Bug 92477 - [HSW BYT SNB] IGT gem_cs_tlb some sub-tests fails
Summary: [HSW BYT SNB] IGT gem_cs_tlb some sub-tests fails
Status: CLOSED FIXED
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: x86-64 (AMD64) Linux (All)
: medium normal
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2015-10-15 18:49 UTC by Humberto Israel Perez Rodriguez
Modified: 2017-07-24 22:44 UTC (History)
2 users (show)

See Also:
i915 platform: BYT, HSW, SNB
i915 features:


Attachments
dmesg.log (124.09 KB, text/plain)
2015-10-15 18:49 UTC, Humberto Israel Perez Rodriguez
no flags Details
i915_error_state.log (25 bytes, text/plain)
2015-10-15 18:50 UTC, Humberto Israel Perez Rodriguez
no flags Details

Description Humberto Israel Perez Rodriguez 2015-10-15 18:49:59 UTC
Created attachment 118901 [details]
dmesg.log

Kernel <drm-intel-testing-2015-10-10>


==Bug detailed description==
--------------------------------------------------
gem_cs_tlb some subtests fails

==Attachments==
--------------------------------------------------
dmesg.log
i915_error_state.log

==Steps to reproduce==
--------------------------------------------------
run any of the following sub-tests : 

<%render%>
<%bsd%>
<%vebox%>

e.g : gem_cs_tlb --run-subtest render


==Actual results==
--------------------------------------------------
the subtests fails

==Expected results==
--------------------------------------------------
The subtests must pass


==Hardware configuration==
--------------------------------------------------

-- Platform: --
Processor: Intel(R) Core(TM) i5-4250U CPU @ 1.30GHz
Motherboard : D54250WYK
Memory : 8GB

-- Software --
Linux distribution: Ubuntu 14.04.03 LTS 64Bits
BIOS: 4.6


==Test Environment==
--------------------------------------------------
kernel: 4.3.0-rc4-drm-intel-testing-2015-10-10
xorg-server-1.17.2
libdrm-2.4.65
xf86-video-intel-2.99.917
mesa-11.0.2
libva-1.6.1
intel-driver-1.6.1
cairo-1.14.2
IGT Version : 1.12-g1f9e055

Command output :
----------------------------------------------------
$gem_cs_tlb --run-subtest render
IGT-Version: 1.12-g1f9e055 (x86_64) (Linux: 4.3.0-rc4-drm-intel-testing-2015-10-10-ww41+ x86_64)
testing render cs tlb coherency:   0%Test assertion failure function run_on_ring, file gem_cs_tlb.c:135:
Failed assertion: gtt_offset == gtt_offset_new
Stack trace:
  #0 [__igt_fail_assert+0xf1]
  #1 [run_on_ring+0x2a3]
  #2 [__real_main151+0x78]
  #3 [main+0x29]
  #4 [__libc_start_main+0xf5]
  #5 [_start+0x29]
  #6 [<unknown>+0x29]
Subtest render failed.
**** DEBUG ****
Test assertion failure function run_on_ring, file gem_cs_tlb.c:135:
Failed assertion: gtt_offset == gtt_offset_new
****  END  ****
Subtest render: FAIL (0.004s)

real    0m5.016s
user    0m0.005s
sys     0m0.012s
Comment 1 Humberto Israel Perez Rodriguez 2015-10-15 18:50:28 UTC
Created attachment 118902 [details]
i915_error_state.log
Comment 2 Elio 2015-10-15 22:54:36 UTC
Same result with BYT on test 
gem_exec_nop@vebox and gem_exec_nop@bsd-min with following configuration:

Kernel: http://vanaheimr.fr.intel.com/shared/out/kernels/drm-intel/WW42.1_4.3.0-rc4_c38f2c2/
 xorg-server-1.17.2
libdrm-2.4.65
xf86-video-intel2.99.917
mesa-11.0.2
libva-1.6.1
intel-driver 1.6.1
cairo 1.14.2
intel-gpu-tools-1.12
Comment 3 cprigent 2015-10-19 09:02:10 UTC
BYT environment:
Baytrail-M
Hardware
Platform: Toshiba Satellite C55t
Processor Intel(R) Celeron(R) CPU  N2820  @ 2.13GHz
Software
Linux distribution: Ubuntu 14.04 LTS 64Bits
BIOS: 1.10
Comment 4 Humberto Israel Perez Rodriguez 2015-10-28 21:33:54 UTC
The following tests cases also fail on BYT-M with the next configuration :

<%gem_cs_tlb@blt%>
<%gem_cs_tlb@render%>
<%gem_cs_tlb@bsd%>


Ubuntu 14.04.03 x86_x64 LTS
xorg-server : 1.17.2
libdrm : 2.4.65
xf86-video-intel : 2.99.917
mesa : 11.0.4
libva : 1.6.1
intel: driver 1.6.1
cairo : 1.14.2
intel-gpu-tools : 1.12 (commit a2c6786)

Kernel: drm-intel-nightly: 2015y-10m-23d-09h-56m-09s
commit 87074657f22e38163e712ca417e1a398d00096b6
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Fri Oct 23 11:56:52 2015 +0200
Comment 5 cprigent 2015-10-30 11:30:45 UTC
gem_cs_tlb@blt fails on HSW-ULT with tag drm-intel-testing-2015-10-23.
Result was Pass with drm-intel-testing-2015-10-10.

Haswell-ULT
Hardware
Platform: Intel NUC D54250WYK
Processo: Intel Core I5-425OU 1.30 GHz
Software
Linux distribution: Ubuntu 14.04 LTS 64 bits
BIOS: WTLPT10H.86A.0021.2013.1.017.1606
Kernel: tag drm-intel-testing-2015-10-23 87074657f22e38163e712ca417e1a398d00096b6 (4.3.0-rc6) from git://anongit.freedesktop.org/drm-intel
commit 87074657f22e38163e712ca417e1a398d00096b6
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Fri Oct 23 11:56:52 2015 +0200
drm-intel-nightly: 2015y-10m-23d-09h-56m-09s UTC integration manifest

Mesa: mesa-11.0.4 from http://cgit.freedesktop.org/mesa/mesa
Xf86_video_intel: 2.99.917 from http://cgit.freedesktop.org/xorg/driver/xf86-video-intel
Libdrm: libdrm-2.4.65 from http://cgit.freedesktop.org/mesa/drm
Cairo: 1.14.2 from http://cgit.freedesktop.org/cairo
libva: libva-1.6.0 from http://cgit.freedesktop.org/libva
intel-driver: 1.6.1. from http://cgit.freedesktop.org/vaapi/intel-driver
xorg: 1.17.99 installed with script git_xorg.sh
Xserver: xorg-server-1.17.2 from http://cgit.freedesktop.org/xorg/xserver
Intel-gpu-tools: 1.12 a2c67866fb447a5d00abb3061b0d735df30fd40c from http://cgit.freedesktop.org/xorg/app/intel-gpu
Comment 6 Elio 2015-11-25 20:47:34 UTC
The same three test cases are failing in BYT with Kernel:

4.4.0-rc1-nightly+

Ubuntu 15.04

Stdout	
IGT-Version: 1.12-gb68a642 (x86_64) (Linux: 4.4.0-rc1-nightly+ x86_64)
Stack trace:
  #0 [__igt_fail_assert+0x101]
  #1 [run_on_ring+0x293]
  #2 [__real_main151+0x166]
  #3 [main+0x23]
  #4 [__libc_start_main+0xf0]
  #5 [_start+0x29]
  #6 [<unknown>+0x29]
Subtest blt: FAIL (0.020s)
Stderr	
Test assertion failure function run_on_ring, file gem_cs_tlb.c:135:
Failed assertion: gtt_offset == gtt_offset_new
Subtest blt failed.
**** DEBUG ****
Test requirement passed: gem_has_blt(fd)
Test assertion failure function run_on_ring, file gem_cs_tlb.c:135:
Failed assertion: gtt_offset == gtt_offset_new
****  END  ****
Comment 7 cprigent 2015-11-29 09:58:29 UTC
gem_cs_tlb@vebox is fail on HSW-ULT with kernel testing tag 2015-11-20

Hardware:
Motherboard: SawTooth Peak
cpu model name : Intel(R) Core(TM) i7-4550U CPU @ 1.50GHz
cpu model : 69
cpu family : 6
Graphic card: Haswell-ULT Integrated Graphics Controller (rev 09)
Software:
Kernel tag drm-intel-testing-2015-11-20 5074e51ef3a2b0ad4c2354e95aec5380a93966b3 (4.4-rc1) from git://anongit.freedesktop.org/drm-intel 
  commit 5074e51ef3a2b0ad4c2354e95aec5380a93966b3
  Author: Imre Deak <imre.deak@intel.com>
  Date:   Fri Nov 20 11:50:03 2015 +0200
  drm-intel-nightly: 2015y-11m-20d-09h-49m-41s UTC integration manifest
Ubuntu 14.04.1 LTS
Bios: HSWLPTU1.86C.0135.R01.1311020052
Libdrm: 2.4.65
Comment 8 cprigent 2015-11-29 11:08:19 UTC
gem_cs_tlb@render is fail on SNB with kernel testing tag 2015-11-20

Hardware:
Motherboard: DQ67SW
cpu model name : Intel(R) Core(TM) i5-2400S CPU @ 2.50GHz
cpu model : 42
cpu family : 6
Graphic card: 2nd Generation Core Processor Family Integrated Graphics
Software:
Kernel tag drm-intel-testing-2015-11-20 5074e51 (4.4-rc1) from git://anongit.freedesktop.org/drm-intel 
  commit 5074e51ef3a2b0ad4c2354e95aec5380a93966b3
  Author: Imre Deak <imre.deak@intel.com>
  Date:   Fri Nov 20 11:50:03 2015 +0200
  drm-intel-nightly: 2015y-11m-20d-09h-49m-41s UTC integration manifest
Ubuntu 14.04.1 LTS
Bios: SWQ6710H.86A.0060.2011.1220.1805
Libdrm: 2.4.65
Comment 9 Chris Wilson 2016-01-22 00:32:23 UTC
commit bd9842eadead0dc17f176f2c7124ab365264c945
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Fri Jan 22 00:26:56 2016 +0000

    igt/gem_cs_tlb: Use softpin to remove GTT layout assumptions
    
    With softpin we can explicitly manage the layout of the objects to be
    executed, deliberately forcing the reuse of active pages in an attempt
    to spot misbehaviour in the CS TLBs. Being explicit allows us to
    eliminate a lot of the CPU overhead between execbuf, hopefully
    increasing the likelihood of a conflict.
    
    Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>


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.