@@ -624,6 +624,20 @@ static void zfcp_erp_strategy_memwait(struct zfcp_erp_action *erp_action)
add_timer(&erp_action->timer);
}
+void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter,
+ int clear, char *dbftag)
+{
+ unsigned long flags;
+ struct zfcp_port *port;
+
+ write_lock_irqsave(&adapter->erp_lock, flags);
+ read_lock(&adapter->port_list_lock);
+ list_for_each_entry(port, &adapter->port_list, list)
+ _zfcp_erp_port_forced_reopen(port, clear, dbftag);
+ read_unlock(&adapter->port_list_lock);
+ write_unlock_irqrestore(&adapter->erp_lock, flags);
+}
+
static void _zfcp_erp_port_reopen_all(struct zfcp_adapter *adapter,
int clear, char *dbftag)
{
@@ -70,6 +70,8 @@ extern void zfcp_erp_port_reopen(struct zfcp_port *port, int clear,
char *dbftag);
extern void zfcp_erp_port_shutdown(struct zfcp_port *, int, char *);
extern void zfcp_erp_port_forced_reopen(struct zfcp_port *, int, char *);
+extern void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter,
+ int clear, char *dbftag);
extern void zfcp_erp_set_lun_status(struct scsi_device *, u32);
extern void zfcp_erp_clear_lun_status(struct scsi_device *, u32);
extern void zfcp_erp_lun_reopen(struct scsi_device *, int, char *);
@@ -368,6 +368,10 @@ static int zfcp_scsi_eh_host_reset_handler(struct scsi_cmnd *scpnt)
struct zfcp_adapter *adapter = zfcp_sdev->port->adapter;
int ret = SUCCESS, fc_ret;
+ if (!(adapter->connection_features & FSF_FEATURE_NPIV_MODE)) {
+ zfcp_erp_port_forced_reopen_all(adapter, 0, "schrh_p");
+ zfcp_erp_wait(adapter);
+ }
zfcp_erp_adapter_reopen(adapter, 0, "schrh_1");
zfcp_erp_wait(adapter);
fc_ret = fc_block_scsi_eh(scpnt);
Suppose more than one non-NPIV FCP device is active on the same channel. Send I/O to storage and have some of the pending I/O run into a SCSI command timeout, e.g. due to bit errors on the fibre. Now the error situation stops. However, we saw FCP requests continue to timeout in the channel. The abort will be successful, but the subsequent TUR fails. Scsi_eh starts. The LUN reset fails. The target reset fails. The host reset only did an FCP device recovery. However, for non-NPIV FCP devices, this does not close and reopen ports on the SAN-side if other non-NPIV FCP device(s) share the same open ports. In order to resolve the continuing FCP request timeouts, we need to explicitly close and reopen ports on the SAN-side. This was missing since the beginning of zfcp in v2.6.0 history commit ea127f975424 ("[PATCH] s390 (7/7): zfcp host adapter."). Note: The FSF requests for forced port reopen could run into FSF request timeouts due to other reasons. This would trigger an internal FCP device recovery. Pending forced port reopen recoveries would get dismissed. So some ports might not get fully reopened during this host reset handler. However, subsequent I/O would trigger the above described escalation and eventually all ports would be forced reopen to resolve any continuing FCP request timeouts due to earlier bit errors. Signed-off-by: Steffen Maier <maier@linux.ibm.com> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: <stable@vger.kernel.org> #3.0+ Reviewed-by: Jens Remus <jremus@linux.ibm.com> Reviewed-by: Benjamin Block <bblock@linux.ibm.com> --- drivers/s390/scsi/zfcp_erp.c | 14 ++++++++++++++ drivers/s390/scsi/zfcp_ext.h | 2 ++ drivers/s390/scsi/zfcp_scsi.c | 4 ++++ 3 files changed, 20 insertions(+)