s390/dasd: add aq_timeouts autoquiesce trigger

Add a sysfs attribute aq_timeouts that controls after how many
timeouts a autoquiesce event might be triggered.

The default value is 32768 which is the maximum number of retries
for the DASD device driver DASD_RETRIES_MAX. This means that the
timeout trigger will never happen.

The default value for DASD retries is 255.
Setting the value to below 255 will trigger the timeout autoquiesce
event before an IO error is generated.

Also add the check for the configured amount of timeouts and trigger
an autoquiesce event if exceeded.

Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Link: https://lore.kernel.org/r/20230405142017.2446986-6-sth@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/s390/block/dasd.c

@@ -1953,6 +1953,16 @@ static void __dasd_device_process_final_queue(struct dasd_device *device,
 	}
 }
 
+/*
+ * check if device should be autoquiesced due to too many timeouts
+ */
+static void __dasd_device_check_autoquiesce_timeout(struct dasd_device *device,
+						    struct dasd_ccw_req *cqr)
+{
+	if ((device->default_retries - cqr->retries) >= device->aq_timeouts)
+		dasd_handle_autoquiesce(device, cqr, DASD_EER_TIMEOUTS);
+}
+
 /*
  * Take a look at the first request on the ccw queue and check
  * if it reached its expire time. If so, terminate the IO.
@@ -1987,6 +1997,7 @@ static void __dasd_device_check_expire(struct dasd_device *device)
 				"remaining\n", cqr, (cqr->expires/HZ),
 				cqr->retries);
 		}
+		__dasd_device_check_autoquiesce_timeout(device, cqr);
 	}
 }
 

drivers/s390/block/dasd_devmap.c

@@ -1552,6 +1552,52 @@ static ssize_t dasd_aqr_store(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(aq_requeue, 0644, dasd_aqr_show, dasd_aqr_store);
 
+/*
+ * aq_timeouts controls how much retries have to time out until
+ * a device gets autoquiesced
+ */
+static ssize_t
+dasd_aq_timeouts_show(struct device *dev, struct device_attribute *attr,
+		      char *buf)
+{
+	struct dasd_device *device;
+	int len;
+
+	device = dasd_device_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(device))
+		return -ENODEV;
+	len = sysfs_emit(buf, "%u\n", device->aq_timeouts);
+	dasd_put_device(device);
+	return len;
+}
+
+static ssize_t
+dasd_aq_timeouts_store(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
+{
+	struct dasd_device *device;
+	unsigned int val;
+
+	device = dasd_device_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(device))
+		return -ENODEV;
+
+	if ((kstrtouint(buf, 10, &val) != 0) ||
+	    val > DASD_RETRIES_MAX || val == 0) {
+		dasd_put_device(device);
+		return -EINVAL;
+	}
+
+	if (val)
+		device->aq_timeouts = val;
+
+	dasd_put_device(device);
+	return count;
+}
+
+static DEVICE_ATTR(aq_timeouts, 0644, dasd_aq_timeouts_show,
+		   dasd_aq_timeouts_store);
+
 /*
  * expiration time for default requests
  */
@@ -2403,6 +2449,7 @@ static struct attribute * dasd_attrs[] = {
 	&dev_attr_ping.attr,
 	&dev_attr_aq_mask.attr,
 	&dev_attr_aq_requeue.attr,
+	&dev_attr_aq_timeouts.attr,
 	NULL,
 };
 

drivers/s390/block/dasd_eckd.c

@@ -2109,6 +2109,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 	device->default_retries = DASD_RETRIES;
 	device->path_thrhld = DASD_ECKD_PATH_THRHLD;
 	device->path_interval = DASD_ECKD_PATH_INTERVAL;
+	device->aq_timeouts = DASD_RETRIES_MAX;
 
 	if (private->conf.gneq) {
 		value = 1;

drivers/s390/block/dasd_int.h

@@ -638,6 +638,7 @@ struct dasd_device {
 	struct kset *paths_info;
 	struct dasd_copy_relation *copy;
 	unsigned long aq_mask;
+	unsigned int aq_timeouts;
 };
 
 struct dasd_block {