[PATCH net-next v9 3/3] net: add sysfs attribute to control napi threaded mode

@@ -337,3 +337,18 @@ Contact:	netdev@vger.kernel.org
 Description:
 		32-bit unsigned integer counting the number of times the link has
 		been down
+
+What:		/sys/class/net/<iface>/threaded
+Date:		Jan 2021
+KernelVersion:	5.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Boolean value to control the threaded mode per device. User could
+		set this value to enable/disable threaded mode for all napi
+		belonging to this device, without the need to do device up/down.
+
+		Possible values:
+		== ==================================
+		0  threaded mode disabled for this dev
+		1  threaded mode enabled for this dev
+		== ==================================

@@ -497,6 +497,8 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
+int dev_set_threaded(struct net_device *dev, bool threaded);
+
 /**
  *	napi_disable - prevent NAPI from scheduling
  *	@n: NAPI context

@@ -4288,8 +4288,9 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 
 	if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
 		/* Paired with smp_mb__before_atomic() in
-		 * napi_enable(). Use READ_ONCE() to guarantee
-		 * a complete read on napi->thread. Only call
+		 * napi_enable()/napi_set_threaded().
+		 * Use READ_ONCE() to guarantee a complete
+		 * read on napi->thread. Only call
 		 * wake_up_process() when it's not NULL.
 		 */
 		thread = READ_ONCE(napi->thread);

@@ -6740,6 +6741,62 @@ static void init_gro_hash(struct napi_struct *napi)
 	napi->gro_bitmask = 0;
 }
 
+static int napi_set_threaded(struct napi_struct *n, bool threaded)
+{
+	int err = 0;
+
+	if (threaded == !!test_bit(NAPI_STATE_THREADED, &n->state))
+		return 0;
+
+	if (!threaded) {
+		clear_bit(NAPI_STATE_THREADED, &n->state);
+		return 0;
+	}
+
+	if (!n->thread) {
+		err = napi_kthread_create(n);
+		if (err)
+			return err;
+	}
+
+	/* Make sure kthread is created before THREADED bit
+	 * is set.
+	 */
+	smp_mb__before_atomic();
+	set_bit(NAPI_STATE_THREADED, &n->state);
+
+	return 0;
+}
+
+static void dev_disable_threaded_all(struct net_device *dev)
+{
+	struct napi_struct *napi;
+
+	list_for_each_entry(napi, &dev->napi_list, dev_list)
+		napi_set_threaded(napi, false);
+	dev->threaded = 0;
+}
+
+int dev_set_threaded(struct net_device *dev, bool threaded)
+{
+	struct napi_struct *napi;
+	int ret;
+
+	dev->threaded = threaded;
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		ret = napi_set_threaded(napi, threaded);
+		if (ret) {
+			/* Error occurred on one of the napi,
+			 * reset threaded mode on all napi.
+			 */
+			dev_disable_threaded_all(dev);
+			break;
+		}
+	}
+
+	return ret;
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {

@@ -538,6 +538,55 @@ static ssize_t phys_switch_id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(phys_switch_id);
 
+static ssize_t threaded_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	int ret;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (!dev_isalive(netdev)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (list_empty(&netdev->napi_list)) {
+		ret = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	ret = sprintf(buf, fmt_dec, netdev->threaded);
+
+unlock:
+	rtnl_unlock();
+	return ret;
+}
+
+static int modify_napi_threaded(struct net_device *dev, unsigned long val)
+{
+	int ret;
+
+	if (list_empty(&dev->napi_list))
+		return -EOPNOTSUPP;
+
+	if (val != 0 && val != 1)
+		return -EOPNOTSUPP;
+
+	ret = dev_set_threaded(dev, val);
+
+	return ret;
+}
+
+static ssize_t threaded_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t len)
+{
+	return netdev_store(dev, attr, buf, len, modify_napi_threaded);
+}
+static DEVICE_ATTR_RW(threaded);
+
 static struct attribute *net_class_attrs[] __ro_after_init = {
 	&dev_attr_netdev_group.attr,
 	&dev_attr_type.attr,

@@ -570,6 +619,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = {
 	&dev_attr_proto_down.attr,
 	&dev_attr_carrier_up_count.attr,
 	&dev_attr_carrier_down_count.attr,
+	&dev_attr_threaded.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(net_class);