[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20121014143540.230021858@decadent.org.uk>
Date: Sun, 14 Oct 2012 15:36:20 +0100
From: Ben Hutchings <ben@...adent.org.uk>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc: akpm@...ux-foundation.org, alan@...rguk.ukuu.org.uk,
Steffen Maier <maier@...ux.vnet.ibm.com>,
James Bottomley <JBottomley@...allels.com>
Subject: [ 047/147] [SCSI] zfcp: Do not wakeup while suspended
3.2-stable review patch. If anyone has any objections, please let me know.
------------------
From: Steffen Maier <maier@...ux.vnet.ibm.com>
commit cb45214960bc989af8b911ebd77da541c797717d upstream.
If the mapping of FCP device bus ID and corresponding subchannel
is modified while the Linux image is suspended, the resume of FCP
devices can fail. During resume, zfcp gets callbacks from cio regarding
the modified subchannels but they can be arbitrarily mixed with the
restore/resume callback. Since the cio callbacks would trigger
adapter recovery, zfcp could wakeup before the resume callback.
Therefore, ignore the cio callbacks regarding subchannels while
being suspended. We can safely do so, since zfcp does not deal itself
with subchannels. For problem determination purposes, we still trace the
ignored callback events.
The following kernel messages could be seen on resume:
kernel: <WWPN>: parent <FCP device bus ID> should not be sleeping
As part of adapter reopen recovery, zfcp performs auto port scanning
which can erroneously try to register new remote ports with
scsi_transport_fc and the device core code complains about the parent
(adapter) still sleeping.
kernel: zfcp.3dff9c: <FCP device bus ID>:\
Setting up the QDIO connection to the FCP adapter failed
<last kernel message repeated 3 more times>
kernel: zfcp.574d43: <FCP device bus ID>:\
ERP cannot recover an error on the FCP device
In such cases, the adapter gave up recovery and remained blocked along
with its child objects: remote ports and LUNs/scsi devices. Even the
adapter shutdown as part of giving up recovery failed because the ccw
device state remained disconnected. Later, the corresponding remote
ports ran into dev_loss_tmo. As a result, the LUNs were erroneously
not available again after resume.
Even a manually triggered adapter recovery (e.g. sysfs attribute
failed, or device offline/online via sysfs) could not recover the
adapter due to the remaining disconnected state of the corresponding
ccw device.
Signed-off-by: Steffen Maier <maier@...ux.vnet.ibm.com>
Signed-off-by: James Bottomley <JBottomley@...allels.com>
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
drivers/s390/scsi/zfcp_ccw.c | 73 ++++++++++++++++++++++++++++++++++++------
drivers/s390/scsi/zfcp_dbf.c | 20 ++++++++++++
drivers/s390/scsi/zfcp_dbf.h | 1 +
drivers/s390/scsi/zfcp_def.h | 1 +
drivers/s390/scsi/zfcp_ext.h | 1 +
5 files changed, 86 insertions(+), 10 deletions(-)
diff --git a/drivers/s390/scsi/zfcp_ccw.c b/drivers/s390/scsi/zfcp_ccw.c
index e37f045..9646766 100644
--- a/drivers/s390/scsi/zfcp_ccw.c
+++ b/drivers/s390/scsi/zfcp_ccw.c
@@ -39,17 +39,23 @@ void zfcp_ccw_adapter_put(struct zfcp_adapter *adapter)
spin_unlock_irqrestore(&zfcp_ccw_adapter_ref_lock, flags);
}
-static int zfcp_ccw_activate(struct ccw_device *cdev)
-
+/**
+ * zfcp_ccw_activate - activate adapter and wait for it to finish
+ * @cdev: pointer to belonging ccw device
+ * @clear: Status flags to clear.
+ * @tag: s390dbf trace record tag
+ */
+static int zfcp_ccw_activate(struct ccw_device *cdev, int clear, char *tag)
{
struct zfcp_adapter *adapter = zfcp_ccw_adapter_by_cdev(cdev);
if (!adapter)
return 0;
+ zfcp_erp_clear_adapter_status(adapter, clear);
zfcp_erp_set_adapter_status(adapter, ZFCP_STATUS_COMMON_RUNNING);
zfcp_erp_adapter_reopen(adapter, ZFCP_STATUS_COMMON_ERP_FAILED,
- "ccresu2");
+ tag);
zfcp_erp_wait(adapter);
flush_work(&adapter->scan_work);
@@ -164,26 +170,29 @@ static int zfcp_ccw_set_online(struct ccw_device *cdev)
BUG_ON(!zfcp_reqlist_isempty(adapter->req_list));
adapter->req_no = 0;
- zfcp_ccw_activate(cdev);
+ zfcp_ccw_activate(cdev, 0, "ccsonl1");
zfcp_ccw_adapter_put(adapter);
return 0;
}
/**
- * zfcp_ccw_set_offline - set_offline function of zfcp driver
+ * zfcp_ccw_offline_sync - shut down adapter and wait for it to finish
* @cdev: pointer to belonging ccw device
+ * @set: Status flags to set.
+ * @tag: s390dbf trace record tag
*
* This function gets called by the common i/o layer and sets an adapter
* into state offline.
*/
-static int zfcp_ccw_set_offline(struct ccw_device *cdev)
+static int zfcp_ccw_offline_sync(struct ccw_device *cdev, int set, char *tag)
{
struct zfcp_adapter *adapter = zfcp_ccw_adapter_by_cdev(cdev);
if (!adapter)
return 0;
- zfcp_erp_adapter_shutdown(adapter, 0, "ccsoff1");
+ zfcp_erp_set_adapter_status(adapter, set);
+ zfcp_erp_adapter_shutdown(adapter, 0, tag);
zfcp_erp_wait(adapter);
zfcp_ccw_adapter_put(adapter);
@@ -191,6 +200,18 @@ static int zfcp_ccw_set_offline(struct ccw_device *cdev)
}
/**
+ * zfcp_ccw_set_offline - set_offline function of zfcp driver
+ * @cdev: pointer to belonging ccw device
+ *
+ * This function gets called by the common i/o layer and sets an adapter
+ * into state offline.
+ */
+static int zfcp_ccw_set_offline(struct ccw_device *cdev)
+{
+ return zfcp_ccw_offline_sync(cdev, 0, "ccsoff1");
+}
+
+/**
* zfcp_ccw_notify - ccw notify function
* @cdev: pointer to belonging ccw device
* @event: indicates if adapter was detached or attached
@@ -207,6 +228,11 @@ static int zfcp_ccw_notify(struct ccw_device *cdev, int event)
switch (event) {
case CIO_GONE:
+ if (atomic_read(&adapter->status) &
+ ZFCP_STATUS_ADAPTER_SUSPENDED) { /* notification ignore */
+ zfcp_dbf_hba_basic("ccnigo1", adapter);
+ break;
+ }
dev_warn(&cdev->dev, "The FCP device has been detached\n");
zfcp_erp_adapter_shutdown(adapter, 0, "ccnoti1");
break;
@@ -216,6 +242,11 @@ static int zfcp_ccw_notify(struct ccw_device *cdev, int event)
zfcp_erp_adapter_shutdown(adapter, 0, "ccnoti2");
break;
case CIO_OPER:
+ if (atomic_read(&adapter->status) &
+ ZFCP_STATUS_ADAPTER_SUSPENDED) { /* notification ignore */
+ zfcp_dbf_hba_basic("ccniop1", adapter);
+ break;
+ }
dev_info(&cdev->dev, "The FCP device is operational again\n");
zfcp_erp_set_adapter_status(adapter,
ZFCP_STATUS_COMMON_RUNNING);
@@ -251,6 +282,28 @@ static void zfcp_ccw_shutdown(struct ccw_device *cdev)
zfcp_ccw_adapter_put(adapter);
}
+static int zfcp_ccw_suspend(struct ccw_device *cdev)
+{
+ zfcp_ccw_offline_sync(cdev, ZFCP_STATUS_ADAPTER_SUSPENDED, "ccsusp1");
+ return 0;
+}
+
+static int zfcp_ccw_thaw(struct ccw_device *cdev)
+{
+ /* trace records for thaw and final shutdown during suspend
+ can only be found in system dump until the end of suspend
+ but not after resume because it's based on the memory image
+ right after the very first suspend (freeze) callback */
+ zfcp_ccw_activate(cdev, 0, "ccthaw1");
+ return 0;
+}
+
+static int zfcp_ccw_resume(struct ccw_device *cdev)
+{
+ zfcp_ccw_activate(cdev, ZFCP_STATUS_ADAPTER_SUSPENDED, "ccresu1");
+ return 0;
+}
+
struct ccw_driver zfcp_ccw_driver = {
.driver = {
.owner = THIS_MODULE,
@@ -263,7 +316,7 @@ struct ccw_driver zfcp_ccw_driver = {
.set_offline = zfcp_ccw_set_offline,
.notify = zfcp_ccw_notify,
.shutdown = zfcp_ccw_shutdown,
- .freeze = zfcp_ccw_set_offline,
- .thaw = zfcp_ccw_activate,
- .restore = zfcp_ccw_activate,
+ .freeze = zfcp_ccw_suspend,
+ .thaw = zfcp_ccw_thaw,
+ .restore = zfcp_ccw_resume,
};
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index c6e47d5..e1a8cc2 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -200,6 +200,26 @@ void zfcp_dbf_hba_def_err(struct zfcp_adapter *adapter, u64 req_id, u16 scount,
spin_unlock_irqrestore(&dbf->pay_lock, flags);
}
+/**
+ * zfcp_dbf_hba_basic - trace event for basic adapter events
+ * @adapter: pointer to struct zfcp_adapter
+ */
+void zfcp_dbf_hba_basic(char *tag, struct zfcp_adapter *adapter)
+{
+ struct zfcp_dbf *dbf = adapter->dbf;
+ struct zfcp_dbf_hba *rec = &dbf->hba_buf;
+ unsigned long flags;
+
+ spin_lock_irqsave(&dbf->hba_lock, flags);
+ memset(rec, 0, sizeof(*rec));
+
+ memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
+ rec->id = ZFCP_DBF_HBA_BASIC;
+
+ debug_event(dbf->hba, 1, rec, sizeof(*rec));
+ spin_unlock_irqrestore(&dbf->hba_lock, flags);
+}
+
static void zfcp_dbf_set_common(struct zfcp_dbf_rec *rec,
struct zfcp_adapter *adapter,
struct zfcp_port *port,
diff --git a/drivers/s390/scsi/zfcp_dbf.h b/drivers/s390/scsi/zfcp_dbf.h
index 714f087..3ac7a4b 100644
--- a/drivers/s390/scsi/zfcp_dbf.h
+++ b/drivers/s390/scsi/zfcp_dbf.h
@@ -154,6 +154,7 @@ enum zfcp_dbf_hba_id {
ZFCP_DBF_HBA_RES = 1,
ZFCP_DBF_HBA_USS = 2,
ZFCP_DBF_HBA_BIT = 3,
+ ZFCP_DBF_HBA_BASIC = 4,
};
/**
diff --git a/drivers/s390/scsi/zfcp_def.h b/drivers/s390/scsi/zfcp_def.h
index 2955e1a..5bc4afba 100644
--- a/drivers/s390/scsi/zfcp_def.h
+++ b/drivers/s390/scsi/zfcp_def.h
@@ -77,6 +77,7 @@ struct zfcp_reqlist;
#define ZFCP_STATUS_ADAPTER_SIOSL_ISSUED 0x00000004
#define ZFCP_STATUS_ADAPTER_XCONFIG_OK 0x00000008
#define ZFCP_STATUS_ADAPTER_HOST_CON_INIT 0x00000010
+#define ZFCP_STATUS_ADAPTER_SUSPENDED 0x00000040
#define ZFCP_STATUS_ADAPTER_ERP_PENDING 0x00000100
#define ZFCP_STATUS_ADAPTER_LINK_UNPLUGGED 0x00000200
#define ZFCP_STATUS_ADAPTER_DATA_DIV_ENABLED 0x00000400
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index 36f4227..4eeef78 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -54,6 +54,7 @@ extern void zfcp_dbf_hba_fsf_res(char *, struct zfcp_fsf_req *);
extern void zfcp_dbf_hba_bit_err(char *, struct zfcp_fsf_req *);
extern void zfcp_dbf_hba_berr(struct zfcp_dbf *, struct zfcp_fsf_req *);
extern void zfcp_dbf_hba_def_err(struct zfcp_adapter *, u64, u16, void **);
+extern void zfcp_dbf_hba_basic(char *, struct zfcp_adapter *);
extern void zfcp_dbf_san_req(char *, struct zfcp_fsf_req *, u32);
extern void zfcp_dbf_san_res(char *, struct zfcp_fsf_req *);
extern void zfcp_dbf_san_in_els(char *, struct zfcp_fsf_req *);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists