net: add generic PF_BRIDGE:RTM_ FDB hooks

This adds two new flags NTF_MASTER and NTF_SELF that can
now be used to specify where PF_BRIDGE netlink commands should
be sent. NTF_MASTER sends the commands to the 'dev->master'
device for parsing. Typically this will be the linux net/bridge,
or open-vswitch devices. Also without any flags set the command
will be handled by the master device as well so that current user
space tools continue to work as expected.

The NTF_SELF flag will push the PF_BRIDGE commands to the
device. In the basic example below the commands are then parsed
and programmed in the embedded bridge.

Note if both NTF_SELF and NTF_MASTER bits are set then the
command will be sent to both 'dev->master' and 'dev' this allows
user space to easily keep the embedded bridge and software bridge
in sync.

There is a slight complication in the case with both flags set
when an error occurs. To resolve this the rtnl handler clears
the NTF_ flag in the netlink ack to indicate which sets completed
successfully. The add/del handlers will abort as soon as any
error occurs.

To support this new net device ops were added to call into
the device and the existing bridging code was refactored
to use these. There should be no required changes in user space
to support the current bridge behavior.

A basic setup with a SR-IOV enabled NIC looks like this,

          veth0  veth2
            |      |
          ------------
          |  bridge0 |   <---- software bridging
          ------------
               /
               /
  ethx.y      ethx
    VF         PF
     \         \          <---- propagate FDB entries to HW
     \         \
  --------------------
  |  Embedded Bridge |    <---- hardware offloaded switching
  --------------------

In this case the embedded bridge must be managed to allow 'veth0'
to communicate with 'ethx.y' correctly. At present drivers managing
the embedded bridge either send frames onto the network which
then get dropped by the switch OR the embedded bridge will flood
these frames. With this patch we have a mechanism to manage the
embedded bridge correctly from user space. This example is specific
to SR-IOV but replacing the VF with another PF or dropping this
into the DSA framework generates similar management issues.

Examples session using the 'br'[1] tool to add, dump and then
delete a mac address with a new "embedded" option and enabled
ixgbe driver:

# br fdb add 22:35:19:ac:60:59 dev eth3
# br fdb
port    mac addr                flags
veth0   22:35:19:ac:60:58       static
veth0   9a:5f:81:f7:f6:ec       local
eth3    00:1b:21:55:23:59       local
eth3    22:35:19:ac:60:59       static
veth0   22:35:19:ac:60:57       static
#br fdb add 22:35:19:ac:60:59 embedded dev eth3
#br fdb
port    mac addr                flags
veth0   22:35:19:ac:60:58       static
veth0   9a:5f:81:f7:f6:ec       local
eth3    00:1b:21:55:23:59       local
eth3    22:35:19:ac:60:59       static
veth0   22:35:19:ac:60:57       static
eth3    22:35:19:ac:60:59       local embedded
#br fdb del 22:35:19:ac:60:59 embedded dev eth3

I added a couple lines to 'br' to set the flags correctly is all. It
is my opinion that the merit of this patch is now embedded and SW
bridges can both be modeled correctly in user space using very nearly
the same message passing.

[1] 'br' tool was published as an RFC here and will be renamed 'bridge'
    http://patchwork.ozlabs.org/patch/117664/

Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for
valuable feedback, suggestions, and review.

v2: fixed api descriptions and error case with both NTF_SELF and
    NTF_MASTER set plus updated patch description.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 228 insertions, 112 deletions

diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h
index b188f68..275e5d6 100644
--- a/include/linux/neighbour.h
+++ b/include/linux/neighbour.h
@@ -33,6 +33,9 @@ enum {
 #define NTF_PROXY	0x08	/* == ATF_PUBL */
 #define NTF_ROUTER	0x80
 
+#define NTF_SELF	0x02
+#define NTF_MASTER	0x04
+
 /*
  *	Neighbor Cache Entry States.
  */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d312232..100c48c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -54,6 +54,7 @@
 #include <net/netprio_cgroup.h>
 
 #include <linux/netdev_features.h>
+#include <linux/neighbour.h>
 
 struct netpoll_info;
 struct device;
@@ -905,6 +906,16 @@ struct netdev_fcoe_hbainfo {
  *	feature set might be less than what was returned by ndo_fix_features()).
  *	Must return >0 or -errno if it changed dev->features itself.
  *
+ * int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev,
+ *		      unsigned char *addr, u16 flags)
+ *	Adds an FDB entry to dev for addr.
+ * int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev,
+ *		      unsigned char *addr)
+ *	Deletes the FDB entry from dev coresponding to addr.
+ * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
+ *		       struct net_device *dev, int idx)
+ *	Used to add FDB entries to dump requests. Implementers should add
+ *	entries to skb and update idx with the number of entries.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1002,6 +1013,18 @@ struct net_device_ops {
 						    netdev_features_t features);
 	int			(*ndo_neigh_construct)(struct neighbour *n);
 	void			(*ndo_neigh_destroy)(struct neighbour *n);
+
+	int			(*ndo_fdb_add)(struct ndmsg *ndm,
+					       struct net_device *dev,
+					       unsigned char *addr,
+					       u16 flags);
+	int			(*ndo_fdb_del)(struct ndmsg *ndm,
+					       struct net_device *dev,
+					       unsigned char *addr);
+	int			(*ndo_fdb_dump)(struct sk_buff *skb,
+						struct netlink_callback *cb,
+						struct net_device *dev,
+						int idx);
 };
 
 /*
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 577592e..2c1de89 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -801,6 +801,10 @@ rtattr_failure:
 	return table;
 }
 
+extern int ndo_dflt_fdb_dump(struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     struct net_device *dev,
+			     int idx);
 #endif /* __KERNEL__ */
 
 
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ba829de..d6e5929 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -317,6 +317,9 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_add_slave		 = br_add_slave,
 	.ndo_del_slave		 = br_del_slave,
 	.ndo_fix_features        = br_fix_features,
+	.ndo_fdb_add		 = br_fdb_add,
+	.ndo_fdb_del		 = br_fdb_delete,
+	.ndo_fdb_dump		 = br_fdb_dump,
 };
 
 static void br_dev_free(struct net_device *dev)
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 80dbce4..5945c54 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -535,44 +535,38 @@ errout:
 }
 
 /* Dump information about entries, in response to GETNEIGH */
-int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+int br_fdb_dump(struct sk_buff *skb,
+		struct netlink_callback *cb,
+		struct net_device *dev,
+		int idx)
 {
-	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
-	int idx = 0;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		struct net_bridge *br = netdev_priv(dev);
-		int i;
-
-		if (!(dev->priv_flags & IFF_EBRIDGE))
-			continue;
+	struct net_bridge *br = netdev_priv(dev);
+	int i;
 
-		for (i = 0; i < BR_HASH_SIZE; i++) {
-			struct hlist_node *h;
-			struct net_bridge_fdb_entry *f;
+	if (!(dev->priv_flags & IFF_EBRIDGE))
+		goto out;
 
-			hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) {
-				if (idx < cb->args[0])
-					goto skip;
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		struct hlist_node *h;
+		struct net_bridge_fdb_entry *f;
 
-				if (fdb_fill_info(skb, br, f,
-						  NETLINK_CB(cb->skb).pid,
-						  cb->nlh->nlmsg_seq,
-						  RTM_NEWNEIGH,
-						  NLM_F_MULTI) < 0)
-					break;
+		hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) {
+			if (idx < cb->args[0])
+				goto skip;
+
+			if (fdb_fill_info(skb, br, f,
+					  NETLINK_CB(cb->skb).pid,
+					  cb->nlh->nlmsg_seq,
+					  RTM_NEWNEIGH,
+					  NLM_F_MULTI) < 0)
+				break;
 skip:
-				++idx;
-			}
+			++idx;
 		}
 	}
-	rcu_read_unlock();
-
-	cb->args[0] = idx;
 
-	return skb->len;
+out:
+	return idx;
 }
 
 /* Update (create or replace) forwarding database entry */
@@ -614,43 +608,11 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
 }
 
 /* Add new permanent fdb entry with RTM_NEWNEIGH */
-int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+int br_fdb_add(struct ndmsg *ndm, struct net_device *dev,
+	       unsigned char *addr, u16 nlh_flags)
 {
-	struct net *net = sock_net(skb->sk);
-	struct ndmsg *ndm;
-	struct nlattr *tb[NDA_MAX+1];
-	struct net_device *dev;
 	struct net_bridge_port *p;
-	const __u8 *addr;
-	int err;
-
-	ASSERT_RTNL();
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
-	if (err < 0)
-		return err;
-
-	ndm = nlmsg_data(nlh);
-	if (ndm->ndm_ifindex == 0) {
-		pr_info("bridge: RTM_NEWNEIGH with invalid ifindex\n");
-		return -EINVAL;
-	}
-
-	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
-	if (dev == NULL) {
-		pr_info("bridge: RTM_NEWNEIGH with unknown ifindex\n");
-		return -ENODEV;
-	}
-
-	if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
-		pr_info("bridge: RTM_NEWNEIGH with invalid address\n");
-		return -EINVAL;
-	}
-
-	addr = nla_data(tb[NDA_LLADDR]);
-	if (!is_valid_ether_addr(addr)) {
-		pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n");
-		return -EINVAL;
-	}
+	int err = 0;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
 		pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
@@ -670,14 +632,14 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 		rcu_read_unlock();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
-		err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags);
+		err = fdb_add_entry(p, addr, ndm->ndm_state, nlh_flags);
 		spin_unlock_bh(&p->br->hash_lock);
 	}
 
 	return err;
 }
 
-static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr)
+static int fdb_delete_by_addr(struct net_bridge_port *p, u8 *addr)
 {
 	struct net_bridge *br = p->br;
 	struct hlist_head *head = &br->hash[br_mac_hash(addr)];
@@ -692,40 +654,12 @@ static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr)
 }
 
 /* Remove neighbor entry with RTM_DELNEIGH */
-int br_fdb_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev,
+		  unsigned char *addr)
 {
-	struct net *net = sock_net(skb->sk);
-	struct ndmsg *ndm;
 	struct net_bridge_port *p;
-	struct nlattr *llattr;
-	const __u8 *addr;
-	struct net_device *dev;
 	int err;
 
-	ASSERT_RTNL();
-	if (nlmsg_len(nlh) < sizeof(*ndm))
-		return -EINVAL;
-
-	ndm = nlmsg_data(nlh);
-	if (ndm->ndm_ifindex == 0) {
-		pr_info("bridge: RTM_DELNEIGH with invalid ifindex\n");
-		return -EINVAL;
-	}
-
-	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
-	if (dev == NULL) {
-		pr_info("bridge: RTM_DELNEIGH with unknown ifindex\n");
-		return -ENODEV;
-	}
-
-	llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR);
-	if (llattr == NULL || nla_len(llattr) != ETH_ALEN) {
-		pr_info("bridge: RTM_DELNEIGH with invalid address\n");
-		return -EINVAL;
-	}
-
-	addr = nla_data(llattr);
-
 	p = br_port_get_rtnl(dev);
 	if (p == NULL) {
 		pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index df38108..2080485 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -232,18 +232,6 @@ int __init br_netlink_init(void)
 			      br_rtm_setlink, NULL, NULL);
 	if (err)
 		goto err3;
-	err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH,
-			      br_fdb_add, NULL, NULL);
-	if (err)
-		goto err3;
-	err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH,
-			      br_fdb_delete, NULL, NULL);
-	if (err)
-		goto err3;
-	err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH,
-			      NULL, br_fdb_dump, NULL);
-	if (err)
-		goto err3;
 
 	return 0;
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index f8ffd8c..1a8ad4f 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -360,9 +360,18 @@ extern int br_fdb_insert(struct net_bridge *br,
 extern void br_fdb_update(struct net_bridge *br,
 			  struct net_bridge_port *source,
 			  const unsigned char *addr);
-extern int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb);
-extern int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg);
-extern int br_fdb_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg);
+
+extern int br_fdb_delete(struct ndmsg *ndm,
+			 struct net_device *dev,
+			 unsigned char *addr);
+extern int br_fdb_add(struct ndmsg *nlh,
+		      struct net_device *dev,
+		      unsigned char *addr,
+		      u16 nlh_flags);
+extern int br_fdb_dump(struct sk_buff *skb,
+		       struct netlink_callback *cb,
+		       struct net_device *dev,
+		       int idx);
 
 /* br_forward.c */
 extern void br_deliver(const struct net_bridge_port *to,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2ff6fe4..b348b7f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -35,7 +35,9 @@
 #include <linux/security.h>
 #include <linux/mutex.h>
 #include <linux/if_addr.h>
+#include <linux/if_bridge.h>
 #include <linux/pci.h>
+#include <linux/etherdevice.h>
 
 #include <asm/uaccess.h>
 
@@ -1978,6 +1980,152 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 }
 
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *master = NULL;
+	struct ndmsg *ndm;
+	struct nlattr *tb[NDA_MAX+1];
+	struct net_device *dev;
+	u8 *addr;
+	int err;
+
+	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+	if (err < 0)
+		return err;
+
+	ndm = nlmsg_data(nlh);
+	if (ndm->ndm_ifindex == 0) {
+		pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n");
+		return -EINVAL;
+	}
+
+	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
+	if (dev == NULL) {
+		pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n");
+		return -ENODEV;
+	}
+
+	if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
+		pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n");
+		return -EINVAL;
+	}
+
+	addr = nla_data(tb[NDA_LLADDR]);
+	if (!is_valid_ether_addr(addr)) {
+		pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
+		return -EINVAL;
+	}
+
+	err = -EOPNOTSUPP;
+
+	/* Support fdb on master device the net/bridge default case */
+	if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
+	    (dev->priv_flags & IFF_BRIDGE_PORT)) {
+		master = dev->master;
+		err = master->netdev_ops->ndo_fdb_add(ndm, dev, addr,
+						      nlh->nlmsg_flags);
+		if (err)
+			goto out;
+		else
+			ndm->ndm_flags &= ~NTF_MASTER;
+	}
+
+	/* Embedded bridge, macvlan, and any other device support */
+	if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) {
+		err = dev->netdev_ops->ndo_fdb_add(ndm, dev, addr,
+						   nlh->nlmsg_flags);
+
+		if (!err)
+			ndm->ndm_flags &= ~NTF_SELF;
+	}
+out:
+	return err;
+}
+
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+	struct net *net = sock_net(skb->sk);
+	struct ndmsg *ndm;
+	struct nlattr *llattr;
+	struct net_device *dev;
+	int err = -EINVAL;
+	__u8 *addr;
+
+	if (nlmsg_len(nlh) < sizeof(*ndm))
+		return -EINVAL;
+
+	ndm = nlmsg_data(nlh);
+	if (ndm->ndm_ifindex == 0) {
+		pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n");
+		return -EINVAL;
+	}
+
+	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
+	if (dev == NULL) {
+		pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n");
+		return -ENODEV;
+	}
+
+	llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR);
+	if (llattr == NULL || nla_len(llattr) != ETH_ALEN) {
+		pr_info("PF_BRIGDE: RTM_DELNEIGH with invalid address\n");
+		return -EINVAL;
+	}
+
+	addr = nla_data(llattr);
+	err = -EOPNOTSUPP;
+
+	/* Support fdb on master device the net/bridge default case */
+	if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
+	    (dev->priv_flags & IFF_BRIDGE_PORT)) {
+		struct net_device *master = dev->master;
+
+		if (master->netdev_ops->ndo_fdb_del)
+			err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr);
+
+		if (err)
+			goto out;
+		else
+			ndm->ndm_flags &= ~NTF_MASTER;
+	}
+
+	/* Embedded bridge, macvlan, and any other device support */
+	if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) {
+		err = dev->netdev_ops->ndo_fdb_del(ndm, dev, addr);
+
+		if (!err)
+			ndm->ndm_flags &= ~NTF_SELF;
+	}
+out:
+	return err;
+}
+
+static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int idx = 0;
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (dev->priv_flags & IFF_BRIDGE_PORT) {
+			struct net_device *master = dev->master;
+			const struct net_device_ops *ops = master->netdev_ops;
+
+			if (ops->ndo_fdb_dump)
+				idx = ops->ndo_fdb_dump(skb, cb, dev, idx);
+		}
+
+		if (dev->netdev_ops->ndo_fdb_dump)
+			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
+	}
+	rcu_read_unlock();
+
+	cb->args[0] = idx;
+	return skb->len;
+}
+
 /* Protected by RTNL sempahore.  */
 static struct rtattr **rta_buf;
 static int rtattr_max;
@@ -2150,5 +2298,9 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
 	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
+
+	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
+	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
+	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL);
 }