ipv6/mcast: init as INCLUDE when join SSM INCLUDE group

This an IPv6 version patch of "ipv4/igmp: init group mode as INCLUDE when
join source group". From RFC3810, part 6.1:

   If no per-interface state existed for that
   multicast address before the change (i.e., the change consisted of
   creating a new per-interface record), or if no state exists after the
   change (i.e., the change consisted of deleting a per-interface
   record), then the "non-existent" state is considered to have an
   INCLUDE filter mode and an empty source list.

Which means a new multicast group should start with state IN(). Currently,
for MLDv2 SSM JOIN_SOURCE_GROUP mode, we first call ipv6_sock_mc_join(),
then ip6_mc_source(), which will trigger a TO_IN() message instead of
ALLOW().

The issue was exposed by commit a052517a ("net/multicast: should not
send source list records when have filter mode change"). Before this change,
we sent both ALLOW(A) and TO_IN(A). Now, we only send TO_IN(A).

Fix it by adding a new parameter to init group mode. Also add some wrapper
functions to avoid changing too much code.

v1 -> v2:
In the first version I only cleared the group change record. But this is not
enough. Because when a new group join, it will init as EXCLUDE and trigger
a filter mode change in ip/ip6_mc_add_src(), which will clear all source
addresses sf_crcount. This will prevent early joined address sending state
change records if multi source addressed joined at the same time.

In v2 patch, I fixed it by directly initializing the mode to INCLUDE for SSM
JOIN_SOURCE_GROUP. I also split the original patch into two separated patches
for IPv4 and IPv6.

There is also a difference between v4 and v6 version. For IPv6, when the
interface goes down and up, we will send correct state change record with
unspecified IPv6 address (::) with function ipv6_mc_up(). But after DAD is
completed, we resend the change record TO_IN() in mld_send_initial_cr().
Fix it by sending ALLOW() for INCLUDE mode in mld_send_initial_cr().

Fixes: a052517a ("net/multicast: should not send source list records when have filter mode change")
Reviewed-by: NStefano Brivio <sbrivio@redhat.com>
Signed-off-by: NHangbin Liu <liuhangbin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/net/ipv6.h

@@ -1100,6 +1100,8 @@ void ipv6_sysctl_unregister(void);
 
 int ipv6_sock_mc_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+			  const struct in6_addr *addr, unsigned int mode);
 int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 #endif /* _NET_IPV6_H */

net/ipv6/ipv6_sockglue.c

@@ -729,8 +729,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			struct sockaddr_in6 *psin6;
 
 			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
-			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
-						 &psin6->sin6_addr);
+			retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface,
+						     &psin6->sin6_addr,
+						     MCAST_INCLUDE);
 			/* prior join w/ different source is ok */
 			if (retv && retv != -EADDRINUSE)
 				break;

net/ipv6/mcast.c

@@ -95,6 +95,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 			  int delta);
 static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 			    struct inet6_dev *idev);
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+			     const struct in6_addr *addr, unsigned int mode);
 
 #define MLD_QRV_DEFAULT		2
 /* RFC3810, 9.2. Query Interval */
@@ -132,7 +134,8 @@ static int unsolicited_report_interval(struct inet6_dev *idev)
 	return iv > 0 ? iv : 1;
 }
 
-int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+static int __ipv6_sock_mc_join(struct sock *sk, int ifindex,
+			       const struct in6_addr *addr, unsigned int mode)
 {
 	struct net_device *dev = NULL;
 	struct ipv6_mc_socklist *mc_lst;
@@ -179,7 +182,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	}
 
 	mc_lst->ifindex = dev->ifindex;
-	mc_lst->sfmode = MCAST_EXCLUDE;
+	mc_lst->sfmode = mode;
 	rwlock_init(&mc_lst->sflock);
 	mc_lst->sflist = NULL;
 
@@ -187,7 +190,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	 *	now add/increase the group membership on the device
 	 */
 
-	err = ipv6_dev_mc_inc(dev, addr);
+	err = __ipv6_dev_mc_inc(dev, addr, mode);
 
 	if (err) {
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
@@ -199,8 +202,19 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	return 0;
 }
+
+int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+{
+	return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ipv6_sock_mc_join);
 
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+			  const struct in6_addr *addr, unsigned int mode)
+{
+	return __ipv6_sock_mc_join(sk, ifindex, addr, mode);
+}
+
 /*
  *	socket leave on multicast group
  */
@@ -646,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 	return rv;
 }
 
-static void igmp6_group_added(struct ifmcaddr6 *mc)
+static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode)
 {
 	struct net_device *dev = mc->idev->dev;
 	char buf[MAX_ADDR_LEN];
@@ -672,7 +686,13 @@ static void igmp6_group_added(struct ifmcaddr6 *mc)
 	}
 	/* else v2 */
 
-	mc->mca_crcount = mc->idev->mc_qrv;
+	/* Based on RFC3810 6.1, for newly added INCLUDE SSM, we
+	 * should not send filter-mode change record as the mode
+	 * should be from IN() to IN(A).
+	 */
+	if (mode == MCAST_EXCLUDE)
+		mc->mca_crcount = mc->idev->mc_qrv;
+
 	mld_ifc_event(mc->idev);
 }
 
@@ -770,13 +790,14 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	spin_lock_bh(&im->mca_lock);
 	if (pmc) {
 		im->idev = pmc->idev;
-		im->mca_crcount = idev->mc_qrv;
 		im->mca_sfmode = pmc->mca_sfmode;
 		if (pmc->mca_sfmode == MCAST_INCLUDE) {
 			im->mca_tomb = pmc->mca_tomb;
 			im->mca_sources = pmc->mca_sources;
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = im->mca_crcount;
+				psf->sf_crcount = idev->mc_qrv;
+		} else {
+			im->mca_crcount = idev->mc_qrv;
 		}
 		in6_dev_put(pmc->idev);
 		kfree(pmc);
@@ -831,7 +852,8 @@ static void ma_put(struct ifmcaddr6 *mc)
 }
 
 static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
-				   const struct in6_addr *addr)
+				   const struct in6_addr *addr,
+				   unsigned int mode)
 {
 	struct ifmcaddr6 *mc;
 
@@ -849,9 +871,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 	refcount_set(&mc->mca_refcnt, 1);
 	spin_lock_init(&mc->mca_lock);
 
-	/* initial mode is (EX, empty) */
-	mc->mca_sfmode = MCAST_EXCLUDE;
-	mc->mca_sfcount[MCAST_EXCLUDE] = 1;
+	mc->mca_sfmode = mode;
+	mc->mca_sfcount[mode] = 1;
 
 	if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) ||
 	    IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL)
@@ -863,7 +884,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 /*
  *	device multicast group inc (add if not found)
  */
-int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+			     const struct in6_addr *addr, unsigned int mode)
 {
 	struct ifmcaddr6 *mc;
 	struct inet6_dev *idev;
@@ -887,14 +909,13 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 		if (ipv6_addr_equal(&mc->mca_addr, addr)) {
 			mc->mca_users++;
 			write_unlock_bh(&idev->lock);
-			ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0,
-				NULL, 0);
+			ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0);
 			in6_dev_put(idev);
 			return 0;
 		}
 	}
 
-	mc = mca_alloc(idev, addr);
+	mc = mca_alloc(idev, addr, mode);
 	if (!mc) {
 		write_unlock_bh(&idev->lock);
 		in6_dev_put(idev);
@@ -911,11 +932,16 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	write_unlock_bh(&idev->lock);
 
 	mld_del_delrec(idev, mc);
-	igmp6_group_added(mc);
+	igmp6_group_added(mc, mode);
 	ma_put(mc);
 	return 0;
 }
 
+int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+{
+	return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE);
+}
+
 /*
  *	device multicast group del
  */
@@ -1751,7 +1777,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 
 		psf_next = psf->sf_next;
 
-		if (!is_in(pmc, psf, type, gdeleted, sdeleted)) {
+		if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) {
 			psf_prev = psf;
 			continue;
 		}
@@ -2066,7 +2092,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev)
 		if (pmc->mca_sfcount[MCAST_EXCLUDE])
 			type = MLD2_CHANGE_TO_EXCLUDE;
 		else
-			type = MLD2_CHANGE_TO_INCLUDE;
+			type = MLD2_ALLOW_NEW_SOURCES;
 		skb = add_grec(skb, pmc, type, 0, 0, 1);
 		spin_unlock_bh(&pmc->mca_lock);
 	}
@@ -2546,7 +2572,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	ipv6_mc_reset(idev);
 	for (i = idev->mc_list; i; i = i->next) {
 		mld_del_delrec(idev, i);
-		igmp6_group_added(i);
+		igmp6_group_added(i, i->mca_sfmode);
 	}
 	read_unlock_bh(&idev->lock);
 }