Merge branch 'bridge-next'

Toshiaki Makita says:

====================
bridge: 802.1ad vlan protocol support

Currently bridge vlan filtering doesn't work fine with 802.1ad protocol.
Only if a bridge is configured without pvid, the bridge receives only
802.1ad tagged frames and no STP is used, it will work.
Otherwise:
- If pvid is configured, it can put only 802.1Q tags but cannot put 802.1ad
  tags.
- If 802.1Q and 802.1ad tagged frames arrive in mixture, it applies filtering
  regardless of their protocols.
- While an 802.1ad bridge should use another mac address for STP BPDU and
  should forward customer's BPDU frames, it can't.
Thus, we can't properly handle frames once 802.1ad is used.

Handling 802.1ad is useful if we want to allow stacked vlans to be used,
e.g., guest VMs wants to use vlan tags and the host also wants to segregate
guest's traffic from other guests' by vlan tags.

Here is the image describing how to configure a bridge to filter VMs traffic.

         +-------+p/u   +-----+  +---------+
 +----+  |       |------|vnet0|--|User A VM|
 |eth0|--|802.1ad|      +-----+  +---------+
 +----+  |bridge |p/u   +-----+  +---------+
         |       |------|vnet1|--|User B VM|
         +-------+      +-----+  +---------+
p/u: pvid/untagged

This patch set enables us to set vlan protocols per bridge.
This tries to implement a bridge like S-VLAN component in IEEE 802.1Q-2011
spec.

Note that there is another possible implementation that sets vlan protocols
per port. Some HW switches seem to take that approach.
However, I think per-bridge approach is better, because;
- I think the typical usage of an 802.1ad bridge is segregating 802.1Q tagged
  traffic (like what is described above), and this doesn't need the ability to
  be set protocols per port. Also, If a bridge has many ports and it supports
  per-port setting, we might have to make much more extra configurations to
  change protocols of all ports.

- I assume that the main perpose to set protocol per port is to assign S-VID
  according to C-VID, or to realize two logical bridges (one is an 802.1Q
  filtering bridge and the other is an 802.1ad filtering bridge) in one bridge.
  The former usually needs additional features such as vlan id mapping, and
  is likely to make bridge's code complicated. If a user wants, such enhanced
  features can be accomplished by a combination of multiple bridges, so it is
  not absolutely necessary to implement these features in a bridge itself.
  The latter is simply unnecessary because we can easily make two bridges of
  which one is an 802.1Q bridge and the other is an 802.1ad bridge.

Here is an example of the enhanced feature that we can realize by using
multiple bridges and veth interfaces. This way is documented in
IEEE 802.1Q-2011 clause 15.4 (C-tagged service interface).

 +----+  +-------+p/u         +------+  +----+  +--+
 |eth0|--|802.1ad|----veth----|802.1Q|--|vnet|--|VM|
 +----+  |bridge |----veth----|bridge|  +----+  +--+
         +-------+p/u         +------+
p/u: pvid/untagged

In this configuration, we can map C-VIDs to any S-VID.
For example;
 C-VID 10 and 20 to S-VID 100
 C-VID 30 to S-VID 110
This is achieved through the 802.1Q bridge that forwards C-tagged frames to
proper ports of the 802.1ad bridge.

Changes:
v1 -> v2:
- Make the way to forward bridge group addresses more generic by introducing
  new mask, group_fwd_mask_required.

RFC -> v1:
- Add S-TAG tx offload.
- Remove a fix around stacked vlan which has already been fixed.
- Take into account Bridge Group Addresses.
- Separate handling of protocol-mismatch from br_vlan_get_tag().
- Change the way to set vlan_proto from netlink to sysfs because no other
  existing configuration per bridge can be set by netlink.
====================

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

5 files changed, 194 insertions, 16 deletions

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index d77e2f0ff0e9d..568cccd39a3d8 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -361,8 +361,9 @@ void br_dev_setup(struct net_device *dev)
 	dev->priv_flags = IFF_EBRIDGE;
 
 	dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
-			NETIF_F_HW_VLAN_CTAG_TX;
-	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX;
+			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
+			   NETIF_F_HW_VLAN_STAG_TX;
 	dev->vlan_features = COMMON_FEATURES;
 
 	br->dev = dev;
@@ -377,6 +378,7 @@ void br_dev_setup(struct net_device *dev)
 
 	br->stp_enabled = BR_NO_STP;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
+	br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
 
 	br->designated_root = br->bridge_id;
 	br->bridge_max_age = br->max_age = 20 * HZ;
@@ -387,4 +389,5 @@ void br_dev_setup(struct net_device *dev)
 	br_netfilter_rtable_init(br);
 	br_stp_timer_init(br);
 	br_multicast_init(br);
+	br_vlan_init(br);
 }
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 04d6348fd530f..366c43649079d 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -177,6 +177,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 	p = br_port_get_rcu(skb->dev);
 
 	if (unlikely(is_link_local_ether_addr(dest))) {
+		u16 fwd_mask = p->br->group_fwd_mask_required;
+
 		/*
 		 * See IEEE 802.1D Table 7-10 Reserved addresses
 		 *
@@ -194,7 +196,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		case 0x00:	/* Bridge Group Address */
 			/* If STP is turned off,
 			   then must forward to keep loop detection */
-			if (p->br->stp_enabled == BR_NO_STP)
+			if (p->br->stp_enabled == BR_NO_STP ||
+			    fwd_mask & (1u << dest[5]))
 				goto forward;
 			break;
 
@@ -203,7 +206,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 
 		default:
 			/* Allow selective forwarding for most other protocols */
-			if (p->br->group_fwd_mask & (1u << dest[5]))
+			fwd_mask |= p->br->group_fwd_mask;
+			if (fwd_mask & (1u << dest[5]))
 				goto forward;
 		}
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 8346e9504cdb5..23caf5b0309ef 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -35,6 +35,8 @@
 #define BR_GROUPFWD_DEFAULT	0
 /* Don't allow forwarding control protocols like STP and LLDP */
 #define BR_GROUPFWD_RESTRICTED	0x4007u
+/* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */
+#define BR_GROUPFWD_8021AD	0xB801u
 
 /* Path to usermode spanning tree program */
 #define BR_STP_PROG	"/sbin/bridge-stp"
@@ -226,6 +228,7 @@ struct net_bridge
 	bool				nf_call_arptables;
 #endif
 	u16				group_fwd_mask;
+	u16				group_fwd_mask_required;
 
 	/* STP */
 	bridge_id			designated_root;
@@ -240,6 +243,7 @@ struct net_bridge
 	unsigned long			bridge_forward_delay;
 
 	u8				group_addr[ETH_ALEN];
+	bool				group_addr_set;
 	u16				root_port;
 
 	enum {
@@ -294,6 +298,7 @@ struct net_bridge
 	u32				auto_cnt;
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	u8				vlan_enabled;
+	__be16				vlan_proto;
 	struct net_port_vlans __rcu	*vlan_info;
 #endif
 };
@@ -593,7 +598,10 @@ 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);
+void br_recalculate_fwd_mask(struct net_bridge *br);
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
+int br_vlan_set_proto(struct net_bridge *br, unsigned long val);
+void br_vlan_init(struct net_bridge *br);
 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);
@@ -689,6 +697,14 @@ 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)
+{
+}
+
+static inline void br_vlan_init(struct net_bridge *br)
+{
+}
+
 static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
 {
 	return -EOPNOTSUPP;
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 8dac65552f190..c9e2572b15f40 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -312,10 +312,19 @@ static ssize_t group_addr_store(struct device *d,
 	    new_addr[5] == 3)		/* 802.1X PAE address */
 		return -EINVAL;
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	spin_lock_bh(&br->lock);
 	for (i = 0; i < 6; i++)
 		br->group_addr[i] = new_addr[i];
 	spin_unlock_bh(&br->lock);
+
+	br->group_addr_set = true;
+	br_recalculate_fwd_mask(br);
+
+	rtnl_unlock();
+
 	return len;
 }
 
@@ -700,6 +709,22 @@ static ssize_t vlan_filtering_store(struct device *d,
 	return store_bridge_parm(d, buf, len, br_vlan_filter_toggle);
 }
 static DEVICE_ATTR_RW(vlan_filtering);
+
+static ssize_t vlan_protocol_show(struct device *d,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%#06x\n", ntohs(br->vlan_proto));
+}
+
+static ssize_t vlan_protocol_store(struct device *d,
+				   struct device_attribute *attr,
+				   const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_vlan_set_proto);
+}
+static DEVICE_ATTR_RW(vlan_protocol);
 #endif
 
 static struct attribute *bridge_attrs[] = {
@@ -745,6 +770,7 @@ static struct attribute *bridge_attrs[] = {
 #endif
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	&dev_attr_vlan_filtering.attr,
+	&dev_attr_vlan_protocol.attr,
 #endif
 	NULL
 };
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index fcc95390f862e..2b2774fe07038 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -60,7 +60,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 		 * that ever changes this code will allow tagged
 		 * traffic to enter the bridge.
 		 */
-		err = vlan_vid_add(dev, htons(ETH_P_8021Q), vid);
+		err = vlan_vid_add(dev, br->vlan_proto, vid);
 		if (err)
 			return err;
 	}
@@ -80,7 +80,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 
 out_filt:
 	if (p)
-		vlan_vid_del(dev, htons(ETH_P_8021Q), vid);
+		vlan_vid_del(dev, br->vlan_proto, vid);
 	return err;
 }
 
@@ -92,8 +92,10 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid)
 	__vlan_delete_pvid(v, vid);
 	clear_bit(vid, v->untagged_bitmap);
 
-	if (v->port_idx)
-		vlan_vid_del(v->parent.port->dev, htons(ETH_P_8021Q), vid);
+	if (v->port_idx) {
+		struct net_bridge_port *p = v->parent.port;
+		vlan_vid_del(p->dev, p->br->vlan_proto, vid);
+	}
 
 	clear_bit(vid, v->vlan_bitmap);
 	v->num_vlans--;
@@ -158,7 +160,8 @@ out:
 bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			struct sk_buff *skb, u16 *vid)
 {
-	int err;
+	bool tagged;
+	__be16 proto;
 
 	/* If VLAN filtering is disabled on the bridge, all packets are
 	 * permitted.
@@ -172,19 +175,41 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	if (!v)
 		goto drop;
 
+	proto = br->vlan_proto;
+
 	/* If vlan tx offload is disabled on bridge device and frame was
 	 * sent from vlan device on the bridge device, it does not have
 	 * HW accelerated vlan tag.
 	 */
 	if (unlikely(!vlan_tx_tag_present(skb) &&
-		     (skb->protocol == htons(ETH_P_8021Q) ||
-		      skb->protocol == htons(ETH_P_8021AD)))) {
+		     skb->protocol == proto)) {
 		skb = vlan_untag(skb);
 		if (unlikely(!skb))
 			return false;
 	}
 
-	err = br_vlan_get_tag(skb, vid);
+	if (!br_vlan_get_tag(skb, vid)) {
+		/* Tagged frame */
+		if (skb->vlan_proto != proto) {
+			/* Protocol-mismatch, empty out vlan_tci for new tag */
+			skb_push(skb, ETH_HLEN);
+			skb = __vlan_put_tag(skb, skb->vlan_proto,
+					     vlan_tx_tag_get(skb));
+			if (unlikely(!skb))
+				return false;
+
+			skb_pull(skb, ETH_HLEN);
+			skb_reset_mac_len(skb);
+			*vid = 0;
+			tagged = false;
+		} else {
+			tagged = true;
+		}
+	} else {
+		/* Untagged frame */
+		tagged = false;
+	}
+
 	if (!*vid) {
 		u16 pvid = br_get_pvid(v);
 
@@ -199,9 +224,9 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		 * ingress frame is considered to belong to this vlan.
 		 */
 		*vid = pvid;
-		if (likely(err))
+		if (likely(!tagged))
 			/* Untagged Frame. */
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid);
+			__vlan_hwaccel_put_tag(skb, proto, pvid);
 		else
 			/* Priority-tagged Frame.
 			 * At this point, We know that skb->vlan_tci had
@@ -254,7 +279,9 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
 	if (!v)
 		return false;
 
-	br_vlan_get_tag(skb, vid);
+	if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto)
+		*vid = 0;
+
 	if (!*vid) {
 		*vid = br_get_pvid(v);
 		if (*vid == VLAN_N_VID)
@@ -351,6 +378,33 @@ out:
 	return found;
 }
 
+/* Must be protected by RTNL. */
+static void recalculate_group_addr(struct net_bridge *br)
+{
+	if (br->group_addr_set)
+		return;
+
+	spin_lock_bh(&br->lock);
+	if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q)) {
+		/* Bridge Group Address */
+		br->group_addr[5] = 0x00;
+	} else { /* vlan_enabled && ETH_P_8021AD */
+		/* Provider Bridge Group Address */
+		br->group_addr[5] = 0x08;
+	}
+	spin_unlock_bh(&br->lock);
+}
+
+/* Must be protected by RTNL. */
+void br_recalculate_fwd_mask(struct net_bridge *br)
+{
+	if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q))
+		br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
+	else /* vlan_enabled && ETH_P_8021AD */
+		br->group_fwd_mask_required = BR_GROUPFWD_8021AD &
+					      ~(1u << br->group_addr[5]);
+}
+
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 {
 	if (!rtnl_trylock())
@@ -361,12 +415,87 @@ int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 
 	br->vlan_enabled = val;
 	br_manage_promisc(br);
+	recalculate_group_addr(br);
+	br_recalculate_fwd_mask(br);
 
 unlock:
 	rtnl_unlock();
 	return 0;
 }
 
+int br_vlan_set_proto(struct net_bridge *br, unsigned long val)
+{
+	int err = 0;
+	struct net_bridge_port *p;
+	struct net_port_vlans *pv;
+	__be16 proto, oldproto;
+	u16 vid, errvid;
+
+	if (val != ETH_P_8021Q && val != ETH_P_8021AD)
+		return -EPROTONOSUPPORT;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	proto = htons(val);
+	if (br->vlan_proto == proto)
+		goto unlock;
+
+	/* Add VLANs for the new proto to the device filter. */
+	list_for_each_entry(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+			err = vlan_vid_add(p->dev, proto, vid);
+			if (err)
+				goto err_filt;
+		}
+	}
+
+	oldproto = br->vlan_proto;
+	br->vlan_proto = proto;
+
+	recalculate_group_addr(br);
+	br_recalculate_fwd_mask(br);
+
+	/* Delete VLANs for the old proto from the device filter. */
+	list_for_each_entry(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+			vlan_vid_del(p->dev, oldproto, vid);
+	}
+
+unlock:
+	rtnl_unlock();
+	return err;
+
+err_filt:
+	errvid = vid;
+	for_each_set_bit(vid, pv->vlan_bitmap, errvid)
+		vlan_vid_del(p->dev, proto, vid);
+
+	list_for_each_entry_continue_reverse(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+			vlan_vid_del(p->dev, proto, vid);
+	}
+
+	goto unlock;
+}
+
+void br_vlan_init(struct net_bridge *br)
+{
+	br->vlan_proto = htons(ETH_P_8021Q);
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */
@@ -433,7 +562,7 @@ void nbp_vlan_flush(struct net_bridge_port *port)
 		return;
 
 	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
-		vlan_vid_del(port->dev, htons(ETH_P_8021Q), vid);
+		vlan_vid_del(port->dev, port->br->vlan_proto, vid);
 
 	__vlan_flush(pv);
 }