[S390] cio: fix I/O cancel function

Function ccw_device_cancel_halt_clear may cause an unexpected kernel
panic if a clear function is currently active at the subchannel for
which it is called. In that case, the iretry counter used to determine
the number of retries is never initialized, leading to an immediate
failure of the function which results in a kernel panic.

Fix this by initializing the iretry counter when the function is
first called. Also replace the kernel panic with a return code: a
single malfunctioning I/O device should not automatically cause a
system-wide kernel panic.

Signed-off-by: Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

2 files changed, 8 insertions, 2 deletions

diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 881bdfd99140..2ff8a22d4257 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1205,6 +1205,7 @@ static void io_subchannel_quiesce(struct subchannel *sch)
 		cdev->handler(cdev, cdev->private->intparm, ERR_PTR(-EIO));
 	while (ret == -EBUSY) {
 		cdev->private->state = DEV_STATE_QUIESCE;
+		cdev->private->iretry = 255;
 		ret = ccw_device_cancel_halt_clear(cdev);
 		if (ret == -EBUSY) {
 			ccw_device_set_timeout(cdev, HZ/10);
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 4395c01a9dac..a845695ac314 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -174,7 +174,10 @@ ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 		ret = cio_clear (sch);
 		return (ret == 0) ? -EBUSY : ret;
 	}
-	panic("Can't stop i/o on subchannel.\n");
+	/* Function was unsuccessful */
+	CIO_MSG_EVENT(0, "0.%x.%04x: could not stop I/O\n",
+		      cdev->private->dev_id.ssid, cdev->private->dev_id.devno);
+	return -EIO;
 }
 
 void ccw_device_update_sense_data(struct ccw_device *cdev)
@@ -766,13 +769,14 @@ ccw_device_online_timeout(struct ccw_device *cdev, enum dev_event dev_event)
 	int ret;
 
 	ccw_device_set_timeout(cdev, 0);
+	cdev->private->iretry = 255;
 	ret = ccw_device_cancel_halt_clear(cdev);
 	if (ret == -EBUSY) {
 		ccw_device_set_timeout(cdev, 3*HZ);
 		cdev->private->state = DEV_STATE_TIMEOUT_KILL;
 		return;
 	}
-	if (ret == -ENODEV)
+	if (ret)
 		dev_fsm_event(cdev, DEV_EVENT_NOTOPER);
 	else if (cdev->handler)
 		cdev->handler(cdev, cdev->private->intparm,
@@ -869,6 +873,7 @@ void ccw_device_kill_io(struct ccw_device *cdev)
 {
 	int ret;
 
+	cdev->private->iretry = 255;
 	ret = ccw_device_cancel_halt_clear(cdev);
 	if (ret == -EBUSY) {
 		ccw_device_set_timeout(cdev, 3*HZ);