bonding: Fix stacked device detection in arp monitoring

Prior to commit fbd929f2dce460456807a51e18d623db3db9f077
	bonding: support QinQ for bond arp interval

the arp monitoring code allowed for proper detection of devices
stacked on top of vlans.  Since the above commit, the
code can still detect a device stacked on top of single
vlan, but not a device stacked on top of Q-in-Q configuration.
The search will only set the inner vlan tag if the route
device is the vlan device.  However, this is not always the
case, as it is possible to extend the stacked configuration.

With this patch it is possible to provision devices on
top Q-in-Q vlan configuration that should be used as
a source of ARP monitoring information.

For example:
ip link add link bond0 vlan10 type vlan proto 802.1q id 10
ip link add link vlan10 vlan100 type vlan proto 802.1q id 100
ip link add link vlan100 type macvlan

Note:  This patch limites the number of stacked VLANs to 2,
just like before.  The original, however had another issue
in that if we had more then 2 levels of VLANs, we would end
up generating incorrectly tagged traffic.  This is no longer
possible.

Fixes: fbd929f2dce460456807a51e18d623db3db9f077 (bonding: support QinQ for bond arp interval)
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@redhat.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: Ding Tianhong <dingtianhong@huawei.com>
CC: Patric McHardy <kaber@trash.net>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 107 insertions, 69 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 69aff72c8957..d3a67896d435 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2126,10 +2126,10 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
  */
 static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 			  __be32 dest_ip, __be32 src_ip,
-			  struct bond_vlan_tag *inner,
-			  struct bond_vlan_tag *outer)
+			  struct bond_vlan_tag *tags)
 {
 	struct sk_buff *skb;
+	int i;
 
 	pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n",
 		 arp_op, slave_dev->name, &dest_ip, &src_ip);
@@ -2141,21 +2141,26 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 		net_err_ratelimited("ARP packet allocation failed\n");
 		return;
 	}
-	if (outer->vlan_id) {
-		if (inner->vlan_id) {
-			pr_debug("inner tag: proto %X vid %X\n",
-				 ntohs(inner->vlan_proto), inner->vlan_id);
-			skb = __vlan_put_tag(skb, inner->vlan_proto,
-					     inner->vlan_id);
-			if (!skb) {
-				net_err_ratelimited("failed to insert inner VLAN tag\n");
-				return;
-			}
-		}
 
-		pr_debug("outer reg: proto %X vid %X\n",
-			 ntohs(outer->vlan_proto), outer->vlan_id);
-		skb = vlan_put_tag(skb, outer->vlan_proto, outer->vlan_id);
+	/* Go through all the tags backwards and add them to the packet */
+	for (i = BOND_MAX_VLAN_ENCAP - 1; i > 0; i--) {
+		if (!tags[i].vlan_id)
+			continue;
+
+		pr_debug("inner tag: proto %X vid %X\n",
+			 ntohs(tags[i].vlan_proto), tags[i].vlan_id);
+		skb = __vlan_put_tag(skb, tags[i].vlan_proto,
+				     tags[i].vlan_id);
+		if (!skb) {
+			net_err_ratelimited("failed to insert inner VLAN tag\n");
+			return;
+		}
+	}
+	/* Set the outer tag */
+	if (tags[0].vlan_id) {
+		pr_debug("outer tag: proto %X vid %X\n",
+			 ntohs(tags[0].vlan_proto), tags[0].vlan_id);
+		skb = vlan_put_tag(skb, tags[0].vlan_proto, tags[0].vlan_id);
 		if (!skb) {
 			net_err_ratelimited("failed to insert outer VLAN tag\n");
 			return;
@@ -2164,22 +2169,52 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 	arp_xmit(skb);
 }
 
+/* Validate the device path between the @start_dev and the @end_dev.
+ * The path is valid if the @end_dev is reachable through device
+ * stacking.
+ * When the path is validated, collect any vlan information in the
+ * path.
+ */
+static bool bond_verify_device_path(struct net_device *start_dev,
+				    struct net_device *end_dev,
+				    struct bond_vlan_tag *tags)
+{
+	struct net_device *upper;
+	struct list_head  *iter;
+	int  idx;
+
+	if (start_dev == end_dev)
+		return true;
+
+	netdev_for_each_upper_dev_rcu(start_dev, upper, iter) {
+		if (bond_verify_device_path(upper, end_dev, tags)) {
+			if (is_vlan_dev(upper)) {
+				idx = vlan_get_encap_level(upper);
+				if (idx >= BOND_MAX_VLAN_ENCAP)
+					return false;
+
+				tags[idx].vlan_proto =
+						    vlan_dev_vlan_proto(upper);
+				tags[idx].vlan_id = vlan_dev_vlan_id(upper);
+			}
+			return true;
+		}
+	}
+
+	return false;
+}
 
 static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 {
-	struct net_device *upper, *vlan_upper;
-	struct list_head *iter, *vlan_iter;
 	struct rtable *rt;
-	struct bond_vlan_tag inner, outer;
+	struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP];
 	__be32 *targets = bond->params.arp_targets, addr;
 	int i;
+	bool ret;
 
 	for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
 		pr_debug("basa: target %pI4\n", &targets[i]);
-		inner.vlan_proto = 0;
-		inner.vlan_id = 0;
-		outer.vlan_proto = 0;
-		outer.vlan_id = 0;
+		memset(tags, 0, sizeof(tags));
 
 		/* Find out through which dev should the packet go */
 		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
@@ -2192,7 +2227,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 				net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
 						     bond->dev->name,
 						     &targets[i]);
-			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], 0, &inner, &outer);
+			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
+				      0, tags);
 			continue;
 		}
 
@@ -2201,52 +2237,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 			goto found;
 
 		rcu_read_lock();
-		/* first we search only for vlan devices. for every vlan
-		 * found we verify its upper dev list, searching for the
-		 * rt->dst.dev. If found we save the tag of the vlan and
-		 * proceed to send the packet.
-		 */
-		netdev_for_each_all_upper_dev_rcu(bond->dev, vlan_upper,
-						  vlan_iter) {
-			if (!is_vlan_dev(vlan_upper))
-				continue;
-
-			if (vlan_upper == rt->dst.dev) {
-				outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper);
-				outer.vlan_id = vlan_dev_vlan_id(vlan_upper);
-				rcu_read_unlock();
-				goto found;
-			}
-			netdev_for_each_all_upper_dev_rcu(vlan_upper, upper,
-							  iter) {
-				if (upper == rt->dst.dev) {
-					/* If the upper dev is a vlan dev too,
-					 *  set the vlan tag to inner tag.
-					 */
-					if (is_vlan_dev(upper)) {
-						inner.vlan_proto = vlan_dev_vlan_proto(upper);
-						inner.vlan_id = vlan_dev_vlan_id(upper);
-					}
-					outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper);
-					outer.vlan_id = vlan_dev_vlan_id(vlan_upper);
-					rcu_read_unlock();
-					goto found;
-				}
-			}
-		}
-
-		/* if the device we're looking for is not on top of any of
-		 * our upper vlans, then just search for any dev that
-		 * matches, and in case it's a vlan - save the id
-		 */
-		netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
-			if (upper == rt->dst.dev) {
-				rcu_read_unlock();
-				goto found;
-			}
-		}
+		ret = bond_verify_device_path(bond->dev, rt->dst.dev, tags);
 		rcu_read_unlock();
 
+		if (ret)
+			goto found;
+
 		/* Not our device - skip */
 		pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
 			 bond->dev->name, &targets[i],
@@ -2259,7 +2255,7 @@ found:
 		addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
 		ip_rt_put(rt);
 		bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
-			      addr, &inner, &outer);
+			      addr, tags);
 	}
 }
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index b8bdd0acc8f3..00bea320e3b5 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -36,6 +36,7 @@
 
 #define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"
 
+#define BOND_MAX_VLAN_ENCAP	2
 #define BOND_MAX_ARP_TARGETS	16
 
 #define BOND_DEFAULT_MIIMON	100
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 724bde8477b2..c901b13b6f03 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -484,4 +484,10 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb,
 		 */
 		skb->protocol = htons(ETH_P_802_2);
 }
+
+static inline int vlan_get_encap_level(struct net_device *dev)
+{
+	BUG_ON(!is_vlan_dev(dev));
+	return vlan_dev_priv(dev)->nest_level;
+}
 #endif /* !(_LINUX_IF_VLAN_H_) */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9d4b1f1b6b75..b42d07b0390b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3056,10 +3056,19 @@ extern int		weight_p;
 extern int		bpf_jit_enable;
 
 bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						     struct list_head **iter);
 struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 						     struct list_head **iter);
 
 /* iterate through upper list, must be called under RCU read lock */
+#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
+	for (iter = &(dev)->adj_list.upper, \
+	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
+	     updev; \
+	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
+
+/* iterate through upper list, must be called under RCU read lock */
 #define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
 	for (iter = &(dev)->all_adj_list.upper, \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b872bfbd172..9abc503b19b7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4542,6 +4542,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
 EXPORT_SYMBOL(netdev_adjacent_get_private);
 
 /**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
+/**
  * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
  * @iter: list_head ** of the current position