bridge: vlan: add per-vlan struct and move to rhashtables

This patch changes the bridge vlan implementation to use rhashtables
instead of bitmaps. The main motivation behind this change is that we
need extensible per-vlan structures (both per-port and global) so more
advanced features can be introduced and the vlan support can be
extended. I've tried to break this up but the moment net_port_vlans is
changed and the whole API goes away, thus this is a larger patch.
A few short goals of this patch are:
- Extensible per-vlan structs stored in rhashtables and a sorted list
- Keep user-visible behaviour (compressed vlans etc)
- Keep fastpath ingress/egress logic the same (optimizations to come
  later)

Here's a brief list of some of the new features we'd like to introduce:
- per-vlan counters
- vlan ingress/egress mapping
- per-vlan igmp configuration
- vlan priorities
- avoid fdb entries replication (e.g. local fdb scaling issues)

The structure is kept single for both global and per-port entries so to
avoid code duplication where possible and also because we'll soon introduce
"port0 / aka bridge as port" which should simplify things further
(thanks to Vlad for the suggestion!).

Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port
rhashtable, if an entry is added to a port it'll get a pointer to its
global context so it can be quickly accessed later. There's also a
sorted vlan list which is used for stable walks and some user-visible
behaviour such as the vlan ranges, also for error paths.
VLANs are stored in a "vlan group" which currently contains the
rhashtable, sorted vlan list and the number of "real" vlan entries.
A good side-effect of this change is that it resembles how hw keeps
per-vlan data.
One important note after this change is that if a VLAN is being looked up
in the bridge's rhashtable for filtering purposes (or to check if it's an
existing usable entry, not just a global context) then the new helper
br_vlan_should_use() needs to be used if the vlan is found. In case the
lookup is done only with a port's vlan group, then this check can be
skipped.

Things tested so far:
- basic vlan ingress/egress
- pvids
- untagged vlans
- undef CONFIG_BRIDGE_VLAN_FILTERING
- adding/deleting vlans in different scenarios (with/without global ctx,
  while transmitting traffic, in ranges etc)
- loading/removing the module while having/adding/deleting vlans
- extracting bridge vlan information (user ABI), compressed requests
- adding/deleting fdbs on vlans
- bridge mac change, promisc mode
- default pvid change
- kmemleak ON during the whole time
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/uapi/linux/if_bridge.h

@@ -127,6 +127,7 @@ enum {
 #define BRIDGE_VLAN_INFO_UNTAGGED	(1<<2)	/* VLAN egresses untagged */
 #define BRIDGE_VLAN_INFO_RANGE_BEGIN	(1<<3) /* VLAN is start of vlan range */
 #define BRIDGE_VLAN_INFO_RANGE_END	(1<<4) /* VLAN is end of vlan range */
+#define BRIDGE_VLAN_INFO_BRENTRY	(1<<5) /* Global bridge VLAN entry */
 
 struct bridge_vlan_info {
 	__u16 flags;

net/bridge/br_device.c

@@ -56,7 +56,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_reset_mac_header(skb);
 	skb_pull(skb, ETH_HLEN);
 
-	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+	if (!br_allowed_ingress(br, skb, &vid))
 		goto out;
 
 	if (is_broadcast_ether_addr(dest))

net/bridge/br_fdb.c

@@ -163,22 +163,27 @@ static void fdb_delete_local(struct net_bridge *br,
 			     struct net_bridge_fdb_entry *f)
 {
 	const unsigned char *addr = f->addr.addr;
-	u16 vid = f->vlan_id;
+	struct net_bridge_vlan_group *vg;
+	const struct net_bridge_vlan *v;
 	struct net_bridge_port *op;
+	u16 vid = f->vlan_id;
 
 	/* Maybe another port has same hw addr? */
 	list_for_each_entry(op, &br->port_list, list) {
+		vg = nbp_vlan_group(op);
 		if (op != p && ether_addr_equal(op->dev->dev_addr, addr) &&
-		    (!vid || nbp_vlan_find(op, vid))) {
+		    (!vid || br_vlan_find(vg, vid))) {
 			f->dst = op;
 			f->added_by_user = 0;
 			return;
 		}
 	}
 
+	vg = br_vlan_group(br);
+	v = br_vlan_find(vg, vid);
 	/* Maybe bridge device has same hw addr? */
 	if (p && ether_addr_equal(br->dev->dev_addr, addr) &&
-	    (!vid || br_vlan_find(br, vid))) {
+	    (!vid || (v && br_vlan_should_use(v)))) {
 		f->dst = NULL;
 		f->added_by_user = 0;
 		return;
@@ -203,14 +208,14 @@ void br_fdb_find_delete_local(struct net_bridge *br,
 
 void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 {
+	struct net_bridge_vlan_group *vg;
 	struct net_bridge *br = p->br;
-	struct net_port_vlans *pv = nbp_get_vlan_info(p);
-	bool no_vlan = !pv;
+	struct net_bridge_vlan *v;
 	int i;
-	u16 vid;
 
 	spin_lock_bh(&br->hash_lock);
 
+	vg = nbp_vlan_group(p);
 	/* Search all chains since old address/hash is unknown */
 	for (i = 0; i < BR_HASH_SIZE; i++) {
 		struct hlist_node *h;
@@ -226,7 +231,7 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 				 * configured, we can safely be done at
 				 * this point.
 				 */
-				if (no_vlan)
+				if (!vg || !vg->num_vlans)
 					goto insert;
 			}
 		}
@@ -236,15 +241,15 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 	/* insert new address,  may fail if invalid address or dup. */
 	fdb_insert(br, p, newaddr, 0);
 
-	if (no_vlan)
+	if (!vg || !vg->num_vlans)
 		goto done;
 
 	/* Now add entries for every VLAN configured on the port.
 	 * This function runs under RTNL so the bitmap will not change
 	 * from under us.
 	 */
-	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
-		fdb_insert(br, p, newaddr, vid);
+	list_for_each_entry(v, &vg->vlan_list, vlist)
+		fdb_insert(br, p, newaddr, v->vid);
 
 done:
 	spin_unlock_bh(&br->hash_lock);
@@ -252,9 +257,9 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 
 void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 {
+	struct net_bridge_vlan_group *vg;
 	struct net_bridge_fdb_entry *f;
-	struct net_port_vlans *pv;
-	u16 vid = 0;
+	struct net_bridge_vlan *v;
 
 	spin_lock_bh(&br->hash_lock);
 
@@ -264,20 +269,18 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 		fdb_delete_local(br, NULL, f);
 
 	fdb_insert(br, NULL, newaddr, 0);
-
+	vg = br_vlan_group(br);
+	if (!vg || !vg->num_vlans)
+		goto out;
 	/* Now remove and add entries for every VLAN configured on the
 	 * bridge.  This function runs under RTNL so the bitmap will not
 	 * change from under us.
 	 */
-	pv = br_get_vlan_info(br);
-	if (!pv)
-		goto out;
-
-	for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) {
-		f = __br_fdb_get(br, br->dev->dev_addr, vid);
+	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
-		fdb_insert(br, NULL, newaddr, vid);
+		fdb_insert(br, NULL, newaddr, v->vid);
 	}
 out:
 	spin_unlock_bh(&br->hash_lock);
@@ -844,9 +847,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	       struct net_device *dev,
 	       const unsigned char *addr, u16 vid, u16 nlh_flags)
 {
+	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p;
+	struct net_bridge_vlan *v;
 	int err = 0;
-	struct net_port_vlans *pv;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
 		pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
@@ -865,9 +869,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EINVAL;
 	}
 
-	pv = nbp_get_vlan_info(p);
+	vg = nbp_vlan_group(p);
 	if (vid) {
-		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
+		v = br_vlan_find(vg, vid);
+		if (!v) {
 			pr_info("bridge: RTM_NEWNEIGH with unconfigured "
 				"vlan %d on port %s\n", vid, dev->name);
 			return -EINVAL;
@@ -877,15 +882,15 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
 	} else {
 		err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
-		if (err || !pv)
+		if (err || !vg || !vg->num_vlans)
 			goto out;
 
 		/* We have vlans configured on this port and user didn't
 		 * specify a VLAN.  To be nice, add/update entry for every
 		 * vlan on this port.
 		 */
-		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
-			err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
+		list_for_each_entry(v, &vg->vlan_list, vlist) {
+			err = __br_fdb_add(ndm, p, addr, nlh_flags, v->vid);
 			if (err)
 				goto out;
 		}
@@ -927,9 +932,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		  struct net_device *dev,
 		  const unsigned char *addr, u16 vid)
 {
+	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p;
+	struct net_bridge_vlan *v;
 	int err;
-	struct net_port_vlans *pv;
 
 	p = br_port_get_rtnl(dev);
 	if (p == NULL) {
@@ -938,9 +944,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EINVAL;
 	}
 
-	pv = nbp_get_vlan_info(p);
+	vg = nbp_vlan_group(p);
 	if (vid) {
-		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
+		v = br_vlan_find(vg, vid);
+		if (!v) {
 			pr_info("bridge: RTM_DELNEIGH with unconfigured "
 				"vlan %d on port %s\n", vid, dev->name);
 			return -EINVAL;
@@ -950,16 +957,11 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	} else {
 		err = -ENOENT;
 		err &= __br_fdb_delete(p, addr, 0);
-		if (!pv)
+		if (!vg || !vg->num_vlans)
 			goto out;
 
-		/* We have vlans configured on this port and user didn't
-		 * specify a VLAN.  To be nice, add/update entry for every
-		 * vlan on this port.
-		 */
-		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
-			err &= __br_fdb_delete(p, addr, vid);
-		}
+		list_for_each_entry(v, &vg->vlan_list, vlist)
+			err &= __br_fdb_delete(p, addr, v->vid);
 	}
 out:
 	return err;

net/bridge/br_forward.c

@@ -30,9 +30,11 @@ static int deliver_clone(const struct net_bridge_port *prev,
 static inline int should_deliver(const struct net_bridge_port *p,
 				 const struct sk_buff *skb)
 {
+	struct net_bridge_vlan_group *vg;
+
+	vg = nbp_vlan_group(p);
 	return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
-		br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) &&
-		p->state == BR_STATE_FORWARDING;
+		br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING;
 }
 
 int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -76,7 +78,10 @@ EXPORT_SYMBOL_GPL(br_forward_finish);
 
 static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 {
-	skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb);
+	struct net_bridge_vlan_group *vg;
+
+	vg = nbp_vlan_group(to);
+	skb = br_handle_vlan(to->br, vg, skb);
 	if (!skb)
 		return;
 
@@ -99,6 +104,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 
 static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 {
+	struct net_bridge_vlan_group *vg;
 	struct net_device *indev;
 
 	if (skb_warn_if_lro(skb)) {
@@ -106,7 +112,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 		return;
 	}
 
-	skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb);
+	vg = nbp_vlan_group(to);
+	skb = br_handle_vlan(to->br, vg, skb);
 	if (!skb)
 		return;
 

net/bridge/br_input.c

@@ -36,28 +36,28 @@ static int br_pass_frame_up(struct sk_buff *skb)
 {
 	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
 	struct net_bridge *br = netdev_priv(brdev);
+	struct net_bridge_vlan_group *vg;
 	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
-	struct net_port_vlans *pv;
 
 	u64_stats_update_begin(&brstats->syncp);
 	brstats->rx_packets++;
 	brstats->rx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
+	vg = br_vlan_group(br);
 	/* Bridge is just like any other port.  Make sure the
 	 * packet is allowed except in promisc modue when someone
 	 * may be running packet capture.
 	 */
-	pv = br_get_vlan_info(br);
 	if (!(brdev->flags & IFF_PROMISC) &&
-	    !br_allowed_egress(br, pv, skb)) {
+	    !br_allowed_egress(vg, skb)) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
 
 	indev = skb->dev;
 	skb->dev = brdev;
-	skb = br_handle_vlan(br, pv, skb);
+	skb = br_handle_vlan(br, vg, skb);
 	if (!skb)
 		return NET_RX_DROP;
 
@@ -140,7 +140,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	if (!p || p->state == BR_STATE_DISABLED)
 		goto drop;
 
-	if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
+	if (!nbp_allowed_ingress(p, skb, &vid))
 		goto out;
 
 	/* insert into forwarding database after filtering to avoid spoofing */

net/bridge/br_mdb.c

@@ -464,11 +464,11 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
-	unsigned short vid = VLAN_N_VID;
+	struct net_bridge_vlan_group *vg;
 	struct net_device *dev, *pdev;
 	struct br_mdb_entry *entry;
 	struct net_bridge_port *p;
-	struct net_port_vlans *pv;
+	struct net_bridge_vlan *v;
 	struct net_bridge *br;
 	int err;
 
@@ -489,10 +489,10 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
-	pv = nbp_get_vlan_info(p);
-	if (br_vlan_enabled(br) && pv && entry->vid == 0) {
-		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
-			entry->vid = vid;
+	vg = nbp_vlan_group(p);
+	if (br_vlan_enabled(br) && vg && entry->vid == 0) {
+		list_for_each_entry(v, &vg->vlan_list, vlist) {
+			entry->vid = v->vid;
 			err = __br_mdb_add(net, br, entry);
 			if (err)
 				break;
@@ -566,11 +566,11 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
-	unsigned short vid = VLAN_N_VID;
+	struct net_bridge_vlan_group *vg;
 	struct net_device *dev, *pdev;
 	struct br_mdb_entry *entry;
 	struct net_bridge_port *p;
-	struct net_port_vlans *pv;
+	struct net_bridge_vlan *v;
 	struct net_bridge *br;
 	int err;
 
@@ -591,10 +591,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
-	pv = nbp_get_vlan_info(p);
-	if (br_vlan_enabled(br) && pv && entry->vid == 0) {
-		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
-			entry->vid = vid;
+	vg = nbp_vlan_group(p);
+	if (br_vlan_enabled(br) && vg && entry->vid == 0) {
+		list_for_each_entry(v, &vg->vlan_list, vlist) {
+			entry->vid = v->vid;
 			err = __br_mdb_del(br, entry);
 			if (!err)
 				__br_mdb_notify(dev, entry, RTM_DELMDB);

net/bridge/br_netlink.c

@@ -21,36 +21,35 @@
 #include "br_private.h"
 #include "br_private_stp.h"
 
-static int br_get_num_vlan_infos(const struct net_port_vlans *pv,
-				 u32 filter_mask)
+static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg,
+				u32 filter_mask,
+				u16 pvid)
 {
-	u16 vid_range_start = 0, vid_range_end = 0;
-	u16 vid_range_flags = 0;
-	u16 pvid, vid, flags;
+	struct net_bridge_vlan *v;
+	u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0;
+	u16 flags;
 	int num_vlans = 0;
 
-	if (filter_mask & RTEXT_FILTER_BRVLAN)
-		return pv->num_vlans;
-
 	if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED))
 		return 0;
 
-	/* Count number of vlan info's
-	 */
-	pvid = br_get_pvid(pv);
-	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+	/* Count number of vlan infos */
+	list_for_each_entry(v, &vg->vlan_list, vlist) {
 		flags = 0;
-		if (vid == pvid)
+		/* only a context, bridge vlan not activated */
+		if (!br_vlan_should_use(v))
+			continue;
+		if (v->vid == pvid)
 			flags |= BRIDGE_VLAN_INFO_PVID;
 
-		if (test_bit(vid, pv->untagged_bitmap))
+		if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
 			flags |= BRIDGE_VLAN_INFO_UNTAGGED;
 
 		if (vid_range_start == 0) {
 			goto initvars;
-		} else if ((vid - vid_range_end) == 1 &&
+		} else if ((v->vid - vid_range_end) == 1 &&
 			flags == vid_range_flags) {
-			vid_range_end = vid;
+			vid_range_end = v->vid;
 			continue;
 		} else {
 			if ((vid_range_end - vid_range_start) > 0)
@@ -59,8 +58,8 @@ static int br_get_num_vlan_infos(const struct net_port_vlans *pv,
 				num_vlans += 1;
 		}
 initvars:
-		vid_range_start = vid;
-		vid_range_end = vid;
+		vid_range_start = v->vid;
+		vid_range_end = v->vid;
 		vid_range_flags = flags;
 	}
 
@@ -74,28 +73,40 @@ static int br_get_num_vlan_infos(const struct net_port_vlans *pv,
 	return num_vlans;
 }
 
+static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg,
+				 u32 filter_mask, u16 pvid)
+{
+	if (!vg)
+		return 0;
+
+	if (filter_mask & RTEXT_FILTER_BRVLAN)
+		return vg->num_vlans;
+
+	return __get_num_vlan_infos(vg, filter_mask, pvid);
+}
+
 static size_t br_get_link_af_size_filtered(const struct net_device *dev,
 					   u32 filter_mask)
 {
-	struct net_port_vlans *pv;
+	struct net_bridge_vlan_group *vg = NULL;
+	struct net_bridge_port *p;
+	struct net_bridge *br;
 	int num_vlan_infos;
+	u16 pvid = 0;
 
 	rcu_read_lock();
-	if (br_port_exists(dev))
-		pv = nbp_get_vlan_info(br_port_get_rcu(dev));
-	else if (dev->priv_flags & IFF_EBRIDGE)
-		pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev));
-	else
-		pv = NULL;
-	if (pv)
-		num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask);
-	else
-		num_vlan_infos = 0;
+	if (br_port_exists(dev)) {
+		p = br_port_get_rcu(dev);
+		vg = nbp_vlan_group(p);
+		pvid = nbp_get_pvid(p);
+	} else if (dev->priv_flags & IFF_EBRIDGE) {
+		br = netdev_priv(dev);
+		vg = br_vlan_group(br);
+		pvid = br_get_pvid(br);
+	}
+	num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask, pvid);
 	rcu_read_unlock();
 
-	if (!num_vlan_infos)
-		return 0;
-
 	/* Each VLAN is returned in bridge_vlan_info along with flags */
 	return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info));
 }
@@ -185,31 +196,33 @@ static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start,
 }
 
 static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb,
-					 const struct net_port_vlans *pv)
+					 struct net_bridge_vlan_group *vg,
+					 u16 pvid)
 {
-	u16 vid_range_start = 0, vid_range_end = 0;
-	u16 vid_range_flags = 0;
-	u16 pvid, vid, flags;
+	struct net_bridge_vlan *v;
+	u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0;
+	u16 flags;
 	int err = 0;
 
 	/* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan
 	 * and mark vlan info with begin and end flags
 	 * if vlaninfo represents a range
 	 */
-	pvid = br_get_pvid(pv);
-	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+	list_for_each_entry(v, &vg->vlan_list, vlist) {
 		flags = 0;
-		if (vid == pvid)
+		if (!br_vlan_should_use(v))
+			continue;
+		if (v->vid == pvid)
 			flags |= BRIDGE_VLAN_INFO_PVID;
 
-		if (test_bit(vid, pv->untagged_bitmap))
+		if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
 			flags |= BRIDGE_VLAN_INFO_UNTAGGED;
 
 		if (vid_range_start == 0) {
 			goto initvars;
-		} else if ((vid - vid_range_end) == 1 &&
+		} else if ((v->vid - vid_range_end) == 1 &&
 			flags == vid_range_flags) {
-			vid_range_end = vid;
+			vid_range_end = v->vid;
 			continue;
 		} else {
 			err = br_fill_ifvlaninfo_range(skb, vid_range_start,
@@ -220,8 +233,8 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb,
 		}
 
 initvars:
-		vid_range_start = vid;
-		vid_range_end = vid;
+		vid_range_start = v->vid;
+		vid_range_end = v->vid;
 		vid_range_flags = flags;
 	}
 
@@ -238,19 +251,22 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb,
 }
 
 static int br_fill_ifvlaninfo(struct sk_buff *skb,
-			      const struct net_port_vlans *pv)
+			      struct net_bridge_vlan_group *vg,
+			      u16 pvid)
 {
 	struct bridge_vlan_info vinfo;
-	u16 pvid, vid;
+	struct net_bridge_vlan *v;
+
+	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 
-	pvid = br_get_pvid(pv);
-	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
-		vinfo.vid = vid;
+		vinfo.vid = v->vid;
 		vinfo.flags = 0;
-		if (vid == pvid)
+		if (v->vid == pvid)
 			vinfo.flags |= BRIDGE_VLAN_INFO_PVID;
 
-		if (test_bit(vid, pv->untagged_bitmap))
+		if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
 			vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
 
 		if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
@@ -269,11 +285,11 @@ static int br_fill_ifvlaninfo(struct sk_buff *skb,
  * Contains port and master info as well as carrier and bridge state.
  */
 static int br_fill_ifinfo(struct sk_buff *skb,
-			  const struct net_bridge_port *port,
+			  struct net_bridge_port *port,
 			  u32 pid, u32 seq, int event, unsigned int flags,
 			  u32 filter_mask, const struct net_device *dev)
 {
-	const struct net_bridge *br;
+	struct net_bridge *br;
 	struct ifinfomsg *hdr;
 	struct nlmsghdr *nlh;
 	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
@@ -320,16 +336,20 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 	/* Check if  the VID information is requested */
 	if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
 	    (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
-		const struct net_port_vlans *pv;
+		struct net_bridge_vlan_group *vg;
 		struct nlattr *af;
+		u16 pvid;
 		int err;
 
-		if (port)
-			pv = nbp_get_vlan_info(port);
-		else
-			pv = br_get_vlan_info(br);
+		if (port) {
+			vg = nbp_vlan_group(port);
+			pvid = nbp_get_pvid(port);
+		} else {
+			vg = br_vlan_group(br);
+			pvid = br_get_pvid(br);
+		}
 
-		if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID))
+		if (!vg || !vg->num_vlans)
 			goto done;
 
 		af = nla_nest_start(skb, IFLA_AF_SPEC);
@@ -337,9 +357,9 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 			goto nla_put_failure;
 
 		if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
-			err = br_fill_ifvlaninfo_compressed(skb, pv);
+			err = br_fill_ifvlaninfo_compressed(skb, vg, pvid);
 		else
-			err = br_fill_ifvlaninfo(skb, pv);
+			err = br_fill_ifvlaninfo(skb, vg, pvid);
 		if (err)
 			goto nla_put_failure;
 		nla_nest_end(skb, af);
@@ -413,14 +433,14 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
 	switch (cmd) {
 	case RTM_SETLINK:
 		if (p) {
+			/* if the MASTER flag is set this will act on the global
+			 * per-VLAN entry as well
+			 */
 			err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
 			if (err)
 				break;
-
-			if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
-				err = br_vlan_add(p->br, vinfo->vid,
-						  vinfo->flags);
 		} else {
+			vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY;
 			err = br_vlan_add(br, vinfo->vid, vinfo->flags);
 		}
 		break;
@@ -857,20 +877,22 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 
 static size_t br_get_link_af_size(const struct net_device *dev)
 {
-	struct net_port_vlans *pv;
-
-	if (br_port_exists(dev))
-		pv = nbp_get_vlan_info(br_port_get_rtnl(dev));
-	else if (dev->priv_flags & IFF_EBRIDGE)
-		pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev));
-	else
-		return 0;
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	int num_vlans = 0;
 
-	if (!pv)
-		return 0;
+	if (br_port_exists(dev)) {
+		p = br_port_get_rtnl(dev);
+		num_vlans = br_get_num_vlan_infos(nbp_vlan_group(p),
+						  RTEXT_FILTER_BRVLAN, 0);
+	} else if (dev->priv_flags & IFF_EBRIDGE) {
+		br = netdev_priv(dev);
+		num_vlans = br_get_num_vlan_infos(br_vlan_group(br),
+						  RTEXT_FILTER_BRVLAN, 0);
+	}
 
 	/* Each VLAN is returned in bridge_vlan_info along with flags */
-	return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info));
+	return num_vlans * nla_total_size(sizeof(struct bridge_vlan_info));
 }
 
 static struct rtnl_af_ops br_af_ops __read_mostly = {

net/bridge/br_private.h

@@ -20,6 +20,7 @@
 #include <net/route.h>
 #include <net/ip6_fib.h>
 #include <linux/if_vlan.h>
+#include <linux/rhashtable.h>
 
 #define BR_HASH_BITS 8
 #define BR_HASH_SIZE (1 << BR_HASH_BITS)
@@ -28,7 +29,6 @@
 
 #define BR_PORT_BITS	10
 #define BR_MAX_PORTS	(1<<BR_PORT_BITS)
-#define BR_VLAN_BITMAP_LEN	BITS_TO_LONGS(VLAN_N_VID)
 
 #define BR_VERSION	"2.3"
 
@@ -77,16 +77,58 @@ struct bridge_mcast_querier {
 };
 #endif
 
-struct net_port_vlans {
-	u16				port_idx;
-	u16				pvid;
+/**
+ * struct net_bridge_vlan - per-vlan entry
+ *
+ * @vnode: rhashtable member
+ * @vid: VLAN id
+ * @flags: bridge vlan flags
+ * @br: if MASTER flag set, this points to a bridge struct
+ * @port: if MASTER flag unset, this points to a port struct
+ * @refcnt: if MASTER flag set, this is bumped for each port referencing it
+ * @brvlan: if MASTER flag unset, this points to the global per-VLAN context
+ *          for this VLAN entry
+ * @vlist: sorted list of VLAN entries
+ * @rcu: used for entry destruction
+ *
+ * This structure is shared between the global per-VLAN entries contained in
+ * the bridge rhashtable and the local per-port per-VLAN entries contained in
+ * the port's rhashtable. The union entries should be interpreted depending on
+ * the entry flags that are set.
+ */
+struct net_bridge_vlan {
+	struct rhash_head		vnode;
+	u16				vid;
+	u16				flags;
 	union {
-		struct net_bridge_port		*port;
 		struct net_bridge	*br;
-	}				parent;
+		struct net_bridge_port	*port;
+	};
+	union {
+		atomic_t		refcnt;
+		struct net_bridge_vlan	*brvlan;
+	};
+	struct list_head		vlist;
+
 	struct rcu_head			rcu;
-	unsigned long			vlan_bitmap[BR_VLAN_BITMAP_LEN];
-	unsigned long			untagged_bitmap[BR_VLAN_BITMAP_LEN];
+};
+
+/**
+ * struct net_bridge_vlan_group
+ *
+ * @vlan_hash: VLAN entry rhashtable
+ * @vlan_list: sorted VLAN entry list
+ * @num_vlans: number of total VLAN entries
+ *
+ * IMPORTANT: Be careful when checking if there're VLAN entries using list
+ *            primitives because the bridge can have entries in its list which
+ *            are just for global context but not for filtering, i.e. they have
+ *            the master flag set but not the brentry flag. If you have to check
+ *            if there're "real" entries in the bridge please test @num_vlans
+ */
+struct net_bridge_vlan_group {
+	struct rhashtable		vlan_hash;
+	struct list_head		vlan_list;
 	u16				num_vlans;
 };
 
@@ -185,7 +227,8 @@ struct net_bridge_port
 	struct netpoll			*np;
 #endif
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
-	struct net_port_vlans __rcu	*vlan_info;
+	struct net_bridge_vlan_group	*vlgrp;
+	u16				pvid;
 #endif
 };
 
@@ -293,10 +336,11 @@ struct net_bridge
 	struct kobject			*ifobj;
 	u32				auto_cnt;
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
+	struct net_bridge_vlan_group	*vlgrp;
 	u8				vlan_enabled;
 	__be16				vlan_proto;
 	u16				default_pvid;
-	struct net_port_vlans __rcu	*vlan_info;
+	u16				pvid;
 #endif
 };
 
@@ -344,6 +388,31 @@ static inline int br_is_root_bridge(const struct net_bridge *br)
 	return !memcmp(&br->bridge_id, &br->designated_root, 8);
 }
 
+/* check if a VLAN entry is global */
+static inline bool br_vlan_is_master(const struct net_bridge_vlan *v)
+{
+	return v->flags & BRIDGE_VLAN_INFO_MASTER;
+}
+
+/* check if a VLAN entry is used by the bridge */
+static inline bool br_vlan_is_brentry(const struct net_bridge_vlan *v)
+{
+	return v->flags & BRIDGE_VLAN_INFO_BRENTRY;
+}
+
+/* check if we should use the vlan entry is usable */
+static inline bool br_vlan_should_use(const struct net_bridge_vlan *v)
+{
+	if (br_vlan_is_master(v)) {
+		if (br_vlan_is_brentry(v))
+			return true;
+		else
+			return false;
+	}
+
+	return true;
+}
+
 /* br_device.c */
 void br_dev_setup(struct net_device *dev);
 void br_dev_delete(struct net_device *dev, struct list_head *list);
@@ -601,18 +670,19 @@ static inline void br_mdb_uninit(void)
 
 /* br_vlan.c */
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
-bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
-			struct sk_buff *skb, u16 *vid);
-bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
+bool br_allowed_ingress(struct net_bridge *br, struct sk_buff *skb, u16 *vid);
+bool nbp_allowed_ingress(struct net_bridge_port *p, struct sk_buff *skb,
+			 u16 *vid);
+bool br_allowed_egress(struct net_bridge_vlan_group *br,
 		       const struct sk_buff *skb);
 bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
-			       const struct net_port_vlans *v,
+			       struct net_bridge_vlan_group *vg,
 			       struct sk_buff *skb);
 int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
-bool br_vlan_find(struct net_bridge *br, u16 vid);
+struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid);
 void br_recalculate_fwd_mask(struct net_bridge *br);
 int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
@@ -623,19 +693,19 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
 void nbp_vlan_flush(struct net_bridge_port *port);
-bool nbp_vlan_find(struct net_bridge_port *port, u16 vid);
 int nbp_vlan_init(struct net_bridge_port *port);
+int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
 
-static inline struct net_port_vlans *br_get_vlan_info(
+static inline struct net_bridge_vlan_group *br_vlan_group(
 					const struct net_bridge *br)
 {
-	return rcu_dereference_rtnl(br->vlan_info);
+	return br->vlgrp;
 }
 
-static inline struct net_port_vlans *nbp_get_vlan_info(
+static inline struct net_bridge_vlan_group *nbp_vlan_group(
 					const struct net_bridge_port *p)
 {
-	return rcu_dereference_rtnl(p->vlan_info);
+	return p->vlgrp;
 }
 
 /* Since bridge now depends on 8021Q module, but the time bridge sees the
@@ -645,9 +715,9 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 {
 	int err = 0;
 
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		*vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
-	else {
+	} else {
 		*vid = 0;
 		err = -EINVAL;
 	}
@@ -655,13 +725,22 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 	return err;
 }
 
-static inline u16 br_get_pvid(const struct net_port_vlans *v)
+static inline u16 br_get_pvid(const struct net_bridge *br)
+{
+	if (!br)
+		return 0;
+
+	smp_rmb();
+	return br->pvid;
+}
+
+static inline u16 nbp_get_pvid(const struct net_bridge_port *p)
 {
-	if (!v)
+	if (!p)
 		return 0;
 
 	smp_rmb();
-	return v->pvid;
+	return p->pvid;
 }
 
 static inline int br_vlan_enabled(struct net_bridge *br)
@@ -670,15 +749,20 @@ static inline int br_vlan_enabled(struct net_bridge *br)
 }
 #else
 static inline bool br_allowed_ingress(struct net_bridge *br,
-				      struct net_port_vlans *v,
 				      struct sk_buff *skb,
 				      u16 *vid)
 {
 	return true;
 }
 
-static inline bool br_allowed_egress(struct net_bridge *br,
-				     const struct net_port_vlans *v,
+static inline bool nbp_allowed_ingress(struct net_bridge_port *p,
+				       struct sk_buff *skb,
+				       u16 *vid)
+{
+	return true;
+}
+
+static inline bool br_allowed_egress(struct net_bridge_vlan_group *vg,
 				     const struct sk_buff *skb)
 {
 	return true;
@@ -691,7 +775,7 @@ static inline bool br_should_learn(struct net_bridge_port *p,
 }
 
 static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
-					     const struct net_port_vlans *v,
+					     struct net_bridge_vlan_group *vg,
 					     struct sk_buff *skb)
 {
 	return skb;
@@ -711,11 +795,6 @@ static inline void br_vlan_flush(struct net_bridge *br)
 {
 }
 
-static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
-{
-	return false;
-}
-
 static inline void br_recalculate_fwd_mask(struct net_bridge *br)
 {
 }
@@ -739,32 +818,28 @@ static inline void nbp_vlan_flush(struct net_bridge_port *port)
 {
 }
 
-static inline struct net_port_vlans *br_get_vlan_info(
-						const struct net_bridge *br)
-{
-	return NULL;
-}
-static inline struct net_port_vlans *nbp_get_vlan_info(
-						const struct net_bridge_port *p)
+static inline struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg,
+						   u16 vid)
 {
 	return NULL;
 }
 
-static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid)
+static inline int nbp_vlan_init(struct net_bridge_port *port)
 {
-	return false;
+	return 0;
 }
 
-static inline int nbp_vlan_init(struct net_bridge_port *port)
+static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag)
 {
 	return 0;
 }
 
-static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag)
+static inline u16 br_get_pvid(const struct net_bridge *br)
 {
 	return 0;
 }
-static inline u16 br_get_pvid(const struct net_port_vlans *v)
+
+static inline u16 nbp_get_pvid(const struct net_bridge_port *p)
 {
 	return 0;
 }
@@ -779,6 +854,24 @@ static inline int __br_vlan_filter_toggle(struct net_bridge *br,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p,
+					 u32 filter_mask)
+{
+	return 0;
+}
+
+static inline struct net_bridge_vlan_group *br_vlan_group(
+					const struct net_bridge *br)
+{
+	return NULL;
+}
+
+static inline struct net_bridge_vlan_group *nbp_vlan_group(
+					const struct net_bridge_port *p)
+{
+	return NULL;
+}
 #endif
 
 struct nf_br_ops {