boot_diags发生崩溃
适用场景
FAS2820
问题描述
boot_diags发生崩溃。
[ 177.529350] Kernel panic - not syncing: Fatal exception in interrupt[ 177.565280] ------------[ cut here ]------------[ 177.574234] sched: Unexpected reschedule of offline CPU#0![ 177.585157] WARNING: CPU: 6 PID: 43 at arch/x86/kernel/apic/ipi.c:68 native_smp_send_reschedule+0x34/0x40[ 177.604220] Modules linked in: lpfc(O) mpi ntb(O) mpt3sas(O) raid_class ses pm80xx(O) ep28xx(O) scsi_transport_fc MsrAccDrv(O) mcpu_mem(O) ice(O) dma_test_drv(O) ioatdma(O) i10nm_edac(O) pciDrv(O) slim_driver(O) qede(O) qed(O) nicX550Diag(O) ixgbe(O) nicI210Diag(O) igc(O) igb(O) i2c_dev rdma_ucm rdma_cm iw_cm ib_ipoib ib_cm ib_umad mlx5_ib ib_uverbs ib_core mlx5_core mlxfw x86_pkg_temp_thermal kvm_intel kvm irqbypass efi_pstore sg wmi acpi_ipmi ipmi_si ipmi_devintf tpm_tis ipmi_msghandler tpm_tis_core tpm rng_core ip_tables autofs4 nvme xhci_pci crc32c_intel i2c_i801 xhci_hcd nvme_core sd_mod t10_pi dca [last unloaded: ixgbe][ 177.714805] CPU: 6 PID: 43 Comm: kworker/6:0 Tainted: G D O 5.10.0-12-clp-commondiags-amd64 #1 Debian 5.10.103-1+clp+36+commondiags6[ 177.740807] Hardware name: NetApp, Inc. FAS2820/FAS2800, BIOS 19.2 05/05/2023[ 177.755019] Workqueue: events sp_console_tx_mirror[ 177.764554] RIP: 0010:native_smp_send_reschedule+0x34/0x40[ 177.775472] Code: 05 e1 73 58 01 73 15 48 8b 05 d8 51 1e 01 be fd 00 00 00 48 8b 40 30 e9 4a 83 ba 00 89 fe 48 c7 c7 88 49 17 82 e8 02 b5 8e 00 <0f> 0b c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 05 a4 51[ 177.812910] RSP: 0018:ffffc900002ec6d0 EFLAGS: 00010086[ 177.823312] RAX: 0000000000000000 RBX: ffff8882f622e980 RCX: ffff8882f639ca68[ 177.837524] RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff8882f639ca60[ 177.851736] RBP: ffff8881091bca40 R08: ffffffff824c4828 R09: 0000000000004ffb[ 177.865952] R10: 00000000fffff000 R11: 3fffffffffffffff R12: ffffc900002ec710[ 177.880162] R13: 0000000000000002 R14: ffff8881091bd104 R15: ffff8882f6200000[ 177.894377] FS: 0000000000000000(0000) GS:ffff8882f6380000(0000) knlGS:0000000000000000[ 177.910497] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033[ 177.921936] CR2: 00007f9ce497aa20 CR3: 000000000240a005 CR4: 0000000000770ee0[ 177.936150] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000[ 177.950361] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400[ 177.964577] PKRU: 55555554[ 177.969949] Call Trace:[ 177.974802] <IRQ>[ 177.978790] check_preempt_curr+0x29/0x60[ 177.986764] ttwu_do_wakeup+0x17/0x150[ 177.994216] try_to_wake_up+0x1ae/0x3c0[ 178.001844] start_new_msg+0x55/0x70 [ipmi_si][ 178.010684] smi_event_handler+0x3b9/0x690 [ipmi_si][ 178.020562] flush_messages+0x2c/0x40 [ipmi_si][ 178.029578] ipmi_panic_request_and_wait+0xf2/0x100 [ipmi_msghandler][ 178.042404] ? __find_bmc_prod_dev_id+0x30/0x30 [ipmi_msghandler][ 178.054537] ? vsnprintf+0x368/0x4f0[ 178.061643] ? number+0x325/0x370[ 178.068230] ? vsnprintf+0x3aa/0x4f0[ 178.075336] ? sprintf+0x56/0x70[ 178.081748] ? wait_for_xmitr+0x40/0xb0[ 178.089376] ? serial8250_console_putchar+0x65/0x80[ 178.099082] ? sp_console_tx_mirror+0x130/0x130[ 178.108095] ? _prb_read_valid+0x84/0x300[ 178.116067] ? prb_read_valid+0x17/0x20[ 178.123695] ? kcs_event+0x20/0xa00 [ipmi_si][ 178.132363] ? smi_event_handler+0x181/0x690 [ipmi_si][ 178.142589] ? smi_send+0x110/0x110 [ipmi_msghandler][ 178.152642] panic_event+0x1c9/0x3c0 [ipmi_msghandler][ 178.162869] ? __printk_safe_flush+0x24/0x120[ 178.171535] atomic_notifier_call_chain+0x49/0x70[ 178.180895] ? mce_intel_feature_clear+0x35/0x40[ 178.190082] panic+0x147/0x2e3[ 178.196150] oops_end.cold+0xc/0x18[ 178.203082] exc_general_protection+0x1be/0x400[ 178.212094] asm_exc_general_protection+0x1e/0x30[ 178.221452] RIP: 0010:queued_spin_lock_slowpath+0x198/0x1e0[ 178.232546] Code: ff ff ff c6 47 01 00 e9 21 ff ff ff c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 04 48 63 f6 48 05 80 f5 02 00 48 03 04 f5 e0 d8 23 82 <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32[ 178.269984] RSP: 0018:ffffc900002ece60 EFLAGS: 00010006[ 178.280385] RAX: 00034ce500054d12 RBX: ffffc90000463db0 RCX: 00000000001c0000[ 178.294597] RDX: ffff8882f63af580 RSI: 0000000000002041 RDI: ffffc90000463db8[ 178.308810] RBP: ffffc90000463db8 R08: 00000000001c0000 R09: ffff88810b878850[ 178.323025] R10: ffff8882f632ea30 R11: 0000000000000000 R12: 0000000000000082[ 178.337238] R13: ffff888105a60000 R14: ffff888105a60000 R15: ffff888105a60538[ 178.351450] _raw_spin_lock_irqsave+0x32/0x40[ 178.360118] complete+0x18/0x40[ 178.366361] process_oq+0x708/0x1ed0 [pm80xx][ 178.375025] ? update_process_times+0xb0/0xc0[ 178.383689] ? timerqueue_add+0x96/0xb0[ 178.391317] ? enqueue_hrtimer+0x37/0x70[ 178.399117] pm80xx_chip_isr+0x40/0x80 [pm80xx][ 178.408131] tasklet_action_common.constprop.0+0xd5/0x110[ 178.418877] __do_softirq+0xd2/0x28f[ 178.425983] asm_call_irq_on_stack+0xf/0x20[ 178.434303] </IRQ>[ 178.438463] do_softirq_own_stack+0x37/0x40[ 178.446782] irq_exit_rcu+0x8e/0xc0[ 178.453716] common_interrupt+0x77/0x130[ 178.461515] asm_common_interrupt+0x1e/0x40[ 178.469835] RIP: 0010:_raw_spin_unlock_irqrestore+0x10/0x20[ 178.480930] Code: 07 85 c0 75 0b ba 01 00 00 00 f0 0f b1 17 74 03 31 c0 c3 b8 01 00 00 00 c3 90 0f 1f 44 00 00 48 89 f8 48 89 f7 c6 00 00 57 9d <0f> 1f 44 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48[ 178.518366] RSP: 0018:ffffc900002dfe70 EFLAGS: 00000282[ 178.528766] RAX: ffffffff82bb0ff8 RBX: 0000000000000014 RCX: 0000000000000000[ 178.542982] RDX: 00000000000002f8 RSI: 0000000000000282 RDI: 0000000000000282[ 178.557194] RBP: ffff888102528780 R08: 0000000000000006 R09: 0000000000000899[ 178.571408] R10: 0000000000000018 R11: 0000000000000018 R12: 0000000000000282[ 178.585621] R13: 000000000000000d R14: ffff8882f63b2400 R15: 0000000000000002[ 178.599835] sp_console_tx_mirror+0xc5/0x130[ 178.608328] process_one_work+0x1c5/0x390[ 178.616300] worker_thread+0x4d/0x3e0[ 178.623581] ? rescuer_thread+0x3c0/0x3c0[ 178.631553] kthread+0x11b/0x140[ 178.637965] ? kthread_create_worker_on_cpu+0x70/0x70[ 178.648020] ret_from_fork+0x1f/0x30[ 178.655128] ---[ end trace a3769fe21521f728 ]---[ 178.822832] Kernel Offset: disabled[ 178.834869] Rebooting in 60 seconds..[ 238.845654] ACPI MEMORY or I/O RESET_REG.