| From: Steffen Maier <maier@linux.ibm.com> |
| Date: Thu, 17 May 2018 19:14:47 +0200 |
| Subject: scsi: zfcp: fix missing REC trigger trace on terminate_rport_io for |
| ERP_FAILED |
| |
| commit d70aab55924b44f213fec2b900b095430b33eec6 upstream. |
| |
| For problem determination we always want to see when we were invoked on the |
| terminate_rport_io callback whether we perform something or not. |
| |
| Temporal event sequence of interest with a long fast_io_fail_tmo of 27 sec: |
| |
| loose remote port |
| |
| t workqueue |
| [s] zfcp_q_<dev> IRQ zfcperp<dev> |
| |
| === ================== =================== ============================ |
| |
| 0 recv RSCN |
| q p.test_link_work |
| block rport |
| start fast_io_fail_tmo |
| send ADISC ELS |
| 4 recv ADISC fail |
| block zfcp_port |
| port forced reopen |
| send open port |
| 12 recv open port fail |
| q p.gid_pn_work |
| zfcp_erp_wakeup |
| (zfcp_erp_wait would return) |
| GID_PN fail |
| |
| Before this point, we got a SCSI trace with tag "sctrpi1" on fast_io_fail, |
| e.g. with the typical 5 sec setting. |
| |
| port.status |= ERP_FAILED |
| |
| If fast_io_fail_tmo triggers after this point, we missed a SCSI trace. |
| |
| workqueue |
| fc_dl_<host> |
| ================== |
| 27 fc_timeout_fail_rport_io |
| fc_terminate_rport_io |
| zfcp_scsi_terminate_rport_io |
| zfcp_erp_port_forced_reopen |
| _zfcp_erp_port_forced_reopen |
| if (port.status & ERP_FAILED) |
| return; |
| |
| Therefore, write a trace before above early return. |
| |
| Example trace record formatted with zfcpdbf from s390-tools: |
| |
| Timestamp : ... |
| Area : REC |
| Subarea : 00 |
| Level : 1 |
| Exception : - |
| CPU ID : .. |
| Caller : 0x... |
| Record ID : 1 ZFCP_DBF_REC_TRIG |
| Tag : sctrpi1 SCSI terminate rport I/O |
| LUN : 0xffffffffffffffff none (invalid) |
| WWPN : 0x<wwpn> |
| D_ID : 0x<n_port_id> |
| Adapter status : 0x... |
| Port status : 0x... |
| LUN status : 0x00000000 none (invalid) |
| Ready count : 0x... |
| Running count : 0x... |
| ERP want : 0x03 ZFCP_ERP_ACTION_REOPEN_PORT_FORCED |
| ERP need : 0xe0 ZFCP_ERP_ACTION_FAILED |
| |
| Signed-off-by: Steffen Maier <maier@linux.ibm.com> |
| Reviewed-by: Benjamin Block <bblock@linux.ibm.com> |
| Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> |
| Signed-off-by: Ben Hutchings <ben@decadent.org.uk> |
| --- |
| drivers/s390/scsi/zfcp_erp.c | 13 +++++++++++-- |
| 1 file changed, 11 insertions(+), 2 deletions(-) |
| |
| --- a/drivers/s390/scsi/zfcp_erp.c |
| +++ b/drivers/s390/scsi/zfcp_erp.c |
| @@ -41,9 +41,13 @@ enum zfcp_erp_steps { |
| * @ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: Forced port recovery. |
| * @ZFCP_ERP_ACTION_REOPEN_ADAPTER: Adapter recovery. |
| * @ZFCP_ERP_ACTION_NONE: Eyecatcher pseudo flag to bitwise or-combine with |
| - * either of the other enum values. |
| + * either of the first four enum values. |
| * Used to indicate that an ERP action could not be |
| * set up despite a detected need for some recovery. |
| + * @ZFCP_ERP_ACTION_FAILED: Eyecatcher pseudo flag to bitwise or-combine with |
| + * either of the first four enum values. |
| + * Used to indicate that ERP not needed because |
| + * the object has ZFCP_STATUS_COMMON_ERP_FAILED. |
| */ |
| enum zfcp_erp_act_type { |
| ZFCP_ERP_ACTION_REOPEN_LUN = 1, |
| @@ -51,6 +55,7 @@ enum zfcp_erp_act_type { |
| ZFCP_ERP_ACTION_REOPEN_PORT_FORCED = 3, |
| ZFCP_ERP_ACTION_REOPEN_ADAPTER = 4, |
| ZFCP_ERP_ACTION_NONE = 0xc0, |
| + ZFCP_ERP_ACTION_FAILED = 0xe0, |
| }; |
| |
| enum zfcp_erp_act_state { |
| @@ -378,8 +383,12 @@ static void _zfcp_erp_port_forced_reopen |
| zfcp_erp_port_block(port, clear); |
| zfcp_scsi_schedule_rport_block(port); |
| |
| - if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) |
| + if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_FAILED) { |
| + zfcp_dbf_rec_trig(id, port->adapter, port, NULL, |
| + ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, |
| + ZFCP_ERP_ACTION_FAILED); |
| return; |
| + } |
| |
| zfcp_erp_action_enqueue(ZFCP_ERP_ACTION_REOPEN_PORT_FORCED, |
| port->adapter, port, NULL, id, 0); |
