Oops#1 Part9 <4>[ 658.330678] xe_guc_sanitize+0x2a/0x50 [xe] <4>[ 658.330734] xe_uc_load_hw+0x19a/0x2b0 [xe] <4>[ 658.330821] ? xe_migrate_init+0x277/0x2d0 [xe] <4>[ 658.330904] xe_gt_init+0x3ae/0xdd0 [xe] <4>[ 658.330973] ? _raw_spin_unlock_irqrestore+0x51/0x80 <4>[ 658.330978] ? __devm_add_action+0x70/0xa0 <4>[ 658.330983] ? xe_irq_install+0x11a/0x490 [xe] <4>[ 658.331059] xe_device_probe+0x32c/0xbe0 [xe] <4>[ 658.331127] ? __drm_dev_dbg+0x7d/0xb0 <4>[ 658.331132] ? __drmm_add_action_or_reset+0x1e/0x50 <4>[ 658.331137] xe_pci_probe+0x39b/0x620 [xe] <4>[ 658.331213] ? trace_hardirqs_on+0x22/0x100 <4>[ 658.331220] local_pci_probe+0x47/0xb0 <4>[ 658.331224] pci_call_probe+0x6c/0x360 <4>[ 658.331230] ? _raw_spin_unlock+0x22/0x50 <4>[ 658.331234] pci_device_probe+0xae/0x110 <4>[ 658.331237] really_probe+0xf1/0x410 <4>[ 658.331241] __driver_probe_device+0x8c/0x190 <4>[ 658.331243] device_driver_attach+0x57/0xd0 <4>[ 658.331246] bind_store+0x77/0xd0 <4>[ 658.331250] drv_attr_store+0x24/0x50 <4>[ 658.331252] sysfs_kf_write+0x4d/0x80 <4>[ 658.331256] kernfs_fop_write_iter+0x188/0x240 <4>[ 658.331260] vfs_write+0x283/0x540 <4>[ 658.331267] ksys_write+0x6f/0xf0 <4>[ 658.331271] __x64_sys_write+0x19/0x30 <4>[ 658.331272] x64_sys_call+0x259/0x26e0 <4>[ 658.331275] do_syscall_64+0xdd/0x1470 <4>[ 658.331280] ? __slab_free+0x129/0x2b0 <4>[ 658.331285] ? __pcs_replace_full_main+0x2ad/0x710 <4>[ 658.331287] ? __pcs_replace_full_main+0x10/0x710 <4>[ 658.331289] ? __fput+0x1bf/0x2f0 <4>[ 658.331291] ? kmem_cache_free+0x165/0x510 <4>[ 658.331295] ? __fput+0x1bf/0x2f0 <4>[ 658.331299] ? fput_close_sync+0x3d/0xa0 Oops#1 Part8 <4>[ 658.331301] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 658.331304] ? do_syscall_64+0x22e/0x1470 <4>[ 658.331307] ? trace_hardirqs_on_prepare+0xe1/0x100 <4>[ 658.331310] ? do_syscall_64+0x22e/0x1470 <4>[ 658.331313] ? do_syscall_64+0x22e/0x1470 <4>[ 658.331315] ? do_syscall_64+0x22e/0x1470 <4>[ 658.331317] ? exc_page_fault+0xbd/0x2c0 <4>[ 658.331321] entry_SYSCALL_64_after_hwframe+0x76/0x7e <4>[ 658.331323] RIP: 0033:0x7773a6b1c5a4 <4>[ 658.331325] 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>[ 658.331327] RSP: 002b:00007ffca72bf098 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 <4>[ 658.331329] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007773a6b1c5a4 <4>[ 658.331330] RDX: 000000000000000c RSI: 00007ffca72bf560 RDI: 0000000000000007 <4>[ 658.331331] RBP: 000000000000000c R08: 0000000000000073 R09: 0000000000000000 <4>[ 658.331332] R10: 0000000000000000 R11: 0000000000000202 R12: 00007ffca72bf560 <4>[ 658.331333] R13: 0000000000000007 R14: 0000000000000006 R15: 00007ffca72bf210 <4>[ 658.331340] <4>[ 658.331341] irq event stamp: 1001178 <4>[ 658.331342] hardirqs last enabled at (1001177): [] _raw_spin_unlock_irqrestore+0x51/0x80 <4>[ 658.331345] hardirqs last disabled at (1001178): [] _raw_spin_lock_irq+0x6f/0x80 <4>[ 658.331347] softirqs last enabled at (1000890): [] __irq_exit_rcu+0x13f/0x160 <4>[ 658.331350] softirqs last disabled at (1000885): [] __irq_exit_rcu+0x13f/0x160 Oops#1 Part7 <4>[ 658.331352] ---[ end trace 0000000000000000 ]--- <7>[ 658.331354] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <4>[ 658.331436] ------------[ cut here ]------------ <4>[ 658.331463] xe 0000:03:00.0: [drm] Tile0: GT0: Failed to invalidate GGTT (-ENODEV) <4>[ 658.331466] WARNING: drivers/gpu/drm/xe/xe_ggtt.c:576 at ggtt_invalidate_gt_tlb.part.0+0x76/0xb0 [xe], CPU#12: kworker/12:11/2604 <4>[ 658.331579] Modules linked in: xe <3>[ 658.331585] xe 0000:03:00.0: probe with driver xe failed with error -12 <4>[ 658.331594] snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_lb mei_gsc_proxy mtd_intel_dg mei_gsc 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 intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling cmdlinepart x86_pkg_temp_thermal hid_generic intel_powerclamp eeepc_wmi spi_nor asus_wmi mei_pxp mei_hdcp sparse_keymap mtd platform_profile coretemp wmi_bmof binfmt_misc kvm_intel usbhid hid kvm snd_intel_dspcfg irqbypass ghash_clmulni_intel snd_hda_codec aesni_intel snd_hda_core snd_hwdep video rapl r8169 snd_pcm intel_cstate realtek i2c_i801 snd_timer i2c_mux spi_intel_pci snd mei_me i2c_smbus spi_intel nls_iso8859_1 soundcore idma64 mei intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry wmi acpi_tad intel_vsec acpi_pad pinctrl_alderlake dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink autofs4 Oops#1 Part6 <4>[ 658.331684] [last unloaded: snd_hda_intel] <4>[ 658.331688] CPU: 12 UID: 0 PID: 2604 Comm: kworker/12:11 Tainted: G S U W 7.0.0-rc3-lgci-xe-xe-pw-163181v1-debug+ #1 PREEMPT(lazy) <4>[ 658.331692] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [W]=WARN <4>[ 658.331694] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1645 03/15/2024 <4>[ 658.331696] Workqueue: xe-destroy-wq __guc_exec_queue_destroy_async [xe] <4>[ 658.331820] RIP: 0010:ggtt_invalidate_gt_tlb.part.0+0x81/0xb0 [xe] <4>[ 658.331922] 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>[ 658.331925] RSP: 0018:ffffc90007d43af0 EFLAGS: 00010246 Oops#1 Part5 <4>[ 658.331928] RAX: ffffffffa11fe887 RBX: 0000000000000000 RCX: 0000000000000000 <4>[ 658.331930] RDX: ffff8881144e1490 RSI: ffffffffa11fe887 RDI: ffffffffa1001fe0 <4>[ 658.331932] RBP: ffffc90007d43b10 R08: 0000000000000000 R09: ffffffffffffffed <4>[ 658.331934] R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffffffffed <4>[ 658.331935] R13: 0000000000000000 R14: ffff8881144e1490 R15: 0000000000000000 <4>[ 658.331937] FS: 0000000000000000(0000) GS:ffff8888db29b000(0000) knlGS:0000000000000000 <4>[ 658.331939] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 658.331941] CR2: 00005d40d284d460 CR3: 000000000344c004 CR4: 0000000000f72ef0 <4>[ 658.331943] PKRU: 55555554 <4>[ 658.331945] Call Trace: <4>[ 658.331946] <4>[ 658.331951] ggtt_node_remove+0x11a/0x140 [xe] <4>[ 658.332054] xe_ggtt_node_remove+0x40/0xa0 [xe] <3>[ 658.332158] xe 0000:03:00.0: [drm] *ERROR* Tile0: GT0: GuC RC setup HOST_CONTROL(0) failed (-ENODEV) <4>[ 658.332155] xe_ggtt_remove_bo+0x87/0x250 [xe] <4>[ 658.332257] ? _raw_write_unlock+0x22/0x50 <4>[ 658.332263] ? drm_vma_offset_remove+0x65/0x80 <4>[ 658.332271] xe_ttm_bo_destroy+0xa2/0x2d0 [xe] <4>[ 658.332367] ? lock_is_held_type+0xa3/0x130 <4>[ 658.332376] ttm_bo_release+0x70/0x310 [ttm] <4>[ 658.332385] ? xe_ggtt_might_lock+0x29/0x60 [xe] <4>[ 658.332485] ? lock_release+0xd0/0x2b0 <4>[ 658.332492] ttm_bo_fini+0x3c/0x70 [ttm] <4>[ 658.332500] xe_gem_object_free+0x1a/0x30 [xe] <7>[ 658.332518] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <4>[ 658.332596] drm_gem_object_free+0x1d/0x40 Oops#1 Part4 <4>[ 658.332600] xe_bo_put+0x12a/0x190 [xe] <4>[ 658.332698] xe_lrc_destroy+0x49/0x90 [xe] <4>[ 658.332819] __xe_exec_queue_fini+0x6b/0xa0 [xe] <4>[ 658.332921] xe_exec_queue_fini+0x2b/0x60 [xe] <4>[ 658.333020] __guc_exec_queue_destroy_async+0x6c/0x1a0 [xe] <4>[ 658.333132] process_one_work+0x22e/0x740 <4>[ 658.333142] worker_thread+0x1e8/0x3d0 <4>[ 658.333146] ? __pfx_worker_thread+0x10/0x10 <4>[ 658.333150] kthread+0x10d/0x150 <4>[ 658.333153] ? __pfx_kthread+0x10/0x10 <4>[ 658.333159] ret_from_fork+0x3d4/0x480 <4>[ 658.333162] ? __pfx_kthread+0x10/0x10 <4>[ 658.333166] ret_from_fork_asm+0x1a/0x30 <4>[ 658.333179] <4>[ 658.333180] irq event stamp: 28637 <4>[ 658.333182] hardirqs last enabled at (28643): [] __up_console_sem+0x79/0xa0 <4>[ 658.333186] hardirqs last disabled at (28648): [] __up_console_sem+0x5e/0xa0 <4>[ 658.333189] softirqs last enabled at (28372): [] __irq_exit_rcu+0x13f/0x160 <4>[ 658.333192] softirqs last disabled at (28367): [] __irq_exit_rcu+0x13f/0x160 <4>[ 658.333195] ---[ end trace 0000000000000000 ]--- <7>[ 658.333778] xe 0000:03:00.0: [drm:guc_ct_change_state [xe]] Tile0: GT0: GuC CT communication channel disabled <7>[ 658.408356] xe 0000:03:00.0: [drm:drm_pagemap_cache_fini [drm_gpusvm_helper]] Destroying dpagemap cache. <7>[ 658.411919] xe 0000:03:00.0: [drm:drm_pagemap_shrinker_fini [drm_gpusvm_helper]] Destroying dpagemap shrinker. <3>[ 660.630433] xe 0000:03:00.0: [drm] *ERROR* TLB invalidation fence timeout, seqno=50 recv=0 <1>[ 660.631560] BUG: unable to handle page fault for address: ffffc9000a38a188 Oops#1 Part3 <1>[ 660.631593] #PF: supervisor write access in kernel mode <1>[ 660.631610] #PF: error_code(0x0002) - not-present page <6>[ 660.631624] PGD 100000067 P4D 100000067 PUD 100aaa067 PMD 0 <4>[ 660.631647] Oops: Oops: 0002 [#1] SMP NOPTI <4>[ 660.631667] CPU: 12 UID: 0 PID: 7856 Comm: kworker/12:20 Tainted: G S U W 7.0.0-rc3-lgci-xe-xe-pw-163181v1-debug+ #1 PREEMPT(lazy) <4>[ 660.631701] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [W]=WARN <4>[ 660.631716] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1645 03/15/2024 <4>[ 660.631737] Workqueue: xe-destroy-wq __guc_exec_queue_destroy_async [xe] <4>[ 660.632242] RIP: 0010:xe_mmio_write32+0x58/0x2b0 [xe] <4>[ 660.632734] 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>[ 660.632770] RSP: 0018:ffffc9000fcdf7e0 EFLAGS: 00010086 <4>[ 660.632788] RAX: 0000000000000002 RBX: ffffc9000a38a188 RCX: 0000000000000000 <4>[ 660.632805] RDX: 0000000000010001 RSI: 000000000000a188 RDI: ffff8881c2890060 <4>[ 660.632822] RBP: ffffc9000fcdf858 R08: 0000000000000000 R09: 0000000000000000 <4>[ 660.632838] R10: ffff8881f5338000 R11: 0000000000000001 R12: ffff8881c2890060 <4>[ 660.632854] R13: 000000000000a188 R14: ffff8881f5338000 R15: 0000000000010001 <4>[ 660.632871] FS: 0000000000000000(0000) GS:ffff8888db29b000(0000) knlGS:0000000000000000 <4>[ 660.632891] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 660.632906] CR2: ffffc9000a38a188 CR3: 000000000344c004 CR4: 0000000000f72ef0 Oops#1 Part2 <4>[ 660.632923] PKRU: 55555554 <4>[ 660.632932] Call Trace: <4>[ 660.632942] <4>[ 660.632960] xe_force_wake_get+0x2a5/0x940 [xe] <4>[ 660.633382] ? _raw_spin_unlock_irqrestore+0x27/0x80 <4>[ 660.633411] ? mark_held_locks+0x46/0x90 <4>[ 660.633434] send_tlb_inval_ggtt+0xfa/0x270 [xe] <4>[ 660.633890] ? trace_hardirqs_on+0x22/0x100 <4>[ 660.633912] ? _raw_spin_unlock_irq+0x27/0x70 <4>[ 660.633931] ? xe_tlb_inval_fence_prep+0xce/0x1e0 [xe] <4>[ 660.634452] xe_tlb_inval_ggtt+0x73/0x250 [xe] <4>[ 660.634810] ? xelpg_ggtt_pte_flags+0x27/0x1a0 [xe] <4>[ 660.634910] ? find_held_lock+0x31/0x90 <4>[ 660.634914] ? ggtt_node_remove+0xcb/0x140 [xe] <4>[ 660.635016] ggtt_invalidate_gt_tlb.part.0+0x1f/0xb0 [xe] <4>[ 660.635117] ggtt_node_remove+0x12c/0x140 [xe] <4>[ 660.635217] xe_ggtt_node_remove+0x40/0xa0 [xe] <4>[ 660.635317] xe_ggtt_remove_bo+0x87/0x250 [xe] <4>[ 660.635418] ? _raw_write_unlock+0x22/0x50 <4>[ 660.635422] ? drm_vma_offset_remove+0x65/0x80 <4>[ 660.635428] xe_ttm_bo_destroy+0xa2/0x2d0 [xe] <4>[ 660.635525] ? lock_is_held_type+0xa3/0x130 <4>[ 660.635531] ttm_bo_release+0x70/0x310 [ttm] <4>[ 660.635541] ? xe_ggtt_might_lock+0x29/0x60 [xe] <4>[ 660.635641] ? lock_release+0xd0/0x2b0 <4>[ 660.635646] ttm_bo_fini+0x3c/0x70 [ttm] <4>[ 660.635654] xe_gem_object_free+0x1a/0x30 [xe] <4>[ 660.635840] drm_gem_object_free+0x1d/0x40 <4>[ 660.635857] xe_bo_put+0x12a/0x190 [xe] <4>[ 660.636257] xe_lrc_destroy+0x49/0x90 [xe] <4>[ 660.636724] __xe_exec_queue_fini+0x6b/0xa0 [xe] <4>[ 660.636929] xe_exec_queue_fini+0x2b/0x60 [xe] Oops#1 Part1 <4>[ 660.637028] __guc_exec_queue_destroy_async+0x6c/0x1a0 [xe] <4>[ 660.637138] process_one_work+0x22e/0x740 <4>[ 660.637144] worker_thread+0x1e8/0x3d0 <4>[ 660.637147] ? __pfx_worker_thread+0x10/0x10 <4>[ 660.637151] kthread+0x10d/0x150 <4>[ 660.637155] ? __pfx_kthread+0x10/0x10 <4>[ 660.637159] ret_from_fork+0x3d4/0x480 <4>[ 660.637163] ? __pfx_kthread+0x10/0x10 <4>[ 660.637167] ret_from_fork_asm+0x1a/0x30 <4>[ 660.637174] <4>[ 660.637176] Modules linked in: xe snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_lb mei_gsc_proxy mtd_intel_dg mei_gsc 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 intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling cmdlinepart x86_pkg_temp_thermal hid_generic intel_powerclamp eeepc_wmi spi_nor asus_wmi mei_pxp mei_hdcp sparse_keymap mtd platform_profile coretemp wmi_bmof binfmt_misc kvm_intel usbhid hid kvm snd_intel_dspcfg irqbypass ghash_clmulni_intel snd_hda_codec aesni_intel snd_hda_core snd_hwdep video rapl r8169 snd_pcm intel_cstate realtek i2c_i801 snd_timer i2c_mux spi_intel_pci snd mei_me i2c_smbus spi_intel nls_iso8859_1 soundcore idma64 mei intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry wmi acpi_tad intel_vsec acpi_pad pinctrl_alderlake dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink <4>[ 660.637222] autofs4 [last unloaded: snd_hda_intel] <4>[ 660.637257] CR2: ffffc9000a38a188 <4>[ 660.637261] ---[ end trace 0000000000000000 ]---