good 285b685a33bea9e5c3d5620597234da8954caf16 black-screen-section = [ 86.642387] amdgpu 0000:01:00.0: GPU fault detected: 146 0x0f68c00c [ 86.642398] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00106FED [ 86.642403] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0A0C000C [ 86.642411] amdgpu 0000:01:00.0: VM fault (0x0c, vmid 5, pasid 32769) at page 1077229, read from 'TC5' (0x54433500) (192) [ 132.234883] amdgpu 0000:01:00.0: IH ring buffer overflow (0x000CDCA0, 0x0000F7F0, 0x0000DCB0) Feb 1 18:24:13 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0010840c Feb 1 18:24:13 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100202 Feb 1 18:24:13 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0408400C Feb 1 18:24:13 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 2, pasid 32769) at page 1049090, read from 'TC10' (0x54433130) (132) Feb 1 18:24:33 ph4 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, last signaled seq=76763, last emitted seq=76765 Feb 1 18:24:33 ph4 kernel: [drm] IP block:gmc_v8_0 is hung! Feb 1 18:24:33 ph4 kernel: [drm] IP block:gfx_v8_0 is hung! Feb 1 18:24:33 ph4 kernel: [drm] GPU recovery disabled. Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0e90c80c Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001075D2 Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x020C800C Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 1, pasid 32769) at page 1078738, read from 'TC3' (0x54433300) (200) Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0e90c00c Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001075D2 Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0200000C Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 1, pasid 32769) at page 1078738, read from 'TC2' (0x54433200) (0) Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0e90480c Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001075D4 Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0204400C Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 1, pasid 32769) at page 1078740, read from 'TC7' (0x54433700) (68) Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0e90400c Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001075DC Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0204800C Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 1, pasid 32769) at page 1078748, read from 'TC6' (0x54433600) (72) Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0e90080c Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001075E0 Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0204400C Feb 1 23:04:18 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 1, pasid 32769) at page 1078752, read from 'TC7' (0x54433700) (68) Feb 1 23:04:20 ph4 kernel: amdgpu 0000:01:00.0: IH ring buffer overflow (0x000C6500, 0x0000A5D0, 0x00006510) Feb 1 23:05:56 ph4 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, last signaled seq=37624, last emitted seq=37625 Feb 1 23:05:56 ph4 kernel: [drm] IP block:gfx_v8_0 is hung! Feb 1 23:05:56 ph4 kernel: [drm] GPU recovery disabled. Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0300440c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00199260 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E04400C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1675872, read from 'TC7' (0x54433700) (68) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0280440c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198CCE Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E04400C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1674446, read from 'TC7' (0x54433700) (68) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0340440c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198D17 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E00400C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1674519, read from 'TC1' (0x54433100) (4) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0200440c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198359 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E0C000C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1672025, read from 'TC5' (0x54433500) (192) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x02c0440c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198355 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E08800C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1672021, read from 'TC9' (0x54433900) (136) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0380440c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001981BE Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E0C400C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1671614, read from 'TC4' (0x54433400) (196) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0af8080c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x001988F1 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E04000C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1673457, read from 'TC8' (0x54433800) (64) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0a38080c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198924 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E08000C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1673508, read from 'TC11' (0x54433131) (128) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0a68400c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198304 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E08800C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1671940, read from 'TC9' (0x54433900) (136) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0cb0000c Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198F81 Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E00400C Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1675137, read from 'TC1' (0x54433100) (4) Feb 2 16:26:05 ph4 kernel: amdgpu 0000:01:00.0: IH ring buffer overflow (0x000C83F0, 0x00005B40, 0x00008400) Feb 2 16:27:33 ph4 kernel: gmc_v8_0_process_interrupt: 4 callbacks suppressed Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0008480c Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00198ECA Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E08800C Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1674954, read from 'TC9' (0x54433900) (136) Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0008480c Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100001 Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0804800C Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 4, pasid 32769) at page 1048577, read from 'TC6' (0x54433600) (72) Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0020000c Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100004 Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0800000C Feb 2 16:27:33 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 4, pasid 32769) at page 1048580, read from 'TC2' (0x54433200) (0) Feb 2 16:27:43 ph4 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, last signaled seq=82952, last emitted seq=82953 Feb 2 16:27:43 ph4 kernel: [drm] IP block:gfx_v8_0 is hung! Feb 2 16:27:43 ph4 kernel: [drm] GPU recovery disabled. Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0098400c Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100013 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E04000C Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1048595, read from 'TC8' (0x54433800) (64) Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x0bd0840c Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0010017A Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E08400C Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32769) at page 1048954, read from 'TC10' (0x54433130) (132) Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x00028414 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100000 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0F084014 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x14, vmid 7, pasid 32769) at page 1048576, write from 'TC10' (0x54433130) (132) Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x00028414 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100000 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0F084014 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x14, vmid 7, pasid 32769) at page 1048576, write from 'TC10' (0x54433130) (132) Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x00028414 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100000 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0F084014 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x14, vmid 7, pasid 32769) at page 1048576, write from 'TC10' (0x54433130) (132) Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: GPU fault detected: 146 0x00028414 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x00100000 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0F084014 Feb 2 16:51:51 ph4 kernel: amdgpu 0000:01:00.0: VM fault (0x14, vmid 7, pasid 32769) at page 1048576, write from 'TC10' (0x54433130) (132) Feb 2 16:52:02 ph4 kernel: [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, last signaled seq=9868, last emitted seq=9870 Feb 2 16:52:02 ph4 kernel: [drm] IP block:gfx_v8_0 is hung! Feb 2 16:52:02 ph4 kernel: [drm] GPU recovery disabled. git bisect start # bad: [db8ae1e77580189f39623478ff6b540da835305f] drm/amdgpu: cache the fence to wait for a VMID git bisect bad db8ae1e77580189f39623478ff6b540da835305f # good: [285b685a33bea9e5c3d5620597234da8954caf16] drm/amdgpu: remove WARN_ON when VM isn't found v2 git bisect good 285b685a33bea9e5c3d5620597234da8954caf16 # bad: [6237b81e2ed7d8a9a62afe013ac207bac6c6f559] drm: amd: Fix trailing semicolons git bisect bad 6237b81e2ed7d8a9a62afe013ac207bac6c6f559 # bad: [67e9638d77b93ab092c1cc18796de045ab87cd6c] drm/ttm: Add a default BO destructor to simplify code (v2) git bisect bad 67e9638d77b93ab092c1cc18796de045ab87cd6c # bad: [d712b817ceb9311cffad47867da26311c06a812b] drm/amdgpu: revert "drm/amdgpu: use AMDGPU_GEM_CREATE_VRAM_CLEARED for VM PD/PTs" v2 git bisect bad d712b817ceb9311cffad47867da26311c06a812b # good: [b7deec77c26b769d5a13af80e70837a5638680a7] drm/radeon: adjust tested variable git bisect good b7deec77c26b769d5a13af80e70837a5638680a7 # good: [6b4f4aea36033f826cbab0b345b21a8b0c632b00] drm/amdgpu: fix vcn_v1_0_dec_ring_emit_wreg git bisect good 6b4f4aea36033f826cbab0b345b21a8b0c632b00 # first bad commit: [d712b817ceb9311cffad47867da26311c06a812b] drm/amdgpu: revert "drm/amdgpu: use AMDGPU_GEM_CREATE_VRAM_CLEARED for VM PD/PTs" v2