3.18-stable patches

added patches:
	scsi-zfcp-fix-scsi_eh-host-reset-with-port_forced-erp-for-non-npiv-fcp-devices.patch

diff --git a/queue-3.18/scsi-zfcp-fix-scsi_eh-host-reset-with-port_forced-erp-for-non-npiv-fcp-devices.patch b/queue-3.18/scsi-zfcp-fix-scsi_eh-host-reset-with-port_forced-erp-for-non-npiv-fcp-devices.patch
new file mode 100644 (file)
index 0000000..9859dbe
--- /dev/null
+++ b/queue-3.18/scsi-zfcp-fix-scsi_eh-host-reset-with-port_forced-erp-for-non-npiv-fcp-devices.patch
@@ -0,0 +1,94 @@
+From 242ec1455151267fe35a0834aa9038e4c4670884 Mon Sep 17 00:00:00 2001
+From: Steffen Maier <maier@linux.ibm.com>
+Date: Tue, 26 Mar 2019 14:36:59 +0100
+Subject: scsi: zfcp: fix scsi_eh host reset with port_forced ERP for non-NPIV FCP devices
+
+From: Steffen Maier <maier@linux.ibm.com>
+
+commit 242ec1455151267fe35a0834aa9038e4c4670884 upstream.
+
+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>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ 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(+)
+
+--- a/drivers/s390/scsi/zfcp_erp.c
++++ b/drivers/s390/scsi/zfcp_erp.c
+@@ -583,6 +583,20 @@ static void zfcp_erp_strategy_memwait(st
+       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 *id)
+ {
+--- a/drivers/s390/scsi/zfcp_ext.h
++++ b/drivers/s390/scsi/zfcp_ext.h
+@@ -56,6 +56,8 @@ extern void zfcp_erp_clear_port_status(s
+ extern int  zfcp_erp_port_reopen(struct zfcp_port *, int, char *);
+ 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 *);
+--- a/drivers/s390/scsi/zfcp_scsi.c
++++ b/drivers/s390/scsi/zfcp_scsi.c
+@@ -294,6 +294,10 @@ static int zfcp_scsi_eh_host_reset_handl
+       struct zfcp_adapter *adapter = zfcp_sdev->port->adapter;
+       int 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);
+       ret = fc_block_scsi_eh(scpnt);

diff --git a/queue-3.18/series b/queue-3.18/series
index 537cd1d23dd04dac69a3fecb7217ae9546835a8c..6b76ca934d065bc0479dd8fea5b361ca40b87de9 100644 (file)
--- a/queue-3.18/series
+++ b/queue-3.18/series
@@ -36,3 +36,4 @@ sctp-get-sctphdr-by-offset-in-sctp_compute_cksum.patch
 mac8390-fix-mmio-access-size-probe.patch
 alsa-pcm-fix-possible-oob-access-in-pcm-oss-plugins.patch
 alsa-pcm-don-t-suspend-stream-in-unrecoverable-pcm-state.patch
+scsi-zfcp-fix-scsi_eh-host-reset-with-port_forced-erp-for-non-npiv-fcp-devices.patch