216200 – AMDGPU hung after enabling HIP for gpu acceleration in Blender Cycles 3.2

Bug 216200 - AMDGPU hung after enabling HIP for gpu acceleration in Blender Cycles 3.2

Summary: AMDGPU hung after enabling HIP for gpu acceleration in Blender Cycles 3.2

Status:	RESOLVED ANSWERED

Alias:	None

Product:	Drivers
Classification:	Unclassified
Component:	Video(DRI - non Intel) (show other bugs)
Hardware:	AMD Linux

Importance:	P1 normal
Assignee:	drivers_video-dri

URL:
Keywords:

Duplicates (1):	216201 (view as bug list)
Depends on:
Blocks:

Reported:	2022-07-03 22:50 UTC by Andrey Solomatin
Modified:	2022-07-04 22:59 UTC (History)
CC List:	1 user (show)

See Also:
Kernel Version:	5.18.9
Subsystem:
Regression:	No
Bisected commit-id:

Attachments
Full journal from the moment the system was launched (630.99 KB, text/plain) 2022-07-03 22:50 UTC, Andrey Solomatin	Details
Add an attachment (proposed patch, testcase, etc.)

Description Andrey Solomatin 2022-07-03 22:50:07 UTC

Created attachment 301326 [details]
Full journal from the moment the system was launched

Description:

HIP for gpu acceleration in Blender render cycles 3.2 causes the screen to freeze.

Video showing the problem on Youtube video hosting: https://www.youtube.com/watch?v=tZzTuvRn3cw

Hardware:

CPU: AMD Ryzen™ 5 3600
MOTHERBOARD: MSI X470 GAMING PLUS MAX
GPU: SAPPHIRE Radeon RX 6600 8192Mb PULSE (11310-01-20G)

Software version:

Arch Linux x86-64
linux 5.18.9.arch1-1
xf86-video-amdgpu 22.0.0-1
mesa 22.1.3-1
rocm-llvm 5.2.0-1
hip-runtime-amd 5.2.0-3
blender 3.2.0-4

Partial log with the problem (see attachment for full log):

Jul 04 01:01:55 sanka kernel: [drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for fences timed out!
Jul 04 01:01:55 sanka kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx_0.0.0 timeout, signaled seq=6213, emitted seq=6215
Jul 04 01:01:55 sanka kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* Process information: process blender pid 2776 thread blender:cs0 pid 2798
Jul 04 01:01:55 sanka kernel: amdgpu 0000:29:00.0: amdgpu: GPU reset begin!
Jul 04 01:01:55 sanka kernel: amdgpu: Failed to suspend process 0x800c
Jul 04 01:01:55 sanka /usr/lib/gdm-x-session[1604]: [2022-07-04 01:01:55.072] [1649] (device_info_linux.cc:45): NumberOfDevices
Jul 04 01:01:55 sanka /usr/lib/gdm-x-session[1604]: [2022-07-04 01:01:55.189] [1649] (device_info_linux.cc:45): NumberOfDevices
Jul 04 01:01:55 sanka /usr/lib/gdm-x-session[1604]: [2022-07-04 01:01:55.189] [1649] (device_info_linux.cc:78): GetDeviceName
Jul 04 01:01:55 sanka kernel: [drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for fences timed out!
Jul 04 01:01:55 sanka kernel: amdgpu 0000:29:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring kiq_2.1.0 test failed (-110)
Jul 04 01:01:55 sanka kernel: [drm:gfx_v10_0_hw_fini [amdgpu]] *ERROR* KGQ disable failed
Jul 04 01:01:55 sanka kernel: amdgpu 0000:29:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring kiq_2.1.0 test failed (-110)
Jul 04 01:01:55 sanka kernel: [drm:gfx_v10_0_hw_fini [amdgpu]] *ERROR* KCQ disable failed
Jul 04 01:01:55 sanka kernel: [drm:gfx_v10_0_hw_fini [amdgpu]] *ERROR* failed to halt cp gfx
Jul 04 01:01:55 sanka kernel: [drm] free PSP TMR buffer
Jul 04 01:01:55 sanka kernel: CPU: 5 PID: 158 Comm: kworker/u64:7 Tainted: G           OE     5.18.9-arch1-1 #1 137f0035b2ece06cb65382579db27e9de66af504
Jul 04 01:01:55 sanka kernel: Hardware name: Micro-Star International Co., Ltd. MS-7B79/X470 GAMING PLUS MAX (MS-7B79), BIOS H.F1 05/24/2022
Jul 04 01:01:55 sanka kernel: Workqueue: amdgpu-reset-dev drm_sched_job_timedout [gpu_sched]
Jul 04 01:01:55 sanka kernel: Call Trace:
Jul 04 01:01:55 sanka kernel:  <TASK>
Jul 04 01:01:55 sanka kernel:  dump_stack_lvl+0x48/0x5d
Jul 04 01:01:55 sanka kernel:  amdgpu_do_asic_reset+0x2a/0x470 [amdgpu c3399060640045ce33894f35f697ceceab8d3be0]
Jul 04 01:01:55 sanka kernel:  amdgpu_device_gpu_recover_imp.cold+0x537/0x8cc [amdgpu c3399060640045ce33894f35f697ceceab8d3be0]
Jul 04 01:01:55 sanka kernel:  amdgpu_job_timedout+0x18c/0x1c0 [amdgpu c3399060640045ce33894f35f697ceceab8d3be0]
Jul 04 01:01:55 sanka kernel:  drm_sched_job_timedout+0x76/0x100 [gpu_sched b54a976254cd79f6332eedc913d0037b3c33b883]
Jul 04 01:01:55 sanka kernel:  process_one_work+0x1c7/0x380
Jul 04 01:01:55 sanka kernel:  worker_thread+0x51/0x380
Jul 04 01:01:55 sanka kernel:  ? rescuer_thread+0x3a0/0x3a0
Jul 04 01:01:55 sanka kernel:  kthread+0xde/0x110
Jul 04 01:01:55 sanka kernel:  ? kthread_complete_and_exit+0x20/0x20
Jul 04 01:01:55 sanka kernel:  ret_from_fork+0x22/0x30
Jul 04 01:01:55 sanka kernel:  </TASK>
Jul 04 01:01:55 sanka kernel: amdgpu 0000:29:00.0: amdgpu: MODE1 reset
Jul 04 01:01:55 sanka kernel: amdgpu 0000:29:00.0: amdgpu: GPU mode1 reset
Jul 04 01:01:55 sanka kernel: amdgpu 0000:29:00.0: amdgpu: GPU smu mode1 reset
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: GPU reset succeeded, trying to resume
Jul 04 01:01:56 sanka kernel: [drm] PCIE GART of 512M enabled (table at 0x0000008000300000).
Jul 04 01:01:56 sanka kernel: [drm] VRAM is lost due to GPU reset!
Jul 04 01:01:56 sanka kernel: [drm] PSP is resuming...
Jul 04 01:01:56 sanka kernel: [drm] reserve 0xa00000 from 0x81fe000000 for PSP TMR
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: RAS: optional ras ta ucode is not available
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: SECUREDISPLAY: securedisplay ta ucode is not available
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: SMU is resuming...
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: smu driver if version = 0x0000000f, smu fw if version = 0x00000013, smu fw program = 0, version = 0x003b2900 (59.41.0)
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: SMU driver if version not matched
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: SMU is resumed successfully!
Jul 04 01:01:56 sanka kernel: [drm] DMUB hardware initialized: version=0x0202000F
Jul 04 01:01:56 sanka kernel: [drm] kiq ring mec 2 pipe 1 q 0
Jul 04 01:01:56 sanka kernel: [drm] VCN decode and encode initialized successfully(under DPG Mode).
Jul 04 01:01:56 sanka kernel: [drm] JPEG decode initialized successfully.
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 5 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 6 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 7 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 8 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 9 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 10 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring kiq_2.1.0 uses VM inv eng 11 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring sdma1 uses VM inv eng 13 on hub 0
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring vcn_dec_0 uses VM inv eng 0 on hub 1
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring vcn_enc_0.0 uses VM inv eng 1 on hub 1
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring vcn_enc_0.1 uses VM inv eng 4 on hub 1
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: ring jpeg_dec uses VM inv eng 5 on hub 1
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: recover vram bo from shadow start
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: recover vram bo from shadow done
Jul 04 01:01:56 sanka kernel: [drm] Skip scheduling IBs!
Jul 04 01:01:56 sanka kernel: [drm] Skip scheduling IBs!
Jul 04 01:01:56 sanka kernel: amdgpu 0000:29:00.0: amdgpu: GPU reset(2) succeeded!
Jul 04 01:01:56 sanka kernel: [drm] Skip scheduling IBs!
Jul 04 01:01:56 sanka kernel: [drm] Skip scheduling IBs!
Jul 04 01:01:56 sanka kernel: [drm] Skip scheduling IBs!
...I skip repeated lines...
Jul 04 01:01:56 sanka kernel: [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
Jul 04 01:01:56 sanka kernel: [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
Jul 04 01:01:56 sanka kernel: [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[2747]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka /usr/lib/gdm-x-session[1000]: amdgpu: The CS has been cancelled because the context is lost.
Jul 04 01:01:56 sanka kernel: [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
Jul 04 01:01:56 sanka kernel: [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
Jul 04 01:01:56 sanka kernel: [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!

Comment 1 Andrey Solomatin 2022-07-04 05:04:05 UTC

*** Bug 216201 has been marked as a duplicate of this bug. ***

Comment 2 Artem S. Tashkinov 2022-07-04 22:59:48 UTC

Please report here: https://gitlab.freedesktop.org/drm/amd/-/issues

Note You need to log in before you can comment on or make changes to this bug.