Oops#1 Part18 <7>[ 199.038045] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[3] 0x400c 0x13c <7>[ 199.038108] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[4] 0x4010 0x100 <7>[ 199.038169] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[5] 0x4014 0x100 <7>[ 199.038229] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[6] 0x4018 0x100 <7>[ 199.038289] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[7] 0x401c 0x100 <7>[ 199.038348] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[8] 0x4020 0x100 <7>[ 199.038407] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[9] 0x4024 0x100 <7>[ 199.038466] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[10] 0x4028 0x100 <7>[ 199.038524] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[11] 0x402c 0x100 <7>[ 199.038584] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[12] 0x4030 0x100 <7>[ 199.038642] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[13] 0x4034 0x100 <7>[ 199.038702] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[14] 0x4038 0x100 <7>[ 199.038762] xe 0000:03:00.0: [drm:xe_mocs_init [xe]] Tile0: GT0: GLOB_MOCS[15] 0x403c 0x100 <7>[ 199.038847] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: Applying rcs0 save-restore MMIOs <7>[ 199.038934] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x2050] = 0x10001000 <7>[ 199.039001] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x20c4] = 0x3f7e0306 <7>[ 199.039067] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x20d4] = 0xc080c080 Oops#1 Part17 <7>[ 199.039132] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x24d0] = 0x00006210 <7>[ 199.039192] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x24d4] = 0x000062a8 <7>[ 199.039253] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x24d8] = 0x1000dafc <7>[ 199.039312] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x24dc] = 0x1000db01 <7>[ 199.039371] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x24e0] = 0x0000db1c <7>[ 199.039434] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe194] = 0x00400040 <7>[ 199.039499] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe48c] = 0x02000200 <7>[ 199.039563] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe49c] = 0x40004000 <7>[ 199.039627] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe4c4] = 0x10401040 <7>[ 199.039691] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe4f0] = 0x00020002 <7>[ 199.039759] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe530] = 0x00000400 <7>[ 199.039848] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe7c8] = 0x04002000 <7>[ 199.039922] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0xe7cc] = 0x00009000 <7>[ 199.039990] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x14800] = 0x00020002 <7>[ 199.040130] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: Applying bcs0 save-restore MMIOs <7>[ 199.040194] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x22050] = 0x10001000 Oops#1 Part16 <7>[ 199.040258] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x220c4] = 0x3f7e0306 <7>[ 199.040320] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x220d4] = 0xc080c080 <7>[ 199.040460] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: Applying bcs8 save-restore MMIOs <7>[ 199.040525] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x3ee050] = 0x10001000 <7>[ 199.040587] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x3ee0c4] = 0x3f7e0306 <7>[ 199.040648] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x3ee0d4] = 0xc080c080 <7>[ 199.040777] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: Applying ccs0 save-restore MMIOs <7>[ 199.040841] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1a050] = 0x10001000 <7>[ 199.040901] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1a0c4] = 0x3f7e0308 <7>[ 199.040961] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1a0d4] = 0xc080c080 <7>[ 199.041022] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1a4d0] = 0x1000dafc <7>[ 199.041080] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1a4d4] = 0x1000db01 <7>[ 199.041139] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1a4d8] = 0x0000db1c <7>[ 199.041279] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: Applying ccs1 save-restore MMIOs <7>[ 199.041341] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1c050] = 0x10001000 Oops#1 Part15 <7>[ 199.041402] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1c0c4] = 0x3f7e0308 <7>[ 199.041462] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1c0d4] = 0xc080c080 <7>[ 199.041523] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1c4d0] = 0x1000dafc <7>[ 199.041583] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1c4d4] = 0x1000db01 <7>[ 199.041643] xe 0000:03:00.0: [drm:xe_reg_sr_apply_mmio [xe]] Tile0: GT0: REG[0x1c4d8] = 0x0000db1c <7>[ 199.042008] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <7>[ 199.045436] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 0] = 0x0196f1cf <7>[ 199.045499] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 1] = 0x00000800 <7>[ 199.045555] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 2] = 0x00000014 <7>[ 199.045609] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 3] = 0x00000001 <7>[ 199.045664] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 4] = 0x00000c00 <7>[ 199.045717] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 5] = 0xe20b0000 <7>[ 199.045782] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 6] = 0x00000000 <7>[ 199.045835] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 7] = 0x00000000 <7>[ 199.045888] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 8] = 0x00000000 <7>[ 199.045943] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[ 9] = 0x00000000 Oops#1 Part14 <7>[ 199.045996] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[10] = 0x00000000 <7>[ 199.046048] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[11] = 0x00000000 <7>[ 199.046101] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[12] = 0x00000000 <7>[ 199.046153] xe 0000:03:00.0: [drm:guc_print_params [xe]] Tile0: GT0: GuC param[13] = 0x00000000 <7>[ 199.046231] xe 0000:03:00.0: [drm:xe_guc_id_mgr_init [xe]] Tile0: GT0: using 65535 GuC IDs <7>[ 199.046308] xe 0000:03:00.0: [drm:xe_guc_db_mgr_init [xe]] Tile0: GT0: using 256 doorbells <7>[ 199.047367] xe 0000:03:00.0: [drm:guc_buf_cache_init [xe]] Tile0: GT0: reusable buffer with 2097152 dwords at 0xe8c000 for xe_guc_buf_cache_init_with_size [xe] <7>[ 199.048445] xe 0000:03:00.0: [drm:xe_migrate_init [xe]] Migrate min chunk size is 0x00010000 <7>[ 199.049441] xe 0000:03:00.0: [drm:xe_guc_capture_steered_list_init [xe]] Tile0: GT0: capture found 120 ext-regs. <7>[ 199.071860] xe 0000:03:00.0: [drm:xe_guc_ads_populate [xe]] Tile0: GT0: Updated ADS capture size 20480 (was 49152) <7>[ 199.082653] xe 0000:03:00.0: [drm:guc_wait_ucode [xe]] Tile0: GT0: GuC load: init took 10ms, freq = 2150MHz (req = 2133MHz), before = 2150MHz, status = 0x8002F034 <7>[ 199.082931] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel enabled <7>[ 199.083636] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: LRC rcs0 WA job: 4146 dwords <7>[ 199.083713] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x5588] = 0x04000400 Oops#1 Part13 <7>[ 199.083783] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x6204] = 0x00400040 <7>[ 199.083842] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x6208] = 0x00200020 <7>[ 199.083901] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x62a8] = 0x02400240 <7>[ 199.083960] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x7010] = 0x40004000 <7>[ 199.084016] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x7044] = 0x04200420 <7>[ 199.084073] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x7300] = 0x10001000 <7>[ 199.084133] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x83a8] = 0x20002000 <7>[ 199.084195] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x6210] = ~0x3f18000|0x3f18000 (MCR) <7>[ 199.086191] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: LRC bcs0 WA job: 27 dwords <7>[ 199.086262] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: REG[0x22204] = ~0x7e7e|0x606 <7>[ 199.086322] xe 0000:03:00.0: [drm:xe_lrc_emit_hwe_state_instructions [xe]] Tile0: GT0: No non-register state to emit on graphics ver 20.01 <7>[ 199.088634] xe 0000:03:00.0: [drm:xe_gt_record_default_lrcs [xe]] Tile0: GT0: LRC ccs0 WA job: 0 dwords <7>[ 199.088710] xe 0000:03:00.0: [drm:xe_lrc_emit_hwe_state_instructions [xe]] Tile0: GT0: No non-register state to emit on graphics ver 20.01 <5>[ 199.090360] FAULT_INJECTION: forcing a failure. <5>[ 199.090360] name fail_function, interval 0, probability 100, space 1, times 100 Oops#1 Part12 <3>[ 199.090367] xe 0000:03:00.0: [drm] *ERROR* Tile0: GT0: GuC PC query task state failed: -ENOMEM <4>[ 199.090568] ------------[ cut here ]------------ <4>[ 199.090569] xe 0000:03:00.0: [drm] Assertion `ct->g2h_outstanding == 0 || state == XE_GUC_CT_STATE_STOPPED` failed! <4>[ 199.090569] platform: BATTLEMAGE subplatform: 7 <4>[ 199.090569] graphics: Xe2_HPG 20.01 step A0 <4>[ 199.090569] media: Xe2_HPM 13.01 step A1 <4>[ 199.090569] tile: 0 VRAM 12.0 GiB <4>[ 199.090569] GT: 0 type 1 <4>[ 199.090573] WARNING: drivers/gpu/drm/xe/xe_guc_ct.c:541 at guc_ct_change_state+0x264/0x330 [xe], CPU#4: xe_fault_inject/3826 <4>[ 199.090649] Modules linked in: xe_vfio_pci vfio_pci_core vfio_iommu_type1 vfio iommufd snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_gsc_proxy mei_lb mei_gsc mtd_intel_dg xe drm_gpuvm drm_gpusvm_helper drm_buddy drm_ttm_helper ttm gpu_sched drm_suballoc_helper drm_exec drm_display_helper cec rc_core drm_kunit_helpers i2c_algo_bit kunit overlay intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp hid_generic cmdlinepart coretemp eeepc_wmi spi_nor asus_wmi mei_hdcp mei_pxp mtd sparse_keymap platform_profile wmi_bmof kvm_intel kvm usbhid irqbypass ghash_clmulni_intel hid aesni_intel snd_intel_dspcfg rapl r8169 snd_hda_codec intel_cstate snd_hda_core binfmt_misc snd_hwdep video realtek snd_pcm i2c_i801 snd_timer idma64 i2c_mux spi_intel_pci mei_me snd i2c_smbus spi_intel mei soundcore intel_pmc_core pmt_telemetry pmt_discovery nls_iso8859_1 pmt_class intel_pmc_ssram_telemetry pinctrl_alderlake wmi intel_vsec acpi_tad Oops#1 Part11 <4>[ 199.090702] acpi_pad dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink autofs4 [last unloaded: snd_hda_intel] <4>[ 199.090710] CPU: 4 UID: 0 PID: 3826 Comm: xe_fault_inject Tainted: G S U W L 7.0.0-rc3-lgci-xe-xe-4713-45618ec6cfed86e72-debug+ #1 PREEMPT(lazy) <4>[ 199.090713] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [W]=WARN, [L]=SOFTLOCKUP <4>[ 199.090714] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1656 04/18/2024 <4>[ 199.090715] RIP: 0010:guc_ct_change_state+0x2d8/0x330 [xe] <4>[ 199.090786] Code: 51 48 c1 ea 25 44 6b ca 64 44 29 c9 51 48 c7 c1 d8 7f 18 a1 52 4c 8b 55 88 41 52 44 8b 4d 9c 4c 8b 45 90 48 8b 95 78 ff ff ff <67> 48 0f b9 3a 8b 8b 50 01 00 00 48 83 c4 60 85 c9 75 13 44 89 bb Oops#1 Part10 <4>[ 199.090788] RSP: 0018:ffffc900046bf428 EFLAGS: 00010002 <4>[ 199.090790] RAX: ffffffffa11fd88f RBX: ffff888164db0738 RCX: ffffffffa1187fd8 <4>[ 199.090791] RDX: ffff888104d46c10 RSI: ffffffffa11fd88f RDI: ffffffffa1002f20 <4>[ 199.090793] RBP: ffffc900046bf510 R08: ffffffffa11fd8df R09: 0000000000000007 <4>[ 199.090794] R10: ffffffffa11fd990 R11: 0000000000000514 R12: ffff888164db07c8 <4>[ 199.090795] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000001 <4>[ 199.090796] FS: 000079e0190b3980(0000) GS:ffff8888dae9b000(0000) knlGS:0000000000000000 <4>[ 199.090798] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 199.090799] CR2: 00005a0f5ac07da0 CR3: 00000001681e3003 CR4: 0000000000f72ef0 <4>[ 199.090800] PKRU: 55555554 <4>[ 199.090801] Call Trace: <4>[ 199.090802] <4>[ 199.090811] ? xe_guc_submit_enable+0xa8/0xf0 [xe] <4>[ 199.090897] xe_guc_ct_disable+0x17/0x80 [xe] <4>[ 199.090976] xe_guc_sanitize+0x2a/0x50 [xe] <4>[ 199.091054] xe_uc_load_hw+0x19a/0x2b0 [xe] <4>[ 199.091158] ? xe_migrate_init+0x277/0x2d0 [xe] <4>[ 199.091247] xe_gt_init+0x3ae/0xdd0 [xe] <4>[ 199.091324] ? _raw_spin_unlock_irqrestore+0x51/0x80 <4>[ 199.091329] ? __devm_add_action+0x70/0xa0 <4>[ 199.091334] ? xe_irq_install+0x11a/0x490 [xe] <4>[ 199.091422] xe_device_probe+0x32c/0xbe0 [xe] <4>[ 199.091497] ? __drm_dev_dbg+0x7d/0xb0 <4>[ 199.091502] ? __drmm_add_action_or_reset+0x1e/0x50 <4>[ 199.091508] xe_pci_probe+0x39b/0x620 [xe] <4>[ 199.091596] ? trace_hardirqs_on+0x22/0x100 <4>[ 199.091604] local_pci_probe+0x47/0xb0 <4>[ 199.091608] pci_call_probe+0x6c/0x360 Oops#1 Part9 <4>[ 199.091614] ? _raw_spin_unlock+0x22/0x50 <4>[ 199.091619] pci_device_probe+0xae/0x110 <4>[ 199.091623] really_probe+0xf1/0x410 <4>[ 199.091627] __driver_probe_device+0x8c/0x190 <4>[ 199.091630] device_driver_attach+0x57/0xd0 <4>[ 199.091633] bind_store+0x77/0xd0 <4>[ 199.091637] drv_attr_store+0x24/0x50 <4>[ 199.091640] sysfs_kf_write+0x4d/0x80 <4>[ 199.091645] kernfs_fop_write_iter+0x188/0x240 <4>[ 199.091649] vfs_write+0x283/0x540 <4>[ 199.091657] ksys_write+0x6f/0xf0 <4>[ 199.091661] __x64_sys_write+0x19/0x30 <4>[ 199.091663] x64_sys_call+0x259/0x26e0 <4>[ 199.091666] do_syscall_64+0xdd/0x1470 <4>[ 199.091669] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 199.091673] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091676] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091679] ? lock_release+0xd0/0x2b0 <4>[ 199.091685] ? __mutex_unlock_slowpath+0x40/0x340 <4>[ 199.091687] ? lock_release+0xd0/0x2b0 <4>[ 199.091692] ? mutex_unlock+0x12/0x20 <4>[ 199.091694] ? __f_unlock_pos+0x15/0x20 <4>[ 199.091697] ? __x64_sys_getdents64+0x9a/0x130 <4>[ 199.091700] ? __pfx_filldir64+0x10/0x10 <4>[ 199.091704] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 199.091708] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091711] ? __fput+0x1bf/0x2f0 <4>[ 199.091714] ? fput_close_sync+0x3d/0xa0 <4>[ 199.091717] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 199.091720] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091723] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091726] ? __fput+0x1bf/0x2f0 <4>[ 199.091728] ? kmem_cache_free+0x165/0x510 <4>[ 199.091734] ? __fput+0x1bf/0x2f0 <4>[ 199.091737] ? fput_close_sync+0x3d/0xa0 Oops#1 Part8 <4>[ 199.091740] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 199.091743] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091746] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 199.091750] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091752] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091754] ? do_syscall_64+0x22e/0x1470 <4>[ 199.091756] ? exc_page_fault+0xbd/0x2c0 <4>[ 199.091761] entry_SYSCALL_64_after_hwframe+0x76/0x7e <4>[ 199.091763] RIP: 0033:0x79e01b31c5a4 <4>[ 199.091765] Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d a5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 <4>[ 199.091767] RSP: 002b:00007fff58789d78 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 <4>[ 199.091769] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000079e01b31c5a4 <4>[ 199.091770] RDX: 000000000000000c RSI: 00007fff5878a240 RDI: 0000000000000007 <4>[ 199.091771] RBP: 000000000000000c R08: 0000000000000073 R09: 0000000000000000 <4>[ 199.091772] R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff5878a240 <4>[ 199.091774] R13: 0000000000000007 R14: 0000000000000006 R15: 00007fff58789ef0 <4>[ 199.091781] <4>[ 199.091783] irq event stamp: 1282196 <4>[ 199.091784] hardirqs last enabled at (1282195): [] _raw_spin_unlock_irqrestore+0x51/0x80 <4>[ 199.091787] hardirqs last disabled at (1282196): [] _raw_spin_lock_irq+0x6f/0x80 <4>[ 199.091789] softirqs last enabled at (1282092): [] __irq_exit_rcu+0x13f/0x160 <4>[ 199.091792] softirqs last disabled at (1282085): [] __irq_exit_rcu+0x13f/0x160 Oops#1 Part7 <4>[ 199.091794] ---[ end trace 0000000000000000 ]--- <7>[ 199.091796] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <4>[ 199.091886] ------------[ cut here ]------------ <4>[ 199.091893] xe 0000:03:00.0: [drm] Tile0: GT0: Failed to invalidate GGTT (-ENODEV) <4>[ 199.091895] WARNING: drivers/gpu/drm/xe/xe_ggtt.c:576 at ggtt_invalidate_gt_tlb.part.0+0x76/0xb0 [xe], CPU#10: kworker/10:7/2365 <4>[ 199.091961] Modules linked in: xe_vfio_pci vfio_pci_core vfio_iommu_type1 vfio iommufd snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_gsc_proxy mei_lb mei_gsc mtd_intel_dg xe drm_gpuvm drm_gpusvm_helper <3>[ 199.091996] xe 0000:03:00.0: probe with driver xe failed with error -12 <4>[ 199.092073] drm_buddy drm_ttm_helper ttm gpu_sched drm_suballoc_helper drm_exec drm_display_helper cec rc_core drm_kunit_helpers i2c_algo_bit kunit overlay intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp hid_generic cmdlinepart coretemp eeepc_wmi spi_nor asus_wmi mei_hdcp mei_pxp mtd sparse_keymap platform_profile wmi_bmof kvm_intel kvm usbhid irqbypass ghash_clmulni_intel hid aesni_intel snd_intel_dspcfg rapl r8169 snd_hda_codec intel_cstate snd_hda_core binfmt_misc snd_hwdep video realtek snd_pcm i2c_i801 snd_timer idma64 i2c_mux spi_intel_pci mei_me snd i2c_smbus spi_intel mei soundcore intel_pmc_core pmt_telemetry pmt_discovery nls_iso8859_1 pmt_class intel_pmc_ssram_telemetry pinctrl_alderlake wmi intel_vsec acpi_tad acpi_pad dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink autofs4 [last unloaded: snd_hda_intel] Oops#1 Part6 <4>[ 199.092138] CPU: 10 UID: 0 PID: 2365 Comm: kworker/10:7 Tainted: G S U W L 7.0.0-rc3-lgci-xe-xe-4713-45618ec6cfed86e72-debug+ #1 PREEMPT(lazy) <4>[ 199.092141] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [W]=WARN, [L]=SOFTLOCKUP <4>[ 199.092142] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1656 04/18/2024 <4>[ 199.092143] Workqueue: xe-destroy-wq __guc_exec_queue_destroy_async [xe] <4>[ 199.092215] RIP: 0010:ggtt_invalidate_gt_tlb.part.0+0x81/0xb0 [xe] <4>[ 199.092275] Code: 48 8b 7f 08 4c 8b 77 50 4d 85 f6 75 03 4c 8b 37 e8 34 98 62 e1 48 89 c6 48 8d 3d ea c5 3d 00 4d 89 e1 45 89 e8 89 d9 4c 89 f2 <67> 48 0f b9 3a 5b 41 5c 41 5d 41 5e 5d 31 c0 31 d2 31 c9 31 f6 31 <4>[ 199.092277] RSP: 0018:ffffc90003f6faf0 EFLAGS: 00010246 Oops#1 Part5 <4>[ 199.092279] RAX: ffffffffa11fd88f RBX: 0000000000000000 RCX: 0000000000000000 <4>[ 199.092280] RDX: ffff888104d46c10 RSI: ffffffffa11fd88f RDI: ffffffffa1001fe0 <4>[ 199.092281] RBP: ffffc90003f6fb10 R08: 0000000000000000 R09: ffffffffffffffed <4>[ 199.092283] R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffffffffed <4>[ 199.092284] R13: 0000000000000000 R14: ffff888104d46c10 R15: 0000000000000000 <4>[ 199.092285] FS: 0000000000000000(0000) GS:ffff8888db19b000(0000) knlGS:0000000000000000 <4>[ 199.092287] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 199.092288] CR2: 00005a0f5aaf9300 CR3: 000000000344c004 CR4: 0000000000f72ef0 <4>[ 199.092289] PKRU: 55555554 <4>[ 199.092290] Call Trace: <4>[ 199.092291] <4>[ 199.092294] ggtt_node_remove+0x11a/0x140 [xe] <4>[ 199.092357] xe_ggtt_node_remove+0x40/0xa0 [xe] <4>[ 199.092416] xe_ggtt_remove_bo+0x87/0x250 [xe] <4>[ 199.092475] ? _raw_write_unlock+0x22/0x50 <4>[ 199.092480] ? drm_vma_offset_remove+0x65/0x80 <4>[ 199.092485] xe_ttm_bo_destroy+0xa2/0x2d0 [xe] <4>[ 199.092540] ? lock_is_held_type+0xa3/0x130 <4>[ 199.092545] ttm_bo_release+0x70/0x310 [ttm] <3>[ 199.092553] xe 0000:03:00.0: [drm] *ERROR* Tile0: GT0: GuC RC setup HOST_CONTROL(0) failed (-ENODEV) <4>[ 199.092551] ? xe_ggtt_might_lock+0x29/0x60 [xe] <4>[ 199.092609] ? lock_release+0xd0/0x2b0 <4>[ 199.092614] ttm_bo_fini+0x3c/0x70 [ttm] <4>[ 199.092619] xe_gem_object_free+0x1a/0x30 [xe] <4>[ 199.092671] drm_gem_object_free+0x1d/0x40 <4>[ 199.092674] xe_bo_put+0x12a/0x190 [xe] <4>[ 199.092729] xe_lrc_destroy+0x74/0x90 [xe] <4>[ 199.092814] __xe_exec_queue_fini+0x6b/0xa0 [xe] Oops#1 Part4 <7>[ 199.092811] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <4>[ 199.092875] xe_exec_queue_fini+0x2b/0x60 [xe] <4>[ 199.092935] __guc_exec_queue_destroy_async+0x6c/0x1a0 [xe] <4>[ 199.093004] process_one_work+0x22e/0x740 <4>[ 199.093011] worker_thread+0x1e8/0x3d0 <4>[ 199.093014] ? __pfx_worker_thread+0x10/0x10 <4>[ 199.093016] kthread+0x10d/0x150 <4>[ 199.093019] ? __pfx_kthread+0x10/0x10 <4>[ 199.093022] ret_from_fork+0x3d4/0x480 <4>[ 199.093025] ? __pfx_kthread+0x10/0x10 <4>[ 199.093028] ret_from_fork_asm+0x1a/0x30 <4>[ 199.093035] <4>[ 199.093036] irq event stamp: 40503 <4>[ 199.093037] hardirqs last enabled at (40509): [] __up_console_sem+0x79/0xa0 <4>[ 199.093040] hardirqs last disabled at (40514): [] __up_console_sem+0x5e/0xa0 <4>[ 199.093042] softirqs last enabled at (39606): [] __irq_exit_rcu+0x13f/0x160 <4>[ 199.093045] softirqs last disabled at (39599): [] __irq_exit_rcu+0x13f/0x160 <4>[ 199.093047] ---[ end trace 0000000000000000 ]--- <7>[ 199.094133] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <7>[ 199.177681] xe 0000:03:00.0: [drm:drm_pagemap_cache_fini [drm_gpusvm_helper]] Destroying dpagemap cache. <7>[ 199.180913] xe 0000:03:00.0: [drm:drm_pagemap_shrinker_fini [drm_gpusvm_helper]] Destroying dpagemap shrinker. <3>[ 201.367311] xe 0000:03:00.0: [drm] *ERROR* TLB invalidation fence timeout, seqno=51 recv=50 <1>[ 201.368395] BUG: unable to handle page fault for address: ffffc9002138a188 Oops#1 Part3 <1>[ 201.368435] #PF: supervisor write access in kernel mode <1>[ 201.368448] #PF: error_code(0x0002) - not-present page <6>[ 201.368460] PGD 100000067 P4D 100000067 PUD 100ab5067 PMD 0 <4>[ 201.368481] Oops: Oops: 0002 [#1] SMP NOPTI <4>[ 201.368499] CPU: 10 UID: 0 PID: 2361 Comm: kworker/10:3 Tainted: G S U W L 7.0.0-rc3-lgci-xe-xe-4713-45618ec6cfed86e72-debug+ #1 PREEMPT(lazy) <4>[ 201.368528] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [W]=WARN, [L]=SOFTLOCKUP <4>[ 201.368540] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1656 04/18/2024 <4>[ 201.368555] Workqueue: xe-destroy-wq __guc_exec_queue_destroy_async [xe] <4>[ 201.369031] RIP: 0010:xe_mmio_write32+0x58/0x2b0 [xe] <4>[ 201.369499] Code: 24 66 90 65 8b 05 6c 46 2e e3 48 0f a3 05 10 ad d0 e2 0f 82 1d 01 00 00 41 f7 c5 00 00 00 01 0f 84 b7 00 00 00 49 03 5c 24 08 <44> 89 3b 48 8d 65 d8 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 <4>[ 201.369535] RSP: 0018:ffffc90003f4f7e0 EFLAGS: 00010086 <4>[ 201.369554] RAX: 0000000000000002 RBX: ffffc9002138a188 RCX: 0000000000000000 <4>[ 201.369572] RDX: 0000000000010001 RSI: 000000000000a188 RDI: ffff88811de68060 <4>[ 201.369589] RBP: ffffc90003f4f858 R08: 0000000000000000 R09: 0000000000000000 <4>[ 201.369606] R10: ffff888171250000 R11: 0000000000000001 R12: ffff88811de68060 <4>[ 201.369623] R13: 000000000000a188 R14: ffff888171250000 R15: 0000000000010001 <4>[ 201.369640] FS: 0000000000000000(0000) GS:ffff8888db19b000(0000) knlGS:0000000000000000 <4>[ 201.369661] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 201.369676] CR2: ffffc9002138a188 CR3: 000000000344c004 CR4: 0000000000f72ef0 Oops#1 Part2 <4>[ 201.369694] PKRU: 55555554 <4>[ 201.369705] Call Trace: <4>[ 201.369716] <4>[ 201.369736] xe_force_wake_get+0x2a5/0x940 [xe] <4>[ 201.370144] ? _raw_spin_unlock_irqrestore+0x27/0x80 <4>[ 201.370173] ? mark_held_locks+0x46/0x90 <4>[ 201.370197] send_tlb_inval_ggtt+0xfa/0x270 [xe] <4>[ 201.370629] ? trace_hardirqs_on+0x22/0x100 <4>[ 201.370651] ? _raw_spin_unlock_irq+0x27/0x70 <4>[ 201.370670] ? xe_tlb_inval_fence_prep+0xce/0x1e0 [xe] <4>[ 201.371165] xe_tlb_inval_ggtt+0x73/0x250 [xe] <4>[ 201.371646] ? xelpg_ggtt_pte_flags+0x27/0x1a0 [xe] <4>[ 201.372040] ? find_held_lock+0x31/0x90 <4>[ 201.372057] ? ggtt_node_remove+0xcb/0x140 [xe] <4>[ 201.372458] ggtt_invalidate_gt_tlb.part.0+0x1f/0xb0 [xe] <4>[ 201.372851] ggtt_node_remove+0x12c/0x140 [xe] <4>[ 201.373244] xe_ggtt_node_remove+0x40/0xa0 [xe] <4>[ 201.373636] xe_ggtt_remove_bo+0x87/0x250 [xe] <4>[ 201.374028] ? _raw_write_unlock+0x22/0x50 <4>[ 201.374039] ? drm_vma_offset_remove+0x65/0x80 <4>[ 201.374044] xe_ttm_bo_destroy+0xa2/0x2d0 [xe] <4>[ 201.374111] ? lock_is_held_type+0xa3/0x130 <4>[ 201.374117] ttm_bo_release+0x70/0x310 [ttm] <4>[ 201.374123] ? xe_ggtt_might_lock+0x29/0x60 [xe] <4>[ 201.374191] ? lock_release+0xd0/0x2b0 <4>[ 201.374195] ttm_bo_fini+0x3c/0x70 [ttm] <4>[ 201.374201] xe_gem_object_free+0x1a/0x30 [xe] <4>[ 201.374268] drm_gem_object_free+0x1d/0x40 <4>[ 201.374271] xe_bo_put+0x12a/0x190 [xe] <4>[ 201.374338] xe_lrc_destroy+0x49/0x90 [xe] <4>[ 201.374414] __xe_exec_queue_fini+0x6b/0xa0 [xe] <4>[ 201.374482] xe_exec_queue_fini+0x2b/0x60 [xe] <4>[ 201.374549] __guc_exec_queue_destroy_async+0x6c/0x1a0 [xe] Oops#1 Part1 <4>[ 201.374621] process_one_work+0x22e/0x740 <4>[ 201.374626] worker_thread+0x1e8/0x3d0 <4>[ 201.374628] ? __pfx_worker_thread+0x10/0x10 <4>[ 201.374631] kthread+0x10d/0x150 <4>[ 201.374634] ? __pfx_kthread+0x10/0x10 <4>[ 201.374637] ret_from_fork+0x3d4/0x480 <4>[ 201.374640] ? __pfx_kthread+0x10/0x10 <4>[ 201.374643] ret_from_fork_asm+0x1a/0x30 <4>[ 201.374649] <4>[ 201.374650] Modules linked in: xe_vfio_pci vfio_pci_core vfio_iommu_type1 vfio iommufd snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_gsc_proxy mei_lb mei_gsc mtd_intel_dg xe drm_gpuvm drm_gpusvm_helper drm_buddy drm_ttm_helper ttm gpu_sched drm_suballoc_helper drm_exec drm_display_helper cec rc_core drm_kunit_helpers i2c_algo_bit kunit overlay intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp hid_generic cmdlinepart coretemp eeepc_wmi spi_nor asus_wmi mei_hdcp mei_pxp mtd sparse_keymap platform_profile wmi_bmof kvm_intel kvm usbhid irqbypass ghash_clmulni_intel hid aesni_intel snd_intel_dspcfg rapl r8169 snd_hda_codec intel_cstate snd_hda_core binfmt_misc snd_hwdep video realtek snd_pcm i2c_i801 snd_timer idma64 i2c_mux spi_intel_pci mei_me snd i2c_smbus spi_intel mei soundcore intel_pmc_core pmt_telemetry pmt_discovery nls_iso8859_1 pmt_class intel_pmc_ssram_telemetry pinctrl_alderlake wmi intel_vsec acpi_tad <4>[ 201.374686] acpi_pad dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink autofs4 [last unloaded: snd_hda_intel] <4>[ 201.374716] CR2: ffffc9002138a188 <4>[ 201.374719] ---[ end trace 0000000000000000 ]---