net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12.

i) RFC3810, 9.2. Query Interval [QI] says:

   The Query Interval variable denotes the interval between General
   Queries sent by the Querier. Default value: 125 seconds. [...]

ii) RFC3810, 9.3. Query Response Interval [QRI] says:

  The Maximum Response Delay used to calculate the Maximum Response
  Code inserted into the periodic General Queries. Default value:
  10000 (10 seconds) [...] The number of seconds represented by the
  [Query Response Interval] must be less than the [Query Interval].

iii) RFC3810, 9.12. Older Version Querier Present Timeout [OVQPT] says:

  The Older Version Querier Present Timeout is the time-out for
  transitioning a host back to MLDv2 Host Compatibility Mode. When an
  MLDv1 query is received, MLDv2 hosts set their Older Version Querier
  Present Timer to [Older Version Querier Present Timeout].

  This value MUST be ([Robustness Variable] times (the [Query Interval]
  in the last Query received)) plus ([Query Response Interval]).

Hence, on *default* the timeout results in:

  [RV] = 2, [QI] = 125sec, [QRI] = 10sec
  [OVQPT] = [RV] * [QI] + [QRI] = 260sec

Having that said, we currently calculate [OVQPT] (here given as 'switchback'
variable) as ...

  switchback = (idev->mc_qrv + 1) * max_delay

RFC3810, 9.12. says "the [Query Interval] in the last Query received". In
section "9.14. Configuring timers", it is said:

  This section is meant to provide advice to network administrators on
  how to tune these settings to their network. Ambitious router
  implementations might tune these settings dynamically based upon
  changing characteristics of the network. [...]

iv) RFC38010, 9.14.2. Query Interval:

  The overall level of periodic MLD traffic is inversely proportional
  to the Query Interval. A longer Query Interval results in a lower
  overall level of MLD traffic. The value of the Query Interval MUST
  be equal to or greater than the Maximum Response Delay used to
  calculate the Maximum Response Code inserted in General Query
  messages.

I assume that was why switchback is calculated as is (3 * max_delay), although
this setting seems to be meant for routers only to configure their [QI]
interval for non-default intervals. So usage here like this is clearly wrong.

Concluding, the current behaviour in IPv6's multicast code is not conform
to the RFC as switch back is calculated wrongly. That is, it has a too small
value, so MLDv2 hosts switch back again to MLDv2 way too early, i.e. ~30secs
instead of ~260secs on default.

Hence, introduce necessary helper functions and fix this up properly as it
should be.

Introduced in 06da92283 ("[IPV6]: Add MLDv2 support."). Credits to Hannes
Frederic Sowa who also had a hand in this as well. Also thanks to Hangbin Liu
who did initial testing.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: David Stevens <dlstevens@us.ibm.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 110 insertions, 6 deletions

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 98ead2b1a66..8992ff26278 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -108,6 +108,10 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 			    struct inet6_dev *idev);
 
 #define MLD_QRV_DEFAULT		2
+/* RFC3810, 9.2. Query Interval */
+#define MLD_QI_DEFAULT		(125 * HZ)
+/* RFC3810, 9.3. Query Response Interval */
+#define MLD_QRI_DEFAULT		(10 * HZ)
 
 /* RFC3810, 8.1 Query Version Distinctions */
 #define MLD_V1_QUERY_LEN	24
@@ -1112,6 +1116,93 @@ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
 	return true;
 }
 
+static void mld_set_v1_mode(struct inet6_dev *idev)
+{
+	/* RFC3810, relevant sections:
+	 *  - 9.1. Robustness Variable
+	 *  - 9.2. Query Interval
+	 *  - 9.3. Query Response Interval
+	 *  - 9.12. Older Version Querier Present Timeout
+	 */
+	unsigned long switchback;
+
+	switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri;
+
+	idev->mc_v1_seen = jiffies + switchback;
+}
+
+static void mld_update_qrv(struct inet6_dev *idev,
+			   const struct mld2_query *mlh2)
+{
+	/* RFC3810, relevant sections:
+	 *  - 5.1.8. QRV (Querier's Robustness Variable)
+	 *  - 9.1. Robustness Variable
+	 */
+
+	/* The value of the Robustness Variable MUST NOT be zero,
+	 * and SHOULD NOT be one. Catch this here if we ever run
+	 * into such a case in future.
+	 */
+	WARN_ON(idev->mc_qrv == 0);
+
+	if (mlh2->mld2q_qrv > 0)
+		idev->mc_qrv = mlh2->mld2q_qrv;
+
+	if (unlikely(idev->mc_qrv < 2)) {
+		net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n",
+				     idev->mc_qrv, MLD_QRV_DEFAULT);
+		idev->mc_qrv = MLD_QRV_DEFAULT;
+	}
+}
+
+static void mld_update_qi(struct inet6_dev *idev,
+			  const struct mld2_query *mlh2)
+{
+	/* RFC3810, relevant sections:
+	 *  - 5.1.9. QQIC (Querier's Query Interval Code)
+	 *  - 9.2. Query Interval
+	 *  - 9.12. Older Version Querier Present Timeout
+	 *    (the [Query Interval] in the last Query received)
+	 */
+	unsigned long mc_qqi;
+
+	if (mlh2->mld2q_qqic < 128) {
+		mc_qqi = mlh2->mld2q_qqic;
+	} else {
+		unsigned long mc_man, mc_exp;
+
+		mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic);
+		mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic);
+
+		mc_qqi = (mc_man | 0x10) << (mc_exp + 3);
+	}
+
+	idev->mc_qi = mc_qqi * HZ;
+}
+
+static void mld_update_qri(struct inet6_dev *idev,
+			   const struct mld2_query *mlh2)
+{
+	/* RFC3810, relevant sections:
+	 *  - 5.1.3. Maximum Response Code
+	 *  - 9.3. Query Response Interval
+	 */
+	unsigned long mc_qri, mc_mrc = ntohs(mlh2->mld2q_mrc);
+
+	if (mc_mrc < 32768) {
+		mc_qri = mc_mrc;
+	} else {
+		unsigned long mc_man, mc_exp;
+
+		mc_exp = MLDV2_MRC_EXP(mc_mrc);
+		mc_man = MLDV2_MRC_MAN(mc_mrc);
+
+		mc_qri = (mc_man | 0x1000) << (mc_exp + 3);
+	}
+
+	idev->mc_qri = msecs_to_jiffies(mc_qri);
+}
+
 /* called with rcu_read_lock() */
 int igmp6_event_query(struct sk_buff *skb)
 {
@@ -1150,12 +1241,15 @@ int igmp6_event_query(struct sk_buff *skb)
 		return -EINVAL;
 
 	if (len == MLD_V1_QUERY_LEN) {
-		int switchback;
 		/* MLDv1 router present */
-
 		max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay));
-		switchback = (idev->mc_qrv + 1) * max_delay;
-		idev->mc_v1_seen = jiffies + switchback;
+
+		mld_set_v1_mode(idev);
+
+		/* cancel MLDv2 report timer */
+		idev->mc_gq_running = 0;
+		if (del_timer(&idev->mc_gq_timer))
+			__in6_dev_put(idev);
 
 		/* cancel the interface change timer */
 		idev->mc_ifc_count = 0;
@@ -1166,6 +1260,10 @@ int igmp6_event_query(struct sk_buff *skb)
 	} else if (len >= MLD_V2_QUERY_LEN_MIN) {
 		int srcs_offset = sizeof(struct mld2_query) -
 				  sizeof(struct icmp6hdr);
+
+		/* hosts need to stay in MLDv1 mode, discard MLDv2 queries */
+		if (MLD_V1_SEEN(idev))
+			return 0;
 		if (!pskb_may_pull(skb, srcs_offset))
 			return -EINVAL;
 
@@ -1175,8 +1273,10 @@ int igmp6_event_query(struct sk_buff *skb)
 
 		idev->mc_maxdelay = max_delay;
 
-		if (mlh2->mld2q_qrv)
-			idev->mc_qrv = mlh2->mld2q_qrv;
+		mld_update_qrv(idev, mlh2);
+		mld_update_qi(idev, mlh2);
+		mld_update_qri(idev, mlh2);
+
 		if (group_type == IPV6_ADDR_ANY) { /* general query */
 			if (mlh2->mld2q_nsrcs)
 				return -EINVAL; /* no sources allowed */
@@ -2337,7 +2437,11 @@ void ipv6_mc_init_dev(struct inet6_dev *idev)
 			(unsigned long)idev);
 	setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire,
 		    (unsigned long)idev);
+
 	idev->mc_qrv = MLD_QRV_DEFAULT;
+	idev->mc_qi = MLD_QI_DEFAULT;
+	idev->mc_qri = MLD_QRI_DEFAULT;
+
 	idev->mc_maxdelay = unsolicited_report_interval(idev);
 	idev->mc_v1_seen = 0;
 	write_unlock_bh(&idev->lock);