Bug 90035

Summary: [BSW]igt/gem_concurrent_blit sporadically causes system hang
Product: DRI Reporter: lu hua <huax.lu>
Component: DRM/IntelAssignee: Intel GFX Bugs mailing list <intel-gfx-bugs>
Status: CLOSED FIXED QA Contact: Intel GFX Bugs mailing list <intel-gfx-bugs>
Severity: normal    
Priority: highest CC: eero.t.tamminen, intel-gfx-bugs, valtteri.rantala
Version: unspecified   
Hardware: All   
OS: Linux (All)   
Whiteboard:
i915 platform: i915 features:
Attachments:
Description Flags
dmesg none

Description lu hua 2015-04-15 06:51:24 UTC 
Created attachment 115075 [details]
dmesg

==System Environment==
--------------------------
Regression: not sure, it's random and disable in old testing

Non-working platforms: BSW

==kernel==
--------------------------
drm-intel-nightly/5ea91de4ff45adb60031853d64314c3405378fbd
commit 5ea91de4ff45adb60031853d64314c3405378fbd
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Tue Apr 14 20:00:06 2015 +0200

    drm-intel-nightly: 2015y-04m-14d-17h-59m-22s UTC integration manifest

==Bug detailed description==
-----------------------------
It sporadically causes system hang.Fail rate: ~1/15.
for ((i=1;i<=30;i++));do ./gem_concurrent_blit --run-subtest cpu-blt-early-read-forked  ; done, it happens on the 10th cycle.

output:
IGT-Version: 1.10-g9fd6e07 (x86_64) (Linux: 4.0.0_drm-intel-nightly_5ea91d_20150415+ x86_64)
using 2x512 buffers, each 1MiB

dmesg:
[  151.525863] BUG: unable to handle kernel paging request at 0000000073b0311a
[  151.609694] IP: [<ffffffff8105c24a>] task_waking_fair+0x58/0x59
[  151.680876] PGD 2fc3067 PUD 0 
[  151.717730] Oops: 0002 [#1] SMP 
[  151.756671] Modules linked in: dm_mod snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic iTCO_wdt iTCO_vendor_support snd_hda_intel snd_hda_controller snd_hda_codec snd_hda_core snd_hwdep snd_pcm pcspkr serio_raw i2c_i801 lpc_ich mfd_core snd_timer snd soundcore battery ac acpi_cpufreq i915 button video drm_kms_helper drm
[  152.114768] CPU: 3 PID: 4738 Comm: gem_concurrent_ Tainted: G        W       4.0.0_drm-intel-nightly_5ea91d_20150415+ #1272
[  152.248445] task: ffff880002d328f0 ti: ffff880002f7c000 task.ti: ffff880002f7c000
[  152.338295] RIP: 0010:[<ffffffff8105c24a>]  [<ffffffff8105c24a>] task_waking_fair+0x58/0x59
[  152.438685] RSP: 0018:ffff880002f7fc30  EFLAGS: 00010002
[  152.502449] RAX: 00000000084d33e5 RBX: 0000000000000000 RCX: 00000000fffdae3b
[  152.588121] RDX: 00000000fffdad37 RSI: 00000000fffdaa53 RDI: ffff88017a3649b0
[  152.673791] RBP: 000000004a63de82 R08: ffffea0005dcdc00 R09: 0000000000016480
[  152.759463] R10: 0000000000000000 R11: ffffffffa0095e70 R12: ffff88017a365012
[  152.845133] R13: 0000000000000003 R14: ffff88017a3649b0 R15: 0000000000000000
[  152.930807] FS:  00007f35bb27f8c0(0000) GS:ffff88017fd80000(0000) knlGS:0000000000000000
[  153.027956] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[  153.096930] CR2: 0000000073b0311a CR3: 0000000076652000 CR4: 00000000001006e0
[  153.182603] Stack:
[  153.206712]  ffffffff81059148 ffff8800765b4108 0000000000000246 ffff880076492a00
[  153.295945]  ffff8801754a3060 0000000000000000 ffff880177370800 ffff8800764bc800
[  153.385185]  ffff8800765d1340 0000000000000000 ffffffff81799875 ffff880177370800
[  153.474420] Call Trace:
[  153.503754]  [<ffffffff81059148>] ? try_to_wake_up+0x10a/0x243
[  153.573784]  [<ffffffff81799875>] ? __mutex_unlock_slowpath+0x29/0x2f
[  153.651144]  [<ffffffffa0095e7e>] ? i915_gem_do_execbuffer.isra.13+0xd24/0xd88 [i915]
[  153.745210]  [<ffffffffa00a1345>] ? i915_gem_pwrite_ioctl+0x75a/0x7e0 [i915]
[  153.829843]  [<ffffffff81799233>] ? __mutex_lock_interruptible_slowpath+0x21/0xfc
[  153.919696]  [<ffffffff8110948a>] ? __kmalloc+0x65/0x13d
[  153.983490]  [<ffffffffa0096e95>] ? i915_gem_execbuffer2+0x16e/0x205 [i915]
[  154.067094]  [<ffffffffa00047ae>] ? drm_ioctl+0x322/0x38d [drm]
[  154.138185]  [<ffffffffa0096d27>] ? i915_gem_execbuffer+0x339/0x339 [i915]
[  154.220733]  [<ffffffff8105ede9>] ? set_next_entity+0x32/0x55
[  154.289715]  [<ffffffff81060a23>] ? pick_next_task_fair+0xe5/0x3dc
[  154.363917]  [<ffffffff8111daa6>] ? do_vfs_ioctl+0x360/0x424
[  154.431854]  [<ffffffff81798592>] ? __schedule+0x589/0x7c9
[  154.497705]  [<ffffffff8104fad2>] ? task_work_run+0x84/0x96
[  154.564598]  [<ffffffff8111dbb3>] ? SyS_ioctl+0x49/0x7a
[  154.627318]  [<ffffffff8179b0f2>] ? system_call_fastpath+0x12/0x17

==Reproduce steps==
---------------------------- 
1. run ./gem_concurrent_blit --run-subtest cpu-blt-early-read-forked 30 cycles
Comment 1 Gavin Hindman 2015-05-04 16:24:50 UTC 
Is this failure occurring regularly, or just the one time?
Comment 2 lu hua 2015-05-05 07:11:38 UTC 
(In reply to Gavin Hindman from comment #1)
> Is this failure occurring regularly, or just the one time?

It's intermittent. I retest it on the latest drm-inel-nightly kernel and the latest igt, it happens at the 7th cycles.
As comment 0, run it 15 cycles, it occurs once.
Comment 3 Ander Conselvan de Oliveira 2015-05-05 09:23:51 UTC 
The dmesg output is truncated. Can you produce another one with the logs leading to the issue?
Comment 4 lu hua 2015-05-07 08:04:05 UTC 
(In reply to Ander Conselvan de Oliveira from comment #3)
> The dmesg output is truncated. Can you produce another one with the logs
> leading to the issue?

I get this dmesg via serial port.
I try to get dmesg via netconsole: 1. our usb network card doesn't support netconsole. 2. plug pci card, system will reboot.
Comment 5 lu hua 2015-05-22 05:11:53 UTC 
Test on the latest drm-intel-nightly kernel.
Run sub cases cpu-blt-early-read-forked, gtt-blt-overwrite-source-read-rcs-forked and prw-blt-intermix-bcs-forked 50 cycles. I don't see  hang. Close it.
Comment 6 lu hua 2015-05-22 05:12:29 UTC 
Verified.Fixed.
Comment 7 Elizabeth 2017-10-06 14:30:34 UTC 
Closing old verified.

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.