Bug 101712 - [Turks PRO/Radeon HD 6570/7570/8550] CPU lockup after ring 0 stalled
Summary: [Turks PRO/Radeon HD 6570/7570/8550] CPU lockup after ring 0 stalled
Status: RESOLVED MOVED
Alias: None
Product: Mesa
Classification: Unclassified
Component: Drivers/Gallium/r600 (show other bugs)
Version: 17.1
Hardware: x86-64 (AMD64) Linux (All)
: high critical
Assignee: Default DRI bug account
QA Contact: Default DRI bug account
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2017-07-06 23:03 UTC by guiscaranse
Modified: 2019-09-18 19:23 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
Error log about the crash (39.43 KB, text/plain)
2017-07-06 23:03 UTC, guiscaranse
Details
DSMEG (more detailed log) (8.71 KB, text/plain)
2017-07-06 23:07 UTC, guiscaranse
Details
Dmesg after boot (82.76 KB, text/plain)
2017-07-11 15:35 UTC, guiscaranse
Details

Description guiscaranse 2017-07-06 23:03:35 UTC
Created attachment 132487 [details]
Error log about the crash

When trying to render any "heavy" graphics or anything that uses particle animations (as I supose that is causing it), the computer crashes and can only be recovered by a hard reset.
I've already posted at Manjaro (https://forum.manjaro.org/t/xorg-freezes-when-playing-dota/25938/11) more details about this issue, but it's getting worse everyday.

Please, I've already tried everything that was possible. I don't have any alternatives...

Computer specs:
System:    Host: Manjaro-AMD Kernel: 4.9.30-1-MANJARO x86_64 (64 bit gcc: 6.3.1)
           Desktop: MATE 1.18.0 (Gtk 3.22.15) Distro: Manjaro Linux
Machine:   Device: desktop Mobo: ASUSTeK model: M5A97 LE R2.0 v: Rev 1.xx
           UEFI: American Megatrends v: 2701 date: 03/24/2016
CPU:       Octa core AMD FX-8300 Eight-Core (-MCP-) cache: 16384 KB
           flags: (lm nx sse sse2 sse3 sse4_1 sse4_2 sse4a ssse3 svm) bmips: 52993
           clock speeds: max: 3300 MHz 1: 1400 MHz 2: 1400 MHz 3: 1400 MHz
           4: 1400 MHz 5: 3300 MHz 6: 3300 MHz 7: 1400 MHz 8: 1400 MHz
Graphics:  Card: Advanced Micro Devices [AMD/ATI] Turks PRO [Radeon HD 6570/7570/8550]
           bus-ID: 01:00.0
           Display Server: X.Org 1.19.3 driver: radeon
           Resolution: 1360x768@60.02hz
           GLX Renderer: Gallium 0.4 on AMD TURKS (DRM 2.48.0 / 4.9.30-1-MANJARO, LLVM 4.0.0)
           GLX Version: 3.0 Mesa 17.1.1 Direct Rendering: Yes
Audio:     Card-1 Advanced Micro Devices [AMD/ATI] Turks HDMI Audio [Radeon HD 6500/6600 / 6700M Series]
           driver: snd_hda_intel bus-ID: 01:00.1
           Card-2 Advanced Micro Devices [AMD/ATI] SBx00 Azalia (Intel HDA)
           driver: snd_hda_intel bus-ID: 00:14.2
           Card-3 Microsoft driver: USB Audio usb-ID: 004-002
           Sound: Advanced Linux Sound Architecture v: k4.9.30-1-MANJARO
Network:   Card-1: Realtek RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller
           driver: r8168 v: 8.044.02-NAPI port: d000 bus-ID: 02:00.0
           IF: enp2s0 state: down mac: <filter>
           Card-2: Microsoft Xbox 360 Wireless Adapter usb-ID: 006-004
           IF: null-if-id state: N/A mac: N/A
Drives:    HDD Total Size: 1000.2GB (5.0% used)
           ID-1: /dev/sda model: SAMSUNG_HD502HI size: 500.1GB
           ID-2: /dev/sdb model: ST500LT012 size: 500.1GB
Partition: ID-1: / size: 449G used: 39G (9%) fs: ext4 dev: /dev/sda2
           ID-2: swap-1 size: 9.45GB used: 0.00GB (0%) fs: swap dev: /dev/sda3
Sensors:   System Temperatures: cpu: 48.2C mobo: N/A gpu: 42.5
           Fan Speeds (in rpm): cpu: 0
Info:      Processes: 222 Uptime: 1:09 Memory: 2561.3/7730.2MB
           Init: systemd Gcc sys: 7.1.1
           Client: Shell (bash 4.4.121) inxi: 2.3.9
Comment 1 guiscaranse 2017-07-06 23:04:30 UTC
It's turning the OS completely unsable, that is why I marked as urgent
Comment 2 guiscaranse 2017-07-06 23:07:47 UTC
Created attachment 132488 [details]
DSMEG (more detailed log)

Here it is a more detailed log
Comment 3 Julien Isorce 2017-07-07 07:52:35 UTC
Can you try to generate an apitrace (apt-get install apitrace, apitrace trace /path/to/application ).  Then if you reproduce the issue with apitrace replay application.trace you can attach it to this bug. (see also https://bugs.freedesktop.org/show_bug.cgi?id=101325)
Comment 4 guiscaranse 2017-07-07 17:34:38 UTC
(In reply to Julien Isorce from comment #3)
> Can you try to generate an apitrace (apt-get install apitrace, apitrace
> trace /path/to/application ).  Then if you reproduce the issue with apitrace
> replay application.trace you can attach it to this bug. (see also
> https://bugs.freedesktop.org/show_bug.cgi?id=101325)

I was able to reproduce the issue and record it using apitrace (https://mega.nz/#!8M0TDRaJ!Uvh0V8B10JwZqRxAuN2PTUwfoQUN4mteeb-ks2P2mio). Also read the otter issue and i think that probably are related, but no idea how to solve it.
Comment 5 Julien Isorce 2017-07-10 09:49:24 UTC
Thx for the apitrace. I could not reproduce the issue with radeonsi/capverde using apitrace replay darkest.bin.x86_64.trace, can you ?. Though I could see the VRAM increasing a lot at the end.
Could you attach full output of dmesg just after boot ? At least to see the vram size.

Try to run the app with R600_DEBUG=check_vm GALLIUM_DDEBUG="pipelined 5000" 
It should generate infos in ~/ddebug_dumps/
Comment 6 guiscaranse 2017-07-11 15:35:35 UTC
Created attachment 132618 [details]
Dmesg after boot

(In reply to Julien Isorce from comment #5)
> Thx for the apitrace. I could not reproduce the issue with radeonsi/capverde
> using apitrace replay darkest.bin.x86_64.trace, can you ?. Though I could
> see the VRAM increasing a lot at the end.
> Could you attach full output of dmesg just after boot ? At least to see the
> vram size.
> 
> Try to run the app with R600_DEBUG=check_vm GALLIUM_DDEBUG="pipelined 5000" 
> It should generate infos in ~/ddebug_dumps/

Added the dmesg output, will try running the app with the env variables, but I am sure that I can reproduce the issue with apitrace replay
Comment 7 Pander 2018-11-14 10:05:53 UTC
Same issue with Radeon HD 5970 for mesa 18.2.2
Comment 8 GitLab Migration User 2019-09-18 19:23:25 UTC
-- GitLab Migration Automatic Message --

This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity.

You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/mesa/mesa/issues/606.


Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.