Linux: 4.16 [ 4769.983429] [drm] amdgpu kernel modesetting enabled. [ 4769.987191] AMD IOMMUv2 driver by Joerg Roedel <jroedel@suse.de> [ 4769.987192] AMD IOMMUv2 functionality not available on this system [ 4769.996639] CRAT table not found [ 4769.996641] Virtual CRAT table created for CPU [ 4769.996642] Parsing CRAT table with 1 nodes [ 4769.996643] Creating topology SYSFS entries [ 4769.996656] Topology: Add CPU node [ 4769.996656] Finished initializing topology [ 4769.996696] kfd kfd: Initialized module [ 4769.997677] amdgpu 0000:01:00.0: enabling device (0000 -> 0003) [ 4769.997955] [drm] initializing kernel modesetting (HAWAII 0x1002:0x67B1 0x1462:0x2015 0x80). [ 4769.997973] [drm] register mmio base: 0xF7D00000 [ 4769.997973] [drm] register mmio size: 262144 [ 4769.997988] [drm] probing gen 2 caps for device 8086:151 = 261ad03/e [ 4769.997989] [drm] probing mlw for device 8086:151 = 261ad03 [ 4770.879382] ATOM BIOS: MS-V30823-F5 [ 4770.879392] [drm] GPU posting now... [ 4770.887332] [drm] vm size is 64 GB, 2 levels, block size is 10-bit, fragment size is 9-bit [ 4770.890028] amdgpu 0000:01:00.0: VRAM: 8192M 0x000000F400000000 - 0x000000F5FFFFFFFF (8192M used) [ 4770.890030] amdgpu 0000:01:00.0: GTT: 1024M 0x0000000000000000 - 0x000000003FFFFFFF [ 4770.890038] [drm] Detected VRAM RAM=8192M, BAR=256M [ 4770.890039] [drm] RAM width 512bits GDDR5 [ 4770.890189] [TTM] Zone kernel: Available graphics memory: 8091642 kiB [ 4770.890190] [TTM] Zone dma32: Available graphics memory: 2097152 kiB [ 4770.890190] [TTM] Initializing pool allocator [ 4770.890194] [TTM] Initializing DMA pool allocator [ 4770.890238] [drm] amdgpu: 8192M of VRAM memory ready [ 4770.890240] [drm] amdgpu: 8192M of GTT memory ready. [ 4770.890297] [drm] GART: num cpu pages 262144, num gpu pages 262144 [ 4770.890795] [drm] PCIE GART of 1024M enabled (table at 0x000000F400040000). [ 4770.896257] [drm] Found UVD firmware Version: 1.64 Family ID: 9 [ 4770.897460] [drm] Found VCE firmware Version: 50.10 Binary ID: 2 [ 4770.897788] [drm] PCIE gen 3 link speeds already enabled [ 4770.921151] [drm] Display Core initialized with v3.1.27! [ 4770.937358] [drm] SADs count is: -2, don't need to read it [ 4770.937467] [drm] Supports vblank timestamp caching Rev 2 (21.10.2013). [ 4770.937468] [drm] Driver supports precise vblank timestamp query. [ 4770.975298] [drm] UVD initialized successfully. [ 4771.096349] [drm] VCE initialized successfully. [ 4771.100066] [drm] fb mappable at 0xE0429000 [ 4771.100067] [drm] vram apper at 0xE0000000 [ 4771.100068] [drm] size 8294400 [ 4771.100069] [drm] fb depth is 24 [ 4771.100070] [drm] pitch is 7680 [ 4771.100214] amdgpu 0000:01:00.0: fb1: amdgpudrmfb frame buffer device [ 4771.102550] [drm] Initialized amdgpu 3.23.0 20150101 for 0000:01:00.0 on minor 1 [ 4957.928424] [drm] amdgpu: finishing device. [ 4957.929297] amdgpu: [powerplay] VI should always have 2 performance levels [ 4958.035935] general protection fault: 0000 [#1] PREEMPT SMP PTI [ 4958.036732] Modules linked in: amdkfd amd_iommu_v2 amdgpu chash gpu_sched ttm xt_CHECKSUM iptable_mangle tun ipt_MASQUERADE nf_nat_masquerade_ipv4 nf_conntrack_netlink nfnetlink xfrm_user xfrm_algo iptable_nat nf_nat_ipv4 xt_addrtype nf_nat br_netfilter bridge stp llc devlink ebtable_filter ebtables ip6table_filter ip6_tables uinput overlay cfg80211 lz4 lz4_compress rfkill 8021q mrp ipt_REJECT nf_reject_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 xt_tcpudp xt_conntrack nf_conntrack xt_multiport iptable_filter xfs fuse loop dm_cache_smq dm_cache dm_persistent_data dm_bio_prison dm_bufio libcrc32c crc32c_generic nls_iso8859_1 nls_cp437 iTCO_wdt iTCO_vendor_support snd_hda_codec_realtek snd_hda_codec_generic intel_rapl snd_hda_codec_hdmi x86_pkg_temp_thermal intel_powerclamp snd_usb_audio coretemp intel_cstate [ 4958.040269] snd_hda_intel intel_uncore intel_rapl_perf snd_hda_codec pcspkr snd_usbmidi_lib snd_hda_core i2c_i801 snd_rawmidi snd_seq_device snd_hwdep snd_pcm snd_timer mousedev joydev input_leds r8169 snd led_class mei_me mii mei soundcore shpchp lpc_ich ie31200_edac rtc_cmos evdev mac_hid nfsd auth_rpcgss nfs_acl lockd grace crypto_user sunrpc ip_tables x_tables algif_skcipher af_alg dm_crypt dm_mod uas usb_storage hid_plantronics hid_generic sd_mod usbhid hid crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel pcbc ahci libahci xhci_pci aesni_intel ehci_pci libata crypto_simd glue_helper xhci_hcd ehci_hcd cryptd scsi_mod usbcore usb_common aes_x86_64 vfio_pci vfio_virqfd vfio_iommu_type1 vfio kvm_intel kvm irqbypass f2fs fscrypto vfat fat i915 intel_gtt i2c_algo_bit drm_kms_helper [ 4958.044174] syscopyarea sysfillrect sysimgblt fb_sys_fops drm agpgart [ 4958.045133] CPU: 0 PID: 9673 Comm: gpu2host Not tainted 4.16.11-1-zen #1 [ 4958.046089] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./Z77 Pro4-M, BIOS P2.00 07/11/2013 [ 4958.047096] RIP: 0010:destroy+0x1f/0xb0 [amdgpu] [ 4958.048065] RSP: 0018:ffff9daf0bda3c68 EFLAGS: 00010286 [ 4958.049032] RAX: ba2de6022177839c RBX: ffff91576b12d300 RCX: 000000010020000d [ 4958.050008] RDX: 000000010020000e RSI: 0000000000001882 RDI: ffff9156f06ca400 [ 4958.050985] RBP: ffff9156e953ec90 R08: ffff9157cedcfd80 R09: 000000010020000d [ 4958.051968] R10: fffff1d5503b73c0 R11: 000000000020000d R12: ffff9156ff718000 [ 4958.052948] R13: 0000000000000040 R14: ffffffffc151bea0 R15: ffffffffc15bc770 [ 4958.053927] FS: 00007ff6cb7d0b80(0000) GS:ffff9157ef200000(0000) knlGS:0000000000000000 [ 4958.054917] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4958.055907] CR2: 000055a209dd7ea8 CR3: 000000038edf2004 CR4: 00000000001606f0 [ 4958.056898] Call Trace: [ 4958.057924] dal_i2caux_destruct+0x6f/0xb0 [amdgpu] [ 4958.058948] destroy+0x15/0x30 [amdgpu] [ 4958.059969] dal_i2caux_destroy+0x22/0x30 [amdgpu] [ 4958.060990] destruct+0xb5/0x190 [amdgpu] [ 4958.062005] dc_destroy+0x11/0x30 [amdgpu] [ 4958.063015] dm_hw_fini+0x70/0x80 [amdgpu] [ 4958.064023] amdgpu_device_ip_fini+0xf4/0x30f [amdgpu] [ 4958.065033] amdgpu_device_fini+0x6e/0x174 [amdgpu] [ 4958.066032] amdgpu_driver_unload_kms+0x42/0x90 [amdgpu] [ 4958.067019] drm_dev_unregister+0x3f/0x230 [drm] [ 4958.068009] amdgpu_pci_remove+0x19/0x40 [amdgpu] [ 4958.068981] pci_device_remove+0x3b/0xc0 [ 4958.069945] device_release_driver_internal+0x1a8/0x2a0 [ 4958.070907] unbind_store+0x157/0x190 [ 4958.071866] kernfs_fop_write+0x10e/0x190 [ 4958.072818] __vfs_write+0x36/0x180 [ 4958.073760] ? handle_mm_fault+0x106/0x2f0 [ 4958.074702] ? __do_page_fault+0x2cb/0x5c0 [ 4958.075632] SyS_write+0xf4/0x2a0 [ 4958.076554] do_syscall_64+0x74/0x1a0 [ 4958.077463] entry_SYSCALL_64_after_hwframe+0x3d/0xa2 [ 4958.078391] RIP: 0033:0x7ff6caed29d4 [ 4958.079297] RSP: 002b:00007ffd32d56598 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 4958.080210] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007ff6caed29d4 [ 4958.081129] RDX: 000000000000000d RSI: 000055a209dd6ea0 RDI: 0000000000000001 [ 4958.082050] RBP: 000055a209dd6ea0 R08: 000000000000000a R09: 0000000000000000 [ 4958.082972] R10: 000000000000000a R11: 0000000000000246 R12: 00007ff6cb1a05c0 [ 4958.083886] R13: 000000000000000d R14: 00007ff6cb19b5c0 R15: 000000000000000d [ 4958.084797] Code: e8 27 37 06 00 58 5b c3 0f 1f 40 00 0f 1f 44 00 00 55 48 89 fd 53 48 8b 1f 48 8b 43 10 48 8b 78 18 48 8b 43 30 8b 70 04 48 8b 07 <48> 8b 40 30 e8 58 b9 7b f2 48 8b 53 30 48 8b 7b 10 41 b9 00 00 [ 4958.085819] RIP: destroy+0x1f/0xb0 [amdgpu] RSP: ffff9daf0bda3c68 [ 4958.086861] ---[ end trace b1fa9649d864dd1a ]---
Distro: Arch linux: 1.16.11-1 xorg-server: 1.20.0-2 xf86-video-amdgpu: 18.0.1-2 Importance is low, because I'm mainly using it via vfio-pci in vm. Worked in 4.15, so I was able to attach it to host when VM was off, never back to guest, but that's a problem for another report. Here if boot directly with amdgpu not blacklisted I get the panic GPU actually never worked with xf86-video-radeon driver, only after switching to amdgpu with options radeon cik_support=0 options amdgpu cik_support=1 a options amdgpu dpm=1 in modprobe.d Done so far: -blacklisted vfio-pci -toggled options: -amdgpu.dc=1 (now: commmented out) -amdgpu.runpm=1 (now: commmented out)
Can you bisect?
-- GitLab Migration Automatic Message -- This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity. You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/drm/amd/issues/402.
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.