Bug 108895 - GPU Hang
Summary: GPU Hang
Status: RESOLVED MOVED
Alias: None
Product: Mesa
Classification: Unclassified
Component: Drivers/DRI/i965 (show other bugs)
Version: unspecified
Hardware: x86-64 (AMD64) Linux (All)
: medium major
Assignee: Intel 3D Bugs Mailing List
QA Contact: Intel 3D Bugs Mailing List
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2018-11-29 10:33 UTC by Konstantin Petrov
Modified: 2019-09-25 19:15 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
Gpu hang watching online video using mvp (715.52 KB, text/plain)
2018-11-29 10:33 UTC, Konstantin Petrov
Details

Description Konstantin Petrov 2018-11-29 10:33:36 UTC
Created attachment 142658 [details]
Gpu hang watching online video using mvp

Hi:

Gpu hanged while watching online video using mvp on my upboard (cherry trail chip).

[drm] GPU HANG: ecode 8:0:0x85dffffb, in mpv/vo [7610], reason: Hang on render ring, action: reset

uname -a
Linux upboard 4.9.126-upboard+ #9 SMP Thu Sep 13 08:26:36 EEST 2018 x86_64 GNU/Linux

lspci
00:00.0 Host bridge: Intel Corporation Atom/Celeron/Pentium Processor x5-E8000/J3xxx/N3xxx Series SoC Transaction Register (rev 36)
00:02.0 VGA compatible controller: Intel Corporation Atom/Celeron/Pentium Processor x5-E8000/J3xxx/N3xxx Series PCI Configuration Registers (rev 36)
00:14.0 USB controller: Intel Corporation Atom/Celeron/Pentium Processor x5-E8000/J3xxx/N3xxx Series USB xHCI Controller (rev 36)
00:16.0 USB controller: Intel Corporation Device 22b7 (rev 36)
00:1a.0 Encryption controller: Intel Corporation Atom/Celeron/Pentium Processor x5-E8000/J3xxx/N3xxx Series Trusted Execution Engine (rev 36)
00:1c.0 PCI bridge: Intel Corporation Atom/Celeron/Pentium Processor x5-E8000/J3xxx/N3xxx Series PCI Express Port #1 (rev 36)
00:1f.0 ISA bridge: Intel Corporation Atom/Celeron/Pentium Processor x5-E8000/J3xxx/N3xxx Series PCU (rev 36)
01:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 0c)

Thanks
Comment 1 Lakshmi 2018-11-30 06:50:09 UTC
Considering this as not a kernel bug but Mesa. Product is set to Mesa.

render command stream:
  START: 0x1af30000
  HEAD:  0x01401d34
    head = 0x00001d34, wraps = 10
  TAIL:  0x00001d70
  CTL:   0x00003001
    len=16384, enabled
  MODE:  0x00004000
  HWS:   0x007ea000
  ACTHD: 0x00000000 fe68f644
    at ring: 0x00000000
  IPEIR: 0x00000000
  IPEHR: 0x7a000004
  INSTDONE: 0xffdfffff
    busy: CS
  batch: [0x00000000_fe68f000, 0x00000000_fe697000]
  BBADDR: 0x00000000_fe68f645
  BB_STATE: 0x00000020
  INSTPS: 0x8000020b
  INSTPM: 0x00006080
  FADDR: 0x00000000 fe68f800
  RC PSMI: 0x00001010
  FAULT_REG: 0x000000b9
    Valid
    Invalid PTE Fault
    Engine GFX
    Source ID 23
  SYNC_0: 0x00000000 [last synced 0x00000000]
  SYNC_1: 0x00000000 [last synced 0x00000000]
  SYNC_2: 0x00000000 [last synced 0x00000000]
  GFX_MODE: 0x0000a000
  PDP0: 0x000000003b359000
  PDP1: 0x000000003b359000
  PDP2: 0x000000003b359000
  PDP3: 0x0000000004cbe000
  seqno: 0x00782ad2
  last_seqno: 0x00782ae2
  waiting: yes
  ring->head: 0x00002b10
  ring->tail: 0x00001e28
  hangcheck: hung [42]

Bad count in PIPE_CONTROL
0xfe68f644:      0x7a000004: PIPE_CONTROL: no write, no depth stall, no RC write flush, no inst flush
0xfe68f648:      0x00000408:    destination address
0xfe68f64c:      0x00000000:    immediate dword low
0xfe68f650:      0x00000000:    immediate dword high
0xfe68f65c:      0x78230000: 3D UNKNOWN: 3d_965 opcode = 0x7823
0xfe68f660:      0x00007c00: MI_NOOP
0xfe68f664:      0x78210000: 3D UNKNOWN: 3d_965 opcode = 0x7821
0xfe68f668:      0x00007bc0: MI_NOOP
0xfe68f66c:      0x78240000: 3D UNKNOWN: 3d_965 opcode = 0x7824
0xfe68f670:      0x00007b81: MI_NOOP
0xfe68f674:      0x78150009: 3D UNKNOWN: 3d_965 opcode = 0x7815
0xfe68f678:      0x00000000: MI_NOOP
0xfe68f67c:      0x00000000: MI_NOOP
0xfe68f680:      0x00000000: MI_NOOP
0xfe68f684:      0x00000000: MI_NOOP
0xfe68f688:      0x00000000: MI_NOOP
0xfe68f68c:      0x00000000: MI_NOOP
0xfe68f690:      0x00000000: MI_NOOP
0xfe68f694:      0x00000000: MI_NOOP
0xfe68f698:      0x00000000: MI_NOOP
0xfe68f69c:      0x00000000: MI_NOOP
0xfe68f6a0:      0x78190009: 3D UNKNOWN: 3d_965 opcode = 0x7819
Comment 2 Lionel Landwerlin 2018-11-30 09:36:35 UTC
Could we have the Mesa version installed on the system?
Are you using a video driver (like intel-vaapi-driver)?
Comment 3 Konstantin Petrov 2018-11-30 09:38:47 UTC
Here you go:

galia@upboard:/media/galia$ /usr/bin/mpv --no-keepaspect --no-audio --hwdec=auto http://178.16.129.53:8083
--vo=opengl-hq is deprecated! Use --profile=opengl-hq instead.
Playing: http://178.16.129.53:8083
[ytdl_hook] youtube-dl failed, trying to play URL directly ... 
 (+) Video --vid=1 (theora)
libva info: VA-API version 0.39.4
libva info: va_getDriverName() returns 0
libva info: Trying to open /usr/lib/x86_64-linux-gnu/dri/i965_drv_video.so
libva info: Found init function __vaDriverInit_0_39
libva info: va_openDriver() returns 0
[ffmpeg/video] theora: vp3: first frame not a keyframe
[ffmpeg/demuxer] ogg: Broken file, non-keyframe not correctly marked.
[ffmpeg/demuxer] ogg: Broken file, non-keyframe not correctly marked.
[ffmpeg/demuxer] ogg: Broken file, non-keyframe not correctly marked.
[ffmpeg/demuxer] ogg: Broken file, non-keyframe not correctly marked.
[ffmpeg/demuxer] ogg: Broken file, non-keyframe not correctly marked.
[ffmpeg/demuxer] ogg: Broken file, non-keyframe not correctly marked.
Using software decoding.
VO: [opengl] 640x360 yuv420p
V: 03:15:17 Cache:  2s+0KB


Exiting... (Quit)
galia@upboard:/media/galia$ dpkg -l | grep mesa
ii  libegl1-mesa:amd64                    13.0.6-1+b2                          amd64        free implementation of the EGL API -- runtime
ii  libegl1-mesa-drivers:amd64            13.0.6-1+b2                          amd64        transitional dummy package
ii  libgl1-mesa-dev:amd64                 13.0.6-1+b2                          amd64        free implementation of the OpenGL API -- GLX development files
ii  libgl1-mesa-dri:amd64                 13.0.6-1+b2                          amd64        free implementation of the OpenGL API -- DRI modules
ii  libgl1-mesa-glx:amd64                 13.0.6-1+b2                          amd64        free implementation of the OpenGL API -- GLX runtime
ii  libglapi-mesa:amd64                   13.0.6-1+b2                          amd64        free implementation of the GL API -- shared library
ii  libglu1-mesa:amd64                    9.0.0-2.1                            amd64        Mesa OpenGL utility library (GLU)
ii  libwayland-egl1-mesa:amd64            13.0.6-1+b2                          amd64        implementation of the Wayland EGL platform -- runtime
ii  mesa-common-dev:amd64                 13.0.6-1+b2                          amd64        Developer documentation for Mesa
ii  mesa-utils                            8.3.0-3                              amd64        Miscellaneous Mesa GL utilities
Comment 4 Konstantin Petrov 2018-11-30 09:44:46 UTC
Additionally I was watching in parallel another video (which uses hw decoder):

usr/bin/mpv --no-keepaspect --no-audio --hwdec=auto http://87.227.205.118:8090/stream.wmv
--vo=opengl-hq is deprecated! Use --profile=opengl-hq instead.
Playing: http://87.227.205.118:8090/stream.wmv
[ytdl_hook] youtube-dl failed, trying to play URL directly ... 
[ffmpeg/video] h264: Missing reference picture, default is 0
[ffmpeg/video] h264: decode_slice_header error
[ffmpeg/video] h264: Missing reference picture, default is 65532
 (+) Video --vid=1 (h264)
libva info: VA-API version 0.39.4
libva info: va_getDriverName() returns 0
libva info: Trying to open /usr/lib/x86_64-linux-gnu/dri/i965_drv_video.so
libva info: Found init function __vaDriverInit_0_39
libva info: va_openDriver() returns 0
libva info: VA-API version 0.39.4
libva info: va_getDriverName() returns 0
libva info: Trying to open /usr/lib/x86_64-linux-gnu/dri/i965_drv_video.so
libva info: Found init function __vaDriverInit_0_39
libva info: va_openDriver() returns 0
[ffmpeg/video] h264: Missing reference picture, default is 0
[ffmpeg/video] h264: decode_slice_header error
[ffmpeg/video] h264: Missing reference picture, default is 65532
[ffmpeg/video] h264: Missing reference picture, default is 65532
[ffmpeg/video] h264: reference picture missing during reorder
[ffmpeg/video] h264: reference picture missing during reorder
[ffmpeg/video] h264: reference picture missing during reorder
[ffmpeg/video] h264: Missing reference picture, default is 65532
[ffmpeg/video] h264: Missing reference picture, default is 65532
[ffmpeg/video] h264: Missing reference picture, default is 65532
[ffmpeg/video] h264: Missing reference picture, default is 65532
[ffmpeg/video] h264: mmco: unref short failure
[ffmpeg/video] h264: reference picture missing during reorder
[ffmpeg/video] h264: Missing reference picture, default is 65540
[ffmpeg/video] h264: mmco: unref short failure
Using hardware decoding (vaapi).
VO: [opengl] 640x480 vaapi
V: 1102:26:17 Cache:  0s+0KB
Comment 5 GitLab Migration User 2019-09-25 19:15:20 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/1773.


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.