Bug 91452 - [HSW] stuck on render ring, WARN_ON(__i915_wait_request(…))
Summary: [HSW] stuck on render ring, WARN_ON(__i915_wait_request(…))
Status: CLOSED WORKSFORME
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: XOrg git
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: 2015-07-24 14:21 UTC by Andreas Reis
Modified: 2017-07-24 22:45 UTC (History)
1 user (show)

See Also:
i915 platform: HSW
i915 features: GPU hang


Attachments
/sys/class/drm/card0 (71.00 KB, application/x-xz-compressed-tar)
2015-07-24 14:21 UTC, Andreas Reis
no flags Details
/sys/class/drm/card0/error r2 (72.95 KB, application/x-xz)
2015-07-24 16:42 UTC, Andreas Reis
no flags Details

Note You need to log in before you can comment on or make changes to this bug.
Description Andreas Reis 2015-07-24 14:21:07 UTC
Created attachment 117342 [details]
/sys/class/drm/card0

Haswell 4770, 4.2-rc3 + drm-intel-nightly @ 07.22.15, xserver + xf86 intel git versions

Occurs randomly, this with nothing but browsing with Chromium 46.0.2459.0 (started with --ignore-gpu-blacklist though).

[ 6209.976368] [drm] stuck on render ring
[ 6209.976895] [drm] GPU HANG: ecode 7:0:0x85dffffc, in chromium-dev [29630], reason: Ring hung, action: reset
[ 6209.976896] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[ 6209.976896] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[ 6209.976897] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[ 6209.976897] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[ 6209.976898] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[ 6209.976915] ------------[ cut here ]------------
[ 6209.976931] WARNING: CPU: 0 PID: 5475 at drivers/gpu/drm/i915/intel_display.c:11278 intel_mmio_flip_work_func+0x3ac/0x3c0()
[ 6209.976932] WARN_ON(__i915_wait_request(mmio_flip->req, mmio_flip->crtc->reset_counter, false, NULL, &mmio_flip->i915->rps.mmioflips))
[ 6209.976933] Modules linked in:
[ 6209.976934]  
[ 6209.976939] CPU: 0 PID: 5475 Comm: kworker/0:1 Tainted: G        W       4.2.0-1-cu #1
[ 6209.976956] Hardware name: Gigabyte Technology Co., Ltd. G1.Sniper M5/G1.Sniper M5, BIOS T01 02/03/2015
[ 6209.976958] Workqueue: events intel_mmio_flip_work_func
[ 6209.976959]  0000000000000000 00000000dc92c46d ffff880348fa7cd8 ffffffff8193c4aa
[ 6209.976960]  0000000000000000 ffff880348fa7d30 ffff880348fa7d18 ffffffff810e5366
[ 6209.976961]  ffff880348fa7ce8 ffff880348f24f00 ffff880039daf540 ffff88042f21a400
[ 6209.976963] Call Trace:
[ 6209.976966]  [<ffffffff8193c4aa>] dump_stack+0x4c/0x6e
[ 6209.976969]  [<ffffffff810e5366>] warn_slowpath_common+0x86/0xc0
[ 6209.976970]  [<ffffffff810e53f5>] warn_slowpath_fmt+0x55/0x70
[ 6209.976982]  [<ffffffff8162b04c>] intel_mmio_flip_work_func+0x3ac/0x3c0
[ 6209.976984]  [<ffffffff81109d12>] ? finish_task_switch+0x62/0x190
[ 6209.976987]  [<ffffffff810fcc5e>] process_one_work+0x14e/0x440
[ 6209.976988]  [<ffffffff810fcf98>] worker_thread+0x48/0x4a0
[ 6209.976989]  [<ffffffff810fcf50>] ? process_one_work+0x440/0x440
[ 6209.976990]  [<ffffffff810fcf50>] ? process_one_work+0x440/0x440
[ 6209.976991]  [<ffffffff81102838>] kthread+0xd8/0xf0
[ 6209.977009]  [<ffffffff81102760>] ? kthread_worker_fn+0x170/0x170
[ 6209.977010]  [<ffffffff8194321f>] ret_from_fork+0x3f/0x70
[ 6209.977011]  [<ffffffff81102760>] ? kthread_worker_fn+0x170/0x170
[ 6209.977012] ---[ end trace 2b0c2f22f1687665 ]---
[ 6209.979035] drm/i915: Resetting chip after gpu hang
Comment 1 Andreas Reis 2015-07-24 16:40:50 UTC
Another one, this time when opening a Youtube video (vp9) on kernel 4.1.3. Video played fine afterwards.

(With --ignore-gpu-blacklist, Chromium enables all hardware acceleration whereas without, some like video decoding are disabled.)

[ 6616.135895] [drm] stuck on render ring
[ 6616.136576] [drm] GPU HANG: ecode 7:0:0x85dffffc, in chromium-dev [31153], reason: Ring hung, action: reset
[ 6616.136577] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[ 6616.136577] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[ 6616.136578] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[ 6616.136578] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[ 6616.136579] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[ 6616.136611] ------------[ cut here ]------------
[ 6616.136636] WARNING: CPU: 0 PID: 31460 at drivers/gpu/drm/i915/intel_display.c:10007 intel_mmio_flip_work_func+0x30a/0x340 [i915]()
[ 6616.136637] WARN_ON(__i915_wait_request(mmio_flip->req, crtc->reset_counter, false, NULL, NULL) != 0)
[ 6616.136637] Modules linked in:
[ 6616.136638]  
[ 6616.136670] CPU: 0 PID: 31460 Comm: kworker/0:3 Not tainted 4.1.3-1-ARCH #1
[ 6616.136671] Hardware name: Gigabyte Technology Co., Ltd. G1.Sniper M5/G1.Sniper M5, BIOS T01 02/03/2015
[ 6616.136677] Workqueue: events intel_mmio_flip_work_func [i915]
[ 6616.136678]  0000000000000000 000000005f88c409 ffff880118727cd8 ffffffff815866ee
[ 6616.136679]  0000000000000000 ffff880118727d30 ffff880118727d18 ffffffff81078c9a
[ 6616.136681]  ffff880118727ce8 ffff88041b2848b8 ffff88042f215a80 ffff88041b284000
[ 6616.136682] Call Trace:
[ 6616.136686]  [<ffffffff815866ee>] dump_stack+0x4c/0x6e
[ 6616.136688]  [<ffffffff81078c9a>] warn_slowpath_common+0x8a/0xc0
[ 6616.136689]  [<ffffffff81078d25>] warn_slowpath_fmt+0x55/0x70
[ 6616.136697]  [<ffffffffa012d9ea>] intel_mmio_flip_work_func+0x30a/0x340 [i915]
[ 6616.136699]  [<ffffffff8109f5ed>] ? finish_task_switch+0x5d/0x100
[ 6616.136701]  [<ffffffff8109193b>] process_one_work+0x14b/0x470
[ 6616.136702]  [<ffffffff81091ca8>] worker_thread+0x48/0x4c0
[ 6616.136703]  [<ffffffff81091c60>] ? process_one_work+0x470/0x470
[ 6616.136704]  [<ffffffff81091c60>] ? process_one_work+0x470/0x470
[ 6616.136706]  [<ffffffff810977f8>] kthread+0xd8/0xf0
[ 6616.136707]  [<ffffffff81097720>] ? kthread_worker_fn+0x170/0x170
[ 6616.136709]  [<ffffffff8158c3a2>] ret_from_fork+0x42/0x70
[ 6616.136711]  [<ffffffff81097720>] ? kthread_worker_fn+0x170/0x170
[ 6616.136712] ---[ end trace edbdf95da625cbd0 ]---
[ 6616.138754] drm/i915: Resetting chip after gpu hang
[ 6618.200607] ------------[ cut here ]------------
[ 6618.200631] WARNING: CPU: 0 PID: 0 at drivers/gpu/drm/i915/intel_display.c:10098 intel_check_page_flip+0xda/0xf0 [i915]()
[ 6618.200632] Kicking stuck page flip: queued at 396896, now 396900
[ 6618.200632] Modules linked in: 
[ 6618.200663] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G        W       4.1.3-1-ARCH #1
[ 6618.200664] Hardware name: Gigabyte Technology Co., Ltd. G1.Sniper M5/G1.Sniper M5, BIOS T01 02/03/2015
[ 6618.200665]  0000000000000000 b27cae4b982b6f29 ffff88042f203d18 ffffffff815866ee
[ 6618.200666]  0000000000000000 ffff88042f203d70 ffff88042f203d58 ffffffff81078c9a
[ 6618.200667]  ffff88042f203d88 ffff88041b284000 ffff88041cabe800 ffff88041cabe9a0
[ 6618.200669] Call Trace:
[ 6618.200670]  <IRQ>  [<ffffffff815866ee>] dump_stack+0x4c/0x6e
[ 6618.200675]  [<ffffffff81078c9a>] warn_slowpath_common+0x8a/0xc0
[ 6618.200676]  [<ffffffff81078d25>] warn_slowpath_fmt+0x55/0x70
[ 6618.200683]  [<ffffffffa01410ba>] intel_check_page_flip+0xda/0xf0 [i915]
[ 6618.200690]  [<ffffffffa010a52c>] ironlake_irq_handler+0x2ac/0x1000 [i915]
[ 6618.200693]  [<ffffffff810d4d9e>] handle_irq_event_percpu+0x3e/0x1f0
[ 6618.200694]  [<ffffffff810d4f91>] handle_irq_event+0x41/0x70
[ 6618.200696]  [<ffffffff810d811e>] handle_edge_irq+0x9e/0x110
[ 6618.200698]  [<ffffffff810181a2>] handle_irq+0x22/0x40
[ 6618.200700]  [<ffffffff8158eacf>] do_IRQ+0x4f/0xf0
[ 6618.200702]  [<ffffffff8158caee>] common_interrupt+0x6e/0x6e
[ 6618.200703]  <EOI>  [<ffffffff8143fe72>] ? cpuidle_enter_state+0x92/0x240
[ 6618.200706]  [<ffffffff8143fe44>] ? cpuidle_enter_state+0x64/0x240
[ 6618.200707]  [<ffffffff81440057>] cpuidle_enter+0x17/0x20
[ 6618.200708]  [<ffffffff810bccac>] cpu_startup_entry+0x31c/0x450
[ 6618.200710]  [<ffffffff8157ccda>] rest_init+0x8a/0x90
[ 6618.200711]  [<ffffffff818fa021>] start_kernel+0x48e/0x4af
[ 6618.200713]  [<ffffffff818f9120>] ? early_idt_handler_array+0x120/0x120
[ 6618.200714]  [<ffffffff818f9339>] x86_64_start_reservations+0x2a/0x2c
[ 6618.200715]  [<ffffffff818f9485>] x86_64_start_kernel+0x14a/0x16d
[ 6618.200716] ---[ end trace edbdf95da625cbd1 ]---
Comment 2 Andreas Reis 2015-07-24 16:42:54 UTC
Created attachment 117353 [details]
/sys/class/drm/card0/error r2
Comment 3 Andreas Reis 2015-08-20 20:20:08 UTC
This hasn't been occurring as of lately, so feel free to close.
Comment 4 Jani Nikula 2015-08-21 06:40:50 UTC
(In reply to Andreas Reis from comment #3)
> This hasn't been occurring as of lately, so feel free to close.

Thanks for the follow-up, closing.


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.