net: core: limit nested device depth

Current code doesn't limit the number of nested devices.
Nested devices would be handled recursively and this needs huge stack
memory. So, unlimited nested devices could make stack overflow.

This patch adds upper_level and lower_leve, they are common variables
and represent maximum lower/upper depth.
When upper/lower device is attached or dettached,
{lower/upper}_level are updated. and if maximum depth is bigger than 8,
attach routine fails and returns -EMLINK.

Test commands:
    ip link add dummy0 type dummy
    ip link add link dummy0 name vlan1 type vlan id 1
    ip link set vlan1 up

    for i in {2..100}
    do
	    let A=$i-1

	    ip link add name vlan$i link vlan$A type vlan id $i
    done

Splat looks like:
[  140.483124] BUG: looking up invalid subclass: 8
[  140.483505] turning off the locking correctness validator.
[  140.483505] CPU: 0 PID: 1324 Comm: ip Not tainted 5.3.0-rc7+ torvalds#322
[  140.483505] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015
[  140.483505] Call Trace:
[  140.483505]  dump_stack+0x7c/0xbb
[  140.483505]  register_lock_class+0x64d/0x14d0
[  140.483505]  ? is_dynamic_key+0x230/0x230
[  140.483505]  ? module_assert_mutex_or_preempt+0x41/0x70
[  140.483505]  ? __module_address+0x3f/0x3c0
[  140.483505]  lockdep_init_map+0x24e/0x630
[  140.483505]  vlan_dev_init+0x828/0xce0 [8021q]
[  140.483505]  register_netdevice+0x24f/0xd70
[  140.483505]  ? netdev_change_features+0xa0/0xa0
[  140.483505]  ? dev_get_nest_level+0xe1/0x170
[  140.483505]  register_vlan_dev+0x29b/0x710 [8021q]
[  140.483505]  __rtnl_newlink+0xb75/0x1180
[  ... ]

[  168.446539] WARNING: can't dereference registers at 00000000bef3d701 for ip apic_timer_interrupt+0xf/0x20
[  168.466843] ==================================================================
[  168.469452] BUG: KASAN: slab-out-of-bounds in __unwind_start+0x71/0x850
[  168.480707] Write of size 88 at addr ffff8880b8856d38 by task ip/1758
[  168.480707]
[  168.480707] CPU: 1 PID: 1758 Comm: ip Not tainted 5.3.0-rc7+ torvalds#322
[  ... ]
[  168.794493] Rebooting in 5 seconds..

Signed-off-by: Taehee Yoo <ap420073@gmail.com>

include/linux/netdevice.h

@@ -1624,6 +1624,8 @@ enum netdev_priv_flags {
  *	@type:		Interface hardware type
  *	@hard_header_len: Maximum hardware header length.
  *	@min_header_len:  Minimum hardware header length
+ *	@upper_level:	Maximum depth level of upper devices.
+ *	@lower_level:	Maximum depth level of lower devices.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -1854,6 +1856,8 @@ struct net_device {
 	unsigned short		type;
 	unsigned short		hard_header_len;
 	unsigned char		min_header_len;
+	unsigned char		upper_level;
+	unsigned char		lower_level;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;

net/core/dev.c

@@ -146,6 +146,7 @@
 #include "net-sysfs.h"
 
 #define MAX_GRO_SKBS 8
+#define MAX_NEST_DEV 8
 
 /* This should be increased if a protocol with a bigger head is added. */
 #define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -6602,6 +6603,21 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
 
+static struct net_device *netdev_next_upper_dev(struct net_device *dev,
+						struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	upper = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+
 static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
 						    struct list_head **iter)
 {
@@ -6619,6 +6635,33 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
 	return upper->dev;
 }
 
+int netdev_walk_all_upper_dev(struct net_device *dev,
+			      int (*fn)(struct net_device *dev,
+					void *data),
+			      void *data)
+{
+	struct net_device *udev;
+	struct list_head *iter;
+	int ret;
+
+	for (iter = &dev->adj_list.upper,
+	     udev = netdev_next_upper_dev(dev, &iter);
+	     udev;
+	     udev = netdev_next_upper_dev(dev, &iter)) {
+		/* first is the upper device itself */
+		ret = fn(udev, data);
+		if (ret)
+			return ret;
+
+		/* then look at all of its upper devices */
+		ret = netdev_walk_all_upper_dev(udev, fn, data);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
 				  int (*fn)(struct net_device *dev,
 					    void *data),
@@ -6785,6 +6828,52 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 	return lower->dev;
 }
 
+static u8 __netdev_upper_depth(struct net_device *dev)
+{
+	struct net_device *udev;
+	struct list_head *iter;
+	u8 max_depth = 0;
+
+	for (iter = &dev->adj_list.upper,
+	     udev = netdev_next_upper_dev(dev, &iter);
+	     udev;
+	     udev = netdev_next_upper_dev(dev, &iter)) {
+		if (max_depth < udev->upper_level)
+			max_depth = udev->upper_level;
+	}
+
+	return max_depth;
+}
+
+static u8 __netdev_lower_depth(struct net_device *dev)
+{
+	struct net_device *ldev;
+	struct list_head *iter;
+	u8 max_depth = 0;
+
+	for (iter = &dev->adj_list.lower,
+	     ldev = netdev_next_lower_dev(dev, &iter);
+	     ldev;
+	     ldev = netdev_next_lower_dev(dev, &iter)) {
+		if (max_depth < ldev->lower_level)
+			max_depth = ldev->lower_level;
+	}
+
+	return max_depth;
+}
+
+static int __netdev_update_upper_level(struct net_device *dev, void *data)
+{
+	dev->upper_level = __netdev_upper_depth(dev) + 1;
+	return 0;
+}
+
+static int __netdev_update_lower_level(struct net_device *dev, void *data)
+{
+	dev->lower_level = __netdev_lower_depth(dev) + 1;
+	return 0;
+}
+
 int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
 				  int (*fn)(struct net_device *dev,
 					    void *data),
@@ -7063,6 +7152,9 @@ static int __netdev_upper_dev_link(struct net_device *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))
 			return -EEXIST;
@@ -7089,6 +7181,12 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (ret)
 		goto rollback;
 
+	__netdev_update_upper_level(dev, 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);
+
 	return 0;
 
 rollback:
@@ -7171,6 +7269,12 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 				      &changeupper_info.info);
+
+	__netdev_update_upper_level(dev, 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);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
@@ -9157,6 +9261,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
+	dev->upper_level = 1;
+	dev->lower_level = 1;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);