| Summary: | [SKL] GPU HANG: ecode 9:0:0x87f99ff9, in Talos [29014], reason: Ring hung, action: reset | ||
|---|---|---|---|
| Product: | Mesa | Reporter: | Armin K <krejzi> |
| Component: | Drivers/DRI/i965 | Assignee: | Intel 3D Bugs Mailing List <intel-3d-bugs> |
| Status: | RESOLVED WORKSFORME | QA Contact: | Intel 3D Bugs Mailing List <intel-3d-bugs> |
| Severity: | normal | ||
| Priority: | medium | CC: | gary.c.wang, intel-gfx-bugs |
| Version: | 12.0 | ||
| Hardware: | x86-64 (AMD64) | ||
| OS: | Linux (All) | ||
| Whiteboard: | |||
| i915 platform: | SKL | i915 features: | GPU hang |
| Attachments: | Error log | ||
Assigning to Mesa product. From this error dump, hung is happening in render ring batch with active head at 0xdc42cc8c, with 0x78260000 (3DSTATE_BINDING_TABLE_POINTERS_VS) as IPEHR. Batch extract (around 0xdc42cc8c): 0xdc42cc58: 0x78170009: 3D UNKNOWN: 3d_965 opcode = 0x7817 0xdc42cc5c: 0x00000000: MI_NOOP 0xdc42cc60: 0x00000007: MI_NOOP 0xdc42cc64: 0x00000000: MI_NOOP 0xdc42cc68: 0x00000000: MI_NOOP 0xdc42cc6c: 0x00000000: MI_NOOP 0xdc42cc70: 0x00000000: MI_NOOP 0xdc42cc74: 0xdc42fde0: UNKNOWN 0xdc42cc78: 0x00000000: MI_NOOP 0xdc42cc7c: 0x00000000: MI_NOOP 0xdc42cc80: 0x00000000: MI_NOOP 0xdc42cc84: 0x78260000: 3DSTATE_BINDING_TABLE_POINTERS_VS 0xdc42cc88: 0x00000000: dword 1 0xdc42cc8c: 0x782a0000: 3DSTATE_BINDING_TABLE_POINTERS_PS 0xdc42cc90: 0x00004dc0: dword 1 0xdc42cc94: 0x78500003: 3D UNKNOWN: 3d_965 opcode = 0x7850 Can you try mesa-13.0.0? If you can reproduce, please capture and upload an apitrace (https://github.com/apitrace/apitrace) so that we can easily reproduce as well. After half a hour of gameplay on mesa-13.0.0 and kernel-4.8.6, I could not reproduce the issue. Thank you for testing. Please reopen if you discover the hang is still present. |
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.
Created attachment 124479 [details] Error log While playing The Talos Principle, my GPU was hung several times. Linux 4.6.2, xorg-server-1.18.3, GNOME 3.20, xf86-video-intel git ccs May 13th w/ UXA + DRI3 OpenGL vendor string: Intel Open Source Technology Center OpenGL renderer string: Mesa DRI Intel(R) HD Graphics 520 (Skylake GT2) OpenGL core profile version string: 4.3 (Core Profile) Mesa 12.0.0-rc2 (git-a7649ab) OpenGL core profile shading language version string: 4.30 Relevant parts from dmesg: [18745.295358] [drm] stuck on render ring [18745.297107] [drm] GPU HANG: ecode 9:0:0x87f99ff9, in Talos [29014], reason: Ring hung, action: reset [18745.297108] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace. [18745.297109] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel [18745.297110] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue. [18745.297110] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it. [18745.297111] [drm] GPU crash dump saved to /sys/class/drm/card0/error [18745.297133] ------------[ cut here ]------------ [18745.297142] WARNING: CPU: 2 PID: 31435 at drivers/gpu/drm/i915/intel_display.c:11385 intel_mmio_flip_work_func+0x6d/0x361 [18745.297142] WARN_ON(__i915_wait_request(mmio_flip->req, mmio_flip->crtc->reset_counter, false, ((void *)0), &mmio_flip->i915->rps.mmioflips)) [18745.297144] Modules linked in: [18745.297147] CPU: 2 PID: 31435 Comm: kworker/2:3 Not tainted 4.6.2-krejzi #1 [18745.297148] Hardware name: HP HP ProBook 470 G3/8102, BIOS N78 Ver. 01.07 01/25/2016 [18745.297151] Workqueue: events intel_mmio_flip_work_func [18745.297153] 0000000000000286 00000000aad189d1 ffffffff8127aef0 ffff8801d031bda0 [18745.297155] 0000000000000000 ffffffff8109c9fd ffff88000d5f89c0 ffff8801d031be00 [18745.297157] ffff8800788ac340 ffff8800788ac340 ffff880260498300 0000000000000000 [18745.297159] Call Trace: [18745.297162] [<ffffffff8127aef0>] ? dump_stack+0x46/0x59 [18745.297165] [<ffffffff8109c9fd>] ? __warn+0xc8/0xe1 [18745.297182] [<ffffffff8109ca6b>] ? warn_slowpath_fmt+0x55/0x71 [18745.297184] [<ffffffff813cb3dc>] ? intel_mmio_flip_work_func+0x6d/0x361 [18745.297186] [<ffffffff810aee1a>] ? process_one_work+0x139/0x1d4 [18745.297187] [<ffffffff810af38d>] ? worker_thread+0x1d6/0x2a1 [18745.297188] [<ffffffff810af1b7>] ? rescuer_thread+0x2db/0x2db [18745.297190] [<ffffffff810b2ffa>] ? kthread+0xa5/0xad [18745.297193] [<ffffffff81746902>] ? ret_from_fork+0x22/0x40 [18745.297194] [<ffffffff810b2f55>] ? init_completion+0x1d/0x1d [18745.297196] ---[ end trace f640bd76551d7fd9 ]--- [18745.299397] drm/i915: Resetting chip after gpu hang [18747.295538] [drm] RC6 on [20047.296499] [drm] stuck on render ring [20047.298633] [drm] GPU HANG: ecode 9:0:0x85dfdfff, in Talos [29014], reason: Ring hung, action: reset [20047.298673] ------------[ cut here ]------------ [20047.298680] WARNING: CPU: 3 PID: 31948 at drivers/gpu/drm/i915/intel_display.c:11385 intel_mmio_flip_work_func+0x6d/0x361 [20047.298681] WARN_ON(__i915_wait_request(mmio_flip->req, mmio_flip->crtc->reset_counter, false, ((void *)0), &mmio_flip->i915->rps.mmioflips)) [20047.298682] Modules linked in: [20047.298686] CPU: 3 PID: 31948 Comm: kworker/3:1 Tainted: G W 4.6.2-krejzi #1 [20047.298687] Hardware name: HP HP ProBook 470 G3/8102, BIOS N78 Ver. 01.07 01/25/2016 [20047.298690] Workqueue: events intel_mmio_flip_work_func [20047.298692] 0000000000000286 00000000483fccf9 ffffffff8127aef0 ffff880114317da0 [20047.298695] 0000000000000000 ffffffff8109c9fd ffff8800021e4540 ffff880114317e00 [20047.298697] ffff880216f6e540 ffff880216f6e540 ffff8802604d8300 0000000000000000 [20047.298699] Call Trace: [20047.298704] [<ffffffff8127aef0>] ? dump_stack+0x46/0x59 [20047.298707] [<ffffffff8109c9fd>] ? __warn+0xc8/0xe1 [20047.298710] [<ffffffff8109ca6b>] ? warn_slowpath_fmt+0x55/0x71 [20047.298712] [<ffffffff813cb3dc>] ? intel_mmio_flip_work_func+0x6d/0x361 [20047.298730] [<ffffffff810aee1a>] ? process_one_work+0x139/0x1d4 [20047.298731] [<ffffffff810af38d>] ? worker_thread+0x1d6/0x2a1 [20047.298733] [<ffffffff810af1b7>] ? rescuer_thread+0x2db/0x2db [20047.298735] [<ffffffff810b2ffa>] ? kthread+0xa5/0xad [20047.298738] [<ffffffff81746902>] ? ret_from_fork+0x22/0x40 [20047.298740] [<ffffffff810b2f55>] ? init_completion+0x1d/0x1d [20047.298742] ---[ end trace f640bd76551d7fda ]--- [20047.300546] drm/i915: Resetting chip after gpu hang [20049.300603] [drm] RC6 on [21947.299985] [drm] stuck on render ring [21947.301838] [drm] GPU HANG: ecode 9:0:0x86dfdff9, in Talos [29014], reason: Ring hung, action: reset [21947.302017] ------------[ cut here ]------------ [21947.302023] WARNING: CPU: 2 PID: 32564 at drivers/gpu/drm/i915/intel_display.c:11385 intel_mmio_flip_work_func+0x6d/0x361 [21947.302024] WARN_ON(__i915_wait_request(mmio_flip->req, mmio_flip->crtc->reset_counter, false, ((void *)0), &mmio_flip->i915->rps.mmioflips)) [21947.302025] Modules linked in: [21947.302028] CPU: 2 PID: 32564 Comm: kworker/2:0 Tainted: G W 4.6.2-krejzi #1 [21947.302029] Hardware name: HP HP ProBook 470 G3/8102, BIOS N78 Ver. 01.07 01/25/2016 [21947.302032] Workqueue: events intel_mmio_flip_work_func [21947.302033] 0000000000000286 00000000902982bb ffffffff8127aef0 ffff880003883da0 [21947.302035] 0000000000000000 ffffffff8109c9fd ffff880225e1fc00 ffff880003883e00 [21947.302037] ffff8801451c1f40 ffff8801451c1f40 ffff880260498300 0000000000000000 [21947.302039] Call Trace: [21947.302043] [<ffffffff8127aef0>] ? dump_stack+0x46/0x59 [21947.302045] [<ffffffff8109c9fd>] ? __warn+0xc8/0xe1 [21947.302047] [<ffffffff8109ca6b>] ? warn_slowpath_fmt+0x55/0x71 [21947.302049] [<ffffffff813cb3dc>] ? intel_mmio_flip_work_func+0x6d/0x361 [21947.302051] [<ffffffff810aee1a>] ? process_one_work+0x139/0x1d4 [21947.302052] [<ffffffff810af38d>] ? worker_thread+0x1d6/0x2a1 [21947.302053] [<ffffffff810af1b7>] ? rescuer_thread+0x2db/0x2db [21947.302055] [<ffffffff810b2ffa>] ? kthread+0xa5/0xad [21947.302058] [<ffffffff81746902>] ? ret_from_fork+0x22/0x40 [21947.302059] [<ffffffff810b2f55>] ? init_completion+0x1d/0x1d [21947.302060] ---[ end trace f640bd76551d7fdb ]--- [21947.303921] drm/i915: Resetting chip after gpu hang [21949.296001] [drm] RC6 on Attached is the mentioned error file