Merge branch 'bridge-mdb-bulk-delete'

Ido Schimmel says:

====================
Add MDB bulk deletion support

This patchset adds MDB bulk deletion support, allowing user space to
request the deletion of matching entries instead of dumping the entire
MDB and issuing a separate deletion request for each matching entry.
Support is added in both the bridge and VXLAN drivers in a similar
fashion to the existing FDB bulk deletion support.

The parameters according to which bulk deletion can be performed are
similar to the FDB ones, namely: Destination port, VLAN ID, state (e.g.,
"permanent"), routing protocol, source / destination VNI, destination IP
and UDP port. Flushing based on flags (e.g., "offload", "fast_leave",
"added_by_star_ex", "blocked") is not currently supported, but can be
added in the future, if a use case arises.

Patch #1 adds a new uAPI attribute to allow specifying the state mask
according to which bulk deletion will be performed, if any.

Patch #2 adds a new policy according to which bulk deletion requests
(with 'NLM_F_BULK' flag set) will be parsed.

Patches #3-#4 add a new NDO for MDB bulk deletion and invoke it from the
rtnetlink code when a bulk deletion request is made.

Patches #5-#6 implement the MDB bulk deletion NDO in the bridge and
VXLAN drivers, respectively.

Patch #7 allows user space to issue MDB bulk deletion requests by no
longer rejecting the 'NLM_F_BULK' flag when it is set in 'RTM_DELMDB'
requests.

Patches #8-#9 add selftests for both drivers, for both good and bad
flows.

iproute2 changes can be found here [1].

https://github.com/idosch/iproute2/tree/submit/mdb_flush_v1
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vxlan/vxlan_core.c

@@ -3235,6 +3235,7 @@ static const struct net_device_ops vxlan_netdev_ether_ops = {
 	.ndo_fdb_get		= vxlan_fdb_get,
 	.ndo_mdb_add		= vxlan_mdb_add,
 	.ndo_mdb_del		= vxlan_mdb_del,
+	.ndo_mdb_del_bulk	= vxlan_mdb_del_bulk,
 	.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

@@ -74,6 +74,14 @@ struct vxlan_mdb_config {
 	u8 rt_protocol;
 };
 
+struct vxlan_mdb_flush_desc {
+	union vxlan_addr remote_ip;
+	__be32 src_vni;
+	__be32 remote_vni;
+	__be16 remote_port;
+	u8 rt_protocol;
+};
+
 static const struct rhashtable_params vxlan_mdb_rht_params = {
 	.head_offset = offsetof(struct vxlan_mdb_entry, rhnode),
 	.key_offset = offsetof(struct vxlan_mdb_entry, key),
@@ -1306,6 +1314,145 @@ int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return err;
 }
 
+static const struct nla_policy
+vxlan_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC),
+	[MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY,
+					   sizeof(struct in_addr),
+					   sizeof(struct in6_addr)),
+	[MDBE_ATTR_DST_PORT] = { .type = NLA_U16 },
+	[MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+	[MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range),
+	[MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT),
+};
+
+static int vxlan_mdb_flush_desc_init(struct vxlan_dev *vxlan,
+				     struct vxlan_mdb_flush_desc *desc,
+				     struct nlattr *tb[],
+				     struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]);
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	int err;
+
+	if (entry->ifindex && entry->ifindex != vxlan->dev->ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid port net device");
+		return -EINVAL;
+	}
+
+	if (entry->vid) {
+		NL_SET_ERR_MSG_MOD(extack, "VID must not be specified");
+		return -EINVAL;
+	}
+
+	if (!tb[MDBA_SET_ENTRY_ATTRS])
+		return 0;
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+			       tb[MDBA_SET_ENTRY_ATTRS],
+			       vxlan_mdbe_attrs_del_bulk_pol, extack);
+	if (err)
+		return err;
+
+	if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) {
+		u8 state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]);
+
+		if ((state_mask & MDB_PERMANENT) && !(entry->state & MDB_PERMANENT)) {
+			NL_SET_ERR_MSG_MOD(extack, "Only permanent MDB entries are supported");
+			return -EINVAL;
+		}
+	}
+
+	if (mdbe_attrs[MDBE_ATTR_RTPROT])
+		desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]);
+
+	if (mdbe_attrs[MDBE_ATTR_DST])
+		vxlan_nla_get_addr(&desc->remote_ip, mdbe_attrs[MDBE_ATTR_DST]);
+
+	if (mdbe_attrs[MDBE_ATTR_DST_PORT])
+		desc->remote_port =
+			cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT]));
+
+	if (mdbe_attrs[MDBE_ATTR_VNI])
+		desc->remote_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI]));
+
+	if (mdbe_attrs[MDBE_ATTR_SRC_VNI])
+		desc->src_vni =
+			cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI]));
+
+	return 0;
+}
+
+static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan,
+				    struct vxlan_mdb_entry *mdb_entry,
+				    const struct vxlan_mdb_flush_desc *desc)
+{
+	struct vxlan_mdb_remote *remote, *tmp;
+
+	list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list) {
+		struct vxlan_rdst *rd = rtnl_dereference(remote->rd);
+		__be32 remote_vni;
+
+		if (desc->remote_ip.sa.sa_family &&
+		    !vxlan_addr_equal(&desc->remote_ip, &rd->remote_ip))
+			continue;
+
+		/* Encapsulation is performed with source VNI if remote VNI
+		 * is not set.
+		 */
+		remote_vni = rd->remote_vni ? : mdb_entry->key.vni;
+		if (desc->remote_vni && desc->remote_vni != remote_vni)
+			continue;
+
+		if (desc->remote_port && desc->remote_port != rd->remote_port)
+			continue;
+
+		if (desc->rt_protocol &&
+		    desc->rt_protocol != remote->rt_protocol)
+			continue;
+
+		vxlan_mdb_remote_del(vxlan, mdb_entry, remote);
+	}
+}
+
+static void vxlan_mdb_flush(struct vxlan_dev *vxlan,
+			    const struct vxlan_mdb_flush_desc *desc)
+{
+	struct vxlan_mdb_entry *mdb_entry;
+	struct hlist_node *tmp;
+
+	/* The removal of an entry cannot trigger the removal of another entry
+	 * since entries are always added to the head of the list.
+	 */
+	hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) {
+		if (desc->src_vni && desc->src_vni != mdb_entry->key.vni)
+			continue;
+
+		vxlan_mdb_remotes_flush(vxlan, mdb_entry, desc);
+		/* Entry will only be removed if its remotes list is empty. */
+		vxlan_mdb_entry_put(vxlan, mdb_entry);
+	}
+}
+
+int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		       struct netlink_ext_ack *extack)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_mdb_flush_desc desc = {};
+	int err;
+
+	ASSERT_RTNL();
+
+	err = vxlan_mdb_flush_desc_init(vxlan, &desc, tb, extack);
+	if (err)
+		return err;
+
+	vxlan_mdb_flush(vxlan, &desc);
+
+	return 0;
+}
+
 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),
@@ -1575,29 +1722,6 @@ static void vxlan_mdb_check_empty(void *ptr, void *arg)
 	WARN_ON_ONCE(1);
 }
 
-static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan,
-				    struct vxlan_mdb_entry *mdb_entry)
-{
-	struct vxlan_mdb_remote *remote, *tmp;
-
-	list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list)
-		vxlan_mdb_remote_del(vxlan, mdb_entry, remote);
-}
-
-static void vxlan_mdb_entries_flush(struct vxlan_dev *vxlan)
-{
-	struct vxlan_mdb_entry *mdb_entry;
-	struct hlist_node *tmp;
-
-	/* The removal of an entry cannot trigger the removal of another entry
-	 * since entries are always added to the head of the list.
-	 */
-	hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) {
-		vxlan_mdb_remotes_flush(vxlan, mdb_entry);
-		vxlan_mdb_entry_put(vxlan, mdb_entry);
-	}
-}
-
 int vxlan_mdb_init(struct vxlan_dev *vxlan)
 {
 	int err;
@@ -1613,7 +1737,9 @@ int vxlan_mdb_init(struct vxlan_dev *vxlan)
 
 void vxlan_mdb_fini(struct vxlan_dev *vxlan)
 {
-	vxlan_mdb_entries_flush(vxlan);
+	struct vxlan_mdb_flush_desc desc = {};
+
+	vxlan_mdb_flush(vxlan, &desc);
 	WARN_ON_ONCE(vxlan->cfg.flags & VXLAN_F_MDB);
 	rhashtable_free_and_destroy(&vxlan->mdb_tbl, vxlan_mdb_check_empty,
 				    NULL);

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_del_bulk(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,

include/linux/netdevice.h

@@ -1329,6 +1329,9 @@ struct netdev_net_notifier {
  * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[],
  *		      struct netlink_ext_ack *extack);
  *	Deletes the MDB entry from dev.
+ * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[],
+ *			   struct netlink_ext_ack *extack);
+ *	Bulk deletes MDB entries from dev.
  * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb,
  *		       struct netlink_callback *cb);
  *	Dumps MDB entries from dev. The first argument (marker) in the netlink
@@ -1611,6 +1614,9 @@ struct net_device_ops {
 	int			(*ndo_mdb_del)(struct net_device *dev,
 					       struct nlattr *tb[],
 					       struct netlink_ext_ack *extack);
+	int			(*ndo_mdb_del_bulk)(struct net_device *dev,
+						    struct nlattr *tb[],
+						    struct netlink_ext_ack *extack);
 	int			(*ndo_mdb_dump)(struct net_device *dev,
 						struct sk_buff *skb,
 						struct netlink_callback *cb);

include/uapi/linux/if_bridge.h

@@ -757,6 +757,7 @@ enum {
 	MDBE_ATTR_VNI,
 	MDBE_ATTR_IFINDEX,
 	MDBE_ATTR_SRC_VNI,
+	MDBE_ATTR_STATE_MASK,
 	__MDBE_ATTR_MAX,
 };
 #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)

net/bridge/br_device.c

@@ -471,6 +471,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_fdb_get		 = br_fdb_get,
 	.ndo_mdb_add		 = br_mdb_add,
 	.ndo_mdb_del		 = br_mdb_del,
+	.ndo_mdb_del_bulk	 = br_mdb_del_bulk,
 	.ndo_mdb_dump		 = br_mdb_dump,
 	.ndo_mdb_get		 = br_mdb_get,
 	.ndo_bridge_getlink	 = br_getlink,

net/bridge/br_mdb.c

@@ -1412,6 +1412,139 @@ int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return err;
 }
 
+struct br_mdb_flush_desc {
+	u32 port_ifindex;
+	u16 vid;
+	u8 rt_protocol;
+	u8 state;
+	u8 state_mask;
+};
+
+static const struct nla_policy br_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC),
+	[MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT),
+};
+
+static int br_mdb_flush_desc_init(struct br_mdb_flush_desc *desc,
+				  struct nlattr *tb[],
+				  struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]);
+	struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1];
+	int err;
+
+	desc->port_ifindex = entry->ifindex;
+	desc->vid = entry->vid;
+	desc->state = entry->state;
+
+	if (!tb[MDBA_SET_ENTRY_ATTRS])
+		return 0;
+
+	err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX,
+			       tb[MDBA_SET_ENTRY_ATTRS],
+			       br_mdbe_attrs_del_bulk_pol, extack);
+	if (err)
+		return err;
+
+	if (mdbe_attrs[MDBE_ATTR_STATE_MASK])
+		desc->state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]);
+
+	if (mdbe_attrs[MDBE_ATTR_RTPROT])
+		desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]);
+
+	return 0;
+}
+
+static void br_mdb_flush_host(struct net_bridge *br,
+			      struct net_bridge_mdb_entry *mp,
+			      const struct br_mdb_flush_desc *desc)
+{
+	u8 state;
+
+	if (desc->port_ifindex && desc->port_ifindex != br->dev->ifindex)
+		return;
+
+	if (desc->rt_protocol)
+		return;
+
+	state = br_group_is_l2(&mp->addr) ? MDB_PERMANENT : 0;
+	if (desc->state_mask && (state & desc->state_mask) != desc->state)
+		return;
+
+	br_multicast_host_leave(mp, true);
+	if (!mp->ports && netif_running(br->dev))
+		mod_timer(&mp->timer, jiffies);
+}
+
+static void br_mdb_flush_pgs(struct net_bridge *br,
+			     struct net_bridge_mdb_entry *mp,
+			     const struct br_mdb_flush_desc *desc)
+{
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+
+	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;) {
+		u8 state;
+
+		if (desc->port_ifindex &&
+		    desc->port_ifindex != p->key.port->dev->ifindex) {
+			pp = &p->next;
+			continue;
+		}
+
+		if (desc->rt_protocol && desc->rt_protocol != p->rt_protocol) {
+			pp = &p->next;
+			continue;
+		}
+
+		state = p->flags & MDB_PG_FLAGS_PERMANENT ? MDB_PERMANENT : 0;
+		if (desc->state_mask &&
+		    (state & desc->state_mask) != desc->state) {
+			pp = &p->next;
+			continue;
+		}
+
+		br_multicast_del_pg(mp, p, pp);
+	}
+}
+
+static void br_mdb_flush(struct net_bridge *br,
+			 const struct br_mdb_flush_desc *desc)
+{
+	struct net_bridge_mdb_entry *mp;
+
+	spin_lock_bh(&br->multicast_lock);
+
+	/* Safe variant is not needed because entries are removed from the list
+	 * upon group timer expiration or bridge deletion.
+	 */
+	hlist_for_each_entry(mp, &br->mdb_list, mdb_node) {
+		if (desc->vid && desc->vid != mp->addr.vid)
+			continue;
+
+		br_mdb_flush_host(br, mp, desc);
+		br_mdb_flush_pgs(br, mp, desc);
+	}
+
+	spin_unlock_bh(&br->multicast_lock);
+}
+
+int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		    struct netlink_ext_ack *extack)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct br_mdb_flush_desc desc = {};
+	int err;
+
+	err = br_mdb_flush_desc_init(&desc, tb, extack);
+	if (err)
+		return err;
+
+	br_mdb_flush(br, &desc);
+
+	return 0;
+}
+
 static const struct nla_policy br_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = {
 	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
 					      sizeof(struct in_addr),

net/bridge/br_private.h

@@ -1022,6 +1022,8 @@ int br_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags,
 	       struct netlink_ext_ack *extack);
 int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	       struct netlink_ext_ack *extack);
+int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+		    struct netlink_ext_ack *extack);
 int br_mdb_dump(struct net_device *dev, struct sk_buff *skb,
 		struct netlink_callback *cb);
 int br_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq,
@@ -1430,6 +1432,12 @@ static inline int br_mdb_del(struct net_device *dev, struct nlattr *tb[],
 	return -EOPNOTSUPP;
 }
 
+static inline int br_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[],
+				  struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int br_mdb_dump(struct net_device *dev, struct sk_buff *skb,
 			      struct netlink_callback *cb)
 {

net/core/rtnetlink.c

@@ -6410,17 +6410,64 @@ static int rtnl_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return dev->netdev_ops->ndo_mdb_add(dev, tb, nlh->nlmsg_flags, extack);
 }
 
+static int rtnl_validate_mdb_entry_del_bulk(const struct nlattr *attr,
+					    struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(attr);
+	struct br_mdb_entry zero_entry = {};
+
+	if (nla_len(attr) != sizeof(struct br_mdb_entry)) {
+		NL_SET_ERR_MSG_ATTR(extack, attr, "Invalid attribute length");
+		return -EINVAL;
+	}
+
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
+		NL_SET_ERR_MSG(extack, "Unknown entry state");
+		return -EINVAL;
+	}
+
+	if (entry->flags) {
+		NL_SET_ERR_MSG(extack, "Entry flags cannot be set");
+		return -EINVAL;
+	}
+
+	if (entry->vid >= VLAN_N_VID - 1) {
+		NL_SET_ERR_MSG(extack, "Invalid entry VLAN id");
+		return -EINVAL;
+	}
+
+	if (memcmp(&entry->addr, &zero_entry.addr, sizeof(entry->addr))) {
+		NL_SET_ERR_MSG(extack, "Entry address cannot be set");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nla_policy mdba_del_bulk_policy[MDBA_SET_ENTRY_MAX + 1] = {
+	[MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+						  rtnl_validate_mdb_entry_del_bulk,
+						  sizeof(struct br_mdb_entry)),
+	[MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED },
+};
+
 static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
+	bool del_bulk = !!(nlh->nlmsg_flags & NLM_F_BULK);
 	struct nlattr *tb[MDBA_SET_ENTRY_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct br_port_msg *bpm;
 	struct net_device *dev;
 	int err;
 
-	err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
-				     MDBA_SET_ENTRY_MAX, mdba_policy, extack);
+	if (!del_bulk)
+		err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
+					     MDBA_SET_ENTRY_MAX, mdba_policy,
+					     extack);
+	else
+		err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX,
+				  mdba_del_bulk_policy, extack);
 	if (err)
 		return err;
 
@@ -6441,6 +6488,14 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (del_bulk) {
+		if (!dev->netdev_ops->ndo_mdb_del_bulk) {
+			NL_SET_ERR_MSG(extack, "Device does not support MDB bulk deletion");
+			return -EOPNOTSUPP;
+		}
+		return dev->netdev_ops->ndo_mdb_del_bulk(dev, tb, extack);
+	}
+
 	if (!dev->netdev_ops->ndo_mdb_del) {
 		NL_SET_ERR_MSG(extack, "Device does not support MDB operations");
 		return -EOPNOTSUPP;
@@ -6686,5 +6741,6 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_BRIDGE, RTM_GETMDB, rtnl_mdb_get, rtnl_mdb_dump, 0);
 	rtnl_register(PF_BRIDGE, RTM_NEWMDB, rtnl_mdb_add, NULL, 0);
-	rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL,
+		      RTNL_FLAG_BULK_DEL_SUPPORTED);
 }

tools/testing/selftests/net/forwarding/bridge_mdb.sh

@@ -803,11 +803,198 @@ cfg_test_dump()
 	cfg_test_dump_common "L2" l2_grps_get
 }
 
+# Check flush functionality with different parameters.
+cfg_test_flush()
+{
+	local num_entries
+
+	# Add entries with different attributes and check that they are all
+	# flushed when the flush command is given with no parameters.
+
+	# Different port.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.2 vid 10
+
+	# Different VLAN ID.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.3 vid 10
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.4 vid 20
+
+	# Different routing protocol.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.5 vid 10 proto bgp
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.6 vid 10 proto zebra
+
+	# Different state.
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.7 vid 10 permanent
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.8 vid 10 temp
+
+	bridge mdb flush dev br0
+	num_entries=$(bridge mdb show dev br0 | wc -l)
+	[[ $num_entries -eq 0 ]]
+	check_err $? 0 "Not all entries flushed after flush all"
+
+	# Check that when flushing by port only entries programmed with the
+	# specified port are flushed and the rest are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port br0 grp 239.1.1.1 vid 10
+
+	bridge mdb flush dev br0 port $swp1
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_fail $? "Entry not flushed by specified port"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_err $? "Entry flushed by wrong port"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port br0"
+	check_err $? "Host entry flushed by wrong port"
+
+	bridge mdb flush dev br0 port br0
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port br0"
+	check_fail $? "Host entry not flushed by specified port"
+
+	bridge mdb flush dev br0
+
+	# Check that when flushing by VLAN ID only entries programmed with the
+	# specified VLAN ID are flushed and the rest are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 10
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 20
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 20
+
+	bridge mdb flush dev br0 vid 10
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 &> /dev/null
+	check_fail $? "Entry not flushed by specified VLAN ID"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 20 &> /dev/null
+	check_err $? "Entry flushed by wrong VLAN ID"
+
+	bridge mdb flush dev br0
+
+	# Check that all permanent entries are flushed when "permanent" is
+	# specified and that temporary entries are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 permanent vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 temp vid 10
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_fail $? "Entry not flushed by \"permanent\" state"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_err $? "Entry flushed by wrong state (\"permanent\")"
+
+	bridge mdb flush dev br0
+
+	# Check that all temporary entries are flushed when "nopermanent" is
+	# specified and that permanent entries are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 permanent vid 10
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 temp vid 10
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_err $? "Entry flushed by wrong state (\"nopermanent\")"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_fail $? "Entry not flushed by \"nopermanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that L2 host entries are not flushed when "nopermanent" is
+	# specified, but flushed when "permanent" is specified.
+
+	bridge mdb add dev br0 port br0 grp 01:02:03:04:05:06 permanent vid 10
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp 01:02:03:04:05:06 vid 10 &> /dev/null
+	check_err $? "L2 host entry flushed by wrong state (\"nopermanent\")"
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp 01:02:03:04:05:06 vid 10 &> /dev/null
+	check_fail $? "L2 host entry not flushed by \"permanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that IPv4 host entries are not flushed when "permanent" is
+	# specified, but flushed when "nopermanent" is specified.
+
+	bridge mdb add dev br0 port br0 grp 239.1.1.1 temp vid 10
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 &> /dev/null
+	check_err $? "IPv4 host entry flushed by wrong state (\"permanent\")"
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 &> /dev/null
+	check_fail $? "IPv4 host entry not flushed by \"nopermanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that IPv6 host entries are not flushed when "permanent" is
+	# specified, but flushed when "nopermanent" is specified.
+
+	bridge mdb add dev br0 port br0 grp ff0e::1 temp vid 10
+
+	bridge mdb flush dev br0 permanent
+
+	bridge mdb get dev br0 grp ff0e::1 vid 10 &> /dev/null
+	check_err $? "IPv6 host entry flushed by wrong state (\"permanent\")"
+
+	bridge mdb flush dev br0 nopermanent
+
+	bridge mdb get dev br0 grp ff0e::1 vid 10 &> /dev/null
+	check_fail $? "IPv6 host entry not flushed by \"nopermanent\" state"
+
+	bridge mdb flush dev br0
+
+	# Check that when flushing by routing protocol only entries programmed
+	# with the specified routing protocol are flushed and the rest are not.
+
+	bridge mdb add dev br0 port $swp1 grp 239.1.1.1 vid 10 proto bgp
+	bridge mdb add dev br0 port $swp2 grp 239.1.1.1 vid 10 proto zebra
+	bridge mdb add dev br0 port br0 grp 239.1.1.1 vid 10
+
+	bridge mdb flush dev br0 proto bgp
+
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp1"
+	check_fail $? "Entry not flushed by specified routing protocol"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port $swp2"
+	check_err $? "Entry flushed by wrong routing protocol"
+	bridge mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q "port br0"
+	check_err $? "Host entry flushed by wrong routing protocol"
+
+	bridge mdb flush dev br0
+
+	# Test that an error is returned when trying to flush using unsupported
+	# parameters.
+
+	bridge mdb flush dev br0 src_vni 10 &> /dev/null
+	check_fail $? "Managed to flush by source VNI"
+
+	bridge mdb flush dev br0 dst 198.51.100.1 &> /dev/null
+	check_fail $? "Managed to flush by destination IP"
+
+	bridge mdb flush dev br0 dst_port 4789 &> /dev/null
+	check_fail $? "Managed to flush by UDP destination port"
+
+	bridge mdb flush dev br0 vni 10 &> /dev/null
+	check_fail $? "Managed to flush by destination VNI"
+
+	log_test "Flush tests"
+}
+
 cfg_test()
 {
 	cfg_test_host
 	cfg_test_port
 	cfg_test_dump
+	cfg_test_flush
 }
 
 __fwd_test_host_ip()
@@ -1166,8 +1353,8 @@ ctrl_test()
 	ctrl_mldv2_is_in_test
 }
 
-if ! bridge mdb help 2>&1 | grep -q "get"; then
-	echo "SKIP: iproute2 too old, missing bridge mdb get support"
+if ! bridge mdb help 2>&1 | grep -q "flush"; then
+	echo "SKIP: iproute2 too old, missing bridge mdb flush support"
 	exit $ksft_skip
 fi
 

tools/testing/selftests/net/test_vxlan_mdb.sh

@@ -79,6 +79,7 @@ CONTROL_PATH_TESTS="
 	dump_ipv6_ipv4
 	dump_ipv4_ipv6
 	dump_ipv6_ipv6
+	flush
 "
 
 DATA_PATH_TESTS="
@@ -968,6 +969,202 @@ dump_ipv6_ipv6()
 	dump_common $ns1 $local_addr $remote_prefix $fn
 }
 
+flush()
+{
+	local num_entries
+
+	echo
+	echo "Control path: Flush"
+	echo "-------------------"
+
+	# Add entries with different attributes and check that they are all
+	# flushed when the flush command is given with no parameters.
+
+	# Different source VNI.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.2 permanent dst 198.51.100.1 src_vni 10011"
+
+	# Different routing protocol.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.3 permanent proto bgp dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.4 permanent proto zebra dst 198.51.100.1 src_vni 10010"
+
+	# Different destination IP.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.5 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.6 permanent dst 198.51.100.2 src_vni 10010"
+
+	# Different destination port.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.7 permanent dst 198.51.100.1 dst_port 11111 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.8 permanent dst 198.51.100.1 dst_port 22222 src_vni 10010"
+
+	# Different VNI.
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.9 permanent dst 198.51.100.1 vni 10010 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.10 permanent dst 198.51.100.1 vni 10020 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+	num_entries=$(bridge -n $ns1_v4 mdb show dev vx0 | wc -l)
+	[[ $num_entries -eq 0 ]]
+	log_test $? 0 "Flush all"
+
+	# Check that entries are flushed when port is specified as the VXLAN
+	# device and that an error is returned when port is specified as a
+	# different net device.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 port vx0"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010"
+	log_test $? 254 "Flush by port"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 port veth0"
+	log_test $? 255 "Flush by wrong port"
+
+	# Check that when flushing by source VNI only entries programmed with
+	# the specified source VNI are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10011"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10011"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010"
+	log_test $? 254 "Flush by specified source VNI"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10011"
+	log_test $? 0 "Flush by unspecified source VNI"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that all entries are flushed when "permanent" is specified and
+	# that an error is returned when "nopermanent" is specified.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 permanent"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010"
+	log_test $? 254 "Flush by \"permanent\" state"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 nopermanent"
+	log_test $? 255 "Flush by \"nopermanent\" state"
+
+	# Check that when flushing by routing protocol only entries programmed
+	# with the specified routing protocol are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent proto bgp dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent proto zebra dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 proto bgp"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"proto bgp\""
+	log_test $? 1 "Flush by specified routing protocol"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"proto zebra\""
+	log_test $? 0 "Flush by unspecified routing protocol"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that when flushing by destination IP only entries programmed
+	# with the specified destination IP are flushed and the rest are not.
+
+	# IPv4.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst 198.51.100.2"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.2"
+	log_test $? 1 "Flush by specified destination IP - IPv4"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.1"
+	log_test $? 0 "Flush by unspecified destination IP - IPv4"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# IPv6.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 2001:db8:1000::1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 2001:db8:1000::2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst 2001:db8:1000::2"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 2001:db8:1000::2"
+	log_test $? 1 "Flush by specified destination IP - IPv6"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 2001:db8:1000::1"
+	log_test $? 0 "Flush by unspecified destination IP - IPv6"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that when flushing by UDP destination port only entries
+	# programmed with the specified port are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst_port 11111 dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst_port 22222 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst_port 11111"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"dst_port 11111\""
+	log_test $? 1 "Flush by specified UDP destination port"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \"dst_port 22222\""
+	log_test $? 0 "Flush by unspecified UDP destination port"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# When not specifying a UDP destination port for an entry, traffic is
+	# encapsulated with the device's UDP destination port. Check that when
+	# flushing by the device's UDP destination port only entries programmed
+	# with this port are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst_port 22222 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 dst_port 4789"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.1"
+	log_test $? 1 "Flush by device's UDP destination port"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.2"
+	log_test $? 0 "Flush by unspecified UDP destination port"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Check that when flushing by destination VNI only entries programmed
+	# with the specified destination VNI are flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent vni 20010 dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent vni 20011 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 vni 20010"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \" vni 20010\""
+	log_test $? 1 "Flush by specified destination VNI"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep \" vni 20011\""
+	log_test $? 0 "Flush by unspecified destination VNI"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# When not specifying a destination VNI for an entry, traffic is
+	# encapsulated with the source VNI. Check that when flushing by a
+	# destination VNI that is equal to the source VNI only such entries are
+	# flushed and the rest are not.
+
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent dst 198.51.100.1 src_vni 10010"
+	run_cmd "bridge -n $ns1_v4 mdb add dev vx0 port vx0 grp 239.1.1.1 permanent vni 20010 dst 198.51.100.2 src_vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 vni 10010"
+
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.1"
+	log_test $? 1 "Flush by destination VNI equal to source VNI"
+	run_cmd "bridge -n $ns1_v4 -d -s mdb get dev vx0 grp 239.1.1.1 src_vni 10010 | grep 198.51.100.2"
+	log_test $? 0 "Flush by unspecified destination VNI"
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0"
+
+	# Test that an error is returned when trying to flush using VLAN ID.
+
+	run_cmd "bridge -n $ns1_v4 mdb flush dev vx0 vid 10"
+	log_test $? 255 "Flush by VLAN ID"
+}
+
 ################################################################################
 # Tests - Data path
 
@@ -2292,9 +2489,9 @@ if [ ! -x "$(command -v jq)" ]; then
 	exit $ksft_skip
 fi
 
-bridge mdb help 2>&1 | grep -q "get"
+bridge mdb help 2>&1 | grep -q "flush"
 if [ $? -ne 0 ]; then
-   echo "SKIP: iproute2 bridge too old, missing VXLAN MDB get support"
+   echo "SKIP: iproute2 bridge too old, missing VXLAN MDB flush support"
    exit $ksft_skip
 fi