Hi, When I start X/i3 on a 7900xtx with Linux 6.7-rc1 and Mesa 23.3_rc3, my log is filled with errors like: [ 649.788816] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788819] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x00008088ed3dd000 from client 10 [ 649.788820] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.788821] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788822] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.788823] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788824] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788825] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788826] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 A log with all entries since X session startup is attached. I'm wondering if this is an issue that the amdgpu devs can reproduce or whether I should create an issue on drm/amd? Also, I am having an issue with a partially garbled UEFI (but no artifacts after amdgpudrmfb picks up) and no artifacts in X or in games (This is not an amdgpu issue but I am just mentioning it incase it is related). Also drm/amd#2356 persists too. Writing to power1_cap results in: tee: /sys/class/drm/card0/device/hwmon/hwmon1/power1_cap: Input/output error -- Abhinav Praveen
[ 649.746070] elogind-daemon[1941]: New session 3 of user me. [ 649.761578] gmc_v11_0_process_interrupt: 83 callbacks suppressed [ 649.761580] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.761584] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x00008088ed3dc000 from client 10 [ 649.761586] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.761587] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.761588] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.761589] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.761590] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.761590] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.761591] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.767011] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.767014] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x00008088ed3dd000 from client 10 [ 649.767016] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.767017] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.767018] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.767019] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.767019] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.767020] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.767021] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.769005] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.769008] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x00008088ed3dd000 from client 10 [ 649.769010] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.769011] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.769012] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.769013] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.769013] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.769014] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.769015] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.788708] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788714] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x00008088ed3dd000 from client 10 [ 649.788717] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.788719] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788720] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.788721] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788722] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788723] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788724] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.788737] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788739] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x000080898b18e000 from client 10 [ 649.788741] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.788743] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788744] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.788745] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788746] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788747] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788749] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.788754] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788756] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x000080894a77d000 from client 10 [ 649.788758] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.788759] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788760] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.788762] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788763] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788764] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788765] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.788775] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788777] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x000080898b18e000 from client 10 [ 649.788778] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D53 [ 649.788779] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788781] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x1 [ 649.788782] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788783] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788784] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788785] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.788789] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788791] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x000080894a77d000 from client 10 [ 649.788792] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00000000 [ 649.788793] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: CB/DB (0x0) [ 649.788794] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.788795] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x0 [ 649.788797] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x0 [ 649.788797] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x0 [ 649.788798] amdgpu 0000:03:00.0: amdgpu: RW: 0x0 [ 649.788803] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788805] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x000080898b18e000 from client 10 [ 649.788806] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D53 [ 649.788808] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788809] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x1 [ 649.788810] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788811] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788812] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788812] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 649.788816] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0) [ 649.788819] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x00008088ed3dd000 from client 10 [ 649.788820] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52 [ 649.788821] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe) [ 649.788822] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 649.788823] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1 [ 649.788824] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5 [ 649.788825] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1 [ 649.788826] amdgpu 0000:03:00.0: amdgpu: RW: 0x1
