[PATCH net-next v3 0/3] bonding: support QinQ for bond arp interval

[PATCH net-next v3 0/3] bonding: support QinQ for bond arp interval

[Ding Tianhong]

v1->v2: remvoe the comment "TODO: QinQ?".
	convert pr_xxx() to pr_xxx_ratelimited() for arp interval.

v2->v3: remove the unnecessary log for arp interval and add net ratelimit to
	avoid spam log.

Ding Tianhong (3):
  vlan: make a new function vlan_dev_vlan_proto() and export
  bonding: support QinQ for bond arp interval
  bonding: add net_ratelimt to avoid spam in arp interval

 drivers/net/bonding/bond_main.c | 80 +++++++++++++++++++++++++++--------------
 drivers/net/bonding/bonding.h   |  5 +++
 include/linux/if_vlan.h         |  7 ++++
 net/8021q/vlan_core.c           |  6 ++++
 4 files changed, 72 insertions(+), 26 deletions(-)

-- 
1.8.0

[PATCH net-next v3 1/3] vlan: make a new function vlan_dev_vlan_proto() and export

[Ding Tianhong]

The vlan support 2 proto: 802.1q and 802.1ad, so make a new function
called vlan_dev_vlan_proto() which could return the vlan proto for
input dev.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
 include/linux/if_vlan.h | 7 +++++++
 net/8021q/vlan_core.c   | 6 ++++++
 2 files changed, 13 insertions(+)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index bbedfb5..967a428 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -110,6 +110,7 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
+extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
 
 /**
  *	struct vlan_priority_tci_mapping - vlan egress priority mappings
@@ -216,6 +217,12 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 	return 0;
 }
 
+static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	BUG();
+	return 0;
+}
+
 static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
 					       u32 skprio)
 {
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 35b3c19..3c32bd2 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -106,6 +106,12 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
 static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
 	if (skb_cow(skb, skb_headroom(skb)) < 0)
-- 
1.8.0

[PATCH net-next v3 2/3] bonding: support QinQ for bond arp interval

[Ding Tianhong]

The bond send arp request to indicate that the slave is active, and if the bond dev
is a vlan dev, it will set the vlan tag in skb to notice the vlan group, but the
bond could only send a skb with 802.1q proto, not support for QinQ.

So add outer tag for lower vlan tag and inner tag for upper vlan tag to support QinQ,
The new skb will be consist of two vlan tag just like this:

dst mac | src mac | outer vlan tag | inner vlan tag | data | .....

If We don't need QinQ, the inner vlan tag could be set to 0 and use outer vlan tag
 as a normal vlan group.

Using "ip link" to configure the bond for QinQ and add test log:

ip link add link bond0  bond0.20 type vlan proto 802.1ad id 20
ip link add link bond0.20  bond0.20.200 type vlan proto 802.1q id 200

ifconfig bond0.20 11.11.20.36/24
ifconfig bond0.20.200 11.11.200.36/24

echo +11.11.200.37 > /sys/class/net/bond0/bonding/arp_ip_target

90:e2:ba:07:4a:5c (oui Unknown) > Broadcast, ethertype 802.1Q-QinQ (0x88a8),length 50: vlan 20, p 0,ethertype 802.1Q, vlan 200, p 0, ethertype ARP, Ethernet (len 6), IPv4 (len 4), Request who-has 11.11.200.37 tell 11.11.200.36, length 28

90:e2:ba:06:f9:86 (oui Unknown) > 90:e2:ba:07:4a:5c (oui Unknown), ethertype 802.1Q-QinQ (0x88a8), length 50: vlan 20, p 0, ethertype 802.1Q, vlan 200, p 0, ethertype ARP, Ethernet (len 6), IPv4 (len 4), Reply 11.11.200.37 is-at 90:e2:ba:06:f9:86 (oui Unknown), length 28

v1->v2: remove the comment "TODO: QinQ?".

Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
 drivers/net/bonding/bond_main.c | 63 +++++++++++++++++++++++++++++------------
 drivers/net/bonding/bonding.h   |  5 ++++
 2 files changed, 50 insertions(+), 18 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e717db3..6758c2d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2124,12 +2124,15 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
  * switches in VLAN mode (especially if ports are configured as
  * "native" to a VLAN) might not pass non-tagged frames.
  */
-static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
+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 sk_buff *skb;
 
-	pr_debug("arp %d on slave %s: dst %pI4 src %pI4 vid %d\n",
-		 arp_op, slave_dev->name, &dest_ip, &src_ip, vlan_id);
+	pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n",
+		 arp_op, slave_dev->name, &dest_ip, &src_ip);
 
 	skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
 			 NULL, slave_dev->dev_addr, NULL);
@@ -2138,10 +2141,22 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_
 		pr_err("ARP packet allocation failed\n");
 		return;
 	}
-	if (vlan_id) {
-		skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_id);
+	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) {
+				pr_err("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);
 		if (!skb) {
-			pr_err("failed to insert VLAN tag\n");
+			pr_err("failed to insert outer VLAN tag\n");
 			return;
 		}
 	}
@@ -2154,11 +2169,16 @@ 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;
 	__be32 *targets = bond->params.arp_targets, addr;
-	int i, vlan_id;
+	int i;
 
 	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;
 
 		/* Find out through which dev should the packet go */
 		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
@@ -2170,12 +2190,10 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 			if (bond->params.arp_validate && net_ratelimit())
 				pr_warn("%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, 0);
+			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], 0, &inner, &outer);
 			continue;
 		}
 
-		vlan_id = 0;
-
 		/* bond device itself */
 		if (rt->dst.dev == bond->dev)
 			goto found;
@@ -2185,17 +2203,30 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		 * 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.
-		 *
-		 * TODO: QinQ?
 		 */
 		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) {
-					vlan_id = vlan_dev_vlan_id(vlan_upper);
+					/* 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;
 				}
@@ -2208,10 +2239,6 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		 */
 		netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
 			if (upper == rt->dst.dev) {
-				/* if it's a vlan - get its VID */
-				if (is_vlan_dev(upper))
-					vlan_id = vlan_dev_vlan_id(upper);
-
 				rcu_read_unlock();
 				goto found;
 			}
@@ -2230,7 +2257,7 @@ 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, vlan_id);
+			      addr, &inner, &outer);
 	}
 }
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 0896f1d..b8bdd0a 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -266,6 +266,11 @@ struct bonding {
 #define bond_slave_get_rtnl(dev) \
 	((struct slave *) rtnl_dereference(dev->rx_handler_data))
 
+struct bond_vlan_tag {
+	__be16		vlan_proto;
+	unsigned short	vlan_id;
+};
+
 /**
  * Returns NULL if the net_device does not belong to any of the bond's slaves
  *
-- 
1.8.0

[PATCH net-next v3 3/3] bonding: add net_ratelimt to avoid spam in arp interval

[Ding Tianhong]

Remove the unnecessary log and add net_ratelimit to the others, in order to
avoid spam the log.

Cc: Joe Perches <joe@perches.com>
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
 drivers/net/bonding/bond_main.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6758c2d..9b678fb 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2131,32 +2131,33 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 {
 	struct sk_buff *skb;
 
-	pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n",
-		 arp_op, slave_dev->name, &dest_ip, &src_ip);
+	net_dbg_ratelimited("arp %d on slave %s: dst %pI4 src %pI4\n",
+			    arp_op, slave_dev->name, &dest_ip, &src_ip);
 
 	skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
 			 NULL, slave_dev->dev_addr, NULL);
 
 	if (!skb) {
-		pr_err("ARP packet allocation failed\n");
+		pr_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);
+			net_dbg_ratelimited("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) {
-				pr_err("failed to insert inner VLAN tag\n");
+				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);
+		net_dbg_ratelimited("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);
 		if (!skb) {
-			pr_err("failed to insert outer VLAN tag\n");
+			net_err_ratelimited("failed to insert outer VLAN tag\n");
 			return;
 		}
 	}
@@ -2174,7 +2175,6 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 	int i;
 
 	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;
@@ -2187,9 +2187,10 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 			/* there's no route to target - try to send arp
 			 * probe to generate any traffic (arp_validate=0)
 			 */
-			if (bond->params.arp_validate && net_ratelimit())
-				pr_warn("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
-					bond->dev->name, &targets[i]);
+			if (bond->params.arp_validate)
+				net_dbg_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);
 			continue;
 		}
@@ -2246,9 +2247,9 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		rcu_read_unlock();
 
 		/* Not our device - skip */
-		pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
-			 bond->dev->name, &targets[i],
-			 rt->dst.dev ? rt->dst.dev->name : "NULL");
+		net_dbg_ratelimited("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
+				    bond->dev->name, &targets[i],
+				    rt->dst.dev ? rt->dst.dev->name : "NULL");
 
 		ip_rt_put(rt);
 		continue;
-- 
1.8.0

Re: [PATCH net-next v3 3/3] bonding: add net_ratelimt to avoid spam in arp interval

[Veaceslav Falico]

On Tue, Mar 25, 2014 at 11:21:37AM +0800, Ding Tianhong wrote:
...snip...
>-	pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n",
>-		 arp_op, slave_dev->name, &dest_ip, &src_ip);
>+	net_dbg_ratelimited("arp %d on slave %s: dst %pI4 src %pI4\n",
>+			    arp_op, slave_dev->name, &dest_ip, &src_ip);

I don't think we should ratelimit debug statements - as they're turned on
only when the user is actually debugging, so that all the debug statements
should be shown.

As an example here - I actually used it and grepped for a specific arp. If
it was ratelimited - I might have skipped it.

> 	if (outer->vlan_id) {
> 		if (inner->vlan_id) {
>-			pr_debug("inner tag: proto %X vid %X\n",
>-				 ntohs(inner->vlan_proto), inner->vlan_id);
>+			net_dbg_ratelimited("inner tag: proto %X vid %X\n",
>+					    ntohs(inner->vlan_proto),
>+					    inner->vlan_id);

Same here.

>-		pr_debug("outer reg: proto %X vid %X\n",
>-			 ntohs(outer->vlan_proto), outer->vlan_id);
>+		net_dbg_ratelimited("outer reg: proto %X vid %X\n",
>+				     ntohs(outer->vlan_proto), outer->vlan_id);

And here.

>-			if (bond->params.arp_validate && net_ratelimit())
>-				pr_warn("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
>-					bond->dev->name, &targets[i]);
>+			if (bond->params.arp_validate)
>+				net_dbg_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
>+						    bond->dev->name,
>+						    &targets[i]);

You've changed an already ratelimited warning with a debug statement. This
warning is here for a reason.

>-		pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
>-			 bond->dev->name, &targets[i],
>-			 rt->dst.dev ? rt->dst.dev->name : "NULL");
>+		net_dbg_ratelimited("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
>+				    bond->dev->name, &targets[i],
>+				    rt->dst.dev ? rt->dst.dev->name : "NULL");

Again the dbg ratelimit.

[PATCH net-next v3 1/3] vlan: make a new function vlan_dev_vlan_proto() and export

[Ding Tianhong]

The vlan support 2 proto: 802.1q and 802.1ad, so make a new function
called vlan_dev_vlan_proto() which could return the vlan proto for
input dev.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
 include/linux/if_vlan.h | 7 +++++++
 net/8021q/vlan_core.c   | 6 ++++++
 2 files changed, 13 insertions(+)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index bbedfb5..967a428 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -110,6 +110,7 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
+extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
 
 /**
  *	struct vlan_priority_tci_mapping - vlan egress priority mappings
@@ -216,6 +217,12 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 	return 0;
 }
 
+static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	BUG();
+	return 0;
+}
+
 static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
 					       u32 skprio)
 {
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 35b3c19..3c32bd2 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -106,6 +106,12 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
 static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
 	if (skb_cow(skb, skb_headroom(skb)) < 0)
-- 
1.8.0