Oops#2 Part9 <3>[ 157.503168] xe 0000:03:00.0: [drm] *ERROR* TLB invalidation fence timeout, seqno=51 recv=50 <1>[ 157.504176] BUG: unable to handle page fault for address: ffffc9000b38a188 <1>[ 157.504207] #PF: supervisor write access in kernel mode <1>[ 157.504219] #PF: error_code(0x0002) - not-present page <6>[ 157.504231] PGD 100000067 P4D 100000067 PUD 100ab2067 PMD 0 <4>[ 157.504252] Oops: Oops: 0002 [#1] SMP NOPTI <4>[ 157.504268] CPU: 8 UID: 0 PID: 44 Comm: kworker/8:0 Tainted: G S U W 7.0.0-rc2-lgci-xe-xe-4661-1242b36e0da950a66-debug+ #1 PREEMPT(lazy) <4>[ 157.504296] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [W]=WARN <4>[ 157.504307] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1645 03/15/2024 <4>[ 157.504323] Workqueue: xe-destroy-wq __guc_exec_queue_destroy_async [xe] <4>[ 157.504842] RIP: 0010:xe_mmio_write32+0x58/0x2b0 [xe] <4>[ 157.505358] Code: 24 66 90 65 8b 05 0c 7e 0e e3 48 0f a3 05 b0 e3 b0 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>[ 157.505393] RSP: 0018:ffffc900002cb7e0 EFLAGS: 00010086 <4>[ 157.505411] RAX: 0000000000000002 RBX: ffffc9000b38a188 RCX: 0000000000000000 <4>[ 157.505428] RDX: 0000000000010001 RSI: 000000000000a188 RDI: ffff8881220f8060 <4>[ 157.505446] RBP: ffffc900002cb858 R08: 0000000000000000 R09: 0000000000000000 <4>[ 157.505463] R10: ffff8881541a0000 R11: 0000000000000001 R12: ffff8881220f8060 <4>[ 157.505479] R13: 000000000000a188 R14: ffff8881541a0000 R15: 0000000000010001 <4>[ 157.505496] FS: 0000000000000000(0000) GS:ffff8888db099000(0000) knlGS:0000000000000000 Oops#2 Part8 <4>[ 157.505516] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 157.505531] CR2: ffffc9000b38a188 CR3: 000000000344c002 CR4: 0000000000f72ef0 <4>[ 157.505548] PKRU: 55555554 <4>[ 157.505557] Call Trace: <4>[ 157.505567] <4>[ 157.505585] xe_force_wake_get+0x2a5/0x940 [xe] <4>[ 157.506017] ? _raw_spin_unlock_irqrestore+0x27/0x80 <4>[ 157.506045] ? mark_held_locks+0x46/0x90 <4>[ 157.506068] send_tlb_inval_ggtt+0xfa/0x270 [xe] <4>[ 157.506533] ? trace_hardirqs_on+0x22/0x100 <4>[ 157.506556] ? _raw_spin_unlock_irq+0x27/0x70 <4>[ 157.506574] ? xe_tlb_inval_fence_prep+0xce/0x1e0 [xe] <4>[ 157.507118] xe_tlb_inval_ggtt+0x73/0x250 [xe] <4>[ 157.507643] ? xelpg_ggtt_pte_flags+0x27/0x1a0 [xe] <4>[ 157.508062] ? find_held_lock+0x31/0x90 <4>[ 157.508078] ? ggtt_node_remove+0xcb/0x140 [xe] <4>[ 157.508505] ggtt_invalidate_gt_tlb.part.0+0x1f/0xb0 [xe] <4>[ 157.508924] ggtt_node_remove+0x12c/0x140 [xe] <4>[ 157.509121] xe_ggtt_node_remove+0x40/0xa0 [xe] <4>[ 157.509192] xe_ggtt_remove_bo+0x87/0x250 [xe] <4>[ 157.509264] ? _raw_write_unlock+0x22/0x50 <4>[ 157.509268] ? drm_vma_offset_remove+0x65/0x80 <4>[ 157.509272] xe_ttm_bo_destroy+0xa2/0x2d0 [xe] <4>[ 157.509342] ? lock_is_held_type+0xa3/0x130 <4>[ 157.509347] ttm_bo_release+0x70/0x330 [ttm] <4>[ 157.509355] ? xe_ggtt_might_lock+0x29/0x60 [xe] <4>[ 157.509426] ? lock_release+0xd0/0x2b0 <4>[ 157.509429] ttm_bo_fini+0x3c/0x70 [ttm] <4>[ 157.509435] xe_gem_object_free+0x1a/0x30 [xe] <4>[ 157.509504] drm_gem_object_free+0x1d/0x40 <4>[ 157.509508] xe_bo_put+0x12a/0x190 [xe] Oops#2 Part7 <4>[ 157.509577] xe_lrc_destroy+0x49/0x90 [xe] <4>[ 157.509662] __xe_exec_queue_fini+0x6b/0xa0 [xe] <4>[ 157.509734] xe_exec_queue_fini+0x2b/0x60 [xe] <4>[ 157.509808] __guc_exec_queue_destroy_async+0x6c/0x1a0 [xe] <4>[ 157.509889] process_one_work+0x22e/0x740 <4>[ 157.509894] worker_thread+0x1e8/0x3d0 <4>[ 157.509896] ? __pfx_worker_thread+0x10/0x10 <4>[ 157.509899] kthread+0x10d/0x150 <4>[ 157.509902] ? __pfx_kthread+0x10/0x10 <4>[ 157.509905] ret_from_fork+0x3d4/0x480 <4>[ 157.509908] ? __pfx_kthread+0x10/0x10 <4>[ 157.509911] ret_from_fork_asm+0x1a/0x30 <4>[ 157.509917] <4>[ 157.509918] Modules linked in: snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_gsc_proxy mei_lb mtd_intel_dg mei_gsc 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 intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp hid_generic coretemp cmdlinepart asus_nb_wmi spi_nor asus_wmi mei_pxp mei_hdcp sparse_keymap platform_profile mtd wmi_bmof kvm_intel usbhid kvm hid irqbypass binfmt_misc ghash_clmulni_intel aesni_intel rapl intel_cstate r8169 video snd_intel_dspcfg snd_hda_codec snd_hda_core snd_hwdep realtek snd_pcm snd_timer idma64 i2c_i801 mei_me snd soundcore i2c_mux spi_intel_pci nls_iso8859_1 i2c_smbus mei spi_intel intel_pmc_core pmt_telemetry pmt_discovery pmt_class wmi intel_pmc_ssram_telemetry pinctrl_alderlake acpi_pad acpi_tad intel_vsec dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink Oops#2 Part6 <4>[ 157.509954] autofs4 [last unloaded: snd_hda_intel] <4>[ 157.509981] CR2: ffffc9000b38a188 <4>[ 157.509984] ---[ end trace 0000000000000000 ]--- <4>[ 157.638322] RIP: 0010:xe_mmio_write32+0x58/0x2b0 [xe] <4>[ 157.638427] Code: 24 66 90 65 8b 05 0c 7e 0e e3 48 0f a3 05 b0 e3 b0 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>[ 157.638433] RSP: 0018:ffffc900002cb7e0 EFLAGS: 00010086 <4>[ 157.638436] RAX: 0000000000000002 RBX: ffffc9000b38a188 RCX: 0000000000000000 <4>[ 157.638439] RDX: 0000000000010001 RSI: 000000000000a188 RDI: ffff8881220f8060 <4>[ 157.638442] RBP: ffffc900002cb858 R08: 0000000000000000 R09: 0000000000000000 <4>[ 157.638445] R10: ffff8881541a0000 R11: 0000000000000001 R12: ffff8881220f8060 <4>[ 157.638447] R13: 000000000000a188 R14: ffff8881541a0000 R15: 0000000000010001 <4>[ 157.638450] FS: 0000000000000000(0000) GS:ffff8888db099000(0000) knlGS:0000000000000000 <4>[ 157.638454] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 157.638456] CR2: ffffc9000b38a188 CR3: 000000000344c002 CR4: 0000000000f72ef0 <4>[ 157.638459] PKRU: 55555554 <6>[ 157.638461] note: kworker/8:0[44] exited with irqs disabled Oops#2 Part5 <6>[ 157.638471] note: kworker/8:0[44] exited with preempt_count 1 <6>[ 158.413362] /proc/cgroups lists only v1 controllers, use cgroup.controllers of root cgroup for v2 info <3>[ 159.805701] xe 0000:03:00.0: [drm] *ERROR* TLB invalidation fence timeout, seqno=2931520 recv=0 <4>[ 159.805741] non-slab/vmalloc memory <4>[ 159.805755] ------------[ cut here ]------------ <4>[ 159.805765] list_del corruption. prev->next should be ffffc900002cba90, but was 003d48d44db60f44. (prev=ffffffff813917fe) <4>[ 159.805785] WARNING: lib/list_debug.c:62 at __list_del_entry_valid_or_report+0xd9/0x120, CPU#8: kworker/u64:13/2565 <4>[ 159.805817] Modules linked in: snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_gsc_proxy mei_lb mtd_intel_dg mei_gsc 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 intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp hid_generic coretemp cmdlinepart asus_nb_wmi spi_nor asus_wmi mei_pxp mei_hdcp sparse_keymap platform_profile mtd wmi_bmof kvm_intel usbhid kvm hid irqbypass binfmt_misc ghash_clmulni_intel aesni_intel rapl intel_cstate r8169 video snd_intel_dspcfg snd_hda_codec snd_hda_core snd_hwdep realtek snd_pcm snd_timer idma64 i2c_i801 mei_me snd soundcore i2c_mux spi_intel_pci nls_iso8859_1 i2c_smbus mei spi_intel intel_pmc_core pmt_telemetry pmt_discovery pmt_class wmi intel_pmc_ssram_telemetry pinctrl_alderlake acpi_pad acpi_tad intel_vsec dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink Oops#2 Part4 <4>[ 159.805978] autofs4 [last unloaded: snd_hda_intel] <4>[ 159.806088] CPU: 8 UID: 0 PID: 2565 Comm: kworker/u64:13 Tainted: G S UD W 7.0.0-rc2-lgci-xe-xe-4661-1242b36e0da950a66-debug+ #1 PREEMPT(lazy) <4>[ 159.806117] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [D]=DIE, [W]=WARN <4>[ 159.806129] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1645 03/15/2024 <4>[ 159.806144] Workqueue: gt-ordered-wq xe_tlb_inval_fence_timeout [xe] <4>[ 159.806738] RIP: 0010:__list_del_entry_valid_or_report+0xe3/0x120 <4>[ 159.806760] Code: b5 01 4c 89 ea 48 89 de 67 48 0f b9 3a 31 c0 eb 8b 4c 89 ef e8 be e3 8e ff 48 8d 3d 17 4c b5 01 49 8b 55 00 4c 89 e9 48 89 de <67> 48 0f b9 3a 31 c0 e9 66 ff ff ff 4c 89 e7 e8 99 e3 8e ff 48 8d <4>[ 159.806794] RSP: 0018:ffffc900032efd58 EFLAGS: 00010046 <4>[ 159.806811] RAX: 0000000000000000 RBX: ffffc900002cba90 RCX: ffffffff813917fe <4>[ 159.806827] RDX: 003d48d44db60f44 RSI: ffffc900002cba90 RDI: ffffffff839e3330 <4>[ 159.806843] RBP: ffffc900032efd70 R08: 0000000000000000 R09: 0000000000000000 <4>[ 159.806859] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8881220f8500 Oops#2 Part3 <4>[ 159.806874] R13: ffffffff813917fe R14: ffffffff814903c3 R15: ffff8881220f8480 <4>[ 159.806890] FS: 0000000000000000(0000) GS:ffff8888db099000(0000) knlGS:0000000000000000 <4>[ 159.806909] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 159.806923] CR2: 0000753a304df000 CR3: 000000000344c003 CR4: 0000000000f72ef0 <4>[ 159.806940] PKRU: 55555554 <4>[ 159.806949] Call Trace: <4>[ 159.806959] <4>[ 159.806974] xe_tlb_inval_fence_signal+0x40/0x200 [xe] <4>[ 159.807517] ? lock_acquire+0x2b3/0x2f0 <4>[ 159.807537] xe_tlb_inval_fence_timeout+0xb9/0x220 [xe] <4>[ 159.808065] process_one_work+0x22e/0x740 <4>[ 159.808090] worker_thread+0x1e8/0x3d0 <4>[ 159.808105] ? __pfx_worker_thread+0x10/0x10 <4>[ 159.808120] kthread+0x10d/0x150 <4>[ 159.808137] ? __pfx_kthread+0x10/0x10 <4>[ 159.808156] ret_from_fork+0x3d4/0x480 <4>[ 159.808170] ? __pfx_kthread+0x10/0x10 <4>[ 159.808187] ret_from_fork_asm+0x1a/0x30 <4>[ 159.808214] <4>[ 159.808222] irq event stamp: 272018 <4>[ 159.808233] hardirqs last enabled at (272017): [] _raw_spin_unlock_irq+0x27/0x70 <4>[ 159.808262] hardirqs last disabled at (272018): [] __schedule+0x11e7/0x1dd0 <4>[ 159.808288] softirqs last enabled at (271626): [] neigh_managed_work+0xa7/0xc0 <4>[ 159.808311] softirqs last disabled at (271622): [] neigh_managed_work+0x29/0xc0 <4>[ 159.808332] ---[ end trace 0000000000000000 ]--- <1>[ 159.808354] BUG: unable to handle page fault for address: ffffffff0a0f8510 <1>[ 159.808370] #PF: supervisor read access in kernel mode Oops#2 Part2 <1>[ 159.808383] #PF: error_code(0x0000) - not-present page <6>[ 159.808397] PGD 3451067 P4D 3451067 PUD 0 <4>[ 159.808414] Oops: Oops: 0000 [#2] SMP NOPTI <4>[ 159.808430] CPU: 8 UID: 0 PID: 2565 Comm: kworker/u64:13 Tainted: G S UD W 7.0.0-rc2-lgci-xe-xe-4661-1242b36e0da950a66-debug+ #1 PREEMPT(lazy) <4>[ 159.808461] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER, [D]=DIE, [W]=WARN <4>[ 159.808474] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1645 03/15/2024 <4>[ 159.808492] Workqueue: gt-ordered-wq xe_tlb_inval_fence_timeout [xe] <4>[ 159.809017] RIP: 0010:xe_tlb_inval_fence_signal+0x75/0x200 [xe] <4>[ 159.809530] Code: 48 8b 83 88 00 00 00 48 89 42 08 48 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 83 80 00 00 00 48 83 c0 22 48 89 83 88 00 00 00 <49> 8b 95 b8 00 00 00 49 8d 85 b8 00 00 00 48 39 c2 0f 84 53 01 00 <4>[ 159.809563] RSP: 0018:ffffc900032efd80 EFLAGS: 00010086 <4>[ 159.809578] RAX: dead000000000122 RBX: ffffc900002cba10 RCX: 0000000000000000 <4>[ 159.809594] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 <4>[ 159.809609] RBP: ffffc900032efda0 R08: 0000000000000000 R09: 0000000000000000 <4>[ 159.809625] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>[ 159.809639] R13: ffffffff0a0f8458 R14: ffffffff814903c3 R15: ffff8881220f8480 <4>[ 159.809655] FS: 0000000000000000(0000) GS:ffff8888db099000(0000) knlGS:0000000000000000 <4>[ 159.809674] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 159.809687] CR2: ffffffff0a0f8510 CR3: 000000000344c003 CR4: 0000000000f72ef0 <4>[ 159.809703] PKRU: 55555554 <4>[ 159.809712] Call Trace: <4>[ 159.809720] Oops#2 Part1 <4>[ 159.809729] ? lock_acquire+0x2b3/0x2f0 <4>[ 159.809748] xe_tlb_inval_fence_timeout+0xb9/0x220 [xe] <4>[ 159.810263] process_one_work+0x22e/0x740 <4>[ 159.810284] worker_thread+0x1e8/0x3d0 <4>[ 159.810297] ? __pfx_worker_thread+0x10/0x10 <4>[ 159.810312] kthread+0x10d/0x150 <4>[ 159.810328] ? __pfx_kthread+0x10/0x10 <4>[ 159.810346] ret_from_fork+0x3d4/0x480 <4>[ 159.810359] ? __pfx_kthread+0x10/0x10 <4>[ 159.810376] ret_from_fork_asm+0x1a/0x30 <4>[ 159.810402] <4>[ 159.810410] Modules linked in: snd_hda_codec_intelhdmi snd_hda_codec_hdmi pmt_crashlog mei_gsc_proxy mei_lb mtd_intel_dg mei_gsc 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 intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp hid_generic coretemp cmdlinepart asus_nb_wmi spi_nor asus_wmi mei_pxp mei_hdcp sparse_keymap platform_profile mtd wmi_bmof kvm_intel usbhid kvm hid irqbypass binfmt_misc ghash_clmulni_intel aesni_intel rapl intel_cstate r8169 video snd_intel_dspcfg snd_hda_codec snd_hda_core snd_hwdep realtek snd_pcm snd_timer idma64 i2c_i801 mei_me snd soundcore i2c_mux spi_intel_pci nls_iso8859_1 i2c_smbus mei spi_intel intel_pmc_core pmt_telemetry pmt_discovery pmt_class wmi intel_pmc_ssram_telemetry pinctrl_alderlake acpi_pad acpi_tad intel_vsec dm_multipath msr nvme_fabrics fuse efi_pstore nfnetlink <4>[ 159.810584] autofs4 [last unloaded: snd_hda_intel] <4>[ 159.810733] CR2: ffffffff0a0f8510 <4>[ 159.810746] ---[ end trace 0000000000000000 ]---