Bug 90152

Summary: [BSW] Igt/gem_evict_everything subcase mlocked-hang causes oom killer and kernel BUG at drivers/gpu/drm/i915/i915_drv.h:2737!
Product: DRI Reporter: ye.tian <yex.tian>
Component: DRM/IntelAssignee: Intel GFX Bugs mailing list <intel-gfx-bugs>
Status: CLOSED WORKSFORME QA Contact: Intel GFX Bugs mailing list <intel-gfx-bugs>
Severity: normal    
Priority: medium CC: christophe.prigent, intel-gfx-bugs
Version: unspecified   
Hardware: Other   
OS: All   
Whiteboard:
i915 platform: BSW/CHT i915 features: GEM/Other
Attachments:
Description Flags
dmesg info none

Description ye.tian 2015-04-23 06:22:10 UTC 
Created attachment 115284 [details]
dmesg info

==System Environment==       
-----------------------------------------------------
Regression: not sure
Non-working platforms: BSW

==Kernel==
--------------------------------------------------
commit b9fe357740009b89d4bac30b297bfe9808957e6a
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Mon Apr 20 10:28:37 2015 -0700

    drm-intel-nightly: 2015y-04m-20d-17h-28m-16s UTC integration manifest


==Bug detailed description==
--------------------------------------------------
Igt/gem_evict_everything subcase mlocked-hang causes oom killer and kernel BUG at drivers/gpu/drm/i915/i915_drv.h:2737!

==Output==
-----------------------
root@x-bsw08:/GFX/Test/Intel_gpu_tools/intel-gpu-tools/tests# ./gem_evict_everything --run-subtest mlocked-hang
IGT-Version: 1.10-ge1ce5ea (x86_64) (Linux: 4.0.0_drm-intel-nightly_b9fe35_20150421+ x86_64)
child 0 died with signal 11, Segmentation fault
Subtest mlocked-hang failed.
**** DEBUG ****
Checking 1536 surfaces of size 1048576 bytes (total 1611399168) against RAM
Test requirement passed: !(total <= required)
Test requirement passed: !igt_run_in_simulation()
Test requirement passed: pin > sz
Pinning [1472, 3008] MiB
Test requirement passed: locked
****  END  ****
Subtest mlocked-hang: FAIL (9.726s)

^C^C^C^C^C^C^C

==Output dmesg info==
[   98.752676] ------------[ cut here ]------------
[   98.808109] kernel BUG at drivers/gpu/drm/i915/i915_drv.h:2737!
[   98.879173] invalid opcode: 0000 [#1] SMP
[   98.928543] Modules linked in: ipv6 dm_mod snd_hda_codec_hdmi snd_hda_codec_realtek s
nd_hda_codec_generic iTCO_wdt iTCO_vendor_support snd_hda_intel snd_hda_controller snd_h
da_codec snd_hda_core snd_hwdep snd_pcm serio_raw pcspkr i2c_i801 snd_timer lpc_ich snd
mfd_core soundcore battery ac acpi_cpufreq i915 button video drm_kms_helper drm
[   99.291933] CPU: 3 PID: 4306 Comm: gem_evict_every Not tainted 4.0.0_drm-intel-nightl
y_b9fe35_20150421+ #368
[   99.409956] task: ffff8801752e20c0 ti: ffff880002b94000 task.ti: ffff880002b94000
[   99.499798] RIP: 0010:[<ffffffffa009d520>]  [<ffffffffa009d520>] i915_gem_retire_requ
ests_ring+0xb2/0x16b [i915]
[   99.549519] [drm] stuck on render ring
[   99.582018] [drm] GPU HANG: ecode 8:0:0xe75ffffe, in gem_evict_every [4305], reason:
Ring hung, action: reset
[   99.582020] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, incl
uding userspace.
[   99.582021] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI
-> DRM/Intel
[   99.582022] [drm] drm/i915 developers can then reassign to the right component if it'
s not a kernel issue.
[   99.582023] [drm] The gpu crash dump is required to analyze gpu hangs, so please alwa
ys attach it.
[   99.582024] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[   99.582085] [drm:i915_reset_and_wakeup] resetting chip
[  100.364882] RSP: 0018:ffff880002b97c08  EFLAGS: 00010246
[  100.428639] RAX: ffff88007bb66b68 RBX: ffff8801755e4108 RCX: ffff88007bb66b68
[  100.514312] RDX: ffff8801755e4280 RSI: 0000000000000001 RDI: ffff880002a62540
[  100.599984] RBP: 0000000000000000 R08: ffff880002a62600 R09: 0000000000000000
[  100.685654] R10: ffff880178692948 R11: 00000000fffffffa R12: ffff8801755e4280
[  100.771326] R13: ffff88007bb66a80 R14: ffff880002d99d80 R15: 0000000000000003
[  100.857000] FS:  00007f75dc359740(0000) GS:ffff88017fd80000(0000) knlGS:0000000000000
000
[  100.954148] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  101.023122] CR2: 00007f7573e47008 CR3: 0000000002dc1000 CR4: 00000000001006e0
[  101.108796] Stack:
[  101.132904]  ffff880002528000 0000000000000008 ffff880002b97d3e ffff88007ba81000
[  101.222138]  ffff88017541ba40 ffffffffa009508c 0000054e00000202 ffff880178692910
[  101.311370]  ffff880002b97c48 ffff880002b97c48 0000000000000000 ffff880002528000
[  101.400605] Call Trace:
[  101.429970]  [<ffffffffa009508c>] ? i915_gem_execbuffer_reserve+0x25/0x2e3 [i915]
[  101.519850]  [<ffffffffa0095916>] ? i915_gem_do_execbuffer.isra.13+0x5cc/0xd88 [i915]
[  101.613879]  [<ffffffff81104767>] ? alloc_pages_current+0xad/0xca
[  101.687029]  [<ffffffff810e9ea6>] ? kmalloc_order+0x10/0x3d
[  101.753922]  [<ffffffff810e9eef>] ? kmalloc_order_trace+0x1c/0x7e
[  101.827102]  [<ffffffffa0097085>] ? i915_gem_execbuffer2+0x16e/0x205 [i915]
[  101.910700]  [<ffffffffa00047ae>] ? drm_ioctl+0x322/0x38d [drm]
[  101.981792]  [<ffffffffa0096f17>] ? i915_gem_execbuffer+0x339/0x339 [i915]
[  102.064336]  [<ffffffff8111daa6>] ? do_vfs_ioctl+0x360/0x424
[  102.132270]  [<ffffffff810f1870>] ? __mm_populate+0xf6/0x107
[  102.200207]  [<ffffffff8111dbb3>] ? SyS_ioctl+0x49/0x7a
[  102.262927]  [<ffffffff8179b0f2>] ? system_call_fastpath+0x12/0x17
[  102.337123] Code: 00 00 3b 45 18 78 26 4c 89 ef e8 fb e0 ff ff 48 8b 83 78 01 00 00 4
c 39 e0 74 12 48 8b 68 70 4c 8d a8 18 ff ff ff 48 85 ed 75 c5 <0f> 0b 48 8b ab 88 00 00
00 48 85 ed 0f 84 9e 00 00 00 48 8b 45
[  102.570725] RIP  [<ffffffffa009d520>] i915_gem_retire_requests_ring+0xb2/0x16b [i915]
[  102.664882]  RSP <ffff880002b97c08>
[  102.706896] ---[ end trace db48308df63ef1d9 ]---

==Reproduce steps==
----------------------------
1, ./gem_evict_everything --run-subtest mlocked-hang
Comment 1 Jani Nikula 2015-10-28 19:14:07 UTC 
Timeout, closing. Please reopen if the problem persists with latest kernels.

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.