loop: allow user to set the queue depth

Instead of hardcoding queue depth allow user to set the hw queue depth
using module parameter. Set default value to 128 to retain the existing
behavior.
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Link: https://lore.kernel.org/r/20220215213310.7264-5-kch@nvidia.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

drivers/block/loop.c

@@ -85,6 +85,7 @@
 #include <linux/uaccess.h>
 
 #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ)
+#define LOOP_DEFAULT_HW_Q_DEPTH (128)
 
 static DEFINE_IDR(loop_index_idr);
 static DEFINE_MUTEX(loop_ctl_mutex);
@@ -1785,6 +1786,24 @@ module_param(max_loop, int, 0444);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
 module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
+
+static int hw_queue_depth = LOOP_DEFAULT_HW_Q_DEPTH;
+
+static int loop_set_hw_queue_depth(const char *s, const struct kernel_param *p)
+{
+	int ret = kstrtoint(s, 10, &hw_queue_depth);
+
+	return (ret || (hw_queue_depth < 1)) ? -EINVAL : 0;
+}
+
+static const struct kernel_param_ops loop_hw_qdepth_param_ops = {
+	.set	= loop_set_hw_queue_depth,
+	.get	= param_get_int,
+};
+
+device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444);
+MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 128");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
 
@@ -1979,7 +1998,7 @@ static int loop_add(int i)
 
 	lo->tag_set.ops = &loop_mq_ops;
 	lo->tag_set.nr_hw_queues = 1;
-	lo->tag_set.queue_depth = 128;
+	lo->tag_set.queue_depth = hw_queue_depth;
 	lo->tag_set.numa_node = NUMA_NO_NODE;
 	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
 	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING |