Commit ef4021fe authored by Steffen Maier's avatar Steffen Maier Committed by Martin K. Petersen

scsi: zfcp: fix to prevent port_remove with pure auto scan LUNs (only sdevs)

When the user tries to remove a zfcp port via sysfs, we only rejected it if
there are zfcp unit children under the port. With purely automatically
scanned LUNs there are no zfcp units but only SCSI devices. In such cases,
the port_remove erroneously continued. We close the port and this
implicitly closes all LUNs under the port. The SCSI devices survive with
their private zfcp_scsi_dev still holding a reference to the "removed"
zfcp_port (still allocated but invisible in sysfs) [zfcp_get_port_by_wwpn
in zfcp_scsi_slave_alloc]. This is not a problem as long as the fc_rport
stays blocked. Once (auto) port scan brings back the removed port, we
unblock its fc_rport again by design.  However, there is no mechanism that
would recover (open) the LUNs under the port (no "ersfs_3" without
zfcp_unit [zfcp_erp_strategy_followup_success]).  Any pending or new I/O to
such LUN leads to repeated:

  Done: NEEDS_RETRY Result: hostbyte=DID_IMM_RETRY driverbyte=DRIVER_OK

See also v4.10 commit 6f2ce1c6 ("scsi: zfcp: fix rport unblock race
with LUN recovery"). Even a manual LUN recovery
(echo 0 > /sys/bus/scsi/devices/H:C:T:L/zfcp_failed)
does not help, as the LUN links to the old "removed" port which remains
to lack ZFCP_STATUS_COMMON_RUNNING [zfcp_erp_required_act].
The only workaround is to first ensure that the fc_rport is blocked
(e.g. port_remove again in case it was re-discovered by (auto) port scan),
then delete the SCSI devices, and finally re-discover by (auto) port scan.
The port scan includes an fc_rport unblock, which in turn triggers
a new scan on the scsi target to freshly get new pure auto scan LUNs.

Fix this by rejecting port_remove also if there are SCSI devices
(even without any zfcp_unit) under this port. Re-use mechanics from v3.7
commit d99b601b ("[SCSI] zfcp: restore refcount check on port_remove").
However, we have to give up zfcp_sysfs_port_units_mutex earlier in unit_add
to prevent a deadlock with scsi_host scan taking shost->scan_mutex first
and then zfcp_sysfs_port_units_mutex now in our zfcp_scsi_slave_alloc().
Signed-off-by: default avatarSteffen Maier <maier@linux.ibm.com>
Fixes: b62a8d9b ("[SCSI] zfcp: Use SCSI device data zfcp scsi dev instead of zfcp unit")
Fixes: f8210e34 ("[SCSI] zfcp: Allow midlayer to scan for LUNs when running in NPIV mode")
Cc: <stable@vger.kernel.org> #2.6.37+
Reviewed-by: default avatarBenjamin Block <bblock@linux.ibm.com>
Signed-off-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
parent d27e5e07
...@@ -167,6 +167,7 @@ extern const struct attribute_group *zfcp_port_attr_groups[]; ...@@ -167,6 +167,7 @@ extern const struct attribute_group *zfcp_port_attr_groups[];
extern struct mutex zfcp_sysfs_port_units_mutex; extern struct mutex zfcp_sysfs_port_units_mutex;
extern struct device_attribute *zfcp_sysfs_sdev_attrs[]; extern struct device_attribute *zfcp_sysfs_sdev_attrs[];
extern struct device_attribute *zfcp_sysfs_shost_attrs[]; extern struct device_attribute *zfcp_sysfs_shost_attrs[];
bool zfcp_sysfs_port_is_removing(const struct zfcp_port *const port);
/* zfcp_unit.c */ /* zfcp_unit.c */
extern int zfcp_unit_add(struct zfcp_port *, u64); extern int zfcp_unit_add(struct zfcp_port *, u64);
......
...@@ -129,6 +129,15 @@ static int zfcp_scsi_slave_alloc(struct scsi_device *sdev) ...@@ -129,6 +129,15 @@ static int zfcp_scsi_slave_alloc(struct scsi_device *sdev)
zfcp_sdev->erp_action.port = port; zfcp_sdev->erp_action.port = port;
mutex_lock(&zfcp_sysfs_port_units_mutex);
if (zfcp_sysfs_port_is_removing(port)) {
/* port is already gone */
mutex_unlock(&zfcp_sysfs_port_units_mutex);
put_device(&port->dev); /* undo zfcp_get_port_by_wwpn() */
return -ENXIO;
}
mutex_unlock(&zfcp_sysfs_port_units_mutex);
unit = zfcp_unit_find(port, zfcp_scsi_dev_lun(sdev)); unit = zfcp_unit_find(port, zfcp_scsi_dev_lun(sdev));
if (unit) if (unit)
put_device(&unit->dev); put_device(&unit->dev);
......
...@@ -235,6 +235,53 @@ static ZFCP_DEV_ATTR(adapter, port_rescan, S_IWUSR, NULL, ...@@ -235,6 +235,53 @@ static ZFCP_DEV_ATTR(adapter, port_rescan, S_IWUSR, NULL,
DEFINE_MUTEX(zfcp_sysfs_port_units_mutex); DEFINE_MUTEX(zfcp_sysfs_port_units_mutex);
static void zfcp_sysfs_port_set_removing(struct zfcp_port *const port)
{
lockdep_assert_held(&zfcp_sysfs_port_units_mutex);
atomic_set(&port->units, -1);
}
bool zfcp_sysfs_port_is_removing(const struct zfcp_port *const port)
{
lockdep_assert_held(&zfcp_sysfs_port_units_mutex);
return atomic_read(&port->units) == -1;
}
static bool zfcp_sysfs_port_in_use(struct zfcp_port *const port)
{
struct zfcp_adapter *const adapter = port->adapter;
unsigned long flags;
struct scsi_device *sdev;
bool in_use = true;
mutex_lock(&zfcp_sysfs_port_units_mutex);
if (atomic_read(&port->units) > 0)
goto unlock_port_units_mutex; /* zfcp_unit(s) under port */
spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
__shost_for_each_device(sdev, adapter->scsi_host) {
const struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev);
if (sdev->sdev_state == SDEV_DEL ||
sdev->sdev_state == SDEV_CANCEL)
continue;
if (zsdev->port != port)
continue;
/* alive scsi_device under port of interest */
goto unlock_host_lock;
}
/* port is about to be removed, so no more unit_add or slave_alloc */
zfcp_sysfs_port_set_removing(port);
in_use = false;
unlock_host_lock:
spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
unlock_port_units_mutex:
mutex_unlock(&zfcp_sysfs_port_units_mutex);
return in_use;
}
static ssize_t zfcp_sysfs_port_remove_store(struct device *dev, static ssize_t zfcp_sysfs_port_remove_store(struct device *dev,
struct device_attribute *attr, struct device_attribute *attr,
const char *buf, size_t count) const char *buf, size_t count)
...@@ -257,16 +304,11 @@ static ssize_t zfcp_sysfs_port_remove_store(struct device *dev, ...@@ -257,16 +304,11 @@ static ssize_t zfcp_sysfs_port_remove_store(struct device *dev,
else else
retval = 0; retval = 0;
mutex_lock(&zfcp_sysfs_port_units_mutex); if (zfcp_sysfs_port_in_use(port)) {
if (atomic_read(&port->units) > 0) {
retval = -EBUSY; retval = -EBUSY;
mutex_unlock(&zfcp_sysfs_port_units_mutex);
put_device(&port->dev); /* undo zfcp_get_port_by_wwpn() */ put_device(&port->dev); /* undo zfcp_get_port_by_wwpn() */
goto out; goto out;
} }
/* port is about to be removed, so no more unit_add */
atomic_set(&port->units, -1);
mutex_unlock(&zfcp_sysfs_port_units_mutex);
write_lock_irq(&adapter->port_list_lock); write_lock_irq(&adapter->port_list_lock);
list_del(&port->list); list_del(&port->list);
......
...@@ -124,7 +124,7 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun) ...@@ -124,7 +124,7 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun)
int retval = 0; int retval = 0;
mutex_lock(&zfcp_sysfs_port_units_mutex); mutex_lock(&zfcp_sysfs_port_units_mutex);
if (atomic_read(&port->units) == -1) { if (zfcp_sysfs_port_is_removing(port)) {
/* port is already gone */ /* port is already gone */
retval = -ENODEV; retval = -ENODEV;
goto out; goto out;
...@@ -168,8 +168,14 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun) ...@@ -168,8 +168,14 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun)
write_lock_irq(&port->unit_list_lock); write_lock_irq(&port->unit_list_lock);
list_add_tail(&unit->list, &port->unit_list); list_add_tail(&unit->list, &port->unit_list);
write_unlock_irq(&port->unit_list_lock); write_unlock_irq(&port->unit_list_lock);
/*
* lock order: shost->scan_mutex before zfcp_sysfs_port_units_mutex
* due to zfcp_unit_scsi_scan() => zfcp_scsi_slave_alloc()
*/
mutex_unlock(&zfcp_sysfs_port_units_mutex);
zfcp_unit_scsi_scan(unit); zfcp_unit_scsi_scan(unit);
return retval;
out: out:
mutex_unlock(&zfcp_sysfs_port_units_mutex); mutex_unlock(&zfcp_sysfs_port_units_mutex);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment