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
Is this failure occurring regularly, or just the one time?
(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.
The dmesg output is truncated. Can you produce another one with the logs leading to the issue?
(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.
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.
Verified.Fixed.
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.