a -rc). We do not accept bug reports for unreleased kernels.

• I am running on a stable kernel release.

Hardware: GPU

NVIDIA GeForce RTX 4050 Laptop GPU (UUID: GPU-42dd56b5-95d7-016b-c2ee-39c7a94cba35)

Describe the bug

The nvidia_uvm module consistently causes kernel panic under two types of heavy load: heavy sequential I/O (tar compressing ~30GB) and parallel C++ compilation (yay building stremio, spawning multiple cc1plus processes). The system freezes completely with no recovery — hard reboot required. Unloading nvidia_uvm before the operation prevents the crash entirely.

To Reproduce

• Have nvidia_uvm loaded (default with any graphical session active)
• Run: tar -czf /dest/backup.tar.gz -C /home/user largefolder/ (>20GB)
• OR: build a large AUR package with yay (parallel make, multiple cc1plus processes)
• System freezes within minutes under sustained load

Bug Incidence

Always

nvidia-bug-report.log.gz

nvidia-bug-report.log.gz

More Info

No response

Start by reviewing the attached nvidia-bug-report.log.gz and the nvidia_uvm module context. Reproduce the crash with the listed tar and parallel yay/cc1plus workloads, then compare behavior with nvidia_uvm unloaded; done means the sustained-load operations no longer cause a kernel panic.