Found this particular bug in the dmesg output using latest version of amdgpu drivers for Ubuntu 18.04 (using two RX580 of 8GB):
amdgpu-pro-20.40-1147287-ubuntu-18.04.tar.xz
This is the bug reported:
[67638.271983] BUG: unable to handle kernel paging request at ffff8abd32d37208
[67638.273489] IP: amdgpu_ring_priority_put+0x39/0xe0 [amdgpu]
[67638.274903] PGD 4a799067 P4D 4a799067 PUD 0
[67638.276283] Oops: 0002 [#3] SMP PTI
[67638.277664] Modules linked in: snd_hda_codec_hdmi snd_hda_intel snd_hda_codec intel_rapl x86_pkg_temp_thermal intel_powerclamp snd_hda_core coretemp snd_hwdep snd_pcm snd_timer snd kvm_intel soundcore kvm irqbypass intel_cstate intel_rapl_perf mei_me mei mac_hid acpi_pad intel_pch_thermal shpchp sch_fq_codel ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ip_tables x_tables autofs4 btrfs zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear crct10dif_pclmul crc32_pclmul amdkfd amd_iommu_v2 ghash_clmulni_intel mxm_wmi pcbc e1000e amdgpu i915 aesni_intel aes_x86_64 ptp crypto_simd chash glue_helper cryptd ttm i2c_algo_bit drm_kms_helper syscopyarea pps_core sysfillrect sysimgblt
[67638.283730] fb_sys_fops drm ahci libahci wmi video
[67638.285269] CPU: 1 PID: 10243 Comm: kworker/1:2 Tainted: G D 4.15.0-128-generic #131-Ubuntu
[67638.286830] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./H110 Pro BTC+, BIOS P1.10 06/20/2017
[67638.288436] Workqueue: events amd_sched_job_finish [amdgpu]
[67638.290051] RIP: 0010:amdgpu_ring_priority_put+0x39/0xe0 [amdgpu]
[67638.291632] RSP: 0018:ffffb1704337fe08 EFLAGS: 00010292
[67638.293210] RAX: 00000000ffffffff RBX: ffff8abccc5f5b10 RCX: ffff8abccc5f5c90
[67638.294779] RDX: ffff8abccf330ee8 RSI: 000003aa199d0522 RDI: ffff8abccc5f5b10
[67638.296361] RBP: ffffb1704337fe30 R08: 00003d84432ca6c3 R09: 0000000000000001
[67638.297933] R10: ffffb170435e7920 R11: 0000000000000312 R12: ffff8abd32d37208
[67638.299506] R13: 00000000667416f8 R14: ffff8abcb86a0000 R15: 0000000000000000
[67638.301098] FS: 0000000000000000(0000) GS:ffff8abcddd00000(0000) knlGS:0000000000000000
[67638.302683] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[67638.304284] CR2: ffff8abd32d37208 CR3: 000000004a00a005 CR4: 00000000002606e0
[67638.305874] Call Trace:
[67638.307477] ? __switch_to_asm+0x41/0x70
[67638.309127] amdgpu_job_free_cb+0x2f/0x80 [amdgpu]
[67638.310777] amd_sched_job_finish+0x8d/0xf0 [amdgpu]
[67638.312377] process_one_work+0x1de/0x420
[67638.313950] worker_thread+0x32/0x410
[67638.315467] kthread+0x121/0x140
[67638.316985] ? process_one_work+0x420/0x420
[67638.318488] ? kthread_create_worker_on_cpu+0x70/0x70
[67638.319993] ret_from_fork+0x35/0x40
[67638.321480] Code: 00 00 00 74 45 55 48 63 c6 48 89 e5 41 56 41 55 4c 8d 2c 85 70 02 00 00 41 54 53 48 89 fb b8 ff ff ff ff 48 83 ec 08 4e 8d 24 2f <f0> 41 0f c1 04 24 83 e8 01 85 c0 7f 05 83 fe 01 75 0f 48 83 c4
[67638.323107] RIP: amdgpu_ring_priority_put+0x39/0xe0 [amdgpu] RSP: ffffb1704337fe08
[67638.324688] CR2: ffff8abd32d37208
[67638.326223] ---[ end trace da7a6eb0eca1ccf8 ]--
I have collected all the relevant logs, please let me know how if it is possible to upload them as a tarball.gz
Thanks!
