Skip to content
Snippets Groups Projects

GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7,5.6.2

    • Open Issue created by Jason A. Donenfeld @zx2c4 
    Mar 09 12:24:33 thinkpad kernel: Asynchronous wait on fence 0000:00:02.0:kwin_x11[1756]:7c6d8 timed out (hint:intel_atomic_commit_ready+0x0/0x54)
Mar 09 12:24:37 thinkpad kernel: i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
Mar 09 12:24:37 thinkpad kernel: GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
Mar 09 12:24:37 thinkpad kernel: Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.
Mar 09 12:24:37 thinkpad kernel: Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.
Mar 09 12:24:37 thinkpad kernel: drm/i915 developers can then reassign to the right component if it's not a kernel issue.
Mar 09 12:24:37 thinkpad kernel: The GPU crash dump is required to analyze GPU hangs, so please always attach it.
Mar 09 12:24:37 thinkpad kernel: GPU crash dump saved to /sys/class/drm/card0/error
Mar 09 12:24:37 thinkpad kernel: i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
Mar 09 12:24:52 thinkpad kernel: i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
Mar 09 12:24:52 thinkpad kernel: i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
Mar 09 12:25:07 thinkpad kernel: i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
Mar 09 12:25:07 thinkpad kernel: i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
Mar 09 12:25:22 thinkpad kernel: i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
Mar 09 12:25:22 thinkpad kernel: i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
Mar 09 12:25:33 thinkpad kernel: Asynchronous wait on fence 0000:00:02.0:Xorg[1550]:431f16 timed out (hint:intel_atomic_commit_ready+0x0/0x54)

    See below for /sys/class/drm/card0/error from several different crashes that all go the same way.

    Edited
    To upload designs, you'll need to enable LFS and have an admin enable hashed storage. More information

    Child items ...

    • Activity

    • Jason A. Donenfeld changed the description

      changed the description

    • Binitha Scaria added Community platform: CFL labels

      added Community platform: CFL labels

    • bprakash added GPU hang label

      added GPU hang label

    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      @ickle - I managed to reproduce and have attached a crash log.

      gpu-error.dmesg

      gpu-error

      gpu-error.intel_error_decode

    • Jason A. Donenfeld changed title from coffee lake refresh hang on 5.6-rc5 to GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5

      changed title from coffee lake refresh hang on 5.6-rc5 to GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5

    • Jason A. Donenfeld changed the description

      changed the description

    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      I just got this on 5.6-rc6:

      [38644.227357] Asynchronous wait on fence 0000:00:02.0:Xorg[984]:14cb2c timed out (hint:intel_atomic_commit_ready+0x0/0x54)
[38649.347905] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[38649.347906] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[38649.347906] Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.
[38649.347906] Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.
[38649.347907] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[38649.347907] The GPU crash dump is required to analyze GPU hangs, so please always attach it.
[38649.347907] GPU crash dump saved to /sys/class/drm/card0/error
[38649.347911] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[38656.881176] GpuWatchdog[445268]: segfault at 0 ip 000055986c49f477 sp 00007f29f2148790 error 6 in signal-desktop[5598692cc000+53cf000]
[38656.881189] Code: 7d b7 00 79 09 48 8b 7d a0 e8 e5 5d d3 fe 8b 83 00 01 00 00 85 c0 0f 84 91 00 00 00 48 8b 03 48 89 df be 01 00 00 00 ff 50 68 <c7> 04 25 00 00 00 00 37 13 00 00 c6 05 07 23 70 02 01 80 7d 87 00
[38664.282089] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[38664.282296] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[38674.750794] GpuWatchdog[446027]: segfault at 0 ip 0000561b705a1477 sp 00007faf60ce5790 error 6 in signal-desktop[561b6d3ce000+53cf000]
[38674.750806] Code: 7d b7 00 79 09 48 8b 7d a0 e8 e5 5d d3 fe 8b 83 00 01 00 00 85 c0 0f 84 91 00 00 00 48 8b 03 48 89 df be 01 00 00 00 ff 50 68 <c7> 04 25 00 00 00 00 37 13 00 00 c6 05 07 23 70 02 01 80 7d 87 00
[38679.214076] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[38679.214082] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[38685.081272] GpuWatchdog[446046]: segfault at 0 ip 000055e69c7d6477 sp 00007ffa9a408790 error 6 in signal-desktop[55e699603000+53cf000]
[38685.081286] Code: 7d b7 00 79 09 48 8b 7d a0 e8 e5 5d d3 fe 8b 83 00 01 00 00 85 c0 0f 84 91 00 00 00 48 8b 03 48 89 df be 01 00 00 00 ff 50 68 <c7> 04 25 00 00 00 00 37 13 00 00 c6 05 07 23 70 02 01 80 7d 87 00
[38685.960057] signal-desktop[446075]: segfault at 140 ip 00007fddb85cfeb9 sp 00007ffee9a9b630 error 4 in libGLESv2.so[7fddb831d000+2b7000]
[38685.960061] Code: 00 05 00 00 5b 41 5c 41 5e 41 5f 5d e9 88 00 00 00 41 89 0e 5b 41 5c 41 5e 41 5f 5d c3 53 48 8b 3d 5c 3e 01 00 e8 ed 00 00 00 <ff> 90 40 01 00 00 48 85 c0 74 1f 48 89 c3 48 8b 00 48 89 df ff 50
      GPU HANG: ecode 9:0:00000000
Kernel: 5.6.0-rc6+ x86_64
Driver: 20200114
Time: 1584600941 s 451321 us
Boottime: 44652 s 962929 us
Uptime: 7805 s 805635 us
Capture: 4306472128 jiffies; 48620 ms ago
Reset count: 0
Suspend count: 5
Platform: COFFEELAKE
Subplatform: 0x0
PCI ID: 0x3e9b
PCI Revision: 0x02
PCI Subsystem: 17aa:229f
IOMMU enabled?: 1
DMC loaded: yes
DMC fw version: 1.4
RPM wakelock: yes
PM suspended: no
GT awake: yes
EIR: 0x00000000
IER: 0x08080000
GTIER[0]: 0x01010101
GTIER[1]: 0x01010101
GTIER[2]: 0x80000070
GTIER[3]: 0x00000101
PGTBL_ER: 0x00000000
FORCEWAKE: 0x00010001
DERRMR: 0x2077efef
  fence[0] = 00000000
  fence[1] = 44d301f040d4003
  fence[2] = 00000000
  fence[3] = 4063077020c0001
  fence[4] = 8463077064c0001
  fence[5] = 00000000
  fence[6] = 64a307704500001
  fence[7] = 00000000
  fence[8] = 00000000
  fence[9] = 00000000
  fence[10] = 00000000
  fence[11] = 00000000
  fence[12] = 00000000
  fence[13] = 00000000
  fence[14] = 00000000
  fence[15] = 00000000
  fence[16] = 00000000
  fence[17] = 00000000
  fence[18] = 00000000
  fence[19] = 00000000
  fence[20] = 00000000
  fence[21] = 00000000
  fence[22] = 00000000
  fence[23] = 00000000
  fence[24] = 00000000
  fence[25] = 00000000
  fence[26] = 00000000
  fence[27] = 00000000
  fence[28] = 00000000
  fence[29] = 00000000
  fence[30] = 00000000
  fence[31] = 00000000
ERROR: 0x00000000
DONE_REG: 0xebfff1ff
FAULT_TLB_DATA: 0x00000018 0x4421a0b2
GTT_CACHE_EN: 0xf0007fff
GuC firmware: i915/kbl_guc_33.0.0.bin
	status: RUNNING
	version: wanted 33.0, found 33.0
	uCode: 182528 bytes
	RSA: 256 bytes
HuC firmware: i915/kbl_huc_4.0.0.bin
	status: RUNNING
	version: wanted 4.0, found 4.0
	uCode: 225664 bytes
	RSA: 256 bytes
global --- GuC log buffer = 0x00000000 000c8000
:cL%-H5f+!S2UDU=!XonTY-tJ64jR+H`;s5J!Bh!"&E!d"6:+[@]*TUK<H(3bba5ul1E$2;\o@Z9#q"q"-J@pd[]!m^G&G%7]DcO%!!!!(G$2;/T*m[DeQ8=,j[YU7!!-/_zzzzzzz'n="!Kpl50nh2(KlR#J3HJmhF6WfhZ!!!8]zzzzzzzzz!Bbc1'I,/\
Num Pipes: 3
Pipe [0]:
  Power: on
  SRC: 0eff086f
  STAT: 00000000
Plane [0]:
  CNTR: c4042400
  STRIDE: 0000001e
  SURF: 04500000
  TILEOFF: 00000000
Cursor [0]:
  CNTR: 04000027
  POS: 05d10569
  BASE: 00040000
Pipe [1]:
  Power: off
  SRC: 00000000
  STAT: 00000000
Plane [1]:
  CNTR: 00000000
  STRIDE: 00000000
  SURF: 00000000
  TILEOFF: 00000000
Cursor [1]:
  CNTR: 00000000
  POS: 00000000
  BASE: 00000000
Pipe [2]:
  Power: off
  SRC: 00000000
  STAT: 00000000
Plane [2]:
  CNTR: 00000000
  STRIDE: 00000000
  SURF: 00000000
  TILEOFF: 00000000
Cursor [2]:
  CNTR: 00000000
  POS: 00000000
  BASE: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: EDP
  Power: on
  CONF: c0000000
  HTOTAL: 0f9f0eff
  HBLANK: 0f9f0eff
  HSYNC: 0f4f0f2f
  VTOTAL: 08ad086f
  VBLANK: 08ad086f
  VSYNC: 08770872
engines: 47
gen: 9
gt: 2
iommu: enabled
memory-regions: 5
page-sizes: 11000
platform: COFFEELAKE
ppgtt-size: 48
ppgtt-type: 2
is_mobile: no
is_lp: no
require_force_probe: no
is_dgfx: no
has_64bit_reloc: yes
gpu_reset_clobbers_display: no
has_reset_engine: yes
has_fpga_dbg: yes
has_global_mocs: no
has_gt_uc: yes
has_l3_dpf: no
has_llc: yes
has_logical_ring_contexts: yes
has_logical_ring_elsq: no
has_logical_ring_preemption: yes
has_pooled_eu: no
has_rc6: yes
has_rc6p: no
has_rps: yes
has_runtime_pm: yes
has_snoop: no
has_coherent_ggtt: yes
unfenced_needs_alignment: no
hws_needs_physical: no
cursor_needs_physical: no
has_csr: yes
has_ddi: yes
has_dp_mst: yes
has_dsb: no
has_dsc: no
has_fbc: yes
has_gmch: no
has_hdcp: yes
has_hotplug: yes
has_ipc: yes
has_modular_fia: no
has_overlay: no
has_psr: yes
overlay_needs_physical: no
supports_tv: no
slice total: 1, mask=0001
subslice total: 3
slice0: 3 subslices, mask=00000007
slice1: 0 subslices, mask=00000000
slice2: 0 subslices, mask=00000000
EU total: 24
EU per subslice: 8
has slice power gating: no
has subslice power gating: no
has EU power gating: yes
CS timestamp frequency: 12000 kHz
slice0: 3 subslice(s) (0x00000007):
	subslice0: 8 EUs (0xff)
	subslice1: 8 EUs (0xff)
	subslice2: 8 EUs (0xff)
	subslice3: 0 EUs (0x0)
slice1: 0 subslice(s) (0x00000000):
	subslice0: 0 EUs (0x0)
	subslice1: 0 EUs (0x0)
	subslice2: 0 EUs (0x0)
	subslice3: 0 EUs (0x0)
slice2: 0 subslice(s) (0x00000000):
	subslice0: 0 EUs (0x0)
	subslice1: 0 EUs (0x0)
	subslice2: 0 EUs (0x0)
	subslice3: 0 EUs (0x0)
Has logical contexts? yes
scheduler: 1f
i915.vbt_firmware=(null)
i915.modeset=-1
i915.lvds_channel_mode=0
i915.panel_use_ssc=-1
i915.vbt_sdvo_panel_type=-1
i915.enable_dc=-1
i915.enable_fbc=1
i915.enable_psr=-1
i915.disable_power_well=1
i915.enable_ips=1
i915.invert_brightness=0
i915.enable_guc=2
i915.guc_log_level=-1
i915.guc_firmware_path=(null)
i915.huc_firmware_path=(null)
i915.dmc_firmware_path=(null)
i915.mmio_debug=1
i915.edp_vswing=0
i915.reset=3
i915.inject_probe_failure=0
i915.fastboot=-1
i915.enable_dpcd_backlight=0
i915.force_probe=
i915.fake_lmem_start=0
i915.alpha_support=no
i915.enable_hangcheck=yes
i915.prefault_disable=no
i915.load_detect_test=no
i915.force_reset_modeset_test=no
i915.error_capture=yes
i915.disable_display=no
i915.verbose_state_checks=yes
i915.nuclear_pageflip=no
i915.enable_dp_mst=yes
i915.enable_gvt=no
    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      Happened again on 5.6-rc7. @ickle - how many more of these do you want before you reply? At first I understood the idea of it not being worth your time without the error log. But I've since been able to capture quite a few. Here's yet-another:

      GPU HANG: ecode 9:0:00000000
Kernel: 5.6.0-rc7+ x86_64
Driver: 20200114
Time: 1585345279 s 234746 us
Boottime: 93752 s 558254 us
Uptime: 6147 s 192508 us
Capture: 4311936000 jiffies; 46114 ms ago
Reset count: 0
Suspend count: 6
Platform: COFFEELAKE
Subplatform: 0x0
PCI ID: 0x3e9b
PCI Revision: 0x02
PCI Subsystem: 17aa:229f
IOMMU enabled?: 1
DMC loaded: yes
DMC fw version: 1.4
RPM wakelock: yes
PM suspended: no
GT awake: yes
EIR: 0x00000000
IER: 0x08080000
GTIER[0]: 0x01010101
GTIER[1]: 0x01010101
GTIER[2]: 0x80000070
GTIER[3]: 0x00000101
PGTBL_ER: 0x00000000
FORCEWAKE: 0x00010001
DERRMR: 0x2077efef
  fence[0] = 65e307704640001
  fence[1] = 00000000
  fence[2] = 00000000
  fence[3] = 44e307702540001
  fence[4] = 85a307706600001
  fence[5] = 251f01f02120003
  fence[6] = 00000000
  fence[7] = 460300704504003
  fence[8] = 00000000
  fence[9] = 00000000
  fence[10] = 00000000
  fence[11] = 00000000
  fence[12] = 00000000
  fence[13] = 00000000
  fence[14] = 00000000
  fence[15] = 00000000
  fence[16] = 00000000
  fence[17] = 00000000
  fence[18] = 00000000
  fence[19] = 00000000
  fence[20] = 00000000
  fence[21] = 00000000
  fence[22] = 00000000
  fence[23] = 00000000
  fence[24] = 00000000
  fence[25] = 00000000
  fence[26] = 00000000
  fence[27] = 00000000
  fence[28] = 00000000
  fence[29] = 00000000
  fence[30] = 00000000
  fence[31] = 00000000
ERROR: 0x00000000
DONE_REG: 0xebfff1ff
FAULT_TLB_DATA: 0x00000018 0x4421a0b2
GTT_CACHE_EN: 0xf0007fff
GuC firmware: i915/kbl_guc_33.0.0.bin
	status: RUNNING
	version: wanted 33.0, found 33.0
	uCode: 182528 bytes
	RSA: 256 bytes
HuC firmware: i915/kbl_huc_4.0.0.bin
	status: RUNNING
	version: wanted 4.0, found 4.0
	uCode: 225664 bytes
	RSA: 256 bytes
global --- GuC log buffer = 0x00000000 000c8000
:cL%-H5f+!SDU8Ou":3?ml\eXX&3*2a%rjji+=Em/6F^I?OOZd`[La\1<H(3bba5ul1E$2;\Tm)X-((\sB%cU9do@P5h8N`2meg74J,fQMF`+>?Zg$V^-M-DL*2rGB!!"M>zzzzzzzrNGtrl?Nl6R(VsqVC]nC;q_]9qAQs\!!!!_zzzzzzzzz8dXPA!:hC@
Num Pipes: 3
Pipe [0]:
  Power: on
  SRC: 0eff086f
  STAT: 00000000
Plane [0]:
  CNTR: c4042400
  STRIDE: 0000001e
  SURF: 04640000
  TILEOFF: 00000000
Cursor [0]:
  CNTR: 04000027
  POS: 068b0cd1
  BASE: 00080000
Pipe [1]:
  Power: off
  SRC: 00000000
  STAT: 00000000
Plane [1]:
  CNTR: 00000000
  STRIDE: 00000000
  SURF: 00000000
  TILEOFF: 00000000
Cursor [1]:
  CNTR: 00000000
  POS: 00000000
  BASE: 00000000
Pipe [2]:
  Power: off
  SRC: 00000000
  STAT: 00000000
Plane [2]:
  CNTR: 00000000
  STRIDE: 00000000
  SURF: 00000000
  TILEOFF: 00000000
Cursor [2]:
  CNTR: 00000000
  POS: 00000000
  BASE: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: EDP
  Power: on
  CONF: c0000000
  HTOTAL: 0f9f0eff
  HBLANK: 0f9f0eff
  HSYNC: 0f4f0f2f
  VTOTAL: 08ad086f
  VBLANK: 08ad086f
  VSYNC: 08770872
engines: 47
gen: 9
gt: 2
iommu: enabled
memory-regions: 5
page-sizes: 11000
platform: COFFEELAKE
ppgtt-size: 48
ppgtt-type: 2
is_mobile: no
is_lp: no
require_force_probe: no
is_dgfx: no
has_64bit_reloc: yes
gpu_reset_clobbers_display: no
has_reset_engine: yes
has_fpga_dbg: yes
has_global_mocs: no
has_gt_uc: yes
has_l3_dpf: no
has_llc: yes
has_logical_ring_contexts: yes
has_logical_ring_elsq: no
has_logical_ring_preemption: yes
has_pooled_eu: no
has_rc6: yes
has_rc6p: no
has_rps: yes
has_runtime_pm: yes
has_snoop: no
has_coherent_ggtt: yes
unfenced_needs_alignment: no
hws_needs_physical: no
cursor_needs_physical: no
has_csr: yes
has_ddi: yes
has_dp_mst: yes
has_dsb: no
has_dsc: no
has_fbc: yes
has_gmch: no
has_hdcp: yes
has_hotplug: yes
has_ipc: yes
has_modular_fia: no
has_overlay: no
has_psr: yes
overlay_needs_physical: no
supports_tv: no
slice total: 1, mask=0001
subslice total: 3
slice0: 3 subslices, mask=00000007
slice1: 0 subslices, mask=00000000
slice2: 0 subslices, mask=00000000
EU total: 24
EU per subslice: 8
has slice power gating: no
has subslice power gating: no
has EU power gating: yes
CS timestamp frequency: 12000 kHz
slice0: 3 subslice(s) (0x00000007):
	subslice0: 8 EUs (0xff)
	subslice1: 8 EUs (0xff)
	subslice2: 8 EUs (0xff)
	subslice3: 0 EUs (0x0)
slice1: 0 subslice(s) (0x00000000):
	subslice0: 0 EUs (0x0)
	subslice1: 0 EUs (0x0)
	subslice2: 0 EUs (0x0)
	subslice3: 0 EUs (0x0)
slice2: 0 subslice(s) (0x00000000):
	subslice0: 0 EUs (0x0)
	subslice1: 0 EUs (0x0)
	subslice2: 0 EUs (0x0)
	subslice3: 0 EUs (0x0)
Has logical contexts? yes
scheduler: 1f
i915.vbt_firmware=(null)
i915.modeset=-1
i915.lvds_channel_mode=0
i915.panel_use_ssc=-1
i915.vbt_sdvo_panel_type=-1
i915.enable_dc=-1
i915.enable_fbc=1
i915.enable_psr=-1
i915.disable_power_well=1
i915.enable_ips=1
i915.invert_brightness=0
i915.enable_guc=2
i915.guc_log_level=-1
i915.guc_firmware_path=(null)
i915.huc_firmware_path=(null)
i915.dmc_firmware_path=(null)
i915.mmio_debug=0
i915.edp_vswing=0
i915.reset=3
i915.inject_probe_failure=0
i915.fastboot=-1
i915.enable_dpcd_backlight=0
i915.force_probe=
i915.fake_lmem_start=0
i915.alpha_support=no
i915.enable_hangcheck=yes
i915.prefault_disable=no
i915.load_detect_test=no
i915.force_reset_modeset_test=no
i915.error_capture=yes
i915.disable_display=no
i915.verbose_state_checks=yes
i915.nuclear_pageflip=no
i915.enable_dp_mst=yes
i915.enable_gvt=no
      Edited by Jason A. Donenfeld
    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      CC @bjsprakash - This should have a "severity::critical" tag on it.

      Edited by Jason A. Donenfeld
    • Jason A. Donenfeld mentioned in issue #1507 (closed)

      mentioned in issue #1507 (closed)

    • Jason A. Donenfeld changed title from GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5 to GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7

      changed title from GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5 to GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7

    • Jason A. Donenfeld changed the description

      changed the description

    • bprakash added priority::high severity::critical labels

      added priority::high severity::critical labels

    • Jason A. Donenfeld changed title from GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7 to GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7,5.6.2

      changed title from GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7 to GPU HANG: ecode 9:0:00000000 - coffee lake, 5.6-rc5,rc6,rc7,5.6.2

    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      @ickle It happened again. How many of these do you need in order to take it seriously?

      [19280.824298] Asynchronous wait on fence 0000:00:02.0:kwin_x11[1168]:565c0 timed out (hint:intel_atomic_commit_ready+0x0/0x54)
[19285.732156] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19285.732158] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[19285.732159] Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.
[19285.732159] Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.
[19285.732160] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[19285.732160] The GPU crash dump is required to analyze GPU hangs, so please always attach it.
[19285.732161] GPU crash dump saved to /sys/class/drm/card0/error
[19285.732166] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[19300.668824] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19300.668831] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[19315.598487] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19315.598492] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[19330.745365] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19330.745370] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[19345.678496] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19345.678500] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[19358.693374] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19358.693489] i915 0000:00:02.0: Resetting bcs0 for stopped heartbeat on bcs0
[19360.613352] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19360.613494] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0
[19375.760100] i915 0000:00:02.0: GPU HANG: ecode 9:0:00000000
[19375.760243] i915 0000:00:02.0: Resetting rcs0 for stopped heartbeat on rcs0

      With the card error being:

      GPU HANG: ecode 9:0:00000000
Kernel: 5.6.2+ x86_64
Driver: 20200114
Time: 1586054145 s 459624 us
Boottime: 24584 s 856982 us
Uptime: 3503 s 379677 us
Capture: 4300662912 jiffies; 110070 ms ago
Reset count: 0
Suspend count: 2
Platform: COFFEELAKE
Subplatform: 0x0
PCI ID: 0x3e9b
PCI Revision: 0x02
PCI Subsystem: 17aa:229f
IOMMU enabled?: 1
DMC loaded: yes
DMC fw version: 1.4
RPM wakelock: yes
PM suspended: no
GT awake: yes
EIR: 0x00000000
IER: 0x08080000
GTIER[0]: 0x01010101
GTIER[1]: 0x01010101
GTIER[2]: 0x80000070
GTIER[3]: 0x00000101
PGTBL_ER: 0x00000000
FORCEWAKE: 0x00010001
DERRMR: 0x2077efef
  fence[0] = 7fa307706000001
  fence[1] = 551b07703500001
  fence[2] = 9fdb07707fc0001
  fence[3] = e05b0770c040001
  fence[4] = 00000000
  fence[5] = 00000000
  fence[6] = 30b100702fb2003
  fence[7] = 34d901f030da003
  fence[8] = 00000000
  fence[9] = 00000000
  fence[10] = 00000000
  fence[11] = 00000000
  fence[12] = 00000000
  fence[13] = 00000000
  fence[14] = 00000000
  fence[15] = 00000000
  fence[16] = 00000000
  fence[17] = 00000000
  fence[18] = 00000000
  fence[19] = 00000000
  fence[20] = 00000000
  fence[21] = 00000000
  fence[22] = 00000000
  fence[23] = 00000000
  fence[24] = 00000000
  fence[25] = 00000000
  fence[26] = 00000000
  fence[27] = 00000000
  fence[28] = 00000000
  fence[29] = 00000000
  fence[30] = 00000000
  fence[31] = 00000000
ERROR: 0x00000000
DONE_REG: 0xebfff1ff
FAULT_TLB_DATA: 0x00000018 0x4421a0b2
GTT_CACHE_EN: 0xf0007fff
GuC firmware: i915/kbl_guc_33.0.0.bin
	status: RUNNING
	version: wanted 33.0, found 33.0
	uCode: 182528 bytes
	RSA: 256 bytes
HuC firmware: i915/kbl_huc_4.0.0.bin
	status: RUNNING
	version: wanted 4.0, found 4.0
	uCode: 225664 bytes
	RSA: 256 bytes
global --- GuC log buffer = 0x00000000 000c8000
:cL%-H5f+!S2UDU=Jco`r_d$BVf*/Yj6l0i/0Lu5^;+*Al3(a<R&f4sVRYn6Rg"DP_=f,[n8!f9T.)@92,NR$3fQ>XQ46lK?!;Cpos$-Pa4Y?I>Il$%prr1U6ca&2G!!!#"zzzzzzzM`/?.T0gd\4C[mjaE*Os<S_V6n%PlG!!!!$zzzzzzzzJ,fQLF_@9u!!#e@
Num Pipes: 3
Pipe [0]:
  Power: on
  SRC: 0eff086f
  STAT: 00000000
Plane [0]:
  CNTR: c4042400
  STRIDE: 0000001e
  SURF: 07fc0000
  TILEOFF: 00000000
Cursor [0]:
  CNTR: 04000027
  POS: 06420b9a
  BASE: 00040000
Pipe [1]:
  Power: off
  SRC: 00000000
  STAT: 00000000
Plane [1]:
  CNTR: 00000000
  STRIDE: 00000000
  SURF: 00000000
  TILEOFF: 00000000
Cursor [1]:
  CNTR: 00000000
  POS: 00000000
  BASE: 00000000
Pipe [2]:
  Power: off
  SRC: 00000000
  STAT: 00000000
Plane [2]:
  CNTR: 00000000
  STRIDE: 00000000
  SURF: 00000000
  TILEOFF: 00000000
Cursor [2]:
  CNTR: 00000000
  POS: 00000000
  BASE: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: A
  Power: off
  CONF: 00000000
  HTOTAL: 00000000
  HBLANK: 00000000
  HSYNC: 00000000
  VTOTAL: 00000000
  VBLANK: 00000000
  VSYNC: 00000000
CPU transcoder: EDP
  Power: on
  CONF: c0000000
  HTOTAL: 0f9f0eff
  HBLANK: 0f9f0eff
  HSYNC: 0f4f0f2f
  VTOTAL: 08ad086f
  VBLANK: 08ad086f
  VSYNC: 08770872
engines: 47
gen: 9
gt: 2
iommu: enabled
memory-regions: 5
page-sizes: 11000
platform: COFFEELAKE
ppgtt-size: 48
ppgtt-type: 2
is_mobile: no
is_lp: no
require_force_probe: no
is_dgfx: no
has_64bit_reloc: yes
gpu_reset_clobbers_display: no
has_reset_engine: yes
has_fpga_dbg: yes
has_global_mocs: no
has_gt_uc: yes
has_l3_dpf: no
has_llc: yes
has_logical_ring_contexts: yes
has_logical_ring_elsq: no
has_logical_ring_preemption: yes
has_pooled_eu: no
has_rc6: yes
has_rc6p: no
has_rps: yes
has_runtime_pm: yes
has_snoop: no
has_coherent_ggtt: yes
unfenced_needs_alignment: no
hws_needs_physical: no
cursor_needs_physical: no
has_csr: yes
has_ddi: yes
has_dp_mst: yes
has_dsb: no
has_dsc: no
has_fbc: yes
has_gmch: no
has_hdcp: yes
has_hotplug: yes
has_ipc: yes
has_modular_fia: no
has_overlay: no
has_psr: yes
overlay_needs_physical: no
supports_tv: no
slice total: 1, mask=0001
subslice total: 3
slice0: 3 subslices, mask=00000007
slice1: 0 subslices, mask=00000000
slice2: 0 subslices, mask=00000000
EU total: 24
EU per subslice: 8
has slice power gating: no
has subslice power gating: no
has EU power gating: yes
CS timestamp frequency: 12000 kHz
slice0: 3 subslice(s) (0x00000007):
	subslice0: 8 EUs (0xff)
	subslice1: 8 EUs (0xff)
	subslice2: 8 EUs (0xff)
	subslice3: 0 EUs (0x0)
slice1: 0 subslice(s) (0x00000000):
	subslice0: 0 EUs (0x0)
	subslice1: 0 EUs (0x0)
	subslice2: 0 EUs (0x0)
	subslice3: 0 EUs (0x0)
slice2: 0 subslice(s) (0x00000000):
	subslice0: 0 EUs (0x0)
	subslice1: 0 EUs (0x0)
	subslice2: 0 EUs (0x0)
	subslice3: 0 EUs (0x0)
Has logical contexts? yes
scheduler: 1f
i915.vbt_firmware=(null)
i915.modeset=-1
i915.lvds_channel_mode=0
i915.panel_use_ssc=-1
i915.vbt_sdvo_panel_type=-1
i915.enable_dc=-1
i915.enable_fbc=1
i915.enable_psr=-1
i915.disable_power_well=1
i915.enable_ips=1
i915.invert_brightness=0
i915.enable_guc=2
i915.guc_log_level=-1
i915.guc_firmware_path=(null)
i915.huc_firmware_path=(null)
i915.dmc_firmware_path=(null)
i915.mmio_debug=0
i915.edp_vswing=0
i915.reset=3
i915.inject_probe_failure=0
i915.fastboot=-1
i915.enable_dpcd_backlight=0
i915.force_probe=
i915.fake_lmem_start=0
i915.alpha_support=no
i915.enable_hangcheck=yes
i915.prefault_disable=no
i915.load_detect_test=no
i915.force_reset_modeset_test=no
i915.error_capture=yes
i915.disable_display=no
i915.verbose_state_checks=yes
i915.nuclear_pageflip=no
i915.enable_dp_mst=yes
i915.enable_gvt=no
    • SAI NANDAN
      SAI NANDAN @ysainan ·
      Reporter

      Hi Reporter, please confirm if this issue is still seen on latest kernel also.

      If yes, provide the steps to reproduce it for further debugging.

    • Mahesh Meena removed severity::critical label

      removed severity::critical label

    • Mahesh Meena added severity::major label

      added severity::major label

    • Mahesh Meena
      Mahesh Meena @maheshmeena ·
      Reporter

      Reduced the severity:critical to severity:major. As not seen any latest repro update from reporter.

    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      Probably shouldn't be demoted to major. I've seen this in 5.10. Can you re-up the severity?

    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author 
      Jan 28 21:51:55 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for preemption time out
Jan 28 21:51:55 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:85dffffb, in plasmashell [969]
Jan 28 21:51:55 thinkpad kernel: GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
Jan 28 21:51:55 thinkpad kernel: Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.
Jan 28 21:51:55 thinkpad kernel: Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.
Jan 28 21:51:55 thinkpad kernel: drm/i915 developers can then reassign to the right component if it's not a kernel issue.
Jan 28 21:51:55 thinkpad kernel: The GPU crash dump is required to analyze GPU hangs, so please always attach it.
Jan 28 21:51:55 thinkpad kernel: GPU crash dump saved to /sys/class/drm/card0/error
Jan 28 21:51:55 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for CS error
Jan 28 21:51:55 thinkpad kernel: i915 0000:00:02.0: [drm] plasmashell[969] context reset due to GPU hang
Jan 28 21:51:55 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:d9d864dd, in plasmashell [969]
Jan 28 21:51:56 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for preemption time out
Jan 28 21:51:56 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for CS error
Jan 28 21:51:56 thinkpad kernel: i915 0000:00:02.0: [drm] plasmashell[969] context reset due to GPU hang
Jan 28 21:51:56 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:85dffffb, in plasmashell [969]
Jan 28 21:51:56 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:d9d8e4dd, in plasmashell [969]
Jan 28 21:51:57 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for preemption time out
Jan 28 21:51:57 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for CS error
Jan 28 21:51:57 thinkpad kernel: i915 0000:00:02.0: [drm] plasmashell[969] context reset due to GPU hang
Jan 28 21:51:57 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:85dffffb, in plasmashell [969]
Jan 28 21:51:57 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:d9d8e4dd, in plasmashell [969]
Jan 28 21:51:57 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for preemption time out
Jan 28 21:51:58 thinkpad kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for CS error
Jan 28 21:51:58 thinkpad kernel: i915 0000:00:02.0: [drm] plasmashell[969] context reset due to GPU hang
Jan 28 21:51:58 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:85dffffb, in plasmashell [969]
Jan 28 21:51:58 thinkpad kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:d9d8e4dd, in plasmashell [969]
    • Mahesh Meena added severity::critical label

      added severity::critical label

    • Mahesh Meena removed severity::major label

      removed severity::major label

    • Hardik Patel
      Hardik Patel @hardikdx ·
      Reporter

      Can you please share me steps to reproduce issue? When are you observing GPU HANG?

    • Jason A. Donenfeld
      Jason A. Donenfeld @zx2c4 ·
      Author

      It happens somewhat randomly, and I can't induce it, though it's frequent enough that I'll hit it eventually.

    • Hardik Patel
      Hardik Patel @hardikdx ·
      Reporter

      @zx2c4 Are you running anything or is it in IDLE state? Can you please share in details like what are the tasks / application / tests you are performing and when are you observing an issue? Can you please share BIOS details, OS version and driver details?

    • Hardik Patel
      Hardik Patel @hardikdx ·
      Reporter

      Hi @zx2c4

      Can you please provide me details as I asked in my previous comment? Have you checked behavior with latest driver?

    • Hardik Patel
      Hardik Patel @hardikdx ·
      Reporter

      Hi @zx2c4,

      Can you please provide the details and confirm whether you are able to see this issue any more? I will close this case in case if you do not respond in two days. Requesting you to kindly update on this issue.

    • ravi teja
      ravi teja @raviteja ·
      Reporter

      @zx2c4 Issue still reproducing on latest drm-tip?

    Please register or sign in to reply