------- Comment From sudeeshj...@in.ibm.com 2017-12-04 03:43 EDT------- The reported issue is no more seen with the given kernel.
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:~# root@ltc84-pkvm1:~# 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:~# echo 0x8000000000000000 > /sys/kernel/debug/powerpc/PCI0001/err_injct_outbound root@ltc84-pkvm1:~# root@ltc84-pkvm1:~# root@ltc84-pkvm1:~# root@ltc84-pkvm1:~# echo 0x8000000000000000 > /sys/kernel/debug/powerpc/PCI0001/err_injct_outbound root@ltc84-pkvm1:~# dpkg -l | grep linux-im rc linux-image-4.10.0-26-generic 4.10.0-26.30~lp1694485 ppc64el Linux kernel image for version 4.10.0 on PowerPC 64el SMP ii linux-image-4.10.0-40-generic 4.10.0-40.44~lp1694485 ppc64el Linux kernel image for version 4.10.0 on PowerPC 64el SMP rc linux-image-extra-4.10.0-26-generic 4.10.0-26.30~lp1694485 ppc64el Linux kernel extra modules for version 4.10.0 on PowerPC 64el SMP rc linux-image-extra-4.10.0-40-generic 4.10.0-40.44~lp1694485 ppc64el Linux kernel extra modules for version 4.10.0 on PowerPC 64el SMP root@ltc84-pkvm1:~# uname -a Linux ltc84-pkvm1 4.10.0-40-generic #44~lp1694485 SMP Sat Dec 2 20:43:42 UTC 2017 ppc64le ppc64le ppc64le GNU/Linux root@ltc84-pkvm1:~# root@ltc84-pkvm1:~# dmesg [ 115.720740] Harmless Hypervisor Maintenance interrupt [Recovered] [ 115.720747] EEH: Fenced PHB#1 detected, location: N/A [ 115.721905] EEH: This PCI device has failed 1 times in the last hour [ 115.721906] EEH: Notify device drivers to shutdown [ 115.721916] cxl afu0.0: Deactivating AFU directed mode [ 115.722170] cxl afu0.0: PSL Purge called with link down, ignoring [ 115.722585] Error detail: Unknown [ 115.722586] HMER: 8040000000000000 [ 115.722588] Harmless Hypervisor Maintenance interrupt [Recovered] [ 115.722588] Error detail: Unknown [ 115.722589] HMER: 8040000000000000 [ 115.722682] EEH: Collect temporary log [ 115.722684] PHB3 PHB#1 Diag-data (Version: 1) [ 115.722686] brdgCtl: 0000ffff [ 115.722687] UtlSts: 00200000 00000000 00000000 [ 115.722689] RootSts: ffffffff ffffffff ffffffff ffffffff 0000ffff [ 115.722690] RootErrSts: ffffffff ffffffff ffffffff [ 115.722691] RootErrLog: ffffffff ffffffff ffffffff ffffffff [ 115.722693] RootErrLog1: ffffffff 0000000000000000 0000000000000000 [ 115.722694] nFir: 0000809000000000 0030006e00000000 0000800000000000 [ 115.722695] PhbSts: 0000001800000000 0000001800000000 [ 115.722697] Lem: 8000020000800000 40018e2400022482 8000000000000000 [ 115.722699] OutErr: 8000002000000000 8000000000000000 1210066000020003 0000c00000000000 [ 115.722700] InBErr: 0000000040000000 0000000040000000 0000080000000000 000c104010010000 [ 115.722702] EEH: Reset without hotplug activity [ 120.232880] EEH: Notify device drivers the completion of reset [ 120.232891] cxl-pci 0001:01:00.0: enabling device (0140 -> 0142) [ 120.233197] pci 0001:01 : [PE# 00] Switching PHB to CXL [ 120.233301] pci 0001:01 : [PE# 00] Switching PHB to CXL [ 120.244892] cxl afu0.0: Activating AFU directed mode [ 120.245015] EEH: Notify device driver to resume [ 710.830994] Harmless Hypervisor Maintenance interrupt [Recovered] [ 710.831000] Error detail: Unknown [ 710.831003] HMER: 8040000000000000 [ 710.831006] Harmless Hypervisor Maintenance interrupt [Recovered] [ 710.831008] Error detail: Unknown [ 710.831011] HMER: 8040000000000000 [ 710.831522] EEH: Fenced PHB#1 detected, location: N/A [ 710.833355] EEH: This PCI device has failed 2 times in the last hour [ 710.833356] EEH: Notify device drivers to shutdown [ 710.833364] cxl afu0.0: Deactivating AFU directed mode [ 710.833503] cxl afu0.0: PSL Purge called with link down, ignoring [ 710.833698] EEH: Collect temporary log [ 710.833701] PHB3 PHB#1 Diag-data (Version: 1) [ 710.833703] brdgCtl: 0000ffff [ 710.833704] UtlSts: 00200000 00000000 00000000 [ 710.833706] RootSts: ffffffff ffffffff ffffffff ffffffff 0000ffff [ 710.833708] RootErrSts: ffffffff ffffffff ffffffff [ 710.833709] RootErrLog: ffffffff ffffffff ffffffff ffffffff [ 710.833710] RootErrLog1: ffffffff 0000000000000000 0000000000000000 [ 710.833712] nFir: 0000809000000000 0030006e00000000 0000800000000000 [ 710.833713] PhbSts: 0000001800000000 0000001800000000 [ 710.833715] Lem: 8000020000000000 40018e2400022482 8000000000000000 [ 710.833717] OutErr: 8000002000000000 8000000000000000 1210046000020003 0000800000000000 [ 710.833719] EEH: Reset without hotplug activity [ 715.319705] EEH: Notify device drivers the completion of reset [ 715.319715] cxl-pci 0001:01:00.0: enabling device (0140 -> 0142) [ 715.320017] pci 0001:01 : [PE# 00] Switching PHB to CXL [ 715.320117] pci 0001:01 : [PE# 00] Switching PHB to CXL [ 715.331720] cxl afu0.0: Activating AFU directed mode [ 715.331838] EEH: Notify device driver to resume root@ltc84-pkvm1:~# -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1694485 Title: Ubuntu17.04: CAPI: call trace seen while error injection to the CAPI card. To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu-power-systems/+bug/1694485/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs