net: core: add ignore flag to netdev_adjacent structure

In order to link an adjacent node, netdev_upper_dev_link() is used
and in order to unlink an adjacent node, netdev_upper_dev_unlink() is used.
unlink operation does not fail, but link operation can fail.

In order to exchange adjacent nodes, we should unlink an old adjacent
node first. then, link a new adjacent node.
If link operation is failed, we should link an old adjacent node again.
But this link operation can fail too.
It eventually breaks the adjacent link relationship.

This patch adds an ignore flag into the netdev_adjacent structure.
If this flag is set, netdev_upper_dev_link() ignores an old adjacent
node for a moment.

This patch also adds new functions for other modules.
netdev_adjacent_change_prepare()
netdev_adjacent_change_commit()
netdev_adjacent_change_abort()

netdev_adjacent_change_prepare() inserts new device into adjacent list
but new device is not allowed to use immediately.
If netdev_adjacent_change_prepare() fails, it internally rollbacks
adjacent list so that we don't need any other action.
netdev_adjacent_change_commit() deletes old device in the adjacent list
and allows new device to use.
netdev_adjacent_change_abort() rollbacks adjacent list.

Signed-off-by: Taehee Yoo <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/linux/netdevice.h

···
 				 struct netlink_ext_ack *extack);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev,
+				   struct netlink_ext_ack *extack);
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev);
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+				  struct net_device *new_dev,
+				  struct net_device *dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);

net/core/dev.c

···
 	/* upper master flag, there can only be one master device per list */
 	bool master;
 
+	/* lookup ignore flag */
+	bool ignore;
+
 	/* counter for the number of times this device was added to us */
 	u16 ref_nr;
 
···
 	return NULL;
 }
 
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
 {
 	struct net_device *dev = data;
 
···
 {
 	ASSERT_RTNL();
 
-	return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+	return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
 					     upper_dev);
 }
 EXPORT_SYMBOL(netdev_has_upper_dev);
···
 bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
 				  struct net_device *upper_dev)
 {
-	return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+	return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
 					       upper_dev);
 }
 EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
···
 	return NULL;
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get);
+
+static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev)
+{
+	struct netdev_adjacent *upper;
+
+	ASSERT_RTNL();
+
+	if (list_empty(&dev->adj_list.upper))
+		return NULL;
+
+	upper = list_first_entry(&dev->adj_list.upper,
+				 struct netdev_adjacent, list);
+	if (likely(upper->master) && !upper->ignore)
+		return upper->dev;
+	return NULL;
+}
 
 /**
  * netdev_has_any_lower_dev - Check if device is linked to some device
···
 }
 EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
 
-static struct net_device *netdev_next_upper_dev(struct net_device *dev,
-						struct list_head **iter)
+static struct net_device *__netdev_next_upper_dev(struct net_device *dev,
+						  struct list_head **iter,
+						  bool *ignore)
 {
 	struct netdev_adjacent *upper;
 
···
 		return NULL;
 
 	*iter = &upper->list;
+	*ignore = upper->ignore;
 
 	return upper->dev;
 }
···
 	return upper->dev;
 }
 
-static int netdev_walk_all_upper_dev(struct net_device *dev,
-				     int (*fn)(struct net_device *dev,
-					       void *data),
-				     void *data)
+static int __netdev_walk_all_upper_dev(struct net_device *dev,
+				       int (*fn)(struct net_device *dev,
+						 void *data),
+				       void *data)
 {
 	struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
 	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
 	int ret, cur = 0;
+	bool ignore;
 
 	now = dev;
 	iter = &dev->adj_list.upper;
···
 
 		next = NULL;
 		while (1) {
-			udev = netdev_next_upper_dev(now, &iter);
+			udev = __netdev_next_upper_dev(now, &iter, &ignore);
 			if (!udev)
 				break;
+			if (ignore)
+				continue;
 
 			next = udev;
 			niter = &udev->adj_list.upper;
···
 	return 0;
 }
 EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
+
+static bool __netdev_has_upper_dev(struct net_device *dev,
+				   struct net_device *upper_dev)
+{
+	ASSERT_RTNL();
+
+	return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
+					   upper_dev);
+}
 
 /**
  * netdev_lower_get_next_private - Get the next ->private from the
···
 	return lower->dev;
 }
 
+static struct net_device *__netdev_next_lower_dev(struct net_device *dev,
+						  struct list_head **iter,
+						  bool *ignore)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+	*ignore = lower->ignore;
+
+	return lower->dev;
+}
+
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *dev,
 					void *data),
···
 }
 EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
 
+static int __netdev_walk_all_lower_dev(struct net_device *dev,
+				       int (*fn)(struct net_device *dev,
+						 void *data),
+				       void *data)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
+	bool ignore;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			ldev = __netdev_next_lower_dev(now, &iter, &ignore);
+			if (!ldev)
+				break;
+			if (ignore)
+				continue;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return 0;
+}
+
 static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 						    struct list_head **iter)
 {
···
 	struct net_device *udev;
 	struct list_head *iter;
 	u8 max_depth = 0;
+	bool ignore;
 
 	for (iter = &dev->adj_list.upper,
-	     udev = netdev_next_upper_dev(dev, &iter);
+	     udev = __netdev_next_upper_dev(dev, &iter, &ignore);
 	     udev;
-	     udev = netdev_next_upper_dev(dev, &iter)) {
+	     udev = __netdev_next_upper_dev(dev, &iter, &ignore)) {
+		if (ignore)
+			continue;
 		if (max_depth < udev->upper_level)
 			max_depth = udev->upper_level;
 	}
···
 	struct net_device *ldev;
 	struct list_head *iter;
 	u8 max_depth = 0;
+	bool ignore;
 
 	for (iter = &dev->adj_list.lower,
-	     ldev = netdev_next_lower_dev(dev, &iter);
+	     ldev = __netdev_next_lower_dev(dev, &iter, &ignore);
 	     ldev;
-	     ldev = netdev_next_lower_dev(dev, &iter)) {
+	     ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) {
+		if (ignore)
+			continue;
 		if (max_depth < ldev->lower_level)
 			max_depth = ldev->lower_level;
 	}
···
 	adj->master = master;
 	adj->ref_nr = 1;
 	adj->private = private;
+	adj->ignore = false;
 	dev_hold(adj_dev);
 
 	pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
···
 		return -EBUSY;
 
 	/* To prevent loops, check if dev is not upper device to upper_dev. */
-	if (netdev_has_upper_dev(upper_dev, dev))
+	if (__netdev_has_upper_dev(upper_dev, dev))
 		return -EBUSY;
 
 	if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
 		return -EMLINK;
 
 	if (!master) {
-		if (netdev_has_upper_dev(dev, upper_dev))
+		if (__netdev_has_upper_dev(dev, upper_dev))
 			return -EEXIST;
 	} else {
-		master_dev = netdev_master_upper_dev_get(dev);
+		master_dev = __netdev_master_upper_dev_get(dev);
 		if (master_dev)
 			return master_dev == upper_dev ? -EEXIST : -EBUSY;
 	}
···
 		goto rollback;
 
 	__netdev_update_upper_level(dev, NULL);
-	netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+	__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
 
 	__netdev_update_lower_level(upper_dev, NULL);
-	netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL);
+	__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+				    NULL);
 
 	return 0;
 
···
 				      &changeupper_info.info);
 
 	__netdev_update_upper_level(dev, NULL);
-	netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+	__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
 
 	__netdev_update_lower_level(upper_dev, NULL);
-	netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL);
+	__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+				    NULL);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
+
+static void __netdev_adjacent_dev_set(struct net_device *upper_dev,
+				      struct net_device *lower_dev,
+				      bool val)
+{
+	struct netdev_adjacent *adj;
+
+	adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower);
+	if (adj)
+		adj->ignore = val;
+
+	adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper);
+	if (adj)
+		adj->ignore = val;
+}
+
+static void netdev_adjacent_dev_disable(struct net_device *upper_dev,
+					struct net_device *lower_dev)
+{
+	__netdev_adjacent_dev_set(upper_dev, lower_dev, true);
+}
+
+static void netdev_adjacent_dev_enable(struct net_device *upper_dev,
+				       struct net_device *lower_dev)
+{
+	__netdev_adjacent_dev_set(upper_dev, lower_dev, false);
+}
+
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev,
+				   struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!new_dev)
+		return 0;
+
+	if (old_dev && new_dev != old_dev)
+		netdev_adjacent_dev_disable(dev, old_dev);
+
+	err = netdev_upper_dev_link(new_dev, dev, extack);
+	if (err) {
+		if (old_dev && new_dev != old_dev)
+			netdev_adjacent_dev_enable(dev, old_dev);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(netdev_adjacent_change_prepare);
+
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev)
+{
+	if (!new_dev || !old_dev)
+		return;
+
+	if (new_dev == old_dev)
+		return;
+
+	netdev_adjacent_dev_enable(dev, old_dev);
+	netdev_upper_dev_unlink(old_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_commit);
+
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+				  struct net_device *new_dev,
+				  struct net_device *dev)
+{
+	if (!new_dev)
+		return;
+
+	if (old_dev && new_dev != old_dev)
+		netdev_adjacent_dev_enable(dev, old_dev);
+
+	netdev_upper_dev_unlink(new_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_abort);
 
 /**
  * netdev_bonding_info_change - Dispatch event about slave change