Comment 8 for bug 1694485

Revision history for this message
bugproxy (bugproxy) wrote : Comment bridged from LTC Bugzilla

------- Comment From <email address hidden> 2017-12-01 03:46 EDT-------
(In reply to comment #16)
> The trace reported is no more seen ; But I see some other trace in dmesg;
>
>
>
> root@ltc84-pkvm1:~# echo 10000 > /sys/kernel/debug/powerpc/eeh_max_freezes
> root@ltc84-pkvm1:~# echo 1 > /sys/class/cxl/card0/perst_reloads_same_image
> root@ltc84-pkvm1:~#
> root@ltc84-pkvm1:~#
> root@ltc84-pkvm1:~# lspci | grep acc
> 0001:01:00.0 Processing accelerators: IBM Device 0477 (rev 01)
> 0002:00:00.0 Processing accelerators: IBM Device 4350 (rev 0a)
> root@ltc84-pkvm1:~# echo 0x8000000000000000 >
> /sys/kernel/debug/powerpc/PCI0001/err_injct_outbound
> root@ltc84-pkvm1:~#
> root@ltc84-pkvm1:~# uname -a
> Linux ltc84-pkvm1 4.10.0-40-generic #44-Ubuntu SMP Thu Nov 9 14:48:23 UTC
> 2017 ppc64le ppc64le ppc64le GNU/Linux
> root@ltc84-pkvm1:~#
>
> root@ltc84-pkvm1:~# dmesg
> <snip>
> [ 123.426172] ip6_tables: (C) 2000-2006 Netfilter Core Team
> [ 123.573736] Ebtables v2.0 registered
> [ 123.964678] virbr0: port 1(virbr0-nic) entered blocking state
> [ 123.964682] virbr0: port 1(virbr0-nic) entered disabled state
> [ 123.964870] device virbr0-nic entered promiscuous mode
> [ 124.298173] virbr0: port 1(virbr0-nic) entered blocking state
> [ 124.298176] virbr0: port 1(virbr0-nic) entered listening state
> [ 124.372069] virbr0: port 1(virbr0-nic) entered disabled state
> [ 171.671205] Harmless Hypervisor Maintenance interrupt [Recovered]
> [ 171.671211] Error detail: Unknown
> [ 171.671214] HMER: 8040000000000000
> [ 171.671218] Harmless Hypervisor Maintenance interrupt [Recovered]
> [ 171.671220] Error detail: Unknown
> [ 171.671223] HMER: 8040000000000000
> [ 171.671382] EEH: Fenced PHB#1 detected, location: N/A
> [ 171.672512] EEH: This PCI device has failed 1 times in the last hour
> [ 171.672513] EEH: Notify device drivers to shutdown
> [ 171.672522] cxl afu0.0: Deactivating AFU directed mode
> [ 171.672660] cxl afu0.0: PSL Purge called with link down, ignoring
> [ 171.673304] EEH: Collect temporary log
> [ 171.673306] PHB3 PHB#1 Diag-data (Version: 1)
> [ 171.673307] brdgCtl: 0000ffff
> [ 171.673309] UtlSts: 00200000 00000000 00000000
> [ 171.673311] RootSts: ffffffff ffffffff ffffffff ffffffff 0000ffff
> [ 171.673312] RootErrSts: ffffffff ffffffff ffffffff
> [ 171.673313] RootErrLog: ffffffff ffffffff ffffffff ffffffff
> [ 171.673314] RootErrLog1: ffffffff 0000000000000000 0000000000000000
> [ 171.673316] nFir: 0000809000000000 0030006e00000000
> 0000800000000000
> [ 171.673317] PhbSts: 0000001800000000 0000001800000000
> [ 171.673318] Lem: 8000020000800000 40018e2400022482
> 8000000000000000
> [ 171.673320] OutErr: 8000002000000000 8000000000000000
> 1210026000020003 0000400000000000
> [ 171.673321] InBErr: 0000000040000000 0000000040000000
> 0000080000000000 000c104010010000
> [ 171.673323] EEH: Reset without hotplug activity
> [ 176.174078] EEH: Notify device drivers the completion of reset
> [ 176.174089] cxl-pci 0001:01:00.0: enabling device (0140 -> 0142)
> [ 176.174404] pci 0001:01 : [PE# 00] Switching PHB to CXL
> [ 176.174505] pci 0001:01 : [PE# 00] Switching PHB to CXL
> [ 176.186032] Adapter context unlocked with 0 active contexts
> [ 176.186109] ------------[ cut here ]------------
> [ 176.186120] WARNING: CPU: 10 PID: 971 at
> /build/linux-W3h2EL/linux-4.10.0/drivers/misc/cxl/main.c:317
> cxl_adapter_context_unlock+0x68/0x90 [cxl]
> [ 176.186121] Modules linked in: xt_conntrack ipt_REJECT nf_reject_ipv4
> ebtable_filter ebtables ip6table_filter ip6_tables xt_CHECKSUM
> iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat
> nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack xt_tcpudp
> bridge stp llc iptable_filter kvm_hv kvm joydev input_leds mac_hid at24
> nvmem_core ofpart ipmi_powernv ipmi_devintf ipmi_msghandler cmdlinepart
> powernv_flash uio_pdrv_genirq uio mtd powernv_rng vmx_crypto opal_prd
> ibmpowernv nfsd auth_rpcgss nfs_acl lockd grace ib_iser rdma_cm iw_cm ib_cm
> sunrpc ib_core configfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi
> ip_tables x_tables autofs4 btrfs raid10 raid456 async_raid6_recov
> async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0
> multipath linear hid_generic
> [ 176.186175] usbhid hid uas usb_storage nouveau crc32c_vpmsum
> i2c_algo_bit ttm drm_kms_helper syscopyarea sysfillrect sysimgblt
> fb_sys_fops tg3 cxl drm ahci libahci pnv_php
> [ 176.186191] CPU: 10 PID: 971 Comm: eehd Not tainted 4.10.0-40-generic
> #44-Ubuntu
> [ 176.186193] task: c0000027d32c5800 task.stack: c0000027d3348000
> [ 176.186194] NIP: d000000038db0c50 LR: d000000038db0c4c CTR:
> c0000000006119a0
> [ 176.186196] REGS: c0000027d334b6a0 TRAP: 0700 Not tainted
> (4.10.0-40-generic)
> [ 176.186197] MSR: 900000000282b033 <SF,HV,VEC,VSX,EE,FP,ME,IR,DR,RI,LE>
> [ 176.186205] CR: 28008282 XER: 20000000
> [ 176.186206] CFAR: c000000000b60b34 SOFTE: 1
> GPR00: d000000038db0c4c c0000027d334b920 d000000038de5c40
> 000000000000002f
> GPR04: 0000000000000001 0000000000000464 0000000063206576
> c0000000015fc900
> GPR08: 0000000000000000 0000000000000000 0000000000000000
> 0000000000000001
> GPR12: 0000000000008800 c00000000fb85a00 c0000000001103b8
> c0000063b13d2000
> GPR16: 0000000000000000 0000000000000000 0000000000000000
> 0000000000000000
> GPR20: 0000000000000000 0000000000000000 0000000000000000
> c000000000d64d78
> GPR24: c000000000d64d50 c0000000014c4330 c0000063aecebc00
> c0000063a74fdfc0
> GPR28: c0000063b1347098 0000000000000000 c0000063aecebc00
> 0000000000000006
> [ 176.186237] NIP [d000000038db0c50] cxl_adapter_context_unlock+0x68/0x90
> [cxl]
> [ 176.186243] LR [d000000038db0c4c] cxl_adapter_context_unlock+0x64/0x90
> [cxl]
> [ 176.186244] Call Trace:
> [ 176.186251] [c0000027d334b920] [d000000038db0c4c]
> cxl_adapter_context_unlock+0x64/0x90 [cxl] (unreliable)
> [ 176.186260] [c0000027d334b980] [d000000038dc1634]
> cxl_configure_adapter+0xa6c/0xab0 [cxl]
> [ 176.186268] [c0000027d334ba30] [d000000038dc16d0]
> cxl_pci_slot_reset+0x58/0x250 [cxl]
> [ 176.186272] [c0000027d334bae0] [c00000000003bb14]
> eeh_report_reset+0x154/0x190
> [ 176.186276] [c0000027d334bb20] [c000000000039e68]
> eeh_pe_dev_traverse+0x98/0x170
> [ 176.186279] [c0000027d334bbb0] [c00000000003c25c]
> eeh_handle_normal_event+0x3ec/0x540
> [ 176.186281] [c0000027d334bc60] [c00000000003c614]
> eeh_handle_event+0x174/0x350
> [ 176.186284] [c0000027d334bd10] [c00000000003c9d8]
> eeh_event_handler+0x1e8/0x1f0
> [ 176.186287] [c0000027d334bdc0] [c000000000110514] kthread+0x164/0x1b0
> [ 176.186291] [c0000027d334be30] [c00000000000b4e8]
> ret_from_kernel_thread+0x5c/0x74
> [ 176.186292] Instruction dump:
> [ 176.186294] 2f84ffff 4d9e0020 7c0802a6 f8010010 f821ffa1 39200000
> 7c8407b4 912303d0
> [ 176.186300] 3c620000 e8638070 48021941 e8410018 <0fe00000> 38210060
> e8010010 7c0803a6
> [ 176.186307] ---[ end trace 8780457e503acb38 ]---
> [ 176.186350] cxl afu0.0: Activating AFU directed mode
> [ 176.186481] EEH: Notify device driver to resume
> root@ltc84-pkvm1:~#

Please ignore this comment.