Merge branch 'bridge-igmpv3-mldv2-support'

Nikolay Aleksandrov says:

====================
bridge: add support for IGMPv3 and MLDv2 querier

This patch-set adds support for IGMPv3 and MLDv2 querier in the bridge.
Two new options which can be toggled via netlink and sysfs are added that
control the version per-bridge:
 multicast_igmp_version - default 2, can be set to 3
 multicast_mld_version - default 1, can be set to 2 (this option is
                         disabled if CONFIG_IPV6=n)

Note that the names do not include "querier", I think that these options
can be re-used later as more IGMPv3 support is added to the bridge so we
can avoid adding more options to switch between v2 and v3 behaviour.

The set uses the already existing br_ip{4,6}_multicast_alloc_query
functions and adds the appropriate header based on the chosen version.

For the initial support I have removed the compatibility implementation
(RFC3376 sec 7.3.1, 7.3.2; RFC3810 sec 8.3.1, 8.3.2), because there are
some details that we need to sort out.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/uapi/linux/if_link.h

@@ -275,6 +275,8 @@ enum {
 	IFLA_BR_PAD,
 	IFLA_BR_VLAN_STATS_ENABLED,
 	IFLA_BR_MCAST_STATS_ENABLED,
+	IFLA_BR_MCAST_IGMP_VERSION,
+	IFLA_BR_MCAST_MLD_VERSION,
 	__IFLA_BR_MAX,
 };
 

net/bridge/br_multicast.c

@@ -365,13 +365,18 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 						    __be32 group,
 						    u8 *igmp_type)
 {
+	struct igmpv3_query *ihv3;
+	size_t igmp_hdr_size;
 	struct sk_buff *skb;
 	struct igmphdr *ih;
 	struct ethhdr *eth;
 	struct iphdr *iph;
 
+	igmp_hdr_size = sizeof(*ih);
+	if (br->multicast_igmp_version == 3)
+		igmp_hdr_size = sizeof(*ihv3);
 	skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) +
-						 sizeof(*ih) + 4);
+						 igmp_hdr_size + 4);
 	if (!skb)
 		goto out;
 
@@ -396,7 +401,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 	iph->version = 4;
 	iph->ihl = 6;
 	iph->tos = 0xc0;
-	iph->tot_len = htons(sizeof(*iph) + sizeof(*ih) + 4);
+	iph->tot_len = htons(sizeof(*iph) + igmp_hdr_size + 4);
 	iph->id = 0;
 	iph->frag_off = htons(IP_DF);
 	iph->ttl = 1;
@@ -412,17 +417,37 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 	skb_put(skb, 24);
 
 	skb_set_transport_header(skb, skb->len);
-	ih = igmp_hdr(skb);
 	*igmp_type = IGMP_HOST_MEMBERSHIP_QUERY;
-	ih->type = IGMP_HOST_MEMBERSHIP_QUERY;
-	ih->code = (group ? br->multicast_last_member_interval :
-			    br->multicast_query_response_interval) /
-		   (HZ / IGMP_TIMER_SCALE);
-	ih->group = group;
-	ih->csum = 0;
-	ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr));
-	skb_put(skb, sizeof(*ih));
 
+	switch (br->multicast_igmp_version) {
+	case 2:
+		ih = igmp_hdr(skb);
+		ih->type = IGMP_HOST_MEMBERSHIP_QUERY;
+		ih->code = (group ? br->multicast_last_member_interval :
+				    br->multicast_query_response_interval) /
+			   (HZ / IGMP_TIMER_SCALE);
+		ih->group = group;
+		ih->csum = 0;
+		ih->csum = ip_compute_csum((void *)ih, sizeof(*ih));
+		break;
+	case 3:
+		ihv3 = igmpv3_query_hdr(skb);
+		ihv3->type = IGMP_HOST_MEMBERSHIP_QUERY;
+		ihv3->code = (group ? br->multicast_last_member_interval :
+				      br->multicast_query_response_interval) /
+			     (HZ / IGMP_TIMER_SCALE);
+		ihv3->group = group;
+		ihv3->qqic = br->multicast_query_interval / HZ;
+		ihv3->nsrcs = 0;
+		ihv3->resv = 0;
+		ihv3->suppress = 0;
+		ihv3->qrv = 2;
+		ihv3->csum = 0;
+		ihv3->csum = ip_compute_csum((void *)ihv3, sizeof(*ihv3));
+		break;
+	}
+
+	skb_put(skb, igmp_hdr_size);
 	__skb_pull(skb, sizeof(*eth));
 
 out:
@@ -434,15 +459,20 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 						    const struct in6_addr *grp,
 						    u8 *igmp_type)
 {
-	struct sk_buff *skb;
+	struct mld2_query *mld2q;
+	unsigned long interval;
 	struct ipv6hdr *ip6h;
 	struct mld_msg *mldq;
+	size_t mld_hdr_size;
+	struct sk_buff *skb;
 	struct ethhdr *eth;
 	u8 *hopopt;
-	unsigned long interval;
 
+	mld_hdr_size = sizeof(*mldq);
+	if (br->multicast_mld_version == 2)
+		mld_hdr_size = sizeof(*mld2q);
 	skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) +
-						 8 + sizeof(*mldq));
+						 8 + mld_hdr_size);
 	if (!skb)
 		goto out;
 
@@ -461,7 +491,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	ip6h = ipv6_hdr(skb);
 
 	*(__force __be32 *)ip6h = htonl(0x60000000);
-	ip6h->payload_len = htons(8 + sizeof(*mldq));
+	ip6h->payload_len = htons(8 + mld_hdr_size);
 	ip6h->nexthdr = IPPROTO_HOPOPTS;
 	ip6h->hop_limit = 1;
 	ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
@@ -489,26 +519,47 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 
 	/* ICMPv6 */
 	skb_set_transport_header(skb, skb->len);
-	mldq = (struct mld_msg *) icmp6_hdr(skb);
-
 	interval = ipv6_addr_any(grp) ?
 			br->multicast_query_response_interval :
 			br->multicast_last_member_interval;
-
 	*igmp_type = ICMPV6_MGM_QUERY;
-	mldq->mld_type = ICMPV6_MGM_QUERY;
-	mldq->mld_code = 0;
-	mldq->mld_cksum = 0;
-	mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
-	mldq->mld_reserved = 0;
-	mldq->mld_mca = *grp;
-
-	/* checksum */
-	mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-					  sizeof(*mldq), IPPROTO_ICMPV6,
-					  csum_partial(mldq,
-						       sizeof(*mldq), 0));
-	skb_put(skb, sizeof(*mldq));
+	switch (br->multicast_mld_version) {
+	case 1:
+		mldq = (struct mld_msg *)icmp6_hdr(skb);
+		mldq->mld_type = ICMPV6_MGM_QUERY;
+		mldq->mld_code = 0;
+		mldq->mld_cksum = 0;
+		mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
+		mldq->mld_reserved = 0;
+		mldq->mld_mca = *grp;
+		mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+						  sizeof(*mldq), IPPROTO_ICMPV6,
+						  csum_partial(mldq,
+							       sizeof(*mldq),
+							       0));
+		break;
+	case 2:
+		mld2q = (struct mld2_query *)icmp6_hdr(skb);
+		mld2q->mld2q_mrc = ntohs((u16)jiffies_to_msecs(interval));
+		mld2q->mld2q_type = ICMPV6_MGM_QUERY;
+		mld2q->mld2q_code = 0;
+		mld2q->mld2q_cksum = 0;
+		mld2q->mld2q_resv1 = 0;
+		mld2q->mld2q_resv2 = 0;
+		mld2q->mld2q_suppress = 0;
+		mld2q->mld2q_qrv = 2;
+		mld2q->mld2q_nsrcs = 0;
+		mld2q->mld2q_qqic = br->multicast_query_interval / HZ;
+		mld2q->mld2q_mca = *grp;
+		mld2q->mld2q_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+						     sizeof(*mld2q),
+						     IPPROTO_ICMPV6,
+						     csum_partial(mld2q,
+								  sizeof(*mld2q),
+								  0));
+		break;
+	}
+	skb_put(skb, mld_hdr_size);
 
 	__skb_pull(skb, sizeof(*eth));
 
@@ -608,7 +659,8 @@ static struct net_bridge_mdb_entry *br_multicast_get_group(
 }
 
 struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
-	struct net_bridge_port *port, struct br_ip *group)
+						    struct net_bridge_port *p,
+						    struct br_ip *group)
 {
 	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
@@ -624,7 +676,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
 	}
 
 	hash = br_ip_hash(mdb, group);
-	mp = br_multicast_get_group(br, port, group, hash);
+	mp = br_multicast_get_group(br, p, group, hash);
 	switch (PTR_ERR(mp)) {
 	case 0:
 		break;
@@ -681,9 +733,9 @@ static int br_multicast_add_group(struct net_bridge *br,
 				  struct net_bridge_port *port,
 				  struct br_ip *group)
 {
-	struct net_bridge_mdb_entry *mp;
-	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_mdb_entry *mp;
 	unsigned long now = jiffies;
 	int err;
 
@@ -861,9 +913,9 @@ static void br_multicast_send_query(struct net_bridge *br,
 				    struct net_bridge_port *port,
 				    struct bridge_mcast_own_query *own_query)
 {
-	unsigned long time;
-	struct br_ip br_group;
 	struct bridge_mcast_other_query *other_query = NULL;
+	struct br_ip br_group;
+	unsigned long time;
 
 	if (!netif_running(br->dev) || br->multicast_disabled ||
 	    !br->multicast_querier)
@@ -1831,7 +1883,9 @@ void br_multicast_init(struct net_bridge *br)
 
 	br->ip4_other_query.delay_time = 0;
 	br->ip4_querier.port = NULL;
+	br->multicast_igmp_version = 2;
 #if IS_ENABLED(CONFIG_IPV6)
+	br->multicast_mld_version = 1;
 	br->ip6_other_query.delay_time = 0;
 	br->ip6_querier.port = NULL;
 #endif
@@ -2132,6 +2186,44 @@ int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
 	return err;
 }
 
+int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val)
+{
+	/* Currently we support only version 2 and 3 */
+	switch (val) {
+	case 2:
+	case 3:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&br->multicast_lock);
+	br->multicast_igmp_version = val;
+	spin_unlock_bh(&br->multicast_lock);
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val)
+{
+	/* Currently we support version 1 and 2 */
+	switch (val) {
+	case 1:
+	case 2:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&br->multicast_lock);
+	br->multicast_mld_version = val;
+	spin_unlock_bh(&br->multicast_lock);
+
+	return 0;
+}
+#endif
+
 /**
  * br_multicast_list_adjacent - Returns snooped multicast addresses
  * @dev:	The bridge port adjacent to which to retrieve addresses

net/bridge/br_netlink.c

@@ -858,6 +858,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 	[IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 },
 	[IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 },
 	[IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 },
+	[IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 },
+	[IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 },
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1069,6 +1071,26 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 		mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]);
 		br->multicast_stats_enabled = !!mcast_stats;
 	}
+
+	if (data[IFLA_BR_MCAST_IGMP_VERSION]) {
+		__u8 igmp_version;
+
+		igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]);
+		err = br_multicast_set_igmp_version(br, igmp_version);
+		if (err)
+			return err;
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (data[IFLA_BR_MCAST_MLD_VERSION]) {
+		__u8 mld_version;
+
+		mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]);
+		err = br_multicast_set_mld_version(br, mld_version);
+		if (err)
+			return err;
+	}
+#endif
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (data[IFLA_BR_NF_CALL_IPTABLES]) {
@@ -1135,6 +1157,8 @@ static size_t br_get_size(const struct net_device *brdev)
 	       nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */
 	       nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */
 	       nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */
+	       nla_total_size(sizeof(u8)) +	/* IFLA_BR_MCAST_IGMP_VERSION */
+	       nla_total_size(sizeof(u8)) +	/* IFLA_BR_MCAST_MLD_VERSION */
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_NF_CALL_IPTABLES */
@@ -1210,9 +1234,15 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	    nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT,
 			br->multicast_last_member_count) ||
 	    nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT,
-			br->multicast_startup_query_count))
+			br->multicast_startup_query_count) ||
+	    nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION,
+		       br->multicast_igmp_version))
 		return -EMSGSIZE;
-
+#if IS_ENABLED(CONFIG_IPV6)
+	if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION,
+		       br->multicast_mld_version))
+		return -EMSGSIZE;
+#endif
 	clockval = jiffies_to_clock_t(br->multicast_last_member_interval);
 	if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval,
 			      IFLA_BR_PAD))

net/bridge/br_private.h

@@ -333,6 +333,8 @@ struct net_bridge
 	u32				multicast_last_member_count;
 	u32				multicast_startup_query_count;
 
+	u8				multicast_igmp_version;
+
 	unsigned long			multicast_last_member_interval;
 	unsigned long			multicast_membership_interval;
 	unsigned long			multicast_querier_interval;
@@ -353,6 +355,7 @@ struct net_bridge
 	struct bridge_mcast_other_query	ip6_other_query;
 	struct bridge_mcast_own_query	ip6_own_query;
 	struct bridge_mcast_querier	ip6_querier;
+	u8				multicast_mld_version;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 #endif
 
@@ -582,6 +585,10 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val);
 int br_multicast_toggle(struct net_bridge *br, unsigned long val);
 int br_multicast_set_querier(struct net_bridge *br, unsigned long val);
 int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
+int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val);
+#if IS_ENABLED(CONFIG_IPV6)
+int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val);
+#endif
 struct net_bridge_mdb_entry *
 br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst);
 struct net_bridge_mdb_entry *

net/bridge/br_sysfs_br.c

@@ -440,6 +440,23 @@ static ssize_t hash_max_store(struct device *d, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(hash_max);
 
+static ssize_t multicast_igmp_version_show(struct device *d,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+
+	return sprintf(buf, "%u\n", br->multicast_igmp_version);
+}
+
+static ssize_t multicast_igmp_version_store(struct device *d,
+					    struct device_attribute *attr,
+					    const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_multicast_set_igmp_version);
+}
+static DEVICE_ATTR_RW(multicast_igmp_version);
+
 static ssize_t multicast_last_member_count_show(struct device *d,
 						struct device_attribute *attr,
 						char *buf)
@@ -642,6 +659,25 @@ static ssize_t multicast_stats_enabled_store(struct device *d,
 	return store_bridge_parm(d, buf, len, set_stats_enabled);
 }
 static DEVICE_ATTR_RW(multicast_stats_enabled);
+
+#if IS_ENABLED(CONFIG_IPV6)
+static ssize_t multicast_mld_version_show(struct device *d,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+
+	return sprintf(buf, "%u\n", br->multicast_mld_version);
+}
+
+static ssize_t multicast_mld_version_store(struct device *d,
+					   struct device_attribute *attr,
+					   const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_multicast_set_mld_version);
+}
+static DEVICE_ATTR_RW(multicast_mld_version);
+#endif
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static ssize_t nf_call_iptables_show(
@@ -809,6 +845,10 @@ static struct attribute *bridge_attrs[] = {
 	&dev_attr_multicast_query_response_interval.attr,
 	&dev_attr_multicast_startup_query_interval.attr,
 	&dev_attr_multicast_stats_enabled.attr,
+	&dev_attr_multicast_igmp_version.attr,
+#if IS_ENABLED(CONFIG_IPV6)
+	&dev_attr_multicast_mld_version.attr,
+#endif
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	&dev_attr_nf_call_iptables.attr,