Merge branch 'mdb-get'

Ido Schimmel says:

====================
Add MDB get support

This patchset adds MDB get support, allowing user space to request a
single MDB entry to be retrieved instead of dumping the entire MDB.
Support is added in both the bridge and VXLAN drivers.

Patches #1-gregkh#6 are small preparations in both drivers.

Patches gregkh#7-gregkh#8 add the required uAPI attributes for the new functionality
and the MDB get net device operation (NDO), respectively.

Patches gregkh#9-gregkh#10 implement the MDB get NDO in both drivers.

Patch gregkh#11 registers a handler for RTM_GETMDB messages in rtnetlink core.
The handler derives the net device from the ifindex specified in the
ancillary header and invokes its MDB get NDO.

Patches gregkh#12-gregkh#13 add selftests by converting tests that use MDB dump with
grep to the new MDB get functionality.

iproute2 changes can be found here [1].

v2:
* Patch gregkh#7: Add a comment to describe attributes structure.
* Patch gregkh#9: Add a comment above spin_lock_bh().

[1] https://github.com/idosch/iproute2/tree/submit/mdb_get_v1
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vxlan/vxlan_core.c

@@ -3226,6 +3226,7 @@ static const struct net_device_ops vxlan_netdev_ether_ops = {
 	.ndo_mdb_add		= vxlan_mdb_add,
 	.ndo_mdb_del		= vxlan_mdb_del,
 	.ndo_mdb_dump		= vxlan_mdb_dump,
+	.ndo_mdb_get		= vxlan_mdb_get,
 	.ndo_fill_metadata_dst	= vxlan_fill_metadata_dst,
 };
 

drivers/net/vxlan/vxlan_mdb.c

@@ -370,12 +370,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto,
 	return true;
 }
 
-static void vxlan_mdb_config_group_set(struct vxlan_mdb_config *cfg,
-				       const struct br_mdb_entry *entry,
-				       const struct nlattr *source_attr)
+static void vxlan_mdb_group_set(struct vxlan_mdb_entry_key *group,
+				const struct br_mdb_entry *entry,
+				const struct nlattr *source_attr)
 {
-	struct vxlan_mdb_entry_key *group = &cfg->group;
-
 	switch (entry->addr.proto) {
 	case htons(ETH_P_IP):
 		group->dst.sa.sa_family = AF_INET;
@@ -503,7 +501,7 @@ static int vxlan_mdb_config_attrs_init(struct vxlan_mdb_config *cfg,
 				       entry->addr.proto, extack))
 		return -EINVAL;
 
-	vxlan_mdb_config_group_set(cfg, entry, mdbe_attrs[MDBE_ATTR_SOURCE]);
+	vxlan_mdb_group_set(&cfg->group, entry, mdbe_attrs[MDBE_ATTR_SOURCE]);
 
 	/* rtnetlink code only validates that IPv4 group address is
 	 * multicast.
@@ -927,23 +925,20 @@ vxlan_mdb_nlmsg_src_list_size(const struct vxlan_mdb_entry_key *group,
 	return nlmsg_size;
 }
 
-static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan,
-				   const struct vxlan_mdb_entry *mdb_entry,
-				   const struct vxlan_mdb_remote *remote)
+static size_t
+vxlan_mdb_nlmsg_remote_size(const struct vxlan_dev *vxlan,
+			    const struct vxlan_mdb_entry *mdb_entry,
+			    const struct vxlan_mdb_remote *remote)
 {
 	const struct vxlan_mdb_entry_key *group = &mdb_entry->key;
 	struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
 	size_t nlmsg_size;
 
-	nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) +
-		     /* MDBA_MDB */
-		     nla_total_size(0) +
-		     /* MDBA_MDB_ENTRY */
-		     nla_total_size(0) +
 		     /* MDBA_MDB_ENTRY_INFO */
-		     nla_total_size(sizeof(struct br_mdb_entry)) +
+	nlmsg_size = nla_total_size(sizeof(struct br_mdb_entry)) +
 		     /* MDBA_MDB_EATTR_TIMER */
 		     nla_total_size(sizeof(u32));
+
 	/* MDBA_MDB_EATTR_SOURCE */
 	if (vxlan_mdb_is_sg(group))
 		nlmsg_size += nla_total_size(vxlan_addr_size(&group->dst));
@@ -971,6 +966,19 @@ static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan,
 	return nlmsg_size;
 }
 
+static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan,
+				   const struct vxlan_mdb_entry *mdb_entry,
+				   const struct vxlan_mdb_remote *remote)
+{
+	return NLMSG_ALIGN(sizeof(struct br_port_msg)) +
+	       /* MDBA_MDB */
+	       nla_total_size(0) +
+	       /* MDBA_MDB_ENTRY */
+	       nla_total_size(0) +
+	       /* Remote entry */
+	       vxlan_mdb_nlmsg_remote_size(vxlan, mdb_entry, remote);
+}
+
 static int vxlan_mdb_nlmsg_fill(const struct vxlan_dev *vxlan,
 				struct sk_buff *skb,
 				const struct vxlan_mdb_entry *mdb_entry,
@@ -1298,6 +1306,156 @@ int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return err;
 }
 
+static const struct nla_policy vxlan_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
+					      sizeof(struct in_addr),
+					      sizeof(struct in6_addr)),
+	[MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+};
+
+static int vxlan_mdb_get_parse(struct net_device *dev, struct nlattr *tb[],
+			       struct vxlan_mdb_entry_key *group,
+			       struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_GET_ENTRY]);
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
+	memset(group, 0, sizeof(*group));
+	group->vni = vxlan->default_dst.remote_vni;
+
+	if (!tb[MDBA_GET_ENTRY_ATTRS]) {
+		vxlan_mdb_group_set(group, entry, NULL);
+		return 0;
+	}
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+			       tb[MDBA_GET_ENTRY_ATTRS],
+			       vxlan_mdbe_attrs_get_pol, extack);
+	if (err)
+		return err;
+
+	if (mdbe_attrs[MDBE_ATTR_SOURCE] &&
+	    !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE],
+				       entry->addr.proto, extack))
+		return -EINVAL;
+
+	vxlan_mdb_group_set(group, entry, mdbe_attrs[MDBE_ATTR_SOURCE]);
+
+	if (mdbe_attrs[MDBE_ATTR_SRC_VNI])
+		group->vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI]));
+
+	return 0;
+}
+
+static struct sk_buff *
+vxlan_mdb_get_reply_alloc(const struct vxlan_dev *vxlan,
+			  const struct vxlan_mdb_entry *mdb_entry)
+{
+	struct vxlan_mdb_remote *remote;
+	size_t nlmsg_size;
+
+	nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) +
+		     /* MDBA_MDB */
+		     nla_total_size(0) +
+		     /* MDBA_MDB_ENTRY */
+		     nla_total_size(0);
+
+	list_for_each_entry(remote, &mdb_entry->remotes, list)
+		nlmsg_size += vxlan_mdb_nlmsg_remote_size(vxlan, mdb_entry,
+							  remote);
+
+	return nlmsg_new(nlmsg_size, GFP_KERNEL);
+}
+
+static int
+vxlan_mdb_get_reply_fill(const struct vxlan_dev *vxlan,
+			 struct sk_buff *skb,
+			 const struct vxlan_mdb_entry *mdb_entry,
+			 u32 portid, u32 seq)
+{
+	struct nlattr *mdb_nest, *mdb_entry_nest;
+	struct vxlan_mdb_remote *remote;
+	struct br_port_msg *bpm;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put(skb, portid, seq, RTM_NEWMDB, sizeof(*bpm), 0);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	bpm = nlmsg_data(nlh);
+	memset(bpm, 0, sizeof(*bpm));
+	bpm->family  = AF_BRIDGE;
+	bpm->ifindex = vxlan->dev->ifindex;
+	mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB);
+	if (!mdb_nest) {
+		err = -EMSGSIZE;
+		goto cancel;
+	}
+	mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY);
+	if (!mdb_entry_nest) {
+		err = -EMSGSIZE;
+		goto cancel;
+	}
+
+	list_for_each_entry(remote, &mdb_entry->remotes, list) {
+		err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote);
+		if (err)
+			goto cancel;
+	}
+
+	nla_nest_end(skb, mdb_entry_nest);
+	nla_nest_end(skb, mdb_nest);
+	nlmsg_end(skb, nlh);
+
+	return 0;
+
+cancel:
+	nlmsg_cancel(skb, nlh);
+	return err;
+}
+
+int vxlan_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid,
+		  u32 seq, struct netlink_ext_ack *extack)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_mdb_entry *mdb_entry;
+	struct vxlan_mdb_entry_key group;
+	struct sk_buff *skb;
+	int err;
+
+	ASSERT_RTNL();
+
+	err = vxlan_mdb_get_parse(dev, tb, &group, extack);
+	if (err)
+		return err;
+
+	mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group);
+	if (!mdb_entry) {
+		NL_SET_ERR_MSG_MOD(extack, "MDB entry not found");
+		return -ENOENT;
+	}
+
+	skb = vxlan_mdb_get_reply_alloc(vxlan, mdb_entry);
+	if (!skb)
+		return -ENOMEM;
+
+	err = vxlan_mdb_get_reply_fill(vxlan, skb, mdb_entry, portid, seq);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to fill MDB get reply");
+		goto free;
+	}
+
+	return rtnl_unicast(skb, dev_net(dev), portid);
+
+free:
+	kfree_skb(skb);
+	return err;
+}
+
 struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan,
 						struct sk_buff *skb,
 						__be32 src_vni)

drivers/net/vxlan/vxlan_private.h

@@ -235,6 +235,8 @@ int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags,
 		  struct netlink_ext_ack *extack);
 int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 		  struct netlink_ext_ack *extack);
+int vxlan_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid,
+		  u32 seq, struct netlink_ext_ack *extack);
 struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan,
 						struct sk_buff *skb,
 						__be32 src_vni);

include/linux/netdevice.h

@@ -1609,6 +1609,10 @@ struct net_device_ops {
 	int			(*ndo_mdb_dump)(struct net_device *dev,
 						struct sk_buff *skb,
 						struct netlink_callback *cb);
+	int			(*ndo_mdb_get)(struct net_device *dev,
+					       struct nlattr *tb[], u32 portid,
+					       u32 seq,
+					       struct netlink_ext_ack *extack);
 	int			(*ndo_bridge_setlink)(struct net_device *dev,
 						      struct nlmsghdr *nlh,
 						      u16 flags,

include/uapi/linux/if_bridge.h

@@ -723,6 +723,24 @@ enum {
 };
 #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
 
+/* [MDBA_GET_ENTRY] = {
+ *    struct br_mdb_entry
+ *    [MDBA_GET_ENTRY_ATTRS] = {
+ *       [MDBE_ATTR_SOURCE]
+ *          struct in_addr / struct in6_addr
+ *       [MDBE_ATTR_SRC_VNI]
+ *          u32
+ *    }
+ * }
+ */
+enum {
+	MDBA_GET_ENTRY_UNSPEC,
+	MDBA_GET_ENTRY,
+	MDBA_GET_ENTRY_ATTRS,
+	__MDBA_GET_ENTRY_MAX,
+};
+#define MDBA_GET_ENTRY_MAX (__MDBA_GET_ENTRY_MAX - 1)
+
 /* [MDBA_SET_ENTRY_ATTRS] = {
  *    [MDBE_ATTR_xxx]
  *    ...

net/bridge/br_device.c

@@ -92,7 +92,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto out;
 		}
 
-		mdst = br_mdb_get(brmctx, skb, vid);
+		mdst = br_mdb_entry_skb_get(brmctx, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
 		    br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst))
 			br_multicast_flood(mdst, skb, brmctx, false, true);
@@ -472,6 +472,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_mdb_add		 = br_mdb_add,
 	.ndo_mdb_del		 = br_mdb_del,
 	.ndo_mdb_dump		 = br_mdb_dump,
+	.ndo_mdb_get		 = br_mdb_get,
 	.ndo_bridge_getlink	 = br_getlink,
 	.ndo_bridge_setlink	 = br_setlink,
 	.ndo_bridge_dellink	 = br_dellink,

net/bridge/br_input.c

@@ -175,7 +175,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 
 	switch (pkt_type) {
 	case BR_PKT_MULTICAST:
-		mdst = br_mdb_get(brmctx, skb, vid);
+		mdst = br_mdb_entry_skb_get(brmctx, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
 		    br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) {
 			if ((mdst && mdst->host_joined) ||