From 616a9be25cb9516e546c0de55d61e1e46e54ade9 Mon Sep 17 00:00:00 2001
From: Kenny Mathis <kmathis@chokepoint.net>
Date: Tue, 9 Sep 2014 09:20:15 -0400
Subject: [PATCH 01/15] ipvs: Add simple weighted failover scheduler

Add simple weighted IPVS failover support to the Linux kernel. All
other scheduling modules implement some form of load balancing, while
this offers a simple failover solution. Connections are directed to
the appropriate server based solely on highest weight value and server
availability. Tested functionality with keepalived.

Signed-off-by: Kenny Mathis <kmathis@chokepoint.net>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/Kconfig    | 10 +++++
 net/netfilter/ipvs/Makefile   |  1 +
 net/netfilter/ipvs/ip_vs_fo.c | 79 +++++++++++++++++++++++++++++++++++
 3 files changed, 90 insertions(+)
 create mode 100644 net/netfilter/ipvs/ip_vs_fo.c

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 0c3b1670b0d1..3b6929dec748 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -152,6 +152,16 @@ config	IP_VS_WLC
 	  If you want to compile it in kernel, say Y. To compile it as a
 	  module, choose M here. If unsure, say N.
 
+config  IP_VS_FO
+		tristate "weighted failover scheduling"
+	---help---
+	  The weighted failover scheduling algorithm directs network
+	  connections to the server with the highest weight that is
+	  currently available.
+
+	  If you want to compile it in kernel, say Y. To compile it as a
+	  module, choose M here. If unsure, say N.
+
 config	IP_VS_LBLC
 	tristate "locality-based least-connection scheduling"
 	---help---
diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile
index 34ee602ddb66..38b2723b2e3d 100644
--- a/net/netfilter/ipvs/Makefile
+++ b/net/netfilter/ipvs/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_IP_VS_RR) += ip_vs_rr.o
 obj-$(CONFIG_IP_VS_WRR) += ip_vs_wrr.o
 obj-$(CONFIG_IP_VS_LC) += ip_vs_lc.o
 obj-$(CONFIG_IP_VS_WLC) += ip_vs_wlc.o
+obj-$(CONFIG_IP_VS_FO) += ip_vs_fo.o
 obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o
 obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o
 obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o
diff --git a/net/netfilter/ipvs/ip_vs_fo.c b/net/netfilter/ipvs/ip_vs_fo.c
new file mode 100644
index 000000000000..6a2647d471ff
--- /dev/null
+++ b/net/netfilter/ipvs/ip_vs_fo.c
@@ -0,0 +1,79 @@
+/*
+ * IPVS:        Weighted Fail Over module
+ *
+ * Authors:     Kenny Mathis <kmathis@chokepoint.net>
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ *
+ * Changes:
+ *     Kenny Mathis            :     added initial functionality based on weight
+ *
+ */
+
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <net/ip_vs.h>
+
+/* Weighted Fail Over Module */
+static struct ip_vs_dest *
+ip_vs_fo_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+		  struct ip_vs_iphdr *iph)
+{
+	struct ip_vs_dest *dest, *hweight = NULL;
+	int hw = 0; /* Track highest weight */
+
+	IP_VS_DBG(6, "ip_vs_fo_schedule(): Scheduling...\n");
+
+	/* Basic failover functionality
+	 * Find virtual server with highest weight and send it traffic
+	 */
+	list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
+		if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+		    atomic_read(&dest->weight) > hw) {
+			hweight = dest;
+			hw = atomic_read(&dest->weight);
+		}
+	}
+
+	if (hweight) {
+		IP_VS_DBG_BUF(6, "FO: server %s:%u activeconns %d weight %d\n",
+			      IP_VS_DBG_ADDR(svc->af, &hweight->addr),
+			      ntohs(hweight->port),
+			      atomic_read(&hweight->activeconns),
+			      atomic_read(&hweight->weight));
+		return hweight;
+	}
+
+	ip_vs_scheduler_err(svc, "no destination available");
+	return NULL;
+}
+
+static struct ip_vs_scheduler ip_vs_fo_scheduler = {
+	.name =			"fo",
+	.refcnt =		ATOMIC_INIT(0),
+	.module =		THIS_MODULE,
+	.n_list =		LIST_HEAD_INIT(ip_vs_fo_scheduler.n_list),
+	.schedule =		ip_vs_fo_schedule,
+};
+
+static int __init ip_vs_fo_init(void)
+{
+	return register_ip_vs_scheduler(&ip_vs_fo_scheduler);
+}
+
+static void __exit ip_vs_fo_cleanup(void)
+{
+	unregister_ip_vs_scheduler(&ip_vs_fo_scheduler);
+	synchronize_rcu();
+}
+
+module_init(ip_vs_fo_init);
+module_exit(ip_vs_fo_cleanup);
+MODULE_LICENSE("GPL");

From 6cff339bbd5f9eda7a5e8a521f91a88d046e6d0c Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:20 -0700
Subject: [PATCH 02/15] ipvs: Add destination address family to netlink
 interface

This is necessary to support heterogeneous pools.  For example, if you have
an ipv6 addressed network, you'll want to be able to forward ipv4 traffic
into it.

This patch enforces that destination address family is the same as service
family, as none of the forwarding mechanisms support anything else.

For the old setsockopt mechanism, we simply set the dest address family to
AF_INET as we do with the service.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  3 +++
 include/uapi/linux/ip_vs.h     |  3 +++
 net/netfilter/ipvs/ip_vs_ctl.c | 45 ++++++++++++++++++++++++++++------
 3 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 624a8a54806d..b7e2b624d58e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -648,6 +648,9 @@ struct ip_vs_dest_user_kern {
 	/* thresholds for active connections */
 	u32			u_threshold;	/* upper threshold */
 	u32			l_threshold;	/* lower threshold */
+
+	/* Address family of addr */
+	u16			af;
 };
 
 
diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index fbcffe8041f7..cabe95d5b461 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -384,6 +384,9 @@ enum {
 	IPVS_DEST_ATTR_PERSIST_CONNS,	/* persistent connections */
 
 	IPVS_DEST_ATTR_STATS,		/* nested attribute for dest stats */
+
+	IPVS_DEST_ATTR_ADDR_FAMILY,	/* Address family of address */
+
 	__IPVS_DEST_ATTR_MAX,
 };
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index bd2b208ba56c..594cec7ebc43 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -816,6 +816,8 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	dest->u_threshold = udest->u_threshold;
 	dest->l_threshold = udest->l_threshold;
 
+	dest->af = udest->af;
+
 	spin_lock_bh(&dest->dst_lock);
 	__ip_vs_dst_cache_reset(dest);
 	spin_unlock_bh(&dest->dst_lock);
@@ -846,8 +848,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 
 	EnterFunction(2);
 
+	/* Temporary for consistency */
+	if (udest->af != svc->af)
+		return -EINVAL;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (svc->af == AF_INET6) {
+	if (udest->af == AF_INET6) {
 		atype = ipv6_addr_type(&udest->addr.in6);
 		if ((!(atype & IPV6_ADDR_UNICAST) ||
 			atype & IPV6_ADDR_LINKLOCAL) &&
@@ -875,12 +881,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 		u64_stats_init(&ip_vs_dest_stats->syncp);
 	}
 
-	dest->af = svc->af;
+	dest->af = udest->af;
 	dest->protocol = svc->protocol;
 	dest->vaddr = svc->addr;
 	dest->vport = svc->port;
 	dest->vfwmark = svc->fwmark;
-	ip_vs_addr_copy(svc->af, &dest->addr, &udest->addr);
+	ip_vs_addr_copy(udest->af, &dest->addr, &udest->addr);
 	dest->port = udest->port;
 
 	atomic_set(&dest->activeconns, 0);
@@ -928,7 +934,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		return -ERANGE;
 	}
 
-	ip_vs_addr_copy(svc->af, &daddr, &udest->addr);
+	ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
@@ -949,7 +955,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	if (dest != NULL) {
 		IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
 			      "dest->refcnt=%d, service %u/%s:%u\n",
-			      IP_VS_DBG_ADDR(svc->af, &daddr), ntohs(dport),
+			      IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
 			      atomic_read(&dest->refcnt),
 			      dest->vfwmark,
 			      IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
@@ -992,7 +998,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		return -ERANGE;
 	}
 
-	ip_vs_addr_copy(svc->af, &daddr, &udest->addr);
+	ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
@@ -2244,6 +2250,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
 	udest->weight		= udest_compat->weight;
 	udest->u_threshold	= udest_compat->u_threshold;
 	udest->l_threshold	= udest_compat->l_threshold;
+	udest->af		= AF_INET;
 }
 
 static int
@@ -2480,6 +2487,12 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 			if (count >= get->num_dests)
 				break;
 
+			/* Cannot expose heterogeneous members via sockopt
+			 * interface
+			 */
+			if (dest->af != svc->af)
+				continue;
+
 			entry.addr = dest->addr.ip;
 			entry.port = dest->port;
 			entry.conn_flags = atomic_read(&dest->conn_flags);
@@ -2777,6 +2790,7 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 	[IPVS_DEST_ATTR_INACT_CONNS]	= { .type = NLA_U32 },
 	[IPVS_DEST_ATTR_PERSIST_CONNS]	= { .type = NLA_U32 },
 	[IPVS_DEST_ATTR_STATS]		= { .type = NLA_NESTED },
+	[IPVS_DEST_ATTR_ADDR_FAMILY]	= { .type = NLA_U16 },
 };
 
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
@@ -3032,7 +3046,8 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
 	    nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS,
 			atomic_read(&dest->inactconns)) ||
 	    nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS,
-			atomic_read(&dest->persistconns)))
+			atomic_read(&dest->persistconns)) ||
+	    nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af))
 		goto nla_put_failure;
 	if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &dest->stats))
 		goto nla_put_failure;
@@ -3113,6 +3128,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 {
 	struct nlattr *attrs[IPVS_DEST_ATTR_MAX + 1];
 	struct nlattr *nla_addr, *nla_port;
+	struct nlattr *nla_addr_family;
 
 	/* Parse mandatory identifying destination fields first */
 	if (nla == NULL ||
@@ -3121,6 +3137,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 
 	nla_addr	= attrs[IPVS_DEST_ATTR_ADDR];
 	nla_port	= attrs[IPVS_DEST_ATTR_PORT];
+	nla_addr_family	= attrs[IPVS_DEST_ATTR_ADDR_FAMILY];
 
 	if (!(nla_addr && nla_port))
 		return -EINVAL;
@@ -3130,6 +3147,11 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 	nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr));
 	udest->port = nla_get_be16(nla_port);
 
+	if (nla_addr_family)
+		udest->af = nla_get_u16(nla_addr_family);
+	else
+		udest->af = 0;
+
 	/* If a full entry was requested, check for the additional fields */
 	if (full_entry) {
 		struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh,
@@ -3357,6 +3379,15 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 					    need_full_dest);
 		if (ret)
 			goto out;
+
+		/* Old protocols did not allow the user to specify address
+		 * family, so we set it to zero instead.  We also didn't
+		 * allow heterogeneous pools in the old code, so it's safe
+		 * to assume that this will have the same address family as
+		 * the service.
+		 */
+		if (udest.af == 0)
+			udest.af = svc->af;
 	}
 
 	switch (cmd) {

From 655eef103d0bd99f540a52f7ede032e120756846 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:21 -0700
Subject: [PATCH 03/15] ipvs: Supply destination addr family to
 ip_vs_{lookup_dest,find_dest}

We need to remove the assumption that virtual address family is the same as
real address family in order to support heterogeneous services (that is,
services with v4 vips and v6 backends or the opposite).

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  5 +++--
 net/netfilter/ipvs/ip_vs_conn.c |  8 +++++++-
 net/netfilter/ipvs/ip_vs_ctl.c  | 24 ++++++++++++------------
 net/netfilter/ipvs/ip_vs_sync.c | 10 ++++++++--
 4 files changed, 30 insertions(+), 17 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b7e2b624d58e..2fa1155b24f7 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1399,8 +1399,9 @@ void ip_vs_unregister_nl_ioctl(void);
 int ip_vs_control_init(void);
 void ip_vs_control_cleanup(void);
 struct ip_vs_dest *
-ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
-		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
+ip_vs_find_dest(struct net *net, int svc_af, int dest_af,
+		const union nf_inet_addr *daddr, __be16 dport,
+		const union nf_inet_addr *vaddr, __be16 vport,
 		__u16 protocol, __u32 fwmark, __u32 flags);
 void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 610e19c0e13f..8f4c602bb34b 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -616,7 +616,13 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	rcu_read_lock();
-	dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
+
+	/* This function is only invoked by the synchronization code. We do
+	 * not currently support heterogeneous pools with synchronization,
+	 * so we can make the assumption that the svc_af is the same as the
+	 * dest_af
+	 */
+	dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, cp->af, &cp->daddr,
 			       cp->dport, &cp->vaddr, cp->vport,
 			       cp->protocol, cp->fwmark, cp->flags);
 	if (dest) {
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 594cec7ebc43..c840d895bd1a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -574,8 +574,8 @@ bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
  * Called under RCU lock.
  */
 static struct ip_vs_dest *
-ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
-		  __be16 dport)
+ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af,
+		  const union nf_inet_addr *daddr, __be16 dport)
 {
 	struct ip_vs_dest *dest;
 
@@ -583,9 +583,9 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 	 * Find the destination for the given service
 	 */
 	list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
-		if ((dest->af == svc->af)
-		    && ip_vs_addr_equal(svc->af, &dest->addr, daddr)
-		    && (dest->port == dport)) {
+		if ((dest->af == dest_af) &&
+		    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
+		    (dest->port == dport)) {
 			/* HIT */
 			return dest;
 		}
@@ -602,7 +602,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
  * on the backup.
  * Called under RCU lock, no refcnt is returned.
  */
-struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
+struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int svc_af, int dest_af,
 				   const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
@@ -613,14 +613,14 @@ struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
 	struct ip_vs_service *svc;
 	__be16 port = dport;
 
-	svc = ip_vs_service_find(net, af, fwmark, protocol, vaddr, vport);
+	svc = ip_vs_service_find(net, svc_af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
 	if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
 		port = 0;
-	dest = ip_vs_lookup_dest(svc, daddr, port);
+	dest = ip_vs_lookup_dest(svc, dest_af, daddr, port);
 	if (!dest)
-		dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
+		dest = ip_vs_lookup_dest(svc, dest_af, daddr, port ^ dport);
 	return dest;
 }
 
@@ -938,7 +938,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
-	dest = ip_vs_lookup_dest(svc, &daddr, dport);
+	dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
 	rcu_read_unlock();
 
 	if (dest != NULL) {
@@ -1002,7 +1002,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
-	dest = ip_vs_lookup_dest(svc, &daddr, dport);
+	dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
 	rcu_read_unlock();
 
 	if (dest == NULL) {
@@ -1084,7 +1084,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
-	dest = ip_vs_lookup_dest(svc, &udest->addr, dport);
+	dest = ip_vs_lookup_dest(svc, udest->af, &udest->addr, dport);
 	rcu_read_unlock();
 
 	if (dest == NULL) {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index eadffb29dec0..edd266414b7d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -880,8 +880,14 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 		 * but still handled.
 		 */
 		rcu_read_lock();
-		dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
-				       param->vport, protocol, fwmark, flags);
+		/* This function is only invoked by the synchronization
+		 * code. We do not currently support heterogeneous pools
+		 * with synchronization, so we can make the assumption that
+		 * the svc_af is the same as the dest_af
+		 */
+		dest = ip_vs_find_dest(net, type, type, daddr, dport,
+				       param->vaddr, param->vport, protocol,
+				       fwmark, flags);
 
 		cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
 		rcu_read_unlock();

From ad147aa4dd2135e6d86e3329d4009283ba64287f Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:22 -0700
Subject: [PATCH 04/15] ipvs: Pass destination address family to
 ip_vs_trash_get_dest

Part of a series of diffs to tease out destination family from virtual
family.  This diff just adds a parameter to ip_vs_trash_get and then uses
it for comparison rather than svc->af.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c840d895bd1a..6bd2cc682137 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -657,8 +657,8 @@ static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest)
  *  scheduling.
  */
 static struct ip_vs_dest *
-ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
-		     __be16 dport)
+ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
+		     const union nf_inet_addr *daddr, __be16 dport)
 {
 	struct ip_vs_dest *dest;
 	struct netns_ipvs *ipvs = net_ipvs(svc->net);
@@ -671,11 +671,11 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 		IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
 			      "dest->refcnt=%d\n",
 			      dest->vfwmark,
-			      IP_VS_DBG_ADDR(svc->af, &dest->addr),
+			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
 			      atomic_read(&dest->refcnt));
-		if (dest->af == svc->af &&
-		    ip_vs_addr_equal(svc->af, &dest->addr, daddr) &&
+		if (dest->af == dest_af &&
+		    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
 		    dest->port == dport &&
 		    dest->vfwmark == svc->fwmark &&
 		    dest->protocol == svc->protocol &&
@@ -950,7 +950,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	 * Check if the dest already exists in the trash and
 	 * is from the same service
 	 */
-	dest = ip_vs_trash_get_dest(svc, &daddr, dport);
+	dest = ip_vs_trash_get_dest(svc, udest->af, &daddr, dport);
 
 	if (dest != NULL) {
 		IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "

From ba38528aae6ee2d22226c6a78727ddc13512b068 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:23 -0700
Subject: [PATCH 05/15] ipvs: Supply destination address family to
 ip_vs_conn_new

The assumption that dest af is equal to service af is now unreliable, so we
must specify it manually so as not to copy just the first 4 bytes of a v6
address or doing an illegal read of 16 butes on a v6 address.

We "lie" in two places: for synchronization (which we will explicitly
disallow from happening when we have heterogeneous pools) and for black
hole addresses where there's no real dest.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 3 ++-
 net/netfilter/ipvs/ip_vs_conn.c | 5 +++--
 net/netfilter/ipvs/ip_vs_core.c | 9 +++++----
 net/netfilter/ipvs/ip_vs_ftp.c  | 6 ++++--
 net/netfilter/ipvs/ip_vs_sync.c | 3 ++-
 5 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 2fa1155b24f7..7600dbe5780e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -535,6 +535,7 @@ struct ip_vs_conn {
 	union nf_inet_addr      daddr;          /* destination address */
 	volatile __u32          flags;          /* status flags */
 	__u16                   protocol;       /* Which protocol (TCP/UDP) */
+	__u16			daf;		/* Address family of the dest */
 #ifdef CONFIG_NET_NS
 	struct net              *net;           /* Name space */
 #endif
@@ -1213,7 +1214,7 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 void ip_vs_conn_put(struct ip_vs_conn *cp);
 void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
 
-struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
+struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 				  const union nf_inet_addr *daddr,
 				  __be16 dport, unsigned int flags,
 				  struct ip_vs_dest *dest, __u32 fwmark);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 8f4c602bb34b..fdb4880a3a79 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -854,7 +854,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
  *	Create a new connection entry and hash it into the ip_vs_conn_tab
  */
 struct ip_vs_conn *
-ip_vs_conn_new(const struct ip_vs_conn_param *p,
+ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 	       const union nf_inet_addr *daddr, __be16 dport, unsigned int flags,
 	       struct ip_vs_dest *dest, __u32 fwmark)
 {
@@ -873,6 +873,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
 	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
+	cp->daf		   = dest_af;
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
 	cp->cport	   = p->cport;
@@ -880,7 +881,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
 		       &cp->vaddr, p->vaddr);
 	cp->vport	   = p->vport;
-	ip_vs_addr_set(p->af, &cp->daddr, daddr);
+	ip_vs_addr_set(cp->daf, &cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
 	cp->fwmark         = fwmark;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5c34e8d42e01..1f6ecb74821f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -328,7 +328,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * This adds param.pe_data to the template,
 		 * and thus param.pe_data will be destroyed
 		 * when the template expires */
-		ct = ip_vs_conn_new(&param, &dest->addr, dport,
+		ct = ip_vs_conn_new(&param, dest->af, &dest->addr, dport,
 				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
 		if (ct == NULL) {
 			kfree(param.pe_data);
@@ -357,7 +357,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr,
 			      src_port, &iph->daddr, dst_port, &param);
 
-	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
+	cp = ip_vs_conn_new(&param, dest->af, &dest->addr, dport, flags, dest,
+			    skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
 		*ignored = -1;
@@ -479,7 +480,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
 				      &iph->saddr, pptr[0], &iph->daddr,
 				      pptr[1], &p);
-		cp = ip_vs_conn_new(&p, &dest->addr,
+		cp = ip_vs_conn_new(&p, dest->af, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
 		if (!cp) {
@@ -550,7 +551,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 			ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
 					      &iph->saddr, pptr[0],
 					      &iph->daddr, pptr[1], &p);
-			cp = ip_vs_conn_new(&p, &daddr, 0,
+			cp = ip_vs_conn_new(&p, svc->af, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
 					    NULL, skb->mark);
 			if (!cp)
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 77c173282f38..a64fa15790e5 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -233,7 +233,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			ip_vs_conn_fill_param(ip_vs_conn_net(cp),
 					      AF_INET, IPPROTO_TCP, &cp->caddr,
 					      0, &cp->vaddr, port, &p);
-			n_cp = ip_vs_conn_new(&p, &from, port,
+			/* As above, this is ipv4 only */
+			n_cp = ip_vs_conn_new(&p, AF_INET, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
 					      IP_VS_CONN_F_NFCT,
 					      cp->dest, skb->mark);
@@ -396,7 +397,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 				      htons(ntohs(cp->vport)-1), &p);
 		n_cp = ip_vs_conn_in_get(&p);
 		if (!n_cp) {
-			n_cp = ip_vs_conn_new(&p, &cp->daddr,
+			/* This is ipv4 only */
+			n_cp = ip_vs_conn_new(&p, AF_INET, &cp->daddr,
 					      htons(ntohs(cp->dport)-1),
 					      IP_VS_CONN_F_NFCT, cp->dest,
 					      skb->mark);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index edd266414b7d..7162c86fd50d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -889,7 +889,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 				       param->vaddr, param->vport, protocol,
 				       fwmark, flags);
 
-		cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
+		cp = ip_vs_conn_new(param, type, daddr, dport, flags, dest,
+				    fwmark);
 		rcu_read_unlock();
 		if (!cp) {
 			kfree(param->pe_data);

From 391f503d69779867f05e9296ae523e9002c2d7ee Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:24 -0700
Subject: [PATCH 06/15] ipvs: prevent mixing heterogeneous pools and
 synchronization

The synchronization protocol is not compatible with heterogeneous pools, so
we need to verify that we're not turning both on at the same time.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  4 ++++
 net/netfilter/ipvs/ip_vs_ctl.c | 15 +++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7600dbe5780e..576d7f0bed5d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -990,6 +990,10 @@ struct netns_ipvs {
 	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 	/* net name space ptr */
 	struct net		*net;            /* Needed by timer routines */
+	/* Number of heterogeneous destinations, needed because
+	 * heterogeneous are not supported when synchronization is
+	 * enabled */
+	unsigned int		mixed_address_family_dests;
 };
 
 #define DEFAULT_SYNC_THRESHOLD	3
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 6bd2cc682137..462760eded94 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -779,6 +779,12 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	struct ip_vs_scheduler *sched;
 	int conn_flags;
 
+	/* We cannot modify an address and change the address family */
+	BUG_ON(!add && udest->af != dest->af);
+
+	if (add && udest->af != svc->af)
+		ipvs->mixed_address_family_dests++;
+
 	/* set the weight and the flags */
 	atomic_set(&dest->weight, udest->weight);
 	conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
@@ -1061,6 +1067,9 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
 	list_del_rcu(&dest->n_list);
 	svc->num_dests--;
 
+	if (dest->af != svc->af)
+		net_ipvs(svc->net)->mixed_address_family_dests--;
+
 	if (svcupd) {
 		struct ip_vs_scheduler *sched;
 
@@ -3256,6 +3265,12 @@ static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs)
 	      attrs[IPVS_DAEMON_ATTR_SYNC_ID]))
 		return -EINVAL;
 
+	/* The synchronization protocol is incompatible with mixed family
+	 * services
+	 */
+	if (net_ipvs(net)->mixed_address_family_dests > 0)
+		return -EINVAL;
+
 	return start_sync_thread(net,
 				 nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]),
 				 nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]),

From 4a4739d56b006c4b34dfba03c356056e110521ca Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:25 -0700
Subject: [PATCH 07/15] ipvs: Pull out crosses_local_route_boundary logic

This logic is repeated in both out_rt functions so it was redundant.
Additionally, we'll need to be able to do checks to route v4 to v6 and vice
versa in order to deal with heterogeneous pools.

This patch also updates the callsites to add an additional parameter to the
out route functions.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_xmit.c | 144 +++++++++++++++++---------------
 1 file changed, 77 insertions(+), 67 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 56896a412bce..b3b54d7a6c17 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -157,9 +157,56 @@ retry:
 	return rt;
 }
 
+#ifdef CONFIG_IP_VS_IPV6
+static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
+{
+	return rt->dst.dev && rt->dst.dev->flags & IFF_LOOPBACK;
+}
+#endif
+
+static inline bool crosses_local_route_boundary(int skb_af, struct sk_buff *skb,
+						int rt_mode,
+						bool new_rt_is_local)
+{
+	bool rt_mode_allow_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
+	bool rt_mode_allow_non_local = !!(rt_mode & IP_VS_RT_MODE_LOCAL);
+	bool rt_mode_allow_redirect = !!(rt_mode & IP_VS_RT_MODE_RDR);
+	bool source_is_loopback;
+	bool old_rt_is_local;
+
+#ifdef CONFIG_IP_VS_IPV6
+	if (skb_af == AF_INET6) {
+		int addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr);
+
+		source_is_loopback =
+			(!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
+			(addr_type & IPV6_ADDR_LOOPBACK);
+		old_rt_is_local = __ip_vs_is_local_route6(
+			(struct rt6_info *)skb_dst(skb));
+	} else
+#endif
+	{
+		source_is_loopback = ipv4_is_loopback(ip_hdr(skb)->saddr);
+		old_rt_is_local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
+	}
+
+	if (unlikely(new_rt_is_local)) {
+		if (!rt_mode_allow_local)
+			return true;
+		if (!rt_mode_allow_redirect && !old_rt_is_local)
+			return true;
+	} else {
+		if (!rt_mode_allow_non_local)
+			return true;
+		if (source_is_loopback)
+			return true;
+	}
+	return false;
+}
+
 /* Get route to destination or remote server */
 static int
-__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
+__ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 		   __be32 daddr, int rt_mode, __be32 *ret_saddr)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
@@ -218,30 +265,15 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 	}
 
 	local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
-	if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
-	      rt_mode)) {
-		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
-			     (rt->rt_flags & RTCF_LOCAL) ?
-			     "local":"non-local", &daddr);
+	if (unlikely(crosses_local_route_boundary(skb_af, skb, rt_mode,
+						  local))) {
+		IP_VS_DBG_RL("We are crossing local and non-local addresses"
+			     " daddr=%pI4\n", &dest->addr.ip);
 		goto err_put;
 	}
 	iph = ip_hdr(skb);
-	if (likely(!local)) {
-		if (unlikely(ipv4_is_loopback(iph->saddr))) {
-			IP_VS_DBG_RL("Stopping traffic from loopback address "
-				     "%pI4 to non-local address, dest: %pI4\n",
-				     &iph->saddr, &daddr);
-			goto err_put;
-		}
-	} else {
-		ort = skb_rtable(skb);
-		if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
-		    !(ort->rt_flags & RTCF_LOCAL)) {
-			IP_VS_DBG_RL("Redirect from non-local address %pI4 to "
-				     "local requires NAT method, dest: %pI4\n",
-				     &iph->daddr, &daddr);
-			goto err_put;
-		}
+
+	if (unlikely(local)) {
 		/* skb to local stack, preserve old route */
 		if (!noref)
 			ip_rt_put(rt);
@@ -295,12 +327,6 @@ err_unreach:
 }
 
 #ifdef CONFIG_IP_VS_IPV6
-
-static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
-{
-	return rt->dst.dev && rt->dst.dev->flags & IFF_LOOPBACK;
-}
-
 static struct dst_entry *
 __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
 			struct in6_addr *ret_saddr, int do_xfrm)
@@ -339,7 +365,7 @@ out_err:
  * Get route to destination or remote server
  */
 static int
-__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
+__ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 		      struct in6_addr *daddr, struct in6_addr *ret_saddr,
 		      struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
 {
@@ -393,32 +419,15 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	}
 
 	local = __ip_vs_is_local_route6(rt);
-	if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
-	      rt_mode)) {
-		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n",
-			     local ? "local":"non-local", daddr);
+
+	if (unlikely(crosses_local_route_boundary(skb_af, skb, rt_mode,
+						  local))) {
+		IP_VS_DBG_RL("We are crossing local and non-local addresses"
+			     " daddr=%pI6\n", &dest->addr.in6);
 		goto err_put;
 	}
-	if (likely(!local)) {
-		if (unlikely((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-			     ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
-					    IPV6_ADDR_LOOPBACK)) {
-			IP_VS_DBG_RL("Stopping traffic from loopback address "
-				     "%pI6c to non-local address, "
-				     "dest: %pI6c\n",
-				     &ipv6_hdr(skb)->saddr, daddr);
-			goto err_put;
-		}
-	} else {
-		ort = (struct rt6_info *) skb_dst(skb);
-		if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
-		    !__ip_vs_is_local_route6(ort)) {
-			IP_VS_DBG_RL("Redirect from non-local address %pI6c "
-				     "to local requires NAT method, "
-				     "dest: %pI6c\n",
-				     &ipv6_hdr(skb)->daddr, daddr);
-			goto err_put;
-		}
+
+	if (unlikely(local)) {
 		/* skb to local stack, preserve old route */
 		if (!noref)
 			dst_release(&rt->dst);
@@ -556,8 +565,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	rcu_read_lock();
-	if (__ip_vs_get_out_rt(skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL,
-			       NULL) < 0)
+	if (__ip_vs_get_out_rt(cp->af, skb, NULL, iph->daddr,
+			       IP_VS_RT_MODE_NON_LOCAL, NULL) < 0)
 		goto tx_error;
 
 	ip_send_check(iph);
@@ -586,7 +595,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	rcu_read_lock();
-	if (__ip_vs_get_out_rt_v6(skb, NULL, &ipvsh->daddr.in6, NULL,
+	if (__ip_vs_get_out_rt_v6(cp->af, skb, NULL, &ipvsh->daddr.in6, NULL,
 				  ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0)
 		goto tx_error;
 
@@ -633,7 +642,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	was_input = rt_is_input_route(skb_rtable(skb));
-	local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
 				   IP_VS_RT_MODE_LOCAL |
 				   IP_VS_RT_MODE_NON_LOCAL |
 				   IP_VS_RT_MODE_RDR, NULL);
@@ -721,8 +730,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
 	}
 
-	local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
-				      ipvsh, 0,
+	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
+				      NULL, ipvsh, 0,
 				      IP_VS_RT_MODE_LOCAL |
 				      IP_VS_RT_MODE_NON_LOCAL |
 				      IP_VS_RT_MODE_RDR);
@@ -829,7 +838,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	rcu_read_lock();
-	local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
 				   IP_VS_RT_MODE_LOCAL |
 				   IP_VS_RT_MODE_NON_LOCAL |
 				   IP_VS_RT_MODE_CONNECT |
@@ -928,7 +937,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	rcu_read_lock();
-	local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
+	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
 				      &saddr, ipvsh, 1,
 				      IP_VS_RT_MODE_LOCAL |
 				      IP_VS_RT_MODE_NON_LOCAL |
@@ -1021,7 +1030,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	rcu_read_lock();
-	local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
 				   IP_VS_RT_MODE_LOCAL |
 				   IP_VS_RT_MODE_NON_LOCAL |
 				   IP_VS_RT_MODE_KNOWN_NH, NULL);
@@ -1060,8 +1069,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	rcu_read_lock();
-	local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
-				      ipvsh, 0,
+	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
+				      NULL, ipvsh, 0,
 				      IP_VS_RT_MODE_LOCAL |
 				      IP_VS_RT_MODE_NON_LOCAL);
 	if (local < 0)
@@ -1128,7 +1137,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
 		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
 	rcu_read_lock();
-	local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, rt_mode, NULL);
+	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
+				   NULL);
 	if (local < 0)
 		goto tx_error;
 	rt = skb_rtable(skb);
@@ -1219,8 +1229,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
 		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
 	rcu_read_lock();
-	local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
-				      ipvsh, 0, rt_mode);
+	local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
+				      NULL, ipvsh, 0, rt_mode);
 	if (local < 0)
 		goto tx_error;
 	rt = (struct rt6_info *) skb_dst(skb);

From 919aa0b2bbcf013467295dc9736db6fb575a4fb0 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:26 -0700
Subject: [PATCH 08/15] ipvs: Pull out update_pmtu code

Another step toward heterogeneous pools, this removes another piece of
functionality currently specific to each address family type.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_xmit.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b3b54d7a6c17..034a282a6f8c 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -204,6 +204,15 @@ static inline bool crosses_local_route_boundary(int skb_af, struct sk_buff *skb,
 	return false;
 }
 
+static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
+{
+	struct sock *sk = skb->sk;
+	struct rtable *ort = skb_rtable(skb);
+
+	if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
+		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+}
+
 /* Get route to destination or remote server */
 static int
 __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
@@ -213,7 +222,6 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_dest_dst *dest_dst;
 	struct rtable *rt;			/* Route to the other host */
-	struct rtable *ort;			/* Original route */
 	struct iphdr *iph;
 	__be16 df;
 	int mtu;
@@ -284,16 +292,12 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 		mtu = dst_mtu(&rt->dst);
 		df = iph->frag_off & htons(IP_DF);
 	} else {
-		struct sock *sk = skb->sk;
-
 		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
 		if (mtu < 68) {
 			IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
 			goto err_put;
 		}
-		ort = skb_rtable(skb);
-		if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
-			ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+		maybe_update_pmtu(skb_af, skb, mtu);
 		/* MTU check allowed? */
 		df = sysctl_pmtu_disc(ipvs) ? iph->frag_off & htons(IP_DF) : 0;
 	}
@@ -372,7 +376,6 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	struct ip_vs_dest_dst *dest_dst;
 	struct rt6_info *rt;			/* Route to the other host */
-	struct rt6_info *ort;			/* Original route */
 	struct dst_entry *dst;
 	int mtu;
 	int local, noref = 1;
@@ -438,17 +441,13 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL)))
 		mtu = dst_mtu(&rt->dst);
 	else {
-		struct sock *sk = skb->sk;
-
 		mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
 		if (mtu < IPV6_MIN_MTU) {
 			IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
 				     IPV6_MIN_MTU);
 			goto err_put;
 		}
-		ort = (struct rt6_info *) skb_dst(skb);
-		if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
-			ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+		maybe_update_pmtu(skb_af, skb, mtu);
 	}
 
 	if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {

From c63e4de2be5e1d253adce16dbba57ed42868bc22 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:27 -0700
Subject: [PATCH 09/15] ipvs: Add generic ensure_mtu_is_adequate to handle
 mixed pools

The out_rt functions check to see if the mtu is large enough for the packet
and, if not, send icmp messages (TOOBIG or DEST_UNREACH) to the source and
bail out.  We needed the ability to send ICMP from the out_rt_v6 function
and DEST_UNREACH from the out_rt function, so we just pulled it out into a
common function.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_xmit.c | 77 ++++++++++++++++++++++-----------
 1 file changed, 51 insertions(+), 26 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 034a282a6f8c..fa2fdd7421b7 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -213,17 +213,57 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
 		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
 }
 
+static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
+					  struct ip_vs_iphdr *ipvsh,
+					  struct sk_buff *skb, int mtu)
+{
+#ifdef CONFIG_IP_VS_IPV6
+	if (skb_af == AF_INET6) {
+		struct net *net = dev_net(skb_dst(skb)->dev);
+
+		if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
+			if (!skb->dev)
+				skb->dev = net->loopback_dev;
+			/* only send ICMP too big on first fragment */
+			if (!ipvsh->fragoffs)
+				icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			IP_VS_DBG(1, "frag needed for %pI6c\n",
+				  &ipv6_hdr(skb)->saddr);
+			return false;
+		}
+	} else
+#endif
+	{
+		struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
+		/* If we're going to tunnel the packet and pmtu discovery
+		 * is disabled, we'll just fragment it anyway
+		 */
+		if ((rt_mode & IP_VS_RT_MODE_TUNNEL) && !sysctl_pmtu_disc(ipvs))
+			return true;
+
+		if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) &&
+			     skb->len > mtu && !skb_is_gso(skb))) {
+			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				  htonl(mtu));
+			IP_VS_DBG(1, "frag needed for %pI4\n",
+				  &ip_hdr(skb)->saddr);
+			return false;
+		}
+	}
+
+	return true;
+}
+
 /* Get route to destination or remote server */
 static int
 __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
-		   __be32 daddr, int rt_mode, __be32 *ret_saddr)
+		   __be32 daddr, int rt_mode, __be32 *ret_saddr,
+		   struct ip_vs_iphdr *ipvsh)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
-	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_dest_dst *dest_dst;
 	struct rtable *rt;			/* Route to the other host */
-	struct iphdr *iph;
-	__be16 df;
 	int mtu;
 	int local, noref = 1;
 
@@ -279,7 +319,6 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 			     " daddr=%pI4\n", &dest->addr.ip);
 		goto err_put;
 	}
-	iph = ip_hdr(skb);
 
 	if (unlikely(local)) {
 		/* skb to local stack, preserve old route */
@@ -290,7 +329,6 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 
 	if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL))) {
 		mtu = dst_mtu(&rt->dst);
-		df = iph->frag_off & htons(IP_DF);
 	} else {
 		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
 		if (mtu < 68) {
@@ -298,16 +336,10 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 			goto err_put;
 		}
 		maybe_update_pmtu(skb_af, skb, mtu);
-		/* MTU check allowed? */
-		df = sysctl_pmtu_disc(ipvs) ? iph->frag_off & htons(IP_DF) : 0;
 	}
 
-	/* MTU checking */
-	if (unlikely(df && skb->len > mtu && !skb_is_gso(skb))) {
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
-		IP_VS_DBG(1, "frag needed for %pI4\n", &iph->saddr);
+	if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
 		goto err_put;
-	}
 
 	skb_dst_drop(skb);
 	if (noref) {
@@ -450,15 +482,8 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 		maybe_update_pmtu(skb_af, skb, mtu);
 	}
 
-	if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
-		if (!skb->dev)
-			skb->dev = net->loopback_dev;
-		/* only send ICMP too big on first fragment */
-		if (!ipvsh->fragoffs)
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-		IP_VS_DBG(1, "frag needed for %pI6c\n", &ipv6_hdr(skb)->saddr);
+	if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
 		goto err_put;
-	}
 
 	skb_dst_drop(skb);
 	if (noref) {
@@ -565,7 +590,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	rcu_read_lock();
 	if (__ip_vs_get_out_rt(cp->af, skb, NULL, iph->daddr,
-			       IP_VS_RT_MODE_NON_LOCAL, NULL) < 0)
+			       IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0)
 		goto tx_error;
 
 	ip_send_check(iph);
@@ -644,7 +669,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
 				   IP_VS_RT_MODE_LOCAL |
 				   IP_VS_RT_MODE_NON_LOCAL |
-				   IP_VS_RT_MODE_RDR, NULL);
+				   IP_VS_RT_MODE_RDR, NULL, ipvsh);
 	if (local < 0)
 		goto tx_error;
 	rt = skb_rtable(skb);
@@ -841,7 +866,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 				   IP_VS_RT_MODE_LOCAL |
 				   IP_VS_RT_MODE_NON_LOCAL |
 				   IP_VS_RT_MODE_CONNECT |
-				   IP_VS_RT_MODE_TUNNEL, &saddr);
+				   IP_VS_RT_MODE_TUNNEL, &saddr, ipvsh);
 	if (local < 0)
 		goto tx_error;
 	if (local) {
@@ -1032,7 +1057,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
 				   IP_VS_RT_MODE_LOCAL |
 				   IP_VS_RT_MODE_NON_LOCAL |
-				   IP_VS_RT_MODE_KNOWN_NH, NULL);
+				   IP_VS_RT_MODE_KNOWN_NH, NULL, ipvsh);
 	if (local < 0)
 		goto tx_error;
 	if (local) {
@@ -1137,7 +1162,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
 	rcu_read_lock();
 	local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
-				   NULL);
+				   NULL, iph);
 	if (local < 0)
 		goto tx_error;
 	rt = skb_rtable(skb);

From 8052ba292559f907ea2ad4c827d83c195046dfe1 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:28 -0700
Subject: [PATCH 10/15] ipvs: support ipv4 in ipv6 and ipv6 in ipv4 tunnel
 forwarding

Pull the common logic for preparing an skb to prepend the header into a
single function and then set fields such that they can be used in either
case (generalize tos and tclass to dscp, hop_limit and ttl to ttl, etc)

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_conn.c |  12 ++-
 net/netfilter/ipvs/ip_vs_xmit.c | 148 +++++++++++++++++++++++---------
 2 files changed, 117 insertions(+), 43 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index fdb4880a3a79..13e9cee02c81 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -488,7 +488,12 @@ static inline void ip_vs_bind_xmit(struct ip_vs_conn *cp)
 		break;
 
 	case IP_VS_CONN_F_TUNNEL:
-		cp->packet_xmit = ip_vs_tunnel_xmit;
+#ifdef CONFIG_IP_VS_IPV6
+		if (cp->daf == AF_INET6)
+			cp->packet_xmit = ip_vs_tunnel_xmit_v6;
+		else
+#endif
+			cp->packet_xmit = ip_vs_tunnel_xmit;
 		break;
 
 	case IP_VS_CONN_F_DROUTE:
@@ -514,7 +519,10 @@ static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp)
 		break;
 
 	case IP_VS_CONN_F_TUNNEL:
-		cp->packet_xmit = ip_vs_tunnel_xmit_v6;
+		if (cp->daf == AF_INET6)
+			cp->packet_xmit = ip_vs_tunnel_xmit_v6;
+		else
+			cp->packet_xmit = ip_vs_tunnel_xmit;
 		break;
 
 	case IP_VS_CONN_F_DROUTE:
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index fa2fdd7421b7..91f17c1eb8a2 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -824,6 +824,81 @@ tx_error:
 }
 #endif
 
+/* When forwarding a packet, we must ensure that we've got enough headroom
+ * for the encapsulation packet in the skb.  This also gives us an
+ * opportunity to figure out what the payload_len, dsfield, ttl, and df
+ * values should be, so that we won't need to look at the old ip header
+ * again
+ */
+static struct sk_buff *
+ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
+			   unsigned int max_headroom, __u8 *next_protocol,
+			   __u32 *payload_len, __u8 *dsfield, __u8 *ttl,
+			   __be16 *df)
+{
+	struct sk_buff *new_skb = NULL;
+	struct iphdr *old_iph = NULL;
+#ifdef CONFIG_IP_VS_IPV6
+	struct ipv6hdr *old_ipv6h = NULL;
+#endif
+
+	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
+		new_skb = skb_realloc_headroom(skb, max_headroom);
+		if (!new_skb)
+			goto error;
+		consume_skb(skb);
+		skb = new_skb;
+	}
+
+#ifdef CONFIG_IP_VS_IPV6
+	if (skb_af == AF_INET6) {
+		old_ipv6h = ipv6_hdr(skb);
+		*next_protocol = IPPROTO_IPV6;
+		if (payload_len)
+			*payload_len =
+				ntohs(old_ipv6h->payload_len) +
+				sizeof(*old_ipv6h);
+		*dsfield = ipv6_get_dsfield(old_ipv6h);
+		*ttl = old_ipv6h->hop_limit;
+		if (df)
+			*df = 0;
+	} else
+#endif
+	{
+		old_iph = ip_hdr(skb);
+		/* Copy DF, reset fragment offset and MF */
+		if (df)
+			*df = (old_iph->frag_off & htons(IP_DF));
+		*next_protocol = IPPROTO_IPIP;
+
+		/* fix old IP header checksum */
+		ip_send_check(old_iph);
+		*dsfield = ipv4_get_dsfield(old_iph);
+		*ttl = old_iph->ttl;
+		if (payload_len)
+			*payload_len = ntohs(old_iph->tot_len);
+	}
+
+	return skb;
+error:
+	kfree_skb(skb);
+	return ERR_PTR(-ENOMEM);
+}
+
+static inline int __tun_gso_type_mask(int encaps_af, int orig_af)
+{
+	if (encaps_af == AF_INET) {
+		if (orig_af == AF_INET)
+			return SKB_GSO_IPIP;
+
+		return SKB_GSO_SIT;
+	}
+
+	/* GSO: we need to provide proper SKB_GSO_ value for IPv6:
+	 * SKB_GSO_SIT/IPV6
+	 */
+	return 0;
+}
 
 /*
  *   IP Tunneling transmitter
@@ -852,9 +927,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct rtable *rt;			/* Route to the other host */
 	__be32 saddr;				/* Source for tunnel */
 	struct net_device *tdev;		/* Device to other host */
-	struct iphdr  *old_iph = ip_hdr(skb);
-	u8     tos = old_iph->tos;
-	__be16 df;
+	__u8 next_protocol = 0;
+	__u8 dsfield = 0;
+	__u8 ttl = 0;
+	__be16 df = 0;
+	__be16 *dfp = NULL;
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	int ret, local;
@@ -877,29 +954,21 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	rt = skb_rtable(skb);
 	tdev = rt->dst.dev;
 
-	/* Copy DF, reset fragment offset and MF */
-	df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
-
 	/*
 	 * Okay, now see if we can stuff it in the buffer as-is.
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
 
-	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
-		struct sk_buff *new_skb =
-			skb_realloc_headroom(skb, max_headroom);
+	/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
+	dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
+	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
+					 &next_protocol, NULL, &dsfield,
+					 &ttl, dfp);
+	if (IS_ERR(skb))
+		goto tx_error;
 
-		if (!new_skb)
-			goto tx_error;
-		consume_skb(skb);
-		skb = new_skb;
-		old_iph = ip_hdr(skb);
-	}
-
-	/* fix old IP header checksum */
-	ip_send_check(old_iph);
-
-	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	skb = iptunnel_handle_offloads(
+		skb, false, __tun_gso_type_mask(AF_INET, cp->af));
 	if (IS_ERR(skb))
 		goto tx_error;
 
@@ -916,11 +985,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->version		=	4;
 	iph->ihl		=	sizeof(struct iphdr)>>2;
 	iph->frag_off		=	df;
-	iph->protocol		=	IPPROTO_IPIP;
-	iph->tos		=	tos;
+	iph->protocol		=	next_protocol;
+	iph->tos		=	dsfield;
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
-	iph->ttl		=	old_iph->ttl;
+	iph->ttl		=	ttl;
 	ip_select_ident(skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
@@ -953,7 +1022,10 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct rt6_info *rt;		/* Route to the other host */
 	struct in6_addr saddr;		/* Source for tunnel */
 	struct net_device *tdev;	/* Device to other host */
-	struct ipv6hdr  *old_iph = ipv6_hdr(skb);
+	__u8 next_protocol = 0;
+	__u32 payload_len = 0;
+	__u8 dsfield = 0;
+	__u8 ttl = 0;
 	struct ipv6hdr  *iph;		/* Our new IP header */
 	unsigned int max_headroom;	/* The extra header space needed */
 	int ret, local;
@@ -981,19 +1053,14 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
 
-	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
-		struct sk_buff *new_skb =
-			skb_realloc_headroom(skb, max_headroom);
+	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
+					 &next_protocol, &payload_len,
+					 &dsfield, &ttl, NULL);
+	if (IS_ERR(skb))
+		goto tx_error;
 
-		if (!new_skb)
-			goto tx_error;
-		consume_skb(skb);
-		skb = new_skb;
-		old_iph = ipv6_hdr(skb);
-	}
-
-	/* GSO: we need to provide proper SKB_GSO_ value for IPv6 */
-	skb = iptunnel_handle_offloads(skb, false, 0); /* SKB_GSO_SIT/IPV6 */
+	skb = iptunnel_handle_offloads(
+		skb, false, __tun_gso_type_mask(AF_INET6, cp->af));
 	if (IS_ERR(skb))
 		goto tx_error;
 
@@ -1008,14 +1075,13 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 */
 	iph			=	ipv6_hdr(skb);
 	iph->version		=	6;
-	iph->nexthdr		=	IPPROTO_IPV6;
-	iph->payload_len	=	old_iph->payload_len;
-	be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
+	iph->nexthdr		=	next_protocol;
+	iph->payload_len	=	htons(payload_len);
 	memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
-	ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph));
+	ipv6_change_dsfield(iph, 0, dsfield);
 	iph->daddr = cp->daddr.in6;
 	iph->saddr = saddr;
-	iph->hop_limit		=	old_iph->hop_limit;
+	iph->hop_limit		=	ttl;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;

From f7fa38006983c0933a550fa790a3b3d3856394d1 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 9 Sep 2014 16:40:29 -0700
Subject: [PATCH 11/15] ipvs: address family of LBLC entry depends on svc
 family

The LBLC entries should use svc->af, not dest->af.
Needed to support svc->af != dest->af.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Alex Gartrell <agartrell@fb.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_lblc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 547ff33c1efd..127f14046c51 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -199,11 +199,11 @@ ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
  */
 static inline struct ip_vs_lblc_entry *
 ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
-	       struct ip_vs_dest *dest)
+	       u16 af, struct ip_vs_dest *dest)
 {
 	struct ip_vs_lblc_entry *en;
 
-	en = ip_vs_lblc_get(dest->af, tbl, daddr);
+	en = ip_vs_lblc_get(af, tbl, daddr);
 	if (en) {
 		if (en->dest == dest)
 			return en;
@@ -213,8 +213,8 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
 	if (!en)
 		return NULL;
 
-	en->af = dest->af;
-	ip_vs_addr_copy(dest->af, &en->addr, daddr);
+	en->af = af;
+	ip_vs_addr_copy(af, &en->addr, daddr);
 	en->lastuse = jiffies;
 
 	ip_vs_dest_hold(dest);
@@ -521,13 +521,13 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 	/* If we fail to create a cache entry, we'll just use the valid dest */
 	spin_lock_bh(&svc->sched_lock);
 	if (!tbl->dead)
-		ip_vs_lblc_new(tbl, &iph->daddr, dest);
+		ip_vs_lblc_new(tbl, &iph->daddr, svc->af, dest);
 	spin_unlock_bh(&svc->sched_lock);
 
 out:
 	IP_VS_DBG_BUF(6, "LBLC: destination IP address %s --> server %s:%d\n",
 		      IP_VS_DBG_ADDR(svc->af, &iph->daddr),
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port));
 
 	return dest;
 }

From cf34e646dad101170e00712fe51986cbcdad3044 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 9 Sep 2014 16:40:30 -0700
Subject: [PATCH 12/15] ipvs: address family of LBLCR entry depends on svc
 family

The LBLCR entries should use svc->af, not dest->af.
Needed to support svc->af != dest->af.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Alex Gartrell <agartrell@fb.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_lblcr.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 3f21a2f47de1..2229d2d8bbe0 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -362,18 +362,18 @@ ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
  */
 static inline struct ip_vs_lblcr_entry *
 ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
-		struct ip_vs_dest *dest)
+		u16 af, struct ip_vs_dest *dest)
 {
 	struct ip_vs_lblcr_entry *en;
 
-	en = ip_vs_lblcr_get(dest->af, tbl, daddr);
+	en = ip_vs_lblcr_get(af, tbl, daddr);
 	if (!en) {
 		en = kmalloc(sizeof(*en), GFP_ATOMIC);
 		if (!en)
 			return NULL;
 
-		en->af = dest->af;
-		ip_vs_addr_copy(dest->af, &en->addr, daddr);
+		en->af = af;
+		ip_vs_addr_copy(af, &en->addr, daddr);
 		en->lastuse = jiffies;
 
 		/* initialize its dest set */
@@ -706,13 +706,13 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 	/* If we fail to create a cache entry, we'll just use the valid dest */
 	spin_lock_bh(&svc->sched_lock);
 	if (!tbl->dead)
-		ip_vs_lblcr_new(tbl, &iph->daddr, dest);
+		ip_vs_lblcr_new(tbl, &iph->daddr, svc->af, dest);
 	spin_unlock_bh(&svc->sched_lock);
 
 out:
 	IP_VS_DBG_BUF(6, "LBLCR: destination IP address %s --> server %s:%d\n",
 		      IP_VS_DBG_ADDR(svc->af, &iph->daddr),
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port));
 
 	return dest;
 }

From 4d316f3f9ae3d5fad8d3198eec0a4ef2511471d7 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 17 Sep 2014 00:09:00 +0300
Subject: [PATCH 13/15] ipvs: use correct address family in scheduler logs

Needed to support svc->af != dest->af.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Alex Gartrell <agartrell@fb.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_dh.c  | 2 +-
 net/netfilter/ipvs/ip_vs_fo.c  | 2 +-
 net/netfilter/ipvs/ip_vs_lc.c  | 2 +-
 net/netfilter/ipvs/ip_vs_nq.c  | 3 ++-
 net/netfilter/ipvs/ip_vs_rr.c  | 2 +-
 net/netfilter/ipvs/ip_vs_sed.c | 3 ++-
 net/netfilter/ipvs/ip_vs_sh.c  | 8 ++++----
 net/netfilter/ipvs/ip_vs_wlc.c | 3 ++-
 net/netfilter/ipvs/ip_vs_wrr.c | 2 +-
 9 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index c3b84546ea9e..6be5c538b71e 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -234,7 +234,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 
 	IP_VS_DBG_BUF(6, "DH: destination IP address %s --> server %s:%d\n",
 		      IP_VS_DBG_ADDR(svc->af, &iph->daddr),
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr),
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 		      ntohs(dest->port));
 
 	return dest;
diff --git a/net/netfilter/ipvs/ip_vs_fo.c b/net/netfilter/ipvs/ip_vs_fo.c
index 6a2647d471ff..e09874d02938 100644
--- a/net/netfilter/ipvs/ip_vs_fo.c
+++ b/net/netfilter/ipvs/ip_vs_fo.c
@@ -44,7 +44,7 @@ ip_vs_fo_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 
 	if (hweight) {
 		IP_VS_DBG_BUF(6, "FO: server %s:%u activeconns %d weight %d\n",
-			      IP_VS_DBG_ADDR(svc->af, &hweight->addr),
+			      IP_VS_DBG_ADDR(hweight->af, &hweight->addr),
 			      ntohs(hweight->port),
 			      atomic_read(&hweight->activeconns),
 			      atomic_read(&hweight->weight));
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 2bdcb1cf2127..19a0769a989a 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -59,7 +59,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 	else
 		IP_VS_DBG_BUF(6, "LC: server %s:%u activeconns %d "
 			      "inactconns %d\n",
-			      IP_VS_DBG_ADDR(svc->af, &least->addr),
+			      IP_VS_DBG_ADDR(least->af, &least->addr),
 			      ntohs(least->port),
 			      atomic_read(&least->activeconns),
 			      atomic_read(&least->inactconns));
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index 961a6de9bb29..a8b63401e773 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -107,7 +107,8 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
   out:
 	IP_VS_DBG_BUF(6, "NQ: server %s:%u "
 		      "activeconns %d refcnt %d weight %d overhead %d\n",
-		      IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port),
+		      IP_VS_DBG_ADDR(least->af, &least->addr),
+		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
 		      atomic_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 176b87c35e34..58bacfc461ee 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -95,7 +95,7 @@ stop:
 	spin_unlock_bh(&svc->sched_lock);
 	IP_VS_DBG_BUF(6, "RR: server %s:%u "
 		      "activeconns %d refcnt %d weight %d\n",
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
 		      atomic_read(&dest->activeconns),
 		      atomic_read(&dest->refcnt), atomic_read(&dest->weight));
 
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index e446b9fa7424..f8e2d00f528b 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -108,7 +108,8 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 
 	IP_VS_DBG_BUF(6, "SED: server %s:%u "
 		      "activeconns %d refcnt %d weight %d overhead %d\n",
-		      IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port),
+		      IP_VS_DBG_ADDR(least->af, &least->addr),
+		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
 		      atomic_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index cc65b2f42cd4..98a13433b68c 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -138,7 +138,7 @@ ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
 		return dest;
 
 	IP_VS_DBG_BUF(6, "SH: selected unavailable server %s:%d, reselecting",
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port));
 
 	/* if the original dest is unavailable, loop around the table
 	 * starting from ihash to find a new dest
@@ -153,7 +153,7 @@ ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
 			return dest;
 		IP_VS_DBG_BUF(6, "SH: selected unavailable "
 			      "server %s:%d (offset %d), reselecting",
-			      IP_VS_DBG_ADDR(svc->af, &dest->addr),
+			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port), roffset);
 	}
 
@@ -192,7 +192,7 @@ ip_vs_sh_reassign(struct ip_vs_sh_state *s, struct ip_vs_service *svc)
 			RCU_INIT_POINTER(b->dest, dest);
 
 			IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
-				      i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
+				      i, IP_VS_DBG_ADDR(dest->af, &dest->addr),
 				      atomic_read(&dest->weight));
 
 			/* Don't move to next dest until filling weight */
@@ -342,7 +342,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 
 	IP_VS_DBG_BUF(6, "SH: source IP address %s --> server %s:%d\n",
 		      IP_VS_DBG_ADDR(svc->af, &iph->saddr),
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr),
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 		      ntohs(dest->port));
 
 	return dest;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index b5b4650d50a9..6b366fd90554 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -80,7 +80,8 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 
 	IP_VS_DBG_BUF(6, "WLC: server %s:%u "
 		      "activeconns %d refcnt %d weight %d overhead %d\n",
-		      IP_VS_DBG_ADDR(svc->af, &least->addr), ntohs(least->port),
+		      IP_VS_DBG_ADDR(least->af, &least->addr),
+		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
 		      atomic_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 0546cd572d6b..17e6d4406ca7 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -216,7 +216,7 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 found:
 	IP_VS_DBG_BUF(6, "WRR: server %s:%u "
 		      "activeconns %d refcnt %d weight %d\n",
-		      IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
 		      atomic_read(&dest->activeconns),
 		      atomic_read(&dest->refcnt),
 		      atomic_read(&dest->weight));

From f18ae7206eaebfecc2dd8b017b0d6a0950eabf8b Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 9 Sep 2014 16:40:38 -0700
Subject: [PATCH 14/15] ipvs: use the new dest addr family field

Use the new address family field cp->daf when printing
cp->daddr in logs or connection listing.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Alex Gartrell <agartrell@fb.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_conn.c       | 49 +++++++++++++++++++++------
 net/netfilter/ipvs/ip_vs_core.c       |  6 ++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c |  2 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |  2 +-
 4 files changed, 43 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 13e9cee02c81..b0f7b626b56d 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -27,6 +27,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/in.h>
+#include <linux/inet.h>
 #include <linux/net.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -77,6 +78,13 @@ static unsigned int ip_vs_conn_rnd __read_mostly;
 #define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
 #define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)
 
+/* We need an addrstrlen that works with or without v6 */
+#ifdef CONFIG_IP_VS_IPV6
+#define IP_VS_ADDRSTRLEN INET6_ADDRSTRLEN
+#else
+#define IP_VS_ADDRSTRLEN (8+1)
+#endif
+
 struct ip_vs_aligned_lock
 {
 	spinlock_t	l;
@@ -588,7 +596,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
 		      ip_vs_proto_name(cp->protocol),
 		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
-		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
+		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      ip_vs_fwd_tag(cp), cp->state,
 		      cp->flags, atomic_read(&cp->refcnt),
 		      atomic_read(&dest->refcnt));
@@ -685,7 +693,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 		      ip_vs_proto_name(cp->protocol),
 		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
-		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
+		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      ip_vs_fwd_tag(cp), cp->state,
 		      cp->flags, atomic_read(&cp->refcnt),
 		      atomic_read(&dest->refcnt));
@@ -754,7 +762,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 			      ntohs(ct->cport),
 			      IP_VS_DBG_ADDR(ct->af, &ct->vaddr),
 			      ntohs(ct->vport),
-			      IP_VS_DBG_ADDR(ct->af, &ct->daddr),
+			      IP_VS_DBG_ADDR(ct->daf, &ct->daddr),
 			      ntohs(ct->dport));
 
 		/*
@@ -1051,6 +1059,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 		struct net *net = seq_file_net(seq);
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
+		char dbuf[IP_VS_ADDRSTRLEN];
 
 		if (!ip_vs_conn_net_eq(cp, net))
 			return 0;
@@ -1064,25 +1073,33 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 		}
 		pe_data[len] = '\0';
 
+#ifdef CONFIG_IP_VS_IPV6
+		if (cp->daf == AF_INET6)
+			snprintf(dbuf, sizeof(dbuf), "%pI6", &cp->daddr.in6);
+		else
+#endif
+			snprintf(dbuf, sizeof(dbuf), "%08X",
+				 ntohl(cp->daddr.ip));
+
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
 			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "
-				"%pI6 %04X %-11s %7lu%s\n",
+				"%s %04X %-11s %7lu%s\n",
 				ip_vs_proto_name(cp->protocol),
 				&cp->caddr.in6, ntohs(cp->cport),
 				&cp->vaddr.in6, ntohs(cp->vport),
-				&cp->daddr.in6, ntohs(cp->dport),
+				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp->protocol, cp->state),
 				(cp->timer.expires-jiffies)/HZ, pe_data);
 		else
 #endif
 			seq_printf(seq,
 				"%-3s %08X %04X %08X %04X"
-				" %08X %04X %-11s %7lu%s\n",
+				" %s %04X %-11s %7lu%s\n",
 				ip_vs_proto_name(cp->protocol),
 				ntohl(cp->caddr.ip), ntohs(cp->cport),
 				ntohl(cp->vaddr.ip), ntohs(cp->vport),
-				ntohl(cp->daddr.ip), ntohs(cp->dport),
+				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp->protocol, cp->state),
 				(cp->timer.expires-jiffies)/HZ, pe_data);
 	}
@@ -1120,6 +1137,7 @@ static const char *ip_vs_origin_name(unsigned int flags)
 
 static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 {
+	char dbuf[IP_VS_ADDRSTRLEN];
 
 	if (v == SEQ_START_TOKEN)
 		seq_puts(seq,
@@ -1131,13 +1149,22 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 		if (!ip_vs_conn_net_eq(cp, net))
 			return 0;
 
+#ifdef CONFIG_IP_VS_IPV6
+		if (cp->daf == AF_INET6)
+			snprintf(dbuf, sizeof(dbuf), "%pI6", &cp->daddr.in6);
+		else
+#endif
+			snprintf(dbuf, sizeof(dbuf), "%08X",
+				 ntohl(cp->daddr.ip));
+
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
-			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X %pI6 %04X %-11s %-6s %7lu\n",
+			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "
+				"%s %04X %-11s %-6s %7lu\n",
 				ip_vs_proto_name(cp->protocol),
 				&cp->caddr.in6, ntohs(cp->cport),
 				&cp->vaddr.in6, ntohs(cp->vport),
-				&cp->daddr.in6, ntohs(cp->dport),
+				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp->protocol, cp->state),
 				ip_vs_origin_name(cp->flags),
 				(cp->timer.expires-jiffies)/HZ);
@@ -1145,11 +1172,11 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 #endif
 			seq_printf(seq,
 				"%-3s %08X %04X %08X %04X "
-				"%08X %04X %-11s %-6s %7lu\n",
+				"%s %04X %-11s %-6s %7lu\n",
 				ip_vs_proto_name(cp->protocol),
 				ntohl(cp->caddr.ip), ntohs(cp->cport),
 				ntohl(cp->vaddr.ip), ntohs(cp->vport),
-				ntohl(cp->daddr.ip), ntohs(cp->dport),
+				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp->protocol, cp->state),
 				ip_vs_origin_name(cp->flags),
 				(cp->timer.expires-jiffies)/HZ);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1f6ecb74821f..990decba1fe4 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -492,9 +492,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
 		      "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
 		      ip_vs_fwd_tag(cp),
-		      IP_VS_DBG_ADDR(svc->af, &cp->caddr), ntohs(cp->cport),
-		      IP_VS_DBG_ADDR(svc->af, &cp->vaddr), ntohs(cp->vport),
-		      IP_VS_DBG_ADDR(svc->af, &cp->daddr), ntohs(cp->dport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
+		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      cp->flags, atomic_read(&cp->refcnt));
 
 	ip_vs_conn_stats(cp, svc);
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 2f7ea7564044..5b84c0b56642 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -432,7 +432,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 				pd->pp->name,
 				((direction == IP_VS_DIR_OUTPUT) ?
 				 "output " : "input "),
-				IP_VS_DBG_ADDR(cp->af, &cp->daddr),
+				IP_VS_DBG_ADDR(cp->daf, &cp->daddr),
 				ntohs(cp->dport),
 				IP_VS_DBG_ADDR(cp->af, &cp->caddr),
 				ntohs(cp->cport),
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index e3a697234a98..8e92beb0cca9 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -510,7 +510,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 			      th->fin ? 'F' : '.',
 			      th->ack ? 'A' : '.',
 			      th->rst ? 'R' : '.',
-			      IP_VS_DBG_ADDR(cp->af, &cp->daddr),
+			      IP_VS_DBG_ADDR(cp->daf, &cp->daddr),
 			      ntohs(cp->dport),
 			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
 			      ntohs(cp->cport),

From bc18d37f676f76edbb5e0c37def78c704b5fbed0 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:39 -0700
Subject: [PATCH 15/15] ipvs: Allow heterogeneous pools now that we support
 them

Remove the temporary consistency check and add a case statement to only
allow ipip mixed dests.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 462760eded94..ac7ba689efe7 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -854,10 +854,6 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 
 	EnterFunction(2);
 
-	/* Temporary for consistency */
-	if (udest->af != svc->af)
-		return -EINVAL;
-
 #ifdef CONFIG_IP_VS_IPV6
 	if (udest->af == AF_INET6) {
 		atype = ipv6_addr_type(&udest->addr.in6);
@@ -3403,6 +3399,26 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		 */
 		if (udest.af == 0)
 			udest.af = svc->af;
+
+		if (udest.af != svc->af) {
+			/* The synchronization protocol is incompatible
+			 * with mixed family services
+			 */
+			if (net_ipvs(net)->sync_state) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			/* Which connection types do we support? */
+			switch (udest.conn_flags) {
+			case IP_VS_CONN_F_TUNNEL:
+				/* We are able to forward this */
+				break;
+			default:
+				ret = -EINVAL;
+				goto out;
+			}
+		}
 	}
 
 	switch (cmd) {