DIFR Prefetch causes a freeze in pop_os

[Ilya122]

NVIDIA Open GPU Kernel Modules Version

NVIDIA Open GPU Kernel Module version: 580.159.03 Full version string: NVIDIA UNIX Open Kernel Module for x86_64 580.159.03 Release Build Build date: Fri Apr 24 06:03:03 UTC 2026 Kernel: 6.18.7-76061807-generic GPU: GeForce RTX 5070

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

Pop!_OS 24.04 LTS

Kernel Release

Linux pop-os 6.18.7-76061807-generic #202601231045177824932224.04~b44a3c3 SMP PREEMPT_DYNAMIC Fri M x86_64 x86_64 x86_64 GNU/Linux

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

GPU 0: NVIDIA GeForce RTX 5070

Describe the bug

My PC freezes from time to time (currently experienced once in a day)

Journal suggests it's something in nvidir DIFR

LOG:
Jun 03 10:40:15 pop-os kernel: watchdog: BUG: soft lockup - CPU#2 stuck for 104s! [nvidia-modeset/:1314]
Jun 03 10:40:15 pop-os kernel: Modules linked in: r8153_ecm cdc_ether usbnet r8152 mii uhid ccm rfcomm snd_seq_dummy >
Jun 03 10:40:15 pop-os kernel: snd_compress snd_intel_dspcfg snd_usbmidi_lib btmtk snd_intel_sdw_acpi ac97_bus btrtl>
Jun 03 10:40:15 pop-os kernel: ghash_clmulni_intel ahci nvme_keyring nvme_auth libahci realtek hkdf intel_vsec video>
Jun 03 10:40:15 pop-os kernel: CPU: 2 UID: 0 PID: 1314 Comm: nvidia-modeset/ Tainted: G OEL 6.18.7-760>
Jun 03 10:40:15 pop-os kernel: Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE, [L]=SOFTLOCKUP
Jun 03 10:40:15 pop-os kernel: Hardware name: Micro-Star International Co., Ltd. MS-7D99/B760M GAMING PLUS WIFI (MS-7>
Jun 03 10:40:15 pop-os kernel: RIP: 0010:nvWriteGpEntry+0xa4/0x4a0 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: Code: 10 01 00 00 8b 00 c1 e8 12 01 c0 41 29 c0 43 8d 14 03 41 0f 49 d0 39 f2 7c 04 89>
Jun 03 10:40:15 pop-os kernel: RSP: 0018:ffffce8642d1fd08 EFLAGS: 00000246
Jun 03 10:40:15 pop-os kernel: RAX: ffff89ac47ec5000 RBX: ffff89ac19bd6430 RCX: ffffce86466bd3e8
Jun 03 10:40:15 pop-os kernel: RDX: ffff89ac1cc5f000 RSI: 00000000000003f4 RDI: 0000000000000006
Jun 03 10:40:15 pop-os kernel: RBP: 0000000000000006 R08: 0000000000000000 R09: 0000000000000001
Jun 03 10:40:15 pop-os kernel: R10: 0000000000000004 R11: 0000000000000010 R12: ffffce8640ea40d8
Jun 03 10:40:15 pop-os kernel: R13: 00000000000003f4 R14: 0000000000000384 R15: 0000000000000000
Jun 03 10:40:15 pop-os kernel: FS: 0000000000000000(0000) GS:ffff89b3d494e000(0000) knlGS:0000000000000000
Jun 03 10:40:15 pop-os kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jun 03 10:40:15 pop-os kernel: CR2: 00002ff40013f000 CR3: 000000031cb0e002 CR4: 0000000000f72ef0
Jun 03 10:40:15 pop-os kernel: PKRU: 55555554
Jun 03 10:40:15 pop-os kernel: Call Trace:
Jun 03 10:40:15 pop-os kernel:
Jun 03 10:40:15 pop-os kernel: ? nvPushKickoff+0x28/0x50 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? PrefetchHelperSurfaceEvo+0x45c/0x650 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? nvDIFRPrefetchSurfaces+0xb1/0x1f0 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? DifrPrefetchEventDeferredWork+0x16/0x30 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? nvkms_kthread_q_callback+0xd2/0x180 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? _main_loop+0x81/0x140 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? __pfx__main_loop+0x10/0x10 [nvidia_modeset]
Jun 03 10:40:15 pop-os kernel: ? kthread+0x10d/0x230
Jun 03 10:40:15 pop-os kernel: ? __pfx_kthread+0x10/0x10
Jun 03 10:40:15 pop-os kernel: ? ret_from_fork+0x124/0x140
Jun 03 10:40:15 pop-os kernel: ? __pfx_kthread+0x10/0x10
Jun 03 10:40:15 pop-os kernel: ? ret_from_fork_asm+0x1a/0x30
Jun 03 10:40:15 pop-os kernel:
Jun 03 10:40:43 pop-os kernel: watchdog: BUG: soft lockup - CPU#2 stuck for 131s! [nvidia-modeset/:1314]

To Reproduce

Unsure, I was using the PC normally, I run brave + a game for example.
Most of the times it's ok, freezes unexpectedly. Maybe a race condition or a heap bug that sits there until something hits it.

Bug Incidence

Sometimes

nvidia-bug-report.log.gz

I couldnt upload it in any other way so I just created a repository with the report log, excluding hex dump (Let me know if u need it)
https://github.com/Ilya122/nvidia_bug_report_will_be_deleted_0001/blob/main/report.log

More Info

No response