Thinking more about it, can you try the attached patch? Thanks, Christian. Am 17.08.2017 um 11:27 schrieb Christian König: > Not the slightest idea, but you are not the first one complaining > about problems. > > How do you trigger that? > > Christian. > > Am 17.08.2017 um 03:16 schrieb Dave Airlie: >> I'm seeing this go past a fair bit. >> >> Dave. >> >> [ 3640.825412] BUG: sleeping function called from invalid context at >> /home/airlied/devel/kernel/linux-2.6/kernel/locking/mutex.c:979 >> [ 3640.825415] in_atomic(): 1, irqs_disabled(): 0, pid: 2733, name: >> deqp-vk >> [ 3640.825416] INFO: lockdep is turned off. >> [ 3640.825419] CPU: 5 PID: 2733 Comm: deqp-vk Tainted: G W >> 4.12.0+ #225 >> [ 3640.825420] Hardware name: To be filled by O.E.M. To be filled by >> O.E.M./M5A97 R2.0, BIOS 2603 06/26/2015 >> [ 3640.825422] Call Trace: >> [ 3640.825428] dump_stack+0x68/0x92 >> [ 3640.825430] ___might_sleep+0x1e9/0x1fc >> [ 3640.825433] __might_sleep+0x68/0x6f >> [ 3640.825435] ww_mutex_lock+0x20/0x4e >> [ 3640.825443] ttm_bo_unref+0x252/0x43f [ttm] >> [ 3640.825507] amdgpu_bo_unref+0x22/0x34 [amdgpu] >> [ 3640.825543] amdgpu_vm_free_levels+0x26/0x59 [amdgpu] >> [ 3640.825578] amdgpu_vm_free_levels+0x57/0x59 [amdgpu] >> [ 3640.825614] amdgpu_vm_fini+0x1c6/0x212 [amdgpu] >> [ 3640.825650] ? amdgpu_vm_bo_rmv+0x21b/0x280 [amdgpu] >> [ 3640.825684] amdgpu_driver_postclose_kms+0x157/0x1d9 [amdgpu] >> [ 3640.825701] drm_release+0x28e/0x30f [drm] >> [ 3640.825704] __fput+0x100/0x1bb >> [ 3640.825706] ____fput+0x9/0xb >> [ 3640.825708] task_work_run+0x72/0x9b >> [ 3640.825711] do_exit+0x4f3/0xab1 >> [ 3640.825713] ? lock_acquire+0x125/0x1b9 >> [ 3640.825716] do_group_exit+0x45/0xb0 >> [ 3640.825718] get_signal+0x6e1/0x77f >> [ 3640.825722] do_signal+0x23/0x546 >> [ 3640.825724] ? __send_signal+0x2df/0x70c >> [ 3640.825727] ? trace_hardirqs_on+0xd/0xf >> [ 3640.825729] ? force_sig_info+0xc0/0xcf >> [ 3640.825732] exit_to_usermode_loop+0x39/0x7b >> [ 3640.825734] prepare_exit_to_usermode+0x3c/0x51 >> [ 3640.825736] retint_user+0x8/0x1d >> [ 3640.825738] RIP: 0033:0x7f8885f25f8f >> [ 3640.825739] RSP: 002b:00007fffffffce90 EFLAGS: 00000206 >> [ 3640.825742] RAX: 0000000002244400 RBX: 00007fffffffd140 RCX: >> 00000000024e9950 >> [ 3640.825743] RDX: 00000000024e9800 RSI: 00000000024e9950 RDI: >> 0000000002244400 >> [ 3640.825744] RBP: 00007fffffffcf20 R08: 0000000000000001 R09: >> 0000000002244400 >> [ 3640.825745] R10: 00000000024e9940 R11: 0000000000000100 R12: >> 0000000000000000 >> [ 3640.825746] R13: 0000000002244400 R14: 0000000000000009 R15: >> 0000000000000001 >> _______________________________________________ >> amd-gfx mailing list >> amd-gfx at lists.freedesktop.org >> https://lists.freedesktop.org/mailman/listinfo/amd-gfx > > > _______________________________________________ > amd-gfx mailing list > amd-gfx at lists.freedesktop.org > https://lists.freedesktop.org/mailman/listinfo/amd-gfx -------------- next part -------------- A non-text attachment was scrubbed... Name: 0001-drm-ttm-use-reservation_object_trylock-in-ttm_bo_ind.patch Type: text/x-patch Size: 1190 bytes Desc: not available URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20170817/b1952f1b/attachment.bin>
