Page 6 of 6 FirstFirst ... 456
Results 51 to 60 of 60

Thread: 3D engines causing frequent GPU lockups

  1. #51
    Join Date
    Jan 2009
    Location
    Romania, Bucharest
    Posts
    717

    Default Re: 3D engines causing frequent GPU lockups

    Quote Originally Posted by dzombe View Post
    Getting also same GPU hung problem in games, and seems probably AMD GPU driver error. Example https://i.imgur.com/vTXSj8K.jpg
    So waiting for Mesa 18.2 and new kernel (last crash on 4.16.4-1-default) for openSUSE Tumbleweed 20180427-0.

    Code:
    Bench
     22:36:23 kernel: [drm] GPU recovery disabled.
     22:36:23 kernel: [drm] IP block:gfx_v8_0 is hung!
     22:36:23 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, last signaled seq=227591, last emitted seq=227593
     22:36:13 kernel: amdgpu 0000:07:00.0: VM fault (0x2c, vmid 3) at page 1048576, read from 'TC0' (0x54433000) (72)
     22:36:13 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0604802C
     22:36:13 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100000
     22:36:13 kernel: amdgpu 0000:07:00.0: GPU fault detected: 146 0x0000482c
    
    Cities Skylines
     21:53:50 kernel: [drm] GPU recovery disabled.
     21:53:50 kernel: [drm] IP block:gfx_v8_0 is hung!
     21:53:50 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, last signaled seq=1469210, last emitted seq=1469211
     21:53:48 kernel: [drm] GPU recovery disabled.
     21:53:48 kernel: [drm] IP block:gfx_v8_0 is hung!
     21:53:48 kernel: [drm] IP block:gmc_v8_0 is hung!
     21:53:48 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, last signaled seq=221220, last emitted seq=221222
     21:53:40 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 5) at page 1049364, read from 'TC2' (0x54433200) (8)
     21:53:40 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A008002
     21:53:40 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100314
     21:53:40 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x08a00802
    
    ETS2
     21:16:12 kernel: [drm] No hardware hang detected. Did some blocks stall?
     21:16:12 kernel: [drm] GPU recovery disabled.
     21:16:12 kernel: [drm] IP block:gmc_v8_0 is hung!
     21:16:12 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma1 timeout, last signaled seq=592922, last emitted seq=592926
     21:16:12 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, last signaled seq=483618, last emitted seq=483621
    Thank you very much for this extremely useful information! I believe this is the first time someone else confirms the crash I'm getting, which is very important especially with the suspicion of a hardware issue having been out and about. The screenshot you posted seems to show the exact same graphical garbage that I've been getting, which occurs in both Blender as well as Firefox for me... I wasn't sure whether that's related to the lockup or not.

    If you have more info, please let us know at the Freedesktop bug I opened. iive has been kind enough to stick with me throughout the ridiculously difficult process of testing this bug, which was hardened by the fact that it doesn't even trigger an actual Kernel panic for me so not even apitrace can capture what's happening (the machine simply bricks right then and there).

    https://bugs.freedesktop.org/show_bug.cgi?id=105425

    Is your graphics card also a Pitcairn Islands / GCN 1.0 GPU? Also this is not the video driver directly, as the exact same thing happens when booting the system on either the old "radeon" or new "amdgpu" module.
    openSUSE Tumbleweed x64, KDE Framework 5

  2. #52

    Default Re: 3D engines causing frequent GPU lockups

    Have not tried different drivers, but only default amdgpu.

    DMI: Gigabyte Technology Co., Ltd. AB350-Gaming/AB350-Gaming-CF, BIOS F10 12/01/2017
    CPU0: AMD Ryzen 7 1700 Eight-Core Processor
    VGA: Advanced Micro Devices, Inc. [AMD/ATI] Baffin [Radeon RX 550 640SP / RX 560] (rev cf)
    Subsystem: Gigabyte Technology Co., Ltd Radeon RX 560

    Weird is, WoW was working for months on wine-staging without problems and on Steam only Zaccaria Pinball and Torchlight ran without problems. Have Blender installed only for testing and menus had artifacts long time ago when kernel was 4.12.x Sometimes getting now also stripes under Vivaldi (3D acceleration is turned on) when Horizon View client is working on background https://i.imgur.com/OyVrLko.jpg BTW, Vivaldi does not hung up, moving cursor over it restores normal view!

    Closest answer is maybe https://bugs.freedesktop.org/show_bug.cgi?id=106196

  3. #53
    Join Date
    Jan 2009
    Location
    Romania, Bucharest
    Posts
    717

    Default Re: 3D engines causing frequent GPU lockups

    The Mesa 18.1.0 update, which was supposed to fix several GPU crashes, seems to have managed to expand this freeze instead: I now get it even when playing simple 3D games with low-poly models and low-res textures, such as MegaGlest.

    At this moment the issue is at a point where it may have real life implications: I may be constrained to buy a new video card just to stop this, and if I do that I literally won't have money to eat for a month. As I make my living from animation and game development, it's either that or this issue can be solved. I know it has to be software related, but in some mind boggling way every way to see what's doing it gets covered up and no kernel or MESA parameters make it go away.

    Can someone please ask other developers and people experienced with the video drivers to subscribe to this and post their ideas? iive helped me with a lot of advice, but somehow whatever is doing it managed to dodge everything even he could think of. Perhaps someone else has some new suggestions?
    openSUSE Tumbleweed x64, KDE Framework 5

  4. #54

    Default Re: 3D engines causing frequent GPU lockups

    Update, just for information: Mesa 18.3, kernel 4.19.8-1-default , version 20181218
    Virtualbox taskbar preview tiles and Blender on start are displaying same kind glitches and WoW on next scene loading screen hung up exactly in same way, from log now:
    kernel:
    [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=266605, emitted seq=266607

    that's closer, that bug is reported first 2 years ago. Report or just to wait, seems to be common problem.



  5. #55

    Default Re: 3D engines causing frequent GPU lockups

    5 min of testing DOTA on Steam and crash, Spotify playing, probably all other programs ok and only GPU frozen. Reboot.
    Code:
     -- Reboot --
    jaan  05 15:49:57 systemd-logind[1140]: Power key pressed.
    jaan  05 15:48:46 kernel: [drm] GPU recovery disabled.
    jaan  05 15:48:46 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, signaled seq=38734, emitted seq=38738
    jaan  05 15:48:46 kernel: [drm] GPU recovery disabled.
    jaan  05 15:48:46 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=278576, emitted seq=278578
    jaan  05 15:48:35 kernel: [drm] GPU recovery disabled.
    jaan  05 15:48:35 kernel: [drm:gfx_v8_0_priv_reg_irq [amdgpu]] *ERROR* Illegal register access in command stream
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 5, pasid 32790) at page 1048634, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A03D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x0010003A
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01d03d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 5, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A03D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 4, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0803D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 2, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0403D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 6, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0C03D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 7, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E03D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 1, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0203D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 3, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0603D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 5, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A03D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 4, pasid 32790) at page 1048610, read from 'SDM1' (0x53444d31) (61)
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0803D002
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00100022
    jaan  05 15:48:35 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x01103d02 for process dota2 pid 7980 thread dota2:cs0 pid 7989
    jaan  05 15:48:35 kernel: gmc_v8_0_process_interrupt: 1 callbacks suppressed

  6. #56
    Join Date
    Jun 2008
    Location
    Podunk
    Posts
    26,507
    Blog Entries
    15

    Default Re: 3D engines causing frequent GPU lockups

    Quote Originally Posted by dzombe View Post
    Update, just for information: Mesa 18.3, kernel 4.19.8-1-default , version 20181218
    Virtualbox taskbar preview tiles and Blender on start are displaying same kind glitches and WoW on next scene loading screen hung up exactly in same way, from log now:
    kernel:
    [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=266605, emitted seq=266607

    that's closer, that bug is reported first 2 years ago. Report or just to wait, seems to be common problem.


    Hi
    And if you update to the latest kernel and Tumbleweed snapshot, does it duplicate?

    Code:
    4.19.11-1-default
    20181224
    Cheers Malcolm °¿° SUSE Knowledge Partner (Linux Counter #276890)
    SUSE SLE, openSUSE Leap/Tumbleweed (x86_64) | GNOME DE
    If you find this post helpful and are logged into the web interface,
    please show your appreciation and click on the star below... Thanks!

  7. #57

    Default Re: 3D engines causing frequent GPU lockups

    Tumbleweed 20190108, Linux 4.19.12-1-default
    and actually same thing with WoW (on wine and dxvk93), loading screen to Battleground and hung up. Still are all hung ups related to some kind of menu open, loading screen or scene change. Never on normal 3D action. Spotify error this time is weird, because song did play normally to power off action. I suspect now suspend status, but need more information. Error is not repeatable. It's completely random, got once after logon to server and some day game works normally 4 hours.
    Code:
    jaan 14 22:39:55 systemd-logind[1260]: Power key pressed.
    jaan 14 22:39:37 kernel: [drm] GPU recovery disabled.
    jaan 14 22:39:37 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, signaled seq=479043, emitted seq=479045
    jaan 14 22:39:37 kernel: [drm] GPU recovery disabled.
    jaan 14 22:39:37 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=7482628, emitted seq=7482630
    jaan 14 22:39:27 kernel: amdgpu 0000:07:00.0: VM fault (0x28, vmid 7, pasid 32774) at page 1059608, read from 'TC2' (0x54433200) (8)
    jaan 14 22:39:27 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E008028
    jaan 14 22:39:27 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00102B18
    jaan 14 22:39:27 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x08c00828 for process spotify pid 5362 thread 1.0.94.262:cs0 pid 5388
    jaan 14 22:39:27 kernel: gmc_v8_0_process_interrupt: 6 callbacks suppressed

  8. #58
    Join Date
    Jun 2008
    Location
    Podunk
    Posts
    26,507
    Blog Entries
    15

    Default Re: 3D engines causing frequent GPU lockups

    On Mon 14 Jan 2019 09:06:20 PM CST, dzombe wrote:

    Tumbleweed 20190108, Linux 4.19.12-1-default
    and actually same thing with WoW (on wine and dxvk93), loading screen to
    Battleground and hung up. Still are all hung ups related to some kind of
    menu open, loading screen or scene change. Never on normal 3D action.
    Spotify error this time is weird, because song did play normally to
    power off action. I suspect now suspend status, but need more
    information. Error is not repeatable. It's completely random, got once
    after logon to server and some day game works normally 4 hours.

    Code:
    --------------------

    jaan 14 22:39:55 systemd-logind[1260]: Power key pressed.
    jaan 14 22:39:37 kernel: [drm] GPU recovery disabled.
    jaan 14 22:39:37 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR*
    ring sdma0 timeout, signaled seq=479043, emitted seq=479045 jaan 14
    22:39:37 kernel: [drm] GPU recovery disabled. jaan 14 22:39:37 kernel:
    [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled
    seq=7482628, emitted seq=7482630 jaan 14 22:39:27 kernel: amdgpu
    0000:07:00.0: VM fault (0x28, vmid 7, pasid 32774) at page 1059608,
    read from 'TC2' (0x54433200) (8) jaan 14 22:39:27 kernel: amdgpu
    0000:07:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E008028 jaan 14
    22:39:27 kernel: amdgpu 0000:07:00.0:
    VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00102B18 jaan 14 22:39:27 kernel:
    amdgpu 0000:07:00.0: GPU fault detected: 147 0x08c00828 for process
    spotify pid 5362 thread 1.0.94.262:cs0 pid 5388 jaan 14 22:39:27
    kernel: gmc_v8_0_process_interrupt: 6 callbacks suppressed
    --------------------


    Hi
    You could try enabling the gpu recovery via adding the following to
    YaST bootloader kernel options;

    Code:
    amdgpu.gpu_recovery=1
    --
    Cheers Malcolm °¿° SUSE Knowledge Partner (Linux Counter #276890)
    SLES 15 | GNOME Shell 3.26.2 | 4.12.14-25.25-default
    If you find this post helpful and are logged into the web interface,
    please show your appreciation and click on the star below... Thanks!


  9. #59

    Default Re: 3D engines causing frequent GPU lockups

    Actually doesn't help, wow was working 2 days ok, but now selecting Dota2 event replay, crashed. So there is no solution yet and we can only wait for new firmware.
    Code:
    journalctl -r -g amdgpu
    -- Reboot --
    jaan  19 13:58:11 kernel: amdgpu 0000:07:00.0: GPU reset begin!
    jaan  19 13:58:11 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=631755, emitted seq=631758
    jaan  19 13:58:02 kernel: amdgpu 0000:07:00.0: GPU reset begin!
    jaan  19 13:58:02 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, signaled seq=158578, emitted seq=158579
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 4, pasid 32771) at page 1049515, read from 'TC3' (0x54433300) (4)
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x08004002
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x001003AB
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x0d580402 for process plasmashell pid 2797 thread plasmashel:cs0 pid 2936
    jaan  19 10:29:27 kernel: [drm] Initialized amdgpu 3.27.0 20150101 for 0000:07:00.0 on minor 0
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: fb0: amdgpudrmfb frame buffer device
    jaan  19 10:29:27 kernel: fbcon: amdgpudrmfb (fb0) is primary device
    jaan  19 10:29:27 kernel: [drm] amdgpu: 4096M of GTT memory ready.
    jaan  19 10:29:27 kernel: [drm] amdgpu: 4096M of VRAM memory ready
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: GART: 256M 0x000000FF00000000 - 0x000000FF0FFFFFFF
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: VRAM: 4096M 0x000000F400000000 - 0x000000F4FFFFFFFF (4096M used)
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: No more image in the PCI ROM
    jaan  19 10:29:27 kernel: fb0: switching to amdgpudrmfb from EFI VGA
    jaan  19 10:29:27 kernel: [drm] amdgpu kernel modesetting enabled.
    jaan  19 10:29:27 dracut-cmdline[351]: Using kernel command line parameters: resume=UUID=9d521981-beec-4f08-967d-c03e92d2cf47 root=UUID=9b93c2b3-5b74-433a-a4c2-ccf149d177a1 rootfstype=btrfs rootflags=rw,relatime,ssd,space_cache,subvolid=1023,subvol=/@/.snapshots/296/snapsh>
    jaan  19 10:29:27 kernel: Kernel command line: BOOT_IMAGE=/boot/vmlinuz-4.20.0-1-default root=UUID=9b93c2b3-5b74-433a-a4c2-ccf149d177a1 splash=silent resume=/dev/disk/by-id/nvme-PLEXTOR_PX-512M8PeGN_P02650102370-part3 quiet amdgpu.gpu_recovery=1
    jaan  19 10:29:27 kernel: Command line: BOOT_IMAGE=/boot/vmlinuz-4.20.0-1-default root=UUID=9b93c2b3-5b74-433a-a4c2-ccf149d177a1 splash=silent resume=/dev/disk/by-id/nvme-PLEXTOR_PX-512M8PeGN_P02650102370-part3 quiet amdgpu.gpu_recovery=1
    -- Reboot --

  10. #60
    Join Date
    Jun 2008
    Location
    Podunk
    Posts
    26,507
    Blog Entries
    15

    Default Re: 3D engines causing frequent GPU lockups

    Quote Originally Posted by dzombe View Post
    Actually doesn't help, wow was working 2 days ok, but now selecting Dota2 event replay, crashed. So there is no solution yet and we can only wait for new firmware.
    Code:
    journalctl -r -g amdgpu
    -- Reboot --
    jaan  19 13:58:11 kernel: amdgpu 0000:07:00.0: GPU reset begin!
    jaan  19 13:58:11 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=631755, emitted seq=631758
    jaan  19 13:58:02 kernel: amdgpu 0000:07:00.0: GPU reset begin!
    jaan  19 13:58:02 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, signaled seq=158578, emitted seq=158579
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0: VM fault (0x02, vmid 4, pasid 32771) at page 1049515, read from 'TC3' (0x54433300) (4)
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x08004002
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x001003AB
    jaan  19 13:58:01 kernel: amdgpu 0000:07:00.0: GPU fault detected: 147 0x0d580402 for process plasmashell pid 2797 thread plasmashel:cs0 pid 2936
    jaan  19 10:29:27 kernel: [drm] Initialized amdgpu 3.27.0 20150101 for 0000:07:00.0 on minor 0
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: fb0: amdgpudrmfb frame buffer device
    jaan  19 10:29:27 kernel: fbcon: amdgpudrmfb (fb0) is primary device
    jaan  19 10:29:27 kernel: [drm] amdgpu: 4096M of GTT memory ready.
    jaan  19 10:29:27 kernel: [drm] amdgpu: 4096M of VRAM memory ready
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: GART: 256M 0x000000FF00000000 - 0x000000FF0FFFFFFF
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: VRAM: 4096M 0x000000F400000000 - 0x000000F4FFFFFFFF (4096M used)
    jaan  19 10:29:27 kernel: amdgpu 0000:07:00.0: No more image in the PCI ROM
    jaan  19 10:29:27 kernel: fb0: switching to amdgpudrmfb from EFI VGA
    jaan  19 10:29:27 kernel: [drm] amdgpu kernel modesetting enabled.
    jaan  19 10:29:27 dracut-cmdline[351]: Using kernel command line parameters: resume=UUID=9d521981-beec-4f08-967d-c03e92d2cf47 root=UUID=9b93c2b3-5b74-433a-a4c2-ccf149d177a1 rootfstype=btrfs rootflags=rw,relatime,ssd,space_cache,subvolid=1023,subvol=/@/.snapshots/296/snapsh>
    jaan  19 10:29:27 kernel: Kernel command line: BOOT_IMAGE=/boot/vmlinuz-4.20.0-1-default root=UUID=9b93c2b3-5b74-433a-a4c2-ccf149d177a1 splash=silent resume=/dev/disk/by-id/nvme-PLEXTOR_PX-512M8PeGN_P02650102370-part3 quiet amdgpu.gpu_recovery=1
    jaan  19 10:29:27 kernel: Command line: BOOT_IMAGE=/boot/vmlinuz-4.20.0-1-default root=UUID=9b93c2b3-5b74-433a-a4c2-ccf149d177a1 splash=silent resume=/dev/disk/by-id/nvme-PLEXTOR_PX-512M8PeGN_P02650102370-part3 quiet amdgpu.gpu_recovery=1
    -- Reboot --
    Hi
    I would hazard a guess it's not the amdgpu driver but your desktop environment causing the driver issues...
    Code:
    GPU fault detected: 147 0x0d580402 for process plasmashell pid 2797 thread plasmashel:cs0 pid 2936
    Might be time to report a bug against the kernel and driver to start (post back the bug report number)...
    openSUSE:Submitting bug reports - openSUSE
    Cheers Malcolm °¿° SUSE Knowledge Partner (Linux Counter #276890)
    SUSE SLE, openSUSE Leap/Tumbleweed (x86_64) | GNOME DE
    If you find this post helpful and are logged into the web interface,
    please show your appreciation and click on the star below... Thanks!

Page 6 of 6 FirstFirst ... 456

Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •