[PATCH 0/9] net: support multiple independant multicast routing instances

[PATCH 0/9] net: support multiple independant multicast routing instances

[Patrick McHardy]

Hi Dave,

this is an updated patchset of my patches to support multiple independant
multicast routing instances. Changes since the last posting are:

- rebase to the current net-next-2.6.git tree
- fix up patch subjects to consistently refer to "ipv4: ipmr:"
- fix up list_head conversion patch to add new elements at the head of
  the list instead of at the tail

Please apply or pull from:

git://git.kernel.org/pub/scm/linux/kernel/git/kaber/ipmr-2.6.git master

Thanks!

[PATCH 1/9] net: fib_rules: consolidate IPv4 and DECnet ->default_pref() functions.

[Patrick McHardy]

Both functions are equivalent, consolidate them since a following patch
needs a third implementation for multicast routing.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/fib_rules.h |    1 +
 net/core/fib_rules.c    |   18 ++++++++++++++++++
 net/decnet/dn_rules.c   |   19 +------------------
 net/ipv4/fib_rules.c    |   19 +------------------
 4 files changed, 21 insertions(+), 36 deletions(-)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index c49086d..52bd9e6 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -114,4 +114,5 @@ extern int			fib_rules_lookup(struct fib_rules_ops *,
 extern int			fib_default_rule_add(struct fib_rules_ops *,
 						     u32 pref, u32 table,
 						     u32 flags);
+extern u32			fib_default_rule_pref(struct fib_rules_ops *ops);
 #endif
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 05cce4e..1eb3227 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -39,6 +39,24 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 }
 EXPORT_SYMBOL(fib_default_rule_add);
 
+u32 fib_default_rule_pref(struct fib_rules_ops *ops)
+{
+	struct list_head *pos;
+	struct fib_rule *rule;
+
+	if (!list_empty(&ops->rules_list)) {
+		pos = ops->rules_list.next;
+		if (pos->next != &ops->rules_list) {
+			rule = list_entry(pos->next, struct fib_rule, list);
+			if (rule->pref)
+				return rule->pref - 1;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(fib_default_rule_pref);
+
 static void notify_rule_change(int event, struct fib_rule *rule,
 			       struct fib_rules_ops *ops, struct nlmsghdr *nlh,
 			       u32 pid);
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index 7466c54..2d14093 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -212,23 +212,6 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
-static u32 dn_fib_rule_default_pref(struct fib_rules_ops *ops)
-{
-	struct list_head *pos;
-	struct fib_rule *rule;
-
-	if (!list_empty(&dn_fib_rules_ops->rules_list)) {
-		pos = dn_fib_rules_ops->rules_list.next;
-		if (pos->next != &dn_fib_rules_ops->rules_list) {
-			rule = list_entry(pos->next, struct fib_rule, list);
-			if (rule->pref)
-				return rule->pref - 1;
-		}
-	}
-
-	return 0;
-}
-
 static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops)
 {
 	dn_rt_cache_flush(-1);
@@ -243,7 +226,7 @@ static struct fib_rules_ops dn_fib_rules_ops_template = {
 	.configure	= dn_fib_rule_configure,
 	.compare	= dn_fib_rule_compare,
 	.fill		= dn_fib_rule_fill,
-	.default_pref	= dn_fib_rule_default_pref,
+	.default_pref	= fib_default_rule_pref,
 	.flush_cache	= dn_fib_rule_flush_cache,
 	.nlgroup	= RTNLGRP_DECnet_RULE,
 	.policy		= dn_fib_rule_policy,
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index ca2d07b..73b6784 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -234,23 +234,6 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
-static u32 fib4_rule_default_pref(struct fib_rules_ops *ops)
-{
-	struct list_head *pos;
-	struct fib_rule *rule;
-
-	if (!list_empty(&ops->rules_list)) {
-		pos = ops->rules_list.next;
-		if (pos->next != &ops->rules_list) {
-			rule = list_entry(pos->next, struct fib_rule, list);
-			if (rule->pref)
-				return rule->pref - 1;
-		}
-	}
-
-	return 0;
-}
-
 static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
 {
 	return nla_total_size(4) /* dst */
@@ -272,7 +255,7 @@ static struct fib_rules_ops fib4_rules_ops_template = {
 	.configure	= fib4_rule_configure,
 	.compare	= fib4_rule_compare,
 	.fill		= fib4_rule_fill,
-	.default_pref	= fib4_rule_default_pref,
+	.default_pref	= fib_default_rule_pref,
 	.nlmsg_payload	= fib4_rule_nlmsg_payload,
 	.flush_cache	= fib4_rule_flush_cache,
 	.nlgroup	= RTNLGRP_IPV4_RULE,
-- 
1.7.0.4

[PATCH 2/9] net: fib_rules: set family in fib_rule_hdr centrally

[Patrick McHardy]

All fib_rules implementations need to set the family in their ->fill()
functions. Since the value is available to the generic fib_nl_fill_rule()
function, set it there.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/core/fib_rules.c  |    1 +
 net/decnet/dn_rules.c |    1 -
 net/ipv4/fib_rules.c  |    1 -
 net/ipv6/fib6_rules.c |    1 -
 4 files changed, 1 insertions(+), 3 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 1eb3227..1bc6659 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -535,6 +535,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 		return -EMSGSIZE;
 
 	frh = nlmsg_data(nlh);
+	frh->family = ops->family;
 	frh->table = rule->table;
 	NLA_PUT_U32(skb, FRA_TABLE, rule->table);
 	frh->res1 = 0;
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index 2d14093..1c8cc6d 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -196,7 +196,6 @@ static int dn_fib_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 {
 	struct dn_fib_rule *r = (struct dn_fib_rule *)rule;
 
-	frh->family = AF_DECnet;
 	frh->dst_len = r->dst_len;
 	frh->src_len = r->src_len;
 	frh->tos = 0;
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 73b6784..a18355e 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -213,7 +213,6 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 {
 	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
 
-	frh->family = AF_INET;
 	frh->dst_len = rule4->dst_len;
 	frh->src_len = rule4->src_len;
 	frh->tos = rule4->tos;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 5e463c4..92b2b7f 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -208,7 +208,6 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 {
 	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
 
-	frh->family = AF_INET6;
 	frh->dst_len = rule6->dst.plen;
 	frh->src_len = rule6->src.plen;
 	frh->tos = rule6->tclass;
-- 
1.7.0.4

[PATCH 3/9] net: fib_rules: decouple address families from real address families

[Patrick McHardy]

Decouple the address family values used for fib_rules from the real
address families in socket.h. This allows to use fib_rules for
code that is not a real address family without increasing AF_MAX/NPROTO.

Values up to 127 are reserved for real address families and map directly
to the corresponding AF value, values starting from 128 are for other
uses. rtnetlink is changed to invoke the AF_UNSPEC dumpit/doit handlers
for these families.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/fib_rules.h |    7 +++++++
 net/core/rtnetlink.c      |   15 ++++++++++-----
 net/decnet/dn_rules.c     |    2 +-
 net/ipv4/fib_rules.c      |    2 +-
 net/ipv6/fib6_rules.c     |    2 +-
 5 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h
index 51da65b..405e411 100644
--- a/include/linux/fib_rules.h
+++ b/include/linux/fib_rules.h
@@ -15,6 +15,13 @@
 /* try to find source address in routing lookups */
 #define FIB_RULE_FIND_SADDR	0x00010000
 
+/* fib_rules families. values up to 127 are reserved for real address
+ * families, values above 128 may be used arbitrarily.
+ */
+#define FIB_RULES_IPV4		AF_INET
+#define FIB_RULES_IPV6		AF_INET6
+#define FIB_RULES_DECNET	AF_DECnet
+
 struct fib_rule_hdr {
 	__u8		family;
 	__u8		dst_len;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bf919b6..78c8598 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -118,7 +118,11 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
 {
 	struct rtnl_link *tab;
 
-	tab = rtnl_msg_handlers[protocol];
+	if (protocol < NPROTO)
+		tab = rtnl_msg_handlers[protocol];
+	else
+		tab = NULL;
+
 	if (tab == NULL || tab[msgindex].doit == NULL)
 		tab = rtnl_msg_handlers[PF_UNSPEC];
 
@@ -129,7 +133,11 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
 {
 	struct rtnl_link *tab;
 
-	tab = rtnl_msg_handlers[protocol];
+	if (protocol < NPROTO)
+		tab = rtnl_msg_handlers[protocol];
+	else
+		tab = NULL;
+
 	if (tab == NULL || tab[msgindex].dumpit == NULL)
 		tab = rtnl_msg_handlers[PF_UNSPEC];
 
@@ -1444,9 +1452,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return 0;
 
 	family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family;
-	if (family >= NPROTO)
-		return -EAFNOSUPPORT;
-
 	sz_idx = type>>2;
 	kind = type&3;
 
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index 1c8cc6d..af28dcc 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -217,7 +217,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops)
 }
 
 static struct fib_rules_ops dn_fib_rules_ops_template = {
-	.family		= AF_DECnet,
+	.family		= FIB_RULES_DECNET,
 	.rule_size	= sizeof(struct dn_fib_rule),
 	.addr_size	= sizeof(u16),
 	.action		= dn_fib_rule_action,
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index a18355e..3ec84fe 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -246,7 +246,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
 }
 
 static struct fib_rules_ops fib4_rules_ops_template = {
-	.family		= AF_INET,
+	.family		= FIB_RULES_IPV4,
 	.rule_size	= sizeof(struct fib4_rule),
 	.addr_size	= sizeof(u32),
 	.action		= fib4_rule_action,
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 92b2b7f..8124f16 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -238,7 +238,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
 }
 
 static struct fib_rules_ops fib6_rules_ops_template = {
-	.family			= AF_INET6,
+	.family			= FIB_RULES_IPV6,
 	.rule_size		= sizeof(struct fib6_rule),
 	.addr_size		= sizeof(struct in6_addr),
 	.action			= fib6_rule_action,
-- 
1.7.0.4

[PATCH 4/9] ipv4: raw: move struct raw_sock and raw_sk() to include/net/raw.h

[Patrick McHardy]

A following patch will use struct raw_sock to store state for ipmr,
so having the definitions in icmp.h doesn't fit very well anymore.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/icmp.h |   11 -----------
 include/net/raw.h  |   12 ++++++++++++
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/include/net/icmp.h b/include/net/icmp.h
index 15b3dfe..6e991e0 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -48,15 +48,4 @@ extern void	icmp_out_count(struct net *net, unsigned char type);
 /* Move into dst.h ? */
 extern int 	xrlim_allow(struct dst_entry *dst, int timeout);
 
-struct raw_sock {
-	/* inet_sock has to be the first member */
-	struct inet_sock   inet;
-	struct icmp_filter filter;
-};
-
-static inline struct raw_sock *raw_sk(const struct sock *sk)
-{
-	return (struct raw_sock *)sk;
-}
-
 #endif	/* _ICMP_H */
diff --git a/include/net/raw.h b/include/net/raw.h
index 6c14a65..67cc643 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -19,6 +19,7 @@
 
 
 #include <net/protocol.h>
+#include <linux/icmp.h>
 
 extern struct proto raw_prot;
 
@@ -56,4 +57,15 @@ int raw_seq_open(struct inode *ino, struct file *file,
 void raw_hash_sk(struct sock *sk);
 void raw_unhash_sk(struct sock *sk);
 
+struct raw_sock {
+	/* inet_sock has to be the first member */
+	struct inet_sock   inet;
+	struct icmp_filter filter;
+};
+
+static inline struct raw_sock *raw_sk(const struct sock *sk)
+{
+	return (struct raw_sock *)sk;
+}
+
 #endif	/* _RAW_H */
-- 
1.7.0.4

[PATCH 5/9] ipv4: ipmr: move unres_queue and timer to per-namespace data

[Patrick McHardy]

The unres_queue is currently shared between all namespaces. Following patches
will additionally allow to create multiple multicast routing tables in each
namespace. Having a single shared queue for all these users seems to excessive,
move the queue and the cleanup timer to the per-namespace data to unshare it.

As a side-effect, this fixes a bug in the seq file iteration functions: the
first entry returned is always from the current namespace, entries returned
after that may belong to any namespace.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netns/ipv4.h |    2 +
 net/ipv4/ipmr.c          |   70 +++++++++++++++++++---------------------------
 2 files changed, 31 insertions(+), 41 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2764994..b15e518 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -60,6 +60,8 @@ struct netns_ipv4 {
 
 #ifdef CONFIG_IP_MROUTE
 	struct sock		*mroute_sk;
+	struct timer_list	ipmr_expire_timer;
+	struct mfc_cache	*mfc_unres_queue;
 	struct mfc_cache	**mfc_cache_array;
 	struct vif_device	*vif_table;
 	int			maxvif;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d4f6d1..d6aa65e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -80,8 +80,6 @@ static DEFINE_RWLOCK(mrt_lock);
 
 #define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL)
 
-static struct mfc_cache *mfc_unres_queue;		/* Queue of unresolved entries */
-
 /* Special spinlock for queue of unresolved entries */
 static DEFINE_SPINLOCK(mfc_unres_lock);
 
@@ -100,8 +98,6 @@ static int ipmr_cache_report(struct net *net,
 			     struct sk_buff *pkt, vifi_t vifi, int assert);
 static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm);
 
-static struct timer_list ipmr_expire_timer;
-
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
 
 static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v)
@@ -364,25 +360,26 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
 }
 
 
-/* Single timer process for all the unresolved queue. */
+/* Timer process for the unresolved queue. */
 
-static void ipmr_expire_process(unsigned long dummy)
+static void ipmr_expire_process(unsigned long arg)
 {
+	struct net *net = (struct net *)arg;
 	unsigned long now;
 	unsigned long expires;
 	struct mfc_cache *c, **cp;
 
 	if (!spin_trylock(&mfc_unres_lock)) {
-		mod_timer(&ipmr_expire_timer, jiffies+HZ/10);
+		mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10);
 		return;
 	}
 
-	if (mfc_unres_queue == NULL)
+	if (net->ipv4.mfc_unres_queue == NULL)
 		goto out;
 
 	now = jiffies;
 	expires = 10*HZ;
-	cp = &mfc_unres_queue;
+	cp = &net->ipv4.mfc_unres_queue;
 
 	while ((c=*cp) != NULL) {
 		if (time_after(c->mfc_un.unres.expires, now)) {
@@ -398,8 +395,8 @@ static void ipmr_expire_process(unsigned long dummy)
 		ipmr_destroy_unres(c);
 	}
 
-	if (mfc_unres_queue != NULL)
-		mod_timer(&ipmr_expire_timer, jiffies + expires);
+	if (net->ipv4.mfc_unres_queue != NULL)
+		mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires);
 
 out:
 	spin_unlock(&mfc_unres_lock);
@@ -708,9 +705,8 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 
 	spin_lock_bh(&mfc_unres_lock);
-	for (c=mfc_unres_queue; c; c=c->next) {
-		if (net_eq(mfc_net(c), net) &&
-		    c->mfc_mcastgrp == iph->daddr &&
+	for (c=net->ipv4.mfc_unres_queue; c; c=c->next) {
+		if (c->mfc_mcastgrp == iph->daddr &&
 		    c->mfc_origin == iph->saddr)
 			break;
 	}
@@ -751,10 +747,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 		}
 
 		atomic_inc(&net->ipv4.cache_resolve_queue_len);
-		c->next = mfc_unres_queue;
-		mfc_unres_queue = c;
+		c->next = net->ipv4.mfc_unres_queue;
+		net->ipv4.mfc_unres_queue = c;
 
-		mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires);
+		mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires);
 	}
 
 	/*
@@ -849,18 +845,17 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	 *	need to send on the frames and tidy up.
 	 */
 	spin_lock_bh(&mfc_unres_lock);
-	for (cp = &mfc_unres_queue; (uc=*cp) != NULL;
+	for (cp = &net->ipv4.mfc_unres_queue; (uc=*cp) != NULL;
 	     cp = &uc->next) {
-		if (net_eq(mfc_net(uc), net) &&
-		    uc->mfc_origin == c->mfc_origin &&
+		if (uc->mfc_origin == c->mfc_origin &&
 		    uc->mfc_mcastgrp == c->mfc_mcastgrp) {
 			*cp = uc->next;
 			atomic_dec(&net->ipv4.cache_resolve_queue_len);
 			break;
 		}
 	}
-	if (mfc_unres_queue == NULL)
-		del_timer(&ipmr_expire_timer);
+	if (net->ipv4.mfc_unres_queue == NULL)
+		del_timer(&net->ipv4.ipmr_expire_timer);
 	spin_unlock_bh(&mfc_unres_lock);
 
 	if (uc) {
@@ -912,14 +907,9 @@ static void mroute_clean_tables(struct net *net)
 		struct mfc_cache *c, **cp;
 
 		spin_lock_bh(&mfc_unres_lock);
-		cp = &mfc_unres_queue;
+		cp = &net->ipv4.mfc_unres_queue;
 		while ((c = *cp) != NULL) {
-			if (!net_eq(mfc_net(c), net)) {
-				cp = &c->next;
-				continue;
-			}
 			*cp = c->next;
-
 			ipmr_destroy_unres(c);
 		}
 		spin_unlock_bh(&mfc_unres_lock);
@@ -1819,11 +1809,10 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
 				return mfc;
 	read_unlock(&mrt_lock);
 
-	it->cache = &mfc_unres_queue;
+	it->cache = &net->ipv4.mfc_unres_queue;
 	spin_lock_bh(&mfc_unres_lock);
-	for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
-		if (net_eq(mfc_net(mfc), net) &&
-		    pos-- == 0)
+	for (mfc = net->ipv4.mfc_unres_queue; mfc; mfc = mfc->next)
+		if (pos-- == 0)
 			return mfc;
 	spin_unlock_bh(&mfc_unres_lock);
 
@@ -1857,7 +1846,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (mfc->next)
 		return mfc->next;
 
-	if (it->cache == &mfc_unres_queue)
+	if (it->cache == &net->ipv4.mfc_unres_queue)
 		goto end_of_list;
 
 	BUG_ON(it->cache != net->ipv4.mfc_cache_array);
@@ -1870,13 +1859,11 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 	/* exhausted cache_array, show unresolved */
 	read_unlock(&mrt_lock);
-	it->cache = &mfc_unres_queue;
+	it->cache = &net->ipv4.mfc_unres_queue;
 	it->ct = 0;
 
 	spin_lock_bh(&mfc_unres_lock);
-	mfc = mfc_unres_queue;
-	while (mfc && !net_eq(mfc_net(mfc), net))
-		mfc = mfc->next;
+	mfc = net->ipv4.mfc_unres_queue;
 	if (mfc)
 		return mfc;
 
@@ -1892,7 +1879,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
 
-	if (it->cache == &mfc_unres_queue)
+	if (it->cache == &net->ipv4.mfc_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
 	else if (it->cache == net->ipv4.mfc_cache_array)
 		read_unlock(&mrt_lock);
@@ -1915,7 +1902,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
 			   (unsigned long) mfc->mfc_origin,
 			   mfc->mfc_parent);
 
-		if (it->cache != &mfc_unres_queue) {
+		if (it->cache != &net->ipv4.mfc_unres_queue) {
 			seq_printf(seq, " %8lu %8lu %8lu",
 				   mfc->mfc_un.res.pkt,
 				   mfc->mfc_un.res.bytes,
@@ -1992,6 +1979,9 @@ static int __net_init ipmr_net_init(struct net *net)
 		goto fail_mfc_cache;
 	}
 
+	setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process,
+		    (unsigned long)net);
+
 #ifdef CONFIG_IP_PIMSM
 	net->ipv4.mroute_reg_vif_num = -1;
 #endif
@@ -2047,7 +2037,6 @@ int __init ip_mr_init(void)
 	if (err)
 		goto reg_pernet_fail;
 
-	setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
 	err = register_netdevice_notifier(&ip_mr_notifier);
 	if (err)
 		goto reg_notif_fail;
@@ -2065,7 +2054,6 @@ add_proto_fail:
 	unregister_netdevice_notifier(&ip_mr_notifier);
 #endif
 reg_notif_fail:
-	del_timer(&ipmr_expire_timer);
 	unregister_pernet_subsys(&ipmr_net_ops);
 reg_pernet_fail:
 	kmem_cache_destroy(mrt_cachep);
-- 
1.7.0.4

[PATCH 6/9] ipv4: ipmr: remove net pointer from struct mfc_cache

[Patrick McHardy]

Now that cache entries in unres_queue don't need to be distinguished by their
network namespace pointer anymore, we can remove it from struct mfc_cache
add pass the namespace as function argument to the functions that need it.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/mroute.h |   15 -----------
 net/ipv4/ipmr.c        |   65 +++++++++++++++++++++++------------------------
 2 files changed, 32 insertions(+), 48 deletions(-)

diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index c5f3d53..de7780a 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -192,9 +192,6 @@ struct vif_device {
 
 struct mfc_cache {
 	struct mfc_cache *next;			/* Next entry on cache line 	*/
-#ifdef CONFIG_NET_NS
-	struct net *mfc_net;
-#endif
 	__be32 mfc_mcastgrp;			/* Group the entry belongs to 	*/
 	__be32 mfc_origin;			/* Source of packet 		*/
 	vifi_t mfc_parent;			/* Source interface		*/
@@ -217,18 +214,6 @@ struct mfc_cache {
 	} mfc_un;
 };
 
-static inline
-struct net *mfc_net(const struct mfc_cache *mfc)
-{
-	return read_pnet(&mfc->mfc_net);
-}
-
-static inline
-void mfc_net_set(struct mfc_cache *mfc, struct net *net)
-{
-	write_pnet(&mfc->mfc_net, hold_net(net));
-}
-
 #define MFC_STATIC		1
 #define MFC_NOTIFY		2
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index d6aa65e..f8e25c8 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -93,10 +93,12 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
 
 static struct kmem_cache *mrt_cachep __read_mostly;
 
-static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local);
+static int ip_mr_forward(struct net *net, struct sk_buff *skb,
+			 struct mfc_cache *cache, int local);
 static int ipmr_cache_report(struct net *net,
 			     struct sk_buff *pkt, vifi_t vifi, int assert);
-static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm);
+static int ipmr_fill_mroute(struct net *net, struct sk_buff *skb,
+			    struct mfc_cache *c, struct rtmsg *rtm);
 
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
 
@@ -325,7 +327,6 @@ static int vif_delete(struct net *net, int vifi, int notify,
 
 static inline void ipmr_cache_free(struct mfc_cache *c)
 {
-	release_net(mfc_net(c));
 	kmem_cache_free(mrt_cachep, c);
 }
 
@@ -333,11 +334,10 @@ static inline void ipmr_cache_free(struct mfc_cache *c)
    and reporting error to netlink readers.
  */
 
-static void ipmr_destroy_unres(struct mfc_cache *c)
+static void ipmr_destroy_unres(struct net *net, struct mfc_cache *c)
 {
 	struct sk_buff *skb;
 	struct nlmsgerr *e;
-	struct net *net = mfc_net(c);
 
 	atomic_dec(&net->ipv4.cache_resolve_queue_len);
 
@@ -392,7 +392,7 @@ static void ipmr_expire_process(unsigned long arg)
 
 		*cp = c->next;
 
-		ipmr_destroy_unres(c);
+		ipmr_destroy_unres(net, c);
 	}
 
 	if (net->ipv4.mfc_unres_queue != NULL)
@@ -404,10 +404,10 @@ out:
 
 /* Fill oifs list. It is called under write locked mrt_lock. */
 
-static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
+static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache,
+				   unsigned char *ttls)
 {
 	int vifi;
-	struct net *net = mfc_net(cache);
 
 	cache->mfc_un.res.minvif = MAXVIFS;
 	cache->mfc_un.res.maxvif = 0;
@@ -547,24 +547,22 @@ static struct mfc_cache *ipmr_cache_find(struct net *net,
 /*
  *	Allocate a multicast cache entry
  */
-static struct mfc_cache *ipmr_cache_alloc(struct net *net)
+static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 	if (c == NULL)
 		return NULL;
 	c->mfc_un.res.minvif = MAXVIFS;
-	mfc_net_set(c, net);
 	return c;
 }
 
-static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
+static struct mfc_cache *ipmr_cache_alloc_unres(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
 	if (c == NULL)
 		return NULL;
 	skb_queue_head_init(&c->mfc_un.unres.unresolved);
 	c->mfc_un.unres.expires = jiffies + 10*HZ;
-	mfc_net_set(c, net);
 	return c;
 }
 
@@ -572,7 +570,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
  *	A cache entry has gone into a resolved state from queued
  */
 
-static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
+static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc,
+			       struct mfc_cache *c)
 {
 	struct sk_buff *skb;
 	struct nlmsgerr *e;
@@ -585,7 +584,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
 		if (ip_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
 
-			if (ipmr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) {
+			if (ipmr_fill_mroute(net, skb, c, NLMSG_DATA(nlh)) > 0) {
 				nlh->nlmsg_len = (skb_tail_pointer(skb) -
 						  (u8 *)nlh);
 			} else {
@@ -597,9 +596,9 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
 				memset(&e->msg, 0, sizeof(e->msg));
 			}
 
-			rtnl_unicast(skb, mfc_net(c), NETLINK_CB(skb).pid);
+			rtnl_unicast(skb, net, NETLINK_CB(skb).pid);
 		} else
-			ip_mr_forward(skb, c, 0);
+			ip_mr_forward(net, skb, c, 0);
 	}
 }
 
@@ -717,7 +716,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 		 */
 
 		if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 ||
-		    (c = ipmr_cache_alloc_unres(net)) == NULL) {
+		    (c = ipmr_cache_alloc_unres()) == NULL) {
 			spin_unlock_bh(&mfc_unres_lock);
 
 			kfree_skb(skb);
@@ -814,7 +813,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	if (c != NULL) {
 		write_lock_bh(&mrt_lock);
 		c->mfc_parent = mfc->mfcc_parent;
-		ipmr_update_thresholds(c, mfc->mfcc_ttls);
+		ipmr_update_thresholds(net, c, mfc->mfcc_ttls);
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
@@ -824,14 +823,14 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr))
 		return -EINVAL;
 
-	c = ipmr_cache_alloc(net);
+	c = ipmr_cache_alloc();
 	if (c == NULL)
 		return -ENOMEM;
 
 	c->mfc_origin = mfc->mfcc_origin.s_addr;
 	c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr;
 	c->mfc_parent = mfc->mfcc_parent;
-	ipmr_update_thresholds(c, mfc->mfcc_ttls);
+	ipmr_update_thresholds(net, c, mfc->mfcc_ttls);
 	if (!mrtsock)
 		c->mfc_flags |= MFC_STATIC;
 
@@ -859,7 +858,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	spin_unlock_bh(&mfc_unres_lock);
 
 	if (uc) {
-		ipmr_cache_resolve(uc, c);
+		ipmr_cache_resolve(net, uc, c);
 		ipmr_cache_free(uc);
 	}
 	return 0;
@@ -910,7 +909,7 @@ static void mroute_clean_tables(struct net *net)
 		cp = &net->ipv4.mfc_unres_queue;
 		while ((c = *cp) != NULL) {
 			*cp = c->next;
-			ipmr_destroy_unres(c);
+			ipmr_destroy_unres(net, c);
 		}
 		spin_unlock_bh(&mfc_unres_lock);
 	}
@@ -1221,9 +1220,9 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
  *	Processing handlers for ipmr_forward
  */
 
-static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
+static void ipmr_queue_xmit(struct net *net, struct sk_buff *skb,
+			    struct mfc_cache *c, int vifi)
 {
-	struct net *net = mfc_net(c);
 	const struct iphdr *iph = ip_hdr(skb);
 	struct vif_device *vif = &net->ipv4.vif_table[vifi];
 	struct net_device *dev;
@@ -1335,11 +1334,11 @@ static int ipmr_find_vif(struct net_device *dev)
 
 /* "local" means that we should preserve one skb (for local delivery) */
 
-static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local)
+static int ip_mr_forward(struct net *net, struct sk_buff *skb,
+			 struct mfc_cache *cache, int local)
 {
 	int psend = -1;
 	int vif, ct;
-	struct net *net = mfc_net(cache);
 
 	vif = cache->mfc_parent;
 	cache->mfc_un.res.pkt++;
@@ -1396,7 +1395,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
 			if (psend != -1) {
 				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 				if (skb2)
-					ipmr_queue_xmit(skb2, cache, psend);
+					ipmr_queue_xmit(net, skb2, cache, psend);
 			}
 			psend = ct;
 		}
@@ -1405,9 +1404,9 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
 		if (local) {
 			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 			if (skb2)
-				ipmr_queue_xmit(skb2, cache, psend);
+				ipmr_queue_xmit(net, skb2, cache, psend);
 		} else {
-			ipmr_queue_xmit(skb, cache, psend);
+			ipmr_queue_xmit(net, skb, cache, psend);
 			return 0;
 		}
 	}
@@ -1488,7 +1487,7 @@ int ip_mr_input(struct sk_buff *skb)
 		return -ENODEV;
 	}
 
-	ip_mr_forward(skb, cache, local);
+	ip_mr_forward(net, skb, cache, local);
 
 	read_unlock(&mrt_lock);
 
@@ -1602,11 +1601,11 @@ drop:
 #endif
 
 static int
-ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
+ipmr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc_cache *c,
+		 struct rtmsg *rtm)
 {
 	int ct;
 	struct rtnexthop *nhp;
-	struct net *net = mfc_net(c);
 	u8 *b = skb_tail_pointer(skb);
 	struct rtattr *mp_head;
 
@@ -1686,7 +1685,7 @@ int ipmr_get_route(struct net *net,
 
 	if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
 		cache->mfc_flags |= MFC_NOTIFY;
-	err = ipmr_fill_mroute(skb, cache, rtm);
+	err = ipmr_fill_mroute(net, skb, cache, rtm);
 	read_unlock(&mrt_lock);
 	return err;
 }
-- 
1.7.0.4

[PATCH 7/9] ipv4: ipmr: convert struct mfc_cache to struct list_head

[Patrick McHardy]

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/mroute.h   |    2 +-
 include/net/netns/ipv4.h |    4 +-
 net/ipv4/ipmr.c          |  125 ++++++++++++++++++++++-----------------------
 3 files changed, 64 insertions(+), 67 deletions(-)

diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index de7780a..7ff6c77 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -191,7 +191,7 @@ struct vif_device {
 #define VIFF_STATIC 0x8000
 
 struct mfc_cache {
-	struct mfc_cache *next;			/* Next entry on cache line 	*/
+	struct list_head list;
 	__be32 mfc_mcastgrp;			/* Group the entry belongs to 	*/
 	__be32 mfc_origin;			/* Source of packet 		*/
 	vifi_t mfc_parent;			/* Source interface		*/
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index b15e518..5d06429 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -61,8 +61,8 @@ struct netns_ipv4 {
 #ifdef CONFIG_IP_MROUTE
 	struct sock		*mroute_sk;
 	struct timer_list	ipmr_expire_timer;
-	struct mfc_cache	*mfc_unres_queue;
-	struct mfc_cache	**mfc_cache_array;
+	struct list_head	mfc_unres_queue;
+	struct list_head	*mfc_cache_array;
 	struct vif_device	*vif_table;
 	int			maxvif;
 	atomic_t		cache_resolve_queue_len;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index f8e25c8..21b5edc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -367,35 +367,32 @@ static void ipmr_expire_process(unsigned long arg)
 	struct net *net = (struct net *)arg;
 	unsigned long now;
 	unsigned long expires;
-	struct mfc_cache *c, **cp;
+	struct mfc_cache *c, *next;
 
 	if (!spin_trylock(&mfc_unres_lock)) {
 		mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10);
 		return;
 	}
 
-	if (net->ipv4.mfc_unres_queue == NULL)
+	if (list_empty(&net->ipv4.mfc_unres_queue))
 		goto out;
 
 	now = jiffies;
 	expires = 10*HZ;
-	cp = &net->ipv4.mfc_unres_queue;
 
-	while ((c=*cp) != NULL) {
+	list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) {
 		if (time_after(c->mfc_un.unres.expires, now)) {
 			unsigned long interval = c->mfc_un.unres.expires - now;
 			if (interval < expires)
 				expires = interval;
-			cp = &c->next;
 			continue;
 		}
 
-		*cp = c->next;
-
+		list_del(&c->list);
 		ipmr_destroy_unres(net, c);
 	}
 
-	if (net->ipv4.mfc_unres_queue != NULL)
+	if (!list_empty(&net->ipv4.mfc_unres_queue))
 		mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires);
 
 out:
@@ -537,11 +534,11 @@ static struct mfc_cache *ipmr_cache_find(struct net *net,
 	int line = MFC_HASH(mcastgrp, origin);
 	struct mfc_cache *c;
 
-	for (c = net->ipv4.mfc_cache_array[line]; c; c = c->next) {
-		if (c->mfc_origin==origin && c->mfc_mcastgrp==mcastgrp)
-			break;
+	list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) {
+		if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp)
+			return c;
 	}
-	return c;
+	return NULL;
 }
 
 /*
@@ -699,18 +696,21 @@ static int ipmr_cache_report(struct net *net,
 static int
 ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 {
+	bool found = false;
 	int err;
 	struct mfc_cache *c;
 	const struct iphdr *iph = ip_hdr(skb);
 
 	spin_lock_bh(&mfc_unres_lock);
-	for (c=net->ipv4.mfc_unres_queue; c; c=c->next) {
+	list_for_each_entry(c, &net->ipv4.mfc_unres_queue, list) {
 		if (c->mfc_mcastgrp == iph->daddr &&
-		    c->mfc_origin == iph->saddr)
+		    c->mfc_origin == iph->saddr) {
+			found = true;
 			break;
+		}
 	}
 
-	if (c == NULL) {
+	if (!found) {
 		/*
 		 *	Create a new entry if allowable
 		 */
@@ -746,8 +746,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 		}
 
 		atomic_inc(&net->ipv4.cache_resolve_queue_len);
-		c->next = net->ipv4.mfc_unres_queue;
-		net->ipv4.mfc_unres_queue = c;
+		list_add(&c->list, &net->ipv4.mfc_unres_queue);
 
 		mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires);
 	}
@@ -774,16 +773,15 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
 {
 	int line;
-	struct mfc_cache *c, **cp;
+	struct mfc_cache *c, *next;
 
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
-	for (cp = &net->ipv4.mfc_cache_array[line];
-	     (c = *cp) != NULL; cp = &c->next) {
+	list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[line], list) {
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
 		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
 			write_lock_bh(&mrt_lock);
-			*cp = c->next;
+			list_del(&c->list);
 			write_unlock_bh(&mrt_lock);
 
 			ipmr_cache_free(c);
@@ -795,22 +793,24 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
 
 static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 {
+	bool found = false;
 	int line;
-	struct mfc_cache *uc, *c, **cp;
+	struct mfc_cache *uc, *c;
 
 	if (mfc->mfcc_parent >= MAXVIFS)
 		return -ENFILE;
 
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
-	for (cp = &net->ipv4.mfc_cache_array[line];
-	     (c = *cp) != NULL; cp = &c->next) {
+	list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) {
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
-		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr)
+		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
+			found = true;
 			break;
+		}
 	}
 
-	if (c != NULL) {
+	if (found) {
 		write_lock_bh(&mrt_lock);
 		c->mfc_parent = mfc->mfcc_parent;
 		ipmr_update_thresholds(net, c, mfc->mfcc_ttls);
@@ -835,8 +835,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 		c->mfc_flags |= MFC_STATIC;
 
 	write_lock_bh(&mrt_lock);
-	c->next = net->ipv4.mfc_cache_array[line];
-	net->ipv4.mfc_cache_array[line] = c;
+	list_add(&c->list, &net->ipv4.mfc_cache_array[line]);
 	write_unlock_bh(&mrt_lock);
 
 	/*
@@ -844,16 +843,15 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	 *	need to send on the frames and tidy up.
 	 */
 	spin_lock_bh(&mfc_unres_lock);
-	for (cp = &net->ipv4.mfc_unres_queue; (uc=*cp) != NULL;
-	     cp = &uc->next) {
+	list_for_each_entry(uc, &net->ipv4.mfc_unres_queue, list) {
 		if (uc->mfc_origin == c->mfc_origin &&
 		    uc->mfc_mcastgrp == c->mfc_mcastgrp) {
-			*cp = uc->next;
+			list_del(&uc->list);
 			atomic_dec(&net->ipv4.cache_resolve_queue_len);
 			break;
 		}
 	}
-	if (net->ipv4.mfc_unres_queue == NULL)
+	if (list_empty(&net->ipv4.mfc_unres_queue))
 		del_timer(&net->ipv4.ipmr_expire_timer);
 	spin_unlock_bh(&mfc_unres_lock);
 
@@ -872,6 +870,7 @@ static void mroute_clean_tables(struct net *net)
 {
 	int i;
 	LIST_HEAD(list);
+	struct mfc_cache *c, *next;
 
 	/*
 	 *	Shut down all active vif entries
@@ -885,17 +884,12 @@ static void mroute_clean_tables(struct net *net)
 	/*
 	 *	Wipe the cache
 	 */
-	for (i=0; i<MFC_LINES; i++) {
-		struct mfc_cache *c, **cp;
-
-		cp = &net->ipv4.mfc_cache_array[i];
-		while ((c = *cp) != NULL) {
-			if (c->mfc_flags&MFC_STATIC) {
-				cp = &c->next;
+	for (i = 0; i < MFC_LINES; i++) {
+		list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[i], list) {
+			if (c->mfc_flags&MFC_STATIC)
 				continue;
-			}
 			write_lock_bh(&mrt_lock);
-			*cp = c->next;
+			list_del(&c->list);
 			write_unlock_bh(&mrt_lock);
 
 			ipmr_cache_free(c);
@@ -903,12 +897,9 @@ static void mroute_clean_tables(struct net *net)
 	}
 
 	if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) {
-		struct mfc_cache *c, **cp;
-
 		spin_lock_bh(&mfc_unres_lock);
-		cp = &net->ipv4.mfc_unres_queue;
-		while ((c = *cp) != NULL) {
-			*cp = c->next;
+		list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) {
+			list_del(&c->list);
 			ipmr_destroy_unres(net, c);
 		}
 		spin_unlock_bh(&mfc_unres_lock);
@@ -1789,7 +1780,7 @@ static const struct file_operations ipmr_vif_fops = {
 
 struct ipmr_mfc_iter {
 	struct seq_net_private p;
-	struct mfc_cache **cache;
+	struct list_head *cache;
 	int ct;
 };
 
@@ -1799,18 +1790,18 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
 {
 	struct mfc_cache *mfc;
 
-	it->cache = net->ipv4.mfc_cache_array;
 	read_lock(&mrt_lock);
-	for (it->ct = 0; it->ct < MFC_LINES; it->ct++)
-		for (mfc = net->ipv4.mfc_cache_array[it->ct];
-		     mfc; mfc = mfc->next)
+	for (it->ct = 0; it->ct < MFC_LINES; it->ct++) {
+		it->cache = &net->ipv4.mfc_cache_array[it->ct];
+		list_for_each_entry(mfc, it->cache, list)
 			if (pos-- == 0)
 				return mfc;
+	}
 	read_unlock(&mrt_lock);
 
-	it->cache = &net->ipv4.mfc_unres_queue;
 	spin_lock_bh(&mfc_unres_lock);
-	for (mfc = net->ipv4.mfc_unres_queue; mfc; mfc = mfc->next)
+	it->cache = &net->ipv4.mfc_unres_queue;
+	list_for_each_entry(mfc, it->cache, list)
 		if (pos-- == 0)
 			return mfc;
 	spin_unlock_bh(&mfc_unres_lock);
@@ -1842,18 +1833,19 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (v == SEQ_START_TOKEN)
 		return ipmr_mfc_seq_idx(net, seq->private, 0);
 
-	if (mfc->next)
-		return mfc->next;
+	if (mfc->list.next != it->cache)
+		return list_entry(mfc->list.next, struct mfc_cache, list);
 
 	if (it->cache == &net->ipv4.mfc_unres_queue)
 		goto end_of_list;
 
-	BUG_ON(it->cache != net->ipv4.mfc_cache_array);
+	BUG_ON(it->cache != &net->ipv4.mfc_cache_array[it->ct]);
 
 	while (++it->ct < MFC_LINES) {
-		mfc = net->ipv4.mfc_cache_array[it->ct];
-		if (mfc)
-			return mfc;
+		it->cache = &net->ipv4.mfc_cache_array[it->ct];
+		if (list_empty(it->cache))
+			continue;
+		return list_first_entry(it->cache, struct mfc_cache, list);
 	}
 
 	/* exhausted cache_array, show unresolved */
@@ -1862,9 +1854,8 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	it->ct = 0;
 
 	spin_lock_bh(&mfc_unres_lock);
-	mfc = net->ipv4.mfc_unres_queue;
-	if (mfc)
-		return mfc;
+	if (!list_empty(it->cache))
+		return list_first_entry(it->cache, struct mfc_cache, list);
 
  end_of_list:
 	spin_unlock_bh(&mfc_unres_lock);
@@ -1880,7 +1871,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 
 	if (it->cache == &net->ipv4.mfc_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == net->ipv4.mfc_cache_array)
+	else if (it->cache == &net->ipv4.mfc_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
@@ -1960,6 +1951,7 @@ static const struct net_protocol pim_protocol = {
  */
 static int __net_init ipmr_net_init(struct net *net)
 {
+	unsigned int i;
 	int err = 0;
 
 	net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device),
@@ -1971,13 +1963,18 @@ static int __net_init ipmr_net_init(struct net *net)
 
 	/* Forwarding cache */
 	net->ipv4.mfc_cache_array = kcalloc(MFC_LINES,
-					    sizeof(struct mfc_cache *),
+					    sizeof(struct list_head),
 					    GFP_KERNEL);
 	if (!net->ipv4.mfc_cache_array) {
 		err = -ENOMEM;
 		goto fail_mfc_cache;
 	}
 
+	for (i = 0; i < MFC_LINES; i++)
+		INIT_LIST_HEAD(&net->ipv4.mfc_cache_array[i]);
+
+	INIT_LIST_HEAD(&net->ipv4.mfc_unres_queue);
+
 	setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process,
 		    (unsigned long)net);
 
-- 
1.7.0.4

[PATCH 8/9] ipv4: ipmr: move mroute data into seperate structure

[Patrick McHardy]

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netns/ipv4.h |   13 +--
 net/ipv4/ipmr.c          |  369 +++++++++++++++++++++++++---------------------
 2 files changed, 200 insertions(+), 182 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 5d06429..72e762a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -59,18 +59,7 @@ struct netns_ipv4 {
 	atomic_t rt_genid;
 
 #ifdef CONFIG_IP_MROUTE
-	struct sock		*mroute_sk;
-	struct timer_list	ipmr_expire_timer;
-	struct list_head	mfc_unres_queue;
-	struct list_head	*mfc_cache_array;
-	struct vif_device	*vif_table;
-	int			maxvif;
-	atomic_t		cache_resolve_queue_len;
-	int			mroute_do_assert;
-	int			mroute_do_pim;
-#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
-	int			mroute_reg_vif_num;
-#endif
+	struct mr_table		*mrt;
 #endif
 };
 #endif
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 21b5edc..498f4e9 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -68,6 +68,21 @@
 #define CONFIG_IP_PIMSM	1
 #endif
 
+struct mr_table {
+	struct sock		*mroute_sk;
+	struct timer_list	ipmr_expire_timer;
+	struct list_head	mfc_unres_queue;
+	struct list_head	mfc_cache_array[MFC_LINES];
+	struct vif_device	vif_table[MAXVIFS];
+	int			maxvif;
+	atomic_t		cache_resolve_queue_len;
+	int			mroute_do_assert;
+	int			mroute_do_pim;
+#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
+	int			mroute_reg_vif_num;
+#endif
+};
+
 /* Big lock, protecting vif table, mrt cache and mroute socket state.
    Note that the changes are semaphored via rtnl_lock.
  */
@@ -78,7 +93,7 @@ static DEFINE_RWLOCK(mrt_lock);
  *	Multicast router control variables
  */
 
-#define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL)
+#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
 
 /* Special spinlock for queue of unresolved entries */
 static DEFINE_SPINLOCK(mfc_unres_lock);
@@ -93,11 +108,12 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
 
 static struct kmem_cache *mrt_cachep __read_mostly;
 
-static int ip_mr_forward(struct net *net, struct sk_buff *skb,
-			 struct mfc_cache *cache, int local);
-static int ipmr_cache_report(struct net *net,
+static int ip_mr_forward(struct net *net, struct mr_table *mrt,
+			 struct sk_buff *skb, struct mfc_cache *cache,
+			 int local);
+static int ipmr_cache_report(struct mr_table *mrt,
 			     struct sk_buff *pkt, vifi_t vifi, int assert);
-static int ipmr_fill_mroute(struct net *net, struct sk_buff *skb,
+static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			    struct mfc_cache *c, struct rtmsg *rtm);
 
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
@@ -199,12 +215,12 @@ failure:
 static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
 	dev->stats.tx_packets++;
-	ipmr_cache_report(net, skb, net->ipv4.mroute_reg_vif_num,
-			  IGMPMSG_WHOLEPKT);
+	ipmr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, IGMPMSG_WHOLEPKT);
 	read_unlock(&mrt_lock);
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
@@ -274,17 +290,17 @@ failure:
  *	@notify: Set to 1, if the caller is a notifier_call
  */
 
-static int vif_delete(struct net *net, int vifi, int notify,
+static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 		      struct list_head *head)
 {
 	struct vif_device *v;
 	struct net_device *dev;
 	struct in_device *in_dev;
 
-	if (vifi < 0 || vifi >= net->ipv4.maxvif)
+	if (vifi < 0 || vifi >= mrt->maxvif)
 		return -EADDRNOTAVAIL;
 
-	v = &net->ipv4.vif_table[vifi];
+	v = &mrt->vif_table[vifi];
 
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
@@ -296,17 +312,17 @@ static int vif_delete(struct net *net, int vifi, int notify,
 	}
 
 #ifdef CONFIG_IP_PIMSM
-	if (vifi == net->ipv4.mroute_reg_vif_num)
-		net->ipv4.mroute_reg_vif_num = -1;
+	if (vifi == mrt->mroute_reg_vif_num)
+		mrt->mroute_reg_vif_num = -1;
 #endif
 
-	if (vifi+1 == net->ipv4.maxvif) {
+	if (vifi+1 == mrt->maxvif) {
 		int tmp;
 		for (tmp=vifi-1; tmp>=0; tmp--) {
-			if (VIF_EXISTS(net, tmp))
+			if (VIF_EXISTS(mrt, tmp))
 				break;
 		}
-		net->ipv4.maxvif = tmp+1;
+		mrt->maxvif = tmp+1;
 	}
 
 	write_unlock_bh(&mrt_lock);
@@ -334,12 +350,13 @@ static inline void ipmr_cache_free(struct mfc_cache *c)
    and reporting error to netlink readers.
  */
 
-static void ipmr_destroy_unres(struct net *net, struct mfc_cache *c)
+static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
 {
+	struct net *net = NULL; //mrt->net;
 	struct sk_buff *skb;
 	struct nlmsgerr *e;
 
-	atomic_dec(&net->ipv4.cache_resolve_queue_len);
+	atomic_dec(&mrt->cache_resolve_queue_len);
 
 	while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) {
 		if (ip_hdr(skb)->version == 0) {
@@ -364,23 +381,23 @@ static void ipmr_destroy_unres(struct net *net, struct mfc_cache *c)
 
 static void ipmr_expire_process(unsigned long arg)
 {
-	struct net *net = (struct net *)arg;
+	struct mr_table *mrt = (struct mr_table *)arg;
 	unsigned long now;
 	unsigned long expires;
 	struct mfc_cache *c, *next;
 
 	if (!spin_trylock(&mfc_unres_lock)) {
-		mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10);
+		mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10);
 		return;
 	}
 
-	if (list_empty(&net->ipv4.mfc_unres_queue))
+	if (list_empty(&mrt->mfc_unres_queue))
 		goto out;
 
 	now = jiffies;
 	expires = 10*HZ;
 
-	list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) {
+	list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
 		if (time_after(c->mfc_un.unres.expires, now)) {
 			unsigned long interval = c->mfc_un.unres.expires - now;
 			if (interval < expires)
@@ -389,11 +406,11 @@ static void ipmr_expire_process(unsigned long arg)
 		}
 
 		list_del(&c->list);
-		ipmr_destroy_unres(net, c);
+		ipmr_destroy_unres(mrt, c);
 	}
 
-	if (!list_empty(&net->ipv4.mfc_unres_queue))
-		mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires);
+	if (!list_empty(&mrt->mfc_unres_queue))
+		mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
 
 out:
 	spin_unlock(&mfc_unres_lock);
@@ -401,7 +418,7 @@ out:
 
 /* Fill oifs list. It is called under write locked mrt_lock. */
 
-static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache,
+static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache,
 				   unsigned char *ttls)
 {
 	int vifi;
@@ -410,8 +427,8 @@ static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache,
 	cache->mfc_un.res.maxvif = 0;
 	memset(cache->mfc_un.res.ttls, 255, MAXVIFS);
 
-	for (vifi = 0; vifi < net->ipv4.maxvif; vifi++) {
-		if (VIF_EXISTS(net, vifi) &&
+	for (vifi = 0; vifi < mrt->maxvif; vifi++) {
+		if (VIF_EXISTS(mrt, vifi) &&
 		    ttls[vifi] && ttls[vifi] < 255) {
 			cache->mfc_un.res.ttls[vifi] = ttls[vifi];
 			if (cache->mfc_un.res.minvif > vifi)
@@ -422,16 +439,17 @@ static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache,
 	}
 }
 
-static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
+static int vif_add(struct net *net, struct mr_table *mrt,
+		   struct vifctl *vifc, int mrtsock)
 {
 	int vifi = vifc->vifc_vifi;
-	struct vif_device *v = &net->ipv4.vif_table[vifi];
+	struct vif_device *v = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct in_device *in_dev;
 	int err;
 
 	/* Is vif busy ? */
-	if (VIF_EXISTS(net, vifi))
+	if (VIF_EXISTS(mrt, vifi))
 		return -EADDRINUSE;
 
 	switch (vifc->vifc_flags) {
@@ -441,7 +459,7 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
 		 * Special Purpose VIF in PIM
 		 * All the packets will be sent to the daemon
 		 */
-		if (net->ipv4.mroute_reg_vif_num >= 0)
+		if (mrt->mroute_reg_vif_num >= 0)
 			return -EADDRINUSE;
 		dev = ipmr_reg_vif(net);
 		if (!dev)
@@ -519,22 +537,22 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
 	v->dev = dev;
 #ifdef CONFIG_IP_PIMSM
 	if (v->flags&VIFF_REGISTER)
-		net->ipv4.mroute_reg_vif_num = vifi;
+		mrt->mroute_reg_vif_num = vifi;
 #endif
-	if (vifi+1 > net->ipv4.maxvif)
-		net->ipv4.maxvif = vifi+1;
+	if (vifi+1 > mrt->maxvif)
+		mrt->maxvif = vifi+1;
 	write_unlock_bh(&mrt_lock);
 	return 0;
 }
 
-static struct mfc_cache *ipmr_cache_find(struct net *net,
+static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt,
 					 __be32 origin,
 					 __be32 mcastgrp)
 {
 	int line = MFC_HASH(mcastgrp, origin);
 	struct mfc_cache *c;
 
-	list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) {
+	list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
 		if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp)
 			return c;
 	}
@@ -567,8 +585,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void)
  *	A cache entry has gone into a resolved state from queued
  */
 
-static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc,
-			       struct mfc_cache *c)
+static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
+			       struct mfc_cache *uc, struct mfc_cache *c)
 {
 	struct sk_buff *skb;
 	struct nlmsgerr *e;
@@ -581,7 +599,7 @@ static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc,
 		if (ip_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
 
-			if (ipmr_fill_mroute(net, skb, c, NLMSG_DATA(nlh)) > 0) {
+			if (ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
 				nlh->nlmsg_len = (skb_tail_pointer(skb) -
 						  (u8 *)nlh);
 			} else {
@@ -595,7 +613,7 @@ static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc,
 
 			rtnl_unicast(skb, net, NETLINK_CB(skb).pid);
 		} else
-			ip_mr_forward(net, skb, c, 0);
+			ip_mr_forward(net, mrt, skb, c, 0);
 	}
 }
 
@@ -606,7 +624,7 @@ static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc,
  *	Called under mrt_lock.
  */
 
-static int ipmr_cache_report(struct net *net,
+static int ipmr_cache_report(struct mr_table *mrt,
 			     struct sk_buff *pkt, vifi_t vifi, int assert)
 {
 	struct sk_buff *skb;
@@ -639,7 +657,7 @@ static int ipmr_cache_report(struct net *net,
 		memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
 		msg->im_msgtype = IGMPMSG_WHOLEPKT;
 		msg->im_mbz = 0;
-		msg->im_vif = net->ipv4.mroute_reg_vif_num;
+		msg->im_vif = mrt->mroute_reg_vif_num;
 		ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
 		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
 					     sizeof(struct iphdr));
@@ -671,7 +689,7 @@ static int ipmr_cache_report(struct net *net,
 	skb->transport_header = skb->network_header;
 	}
 
-	if (net->ipv4.mroute_sk == NULL) {
+	if (mrt->mroute_sk == NULL) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -679,7 +697,7 @@ static int ipmr_cache_report(struct net *net,
 	/*
 	 *	Deliver to mrouted
 	 */
-	ret = sock_queue_rcv_skb(net->ipv4.mroute_sk, skb);
+	ret = sock_queue_rcv_skb(mrt->mroute_sk, skb);
 	if (ret < 0) {
 		if (net_ratelimit())
 			printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n");
@@ -694,7 +712,7 @@ static int ipmr_cache_report(struct net *net,
  */
 
 static int
-ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
+ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb)
 {
 	bool found = false;
 	int err;
@@ -702,7 +720,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 
 	spin_lock_bh(&mfc_unres_lock);
-	list_for_each_entry(c, &net->ipv4.mfc_unres_queue, list) {
+	list_for_each_entry(c, &mrt->mfc_unres_queue, list) {
 		if (c->mfc_mcastgrp == iph->daddr &&
 		    c->mfc_origin == iph->saddr) {
 			found = true;
@@ -715,7 +733,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 		 *	Create a new entry if allowable
 		 */
 
-		if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 ||
+		if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 ||
 		    (c = ipmr_cache_alloc_unres()) == NULL) {
 			spin_unlock_bh(&mfc_unres_lock);
 
@@ -733,7 +751,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 		/*
 		 *	Reflect first query at mrouted.
 		 */
-		err = ipmr_cache_report(net, skb, vifi, IGMPMSG_NOCACHE);
+		err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE);
 		if (err < 0) {
 			/* If the report failed throw the cache entry
 			   out - Brad Parker
@@ -745,10 +763,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 			return err;
 		}
 
-		atomic_inc(&net->ipv4.cache_resolve_queue_len);
-		list_add(&c->list, &net->ipv4.mfc_unres_queue);
+		atomic_inc(&mrt->cache_resolve_queue_len);
+		list_add(&c->list, &mrt->mfc_unres_queue);
 
-		mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires);
+		mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires);
 	}
 
 	/*
@@ -770,14 +788,14 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
  *	MFC cache manipulation by user space mroute daemon
  */
 
-static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
+static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
 {
 	int line;
 	struct mfc_cache *c, *next;
 
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
-	list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[line], list) {
+	list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) {
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
 		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
 			write_lock_bh(&mrt_lock);
@@ -791,7 +809,8 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
 	return -ENOENT;
 }
 
-static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
+static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
+			struct mfcctl *mfc, int mrtsock)
 {
 	bool found = false;
 	int line;
@@ -802,7 +821,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
-	list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) {
+	list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
 		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
 			found = true;
@@ -813,7 +832,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	if (found) {
 		write_lock_bh(&mrt_lock);
 		c->mfc_parent = mfc->mfcc_parent;
-		ipmr_update_thresholds(net, c, mfc->mfcc_ttls);
+		ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
@@ -830,12 +849,12 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	c->mfc_origin = mfc->mfcc_origin.s_addr;
 	c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr;
 	c->mfc_parent = mfc->mfcc_parent;
-	ipmr_update_thresholds(net, c, mfc->mfcc_ttls);
+	ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
 	if (!mrtsock)
 		c->mfc_flags |= MFC_STATIC;
 
 	write_lock_bh(&mrt_lock);
-	list_add(&c->list, &net->ipv4.mfc_cache_array[line]);
+	list_add(&c->list, &mrt->mfc_cache_array[line]);
 	write_unlock_bh(&mrt_lock);
 
 	/*
@@ -843,20 +862,20 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	 *	need to send on the frames and tidy up.
 	 */
 	spin_lock_bh(&mfc_unres_lock);
-	list_for_each_entry(uc, &net->ipv4.mfc_unres_queue, list) {
+	list_for_each_entry(uc, &mrt->mfc_unres_queue, list) {
 		if (uc->mfc_origin == c->mfc_origin &&
 		    uc->mfc_mcastgrp == c->mfc_mcastgrp) {
 			list_del(&uc->list);
-			atomic_dec(&net->ipv4.cache_resolve_queue_len);
+			atomic_dec(&mrt->cache_resolve_queue_len);
 			break;
 		}
 	}
-	if (list_empty(&net->ipv4.mfc_unres_queue))
-		del_timer(&net->ipv4.ipmr_expire_timer);
+	if (list_empty(&mrt->mfc_unres_queue))
+		del_timer(&mrt->ipmr_expire_timer);
 	spin_unlock_bh(&mfc_unres_lock);
 
 	if (uc) {
-		ipmr_cache_resolve(net, uc, c);
+		ipmr_cache_resolve(net, mrt, uc, c);
 		ipmr_cache_free(uc);
 	}
 	return 0;
@@ -866,7 +885,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct net *net)
+static void mroute_clean_tables(struct mr_table *mrt)
 {
 	int i;
 	LIST_HEAD(list);
@@ -875,9 +894,9 @@ static void mroute_clean_tables(struct net *net)
 	/*
 	 *	Shut down all active vif entries
 	 */
-	for (i = 0; i < net->ipv4.maxvif; i++) {
-		if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC))
-			vif_delete(net, i, 0, &list);
+	for (i = 0; i < mrt->maxvif; i++) {
+		if (!(mrt->vif_table[i].flags&VIFF_STATIC))
+			vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -885,7 +904,7 @@ static void mroute_clean_tables(struct net *net)
 	 *	Wipe the cache
 	 */
 	for (i = 0; i < MFC_LINES; i++) {
-		list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[i], list) {
+		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
 			if (c->mfc_flags&MFC_STATIC)
 				continue;
 			write_lock_bh(&mrt_lock);
@@ -896,11 +915,11 @@ static void mroute_clean_tables(struct net *net)
 		}
 	}
 
-	if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) {
+	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
 		spin_lock_bh(&mfc_unres_lock);
-		list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) {
+		list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
-			ipmr_destroy_unres(net, c);
+			ipmr_destroy_unres(mrt, c);
 		}
 		spin_unlock_bh(&mfc_unres_lock);
 	}
@@ -909,16 +928,17 @@ static void mroute_clean_tables(struct net *net)
 static void mrtsock_destruct(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	rtnl_lock();
-	if (sk == net->ipv4.mroute_sk) {
+	if (sk == mrt->mroute_sk) {
 		IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
 
 		write_lock_bh(&mrt_lock);
-		net->ipv4.mroute_sk = NULL;
+		mrt->mroute_sk = NULL;
 		write_unlock_bh(&mrt_lock);
 
-		mroute_clean_tables(net);
+		mroute_clean_tables(mrt);
 	}
 	rtnl_unlock();
 }
@@ -936,9 +956,10 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 	struct vifctl vif;
 	struct mfcctl mfc;
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	if (optname != MRT_INIT) {
-		if (sk != net->ipv4.mroute_sk && !capable(CAP_NET_ADMIN))
+		if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN))
 			return -EACCES;
 	}
 
@@ -951,7 +972,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 			return -ENOPROTOOPT;
 
 		rtnl_lock();
-		if (net->ipv4.mroute_sk) {
+		if (mrt->mroute_sk) {
 			rtnl_unlock();
 			return -EADDRINUSE;
 		}
@@ -959,7 +980,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		ret = ip_ra_control(sk, 1, mrtsock_destruct);
 		if (ret == 0) {
 			write_lock_bh(&mrt_lock);
-			net->ipv4.mroute_sk = sk;
+			mrt->mroute_sk = sk;
 			write_unlock_bh(&mrt_lock);
 
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
@@ -967,7 +988,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		rtnl_unlock();
 		return ret;
 	case MRT_DONE:
-		if (sk != net->ipv4.mroute_sk)
+		if (sk != mrt->mroute_sk)
 			return -EACCES;
 		return ip_ra_control(sk, 0, NULL);
 	case MRT_ADD_VIF:
@@ -980,9 +1001,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 			return -ENFILE;
 		rtnl_lock();
 		if (optname == MRT_ADD_VIF) {
-			ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk);
+			ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk);
 		} else {
-			ret = vif_delete(net, vif.vifc_vifi, 0, NULL);
+			ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL);
 		}
 		rtnl_unlock();
 		return ret;
@@ -999,9 +1020,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 			return -EFAULT;
 		rtnl_lock();
 		if (optname == MRT_DEL_MFC)
-			ret = ipmr_mfc_delete(net, &mfc);
+			ret = ipmr_mfc_delete(mrt, &mfc);
 		else
-			ret = ipmr_mfc_add(net, &mfc, sk == net->ipv4.mroute_sk);
+			ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk);
 		rtnl_unlock();
 		return ret;
 		/*
@@ -1012,7 +1033,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		int v;
 		if (get_user(v,(int __user *)optval))
 			return -EFAULT;
-		net->ipv4.mroute_do_assert = (v) ? 1 : 0;
+		mrt->mroute_do_assert = (v) ? 1 : 0;
 		return 0;
 	}
 #ifdef CONFIG_IP_PIMSM
@@ -1026,9 +1047,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 
 		rtnl_lock();
 		ret = 0;
-		if (v != net->ipv4.mroute_do_pim) {
-			net->ipv4.mroute_do_pim = v;
-			net->ipv4.mroute_do_assert = v;
+		if (v != mrt->mroute_do_pim) {
+			mrt->mroute_do_pim = v;
+			mrt->mroute_do_assert = v;
 		}
 		rtnl_unlock();
 		return ret;
@@ -1052,6 +1073,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 	int olr;
 	int val;
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	if (optname != MRT_VERSION &&
 #ifdef CONFIG_IP_PIMSM
@@ -1073,10 +1095,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 		val = 0x0305;
 #ifdef CONFIG_IP_PIMSM
 	else if (optname == MRT_PIM)
-		val = net->ipv4.mroute_do_pim;
+		val = mrt->mroute_do_pim;
 #endif
 	else
-		val = net->ipv4.mroute_do_assert;
+		val = mrt->mroute_do_assert;
 	if (copy_to_user(optval, &val, olr))
 		return -EFAULT;
 	return 0;
@@ -1093,16 +1115,17 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 	struct vif_device *vif;
 	struct mfc_cache *c;
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	switch (cmd) {
 	case SIOCGETVIFCNT:
 		if (copy_from_user(&vr, arg, sizeof(vr)))
 			return -EFAULT;
-		if (vr.vifi >= net->ipv4.maxvif)
+		if (vr.vifi >= mrt->maxvif)
 			return -EINVAL;
 		read_lock(&mrt_lock);
-		vif = &net->ipv4.vif_table[vr.vifi];
-		if (VIF_EXISTS(net, vr.vifi)) {
+		vif = &mrt->vif_table[vr.vifi];
+		if (VIF_EXISTS(mrt, vr.vifi)) {
 			vr.icount = vif->pkt_in;
 			vr.ocount = vif->pkt_out;
 			vr.ibytes = vif->bytes_in;
@@ -1120,7 +1143,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 			return -EFAULT;
 
 		read_lock(&mrt_lock);
-		c = ipmr_cache_find(net, sr.src.s_addr, sr.grp.s_addr);
+		c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
 		if (c) {
 			sr.pktcnt = c->mfc_un.res.pkt;
 			sr.bytecnt = c->mfc_un.res.bytes;
@@ -1143,16 +1166,17 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
 {
 	struct net_device *dev = ptr;
 	struct net *net = dev_net(dev);
+	struct mr_table *mrt = net->ipv4.mrt;
 	struct vif_device *v;
 	int ct;
 	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
-	v = &net->ipv4.vif_table[0];
-	for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) {
+	v = &mrt->vif_table[0];
+	for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 		if (v->dev == dev)
-			vif_delete(net, ct, 1, &list);
+			vif_delete(mrt, ct, 1, &list);
 	}
 	unregister_netdevice_many(&list);
 	return NOTIFY_DONE;
@@ -1211,11 +1235,11 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
  *	Processing handlers for ipmr_forward
  */
 
-static void ipmr_queue_xmit(struct net *net, struct sk_buff *skb,
-			    struct mfc_cache *c, int vifi)
+static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
+			    struct sk_buff *skb, struct mfc_cache *c, int vifi)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	struct vif_device *vif = &net->ipv4.vif_table[vifi];
+	struct vif_device *vif = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct rtable *rt;
 	int    encap = 0;
@@ -1229,7 +1253,7 @@ static void ipmr_queue_xmit(struct net *net, struct sk_buff *skb,
 		vif->bytes_out += skb->len;
 		vif->dev->stats.tx_bytes += skb->len;
 		vif->dev->stats.tx_packets++;
-		ipmr_cache_report(net, skb, vifi, IGMPMSG_WHOLEPKT);
+		ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT);
 		goto out_free;
 	}
 #endif
@@ -1312,12 +1336,12 @@ out_free:
 	return;
 }
 
-static int ipmr_find_vif(struct net_device *dev)
+static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev)
 {
-	struct net *net = dev_net(dev);
 	int ct;
-	for (ct = net->ipv4.maxvif-1; ct >= 0; ct--) {
-		if (net->ipv4.vif_table[ct].dev == dev)
+
+	for (ct = mrt->maxvif-1; ct >= 0; ct--) {
+		if (mrt->vif_table[ct].dev == dev)
 			break;
 	}
 	return ct;
@@ -1325,8 +1349,9 @@ static int ipmr_find_vif(struct net_device *dev)
 
 /* "local" means that we should preserve one skb (for local delivery) */
 
-static int ip_mr_forward(struct net *net, struct sk_buff *skb,
-			 struct mfc_cache *cache, int local)
+static int ip_mr_forward(struct net *net, struct mr_table *mrt,
+			 struct sk_buff *skb, struct mfc_cache *cache,
+			 int local)
 {
 	int psend = -1;
 	int vif, ct;
@@ -1338,7 +1363,7 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb,
 	/*
 	 * Wrong interface: drop packet and (maybe) send PIM assert.
 	 */
-	if (net->ipv4.vif_table[vif].dev != skb->dev) {
+	if (mrt->vif_table[vif].dev != skb->dev) {
 		int true_vifi;
 
 		if (skb_rtable(skb)->fl.iif == 0) {
@@ -1357,26 +1382,26 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb,
 		}
 
 		cache->mfc_un.res.wrong_if++;
-		true_vifi = ipmr_find_vif(skb->dev);
+		true_vifi = ipmr_find_vif(mrt, skb->dev);
 
-		if (true_vifi >= 0 && net->ipv4.mroute_do_assert &&
+		if (true_vifi >= 0 && mrt->mroute_do_assert &&
 		    /* pimsm uses asserts, when switching from RPT to SPT,
 		       so that we cannot check that packet arrived on an oif.
 		       It is bad, but otherwise we would need to move pretty
 		       large chunk of pimd to kernel. Ough... --ANK
 		     */
-		    (net->ipv4.mroute_do_pim ||
+		    (mrt->mroute_do_pim ||
 		     cache->mfc_un.res.ttls[true_vifi] < 255) &&
 		    time_after(jiffies,
 			       cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
 			cache->mfc_un.res.last_assert = jiffies;
-			ipmr_cache_report(net, skb, true_vifi, IGMPMSG_WRONGVIF);
+			ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF);
 		}
 		goto dont_forward;
 	}
 
-	net->ipv4.vif_table[vif].pkt_in++;
-	net->ipv4.vif_table[vif].bytes_in += skb->len;
+	mrt->vif_table[vif].pkt_in++;
+	mrt->vif_table[vif].bytes_in += skb->len;
 
 	/*
 	 *	Forward the frame
@@ -1386,7 +1411,8 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb,
 			if (psend != -1) {
 				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 				if (skb2)
-					ipmr_queue_xmit(net, skb2, cache, psend);
+					ipmr_queue_xmit(net, mrt, skb2, cache,
+							psend);
 			}
 			psend = ct;
 		}
@@ -1395,9 +1421,9 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb,
 		if (local) {
 			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 			if (skb2)
-				ipmr_queue_xmit(net, skb2, cache, psend);
+				ipmr_queue_xmit(net, mrt, skb2, cache, psend);
 		} else {
-			ipmr_queue_xmit(net, skb, cache, psend);
+			ipmr_queue_xmit(net, mrt, skb, cache, psend);
 			return 0;
 		}
 	}
@@ -1417,6 +1443,7 @@ int ip_mr_input(struct sk_buff *skb)
 {
 	struct mfc_cache *cache;
 	struct net *net = dev_net(skb->dev);
+	struct mr_table *mrt = net->ipv4.mrt;
 	int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
 
 	/* Packet is looped back after forward, it should not be
@@ -1437,9 +1464,9 @@ int ip_mr_input(struct sk_buff *skb)
 			       that we can forward NO IGMP messages.
 			     */
 			    read_lock(&mrt_lock);
-			    if (net->ipv4.mroute_sk) {
+			    if (mrt->mroute_sk) {
 				    nf_reset(skb);
-				    raw_rcv(net->ipv4.mroute_sk, skb);
+				    raw_rcv(mrt->mroute_sk, skb);
 				    read_unlock(&mrt_lock);
 				    return 0;
 			    }
@@ -1448,7 +1475,7 @@ int ip_mr_input(struct sk_buff *skb)
 	}
 
 	read_lock(&mrt_lock);
-	cache = ipmr_cache_find(net, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
+	cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
 
 	/*
 	 *	No usable cache entry
@@ -1466,9 +1493,9 @@ int ip_mr_input(struct sk_buff *skb)
 			skb = skb2;
 		}
 
-		vif = ipmr_find_vif(skb->dev);
+		vif = ipmr_find_vif(mrt, skb->dev);
 		if (vif >= 0) {
-			int err = ipmr_cache_unresolved(net, vif, skb);
+			int err = ipmr_cache_unresolved(mrt, vif, skb);
 			read_unlock(&mrt_lock);
 
 			return err;
@@ -1478,7 +1505,7 @@ int ip_mr_input(struct sk_buff *skb)
 		return -ENODEV;
 	}
 
-	ip_mr_forward(net, skb, cache, local);
+	ip_mr_forward(net, mrt, skb, cache, local);
 
 	read_unlock(&mrt_lock);
 
@@ -1500,6 +1527,7 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
 	struct net_device *reg_dev = NULL;
 	struct iphdr *encap;
 	struct net *net = dev_net(skb->dev);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	encap = (struct iphdr *)(skb_transport_header(skb) + pimlen);
 	/*
@@ -1514,8 +1542,8 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
 		return 1;
 
 	read_lock(&mrt_lock);
-	if (net->ipv4.mroute_reg_vif_num >= 0)
-		reg_dev = net->ipv4.vif_table[net->ipv4.mroute_reg_vif_num].dev;
+	if (mrt->mroute_reg_vif_num >= 0)
+		reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev;
 	if (reg_dev)
 		dev_hold(reg_dev);
 	read_unlock(&mrt_lock);
@@ -1550,13 +1578,14 @@ int pim_rcv_v1(struct sk_buff * skb)
 {
 	struct igmphdr *pim;
 	struct net *net = dev_net(skb->dev);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
 		goto drop;
 
 	pim = igmp_hdr(skb);
 
-	if (!net->ipv4.mroute_do_pim ||
+	if (!mrt->mroute_do_pim ||
 	    pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER)
 		goto drop;
 
@@ -1592,7 +1621,7 @@ drop:
 #endif
 
 static int
-ipmr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc_cache *c,
+ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c,
 		 struct rtmsg *rtm)
 {
 	int ct;
@@ -1604,19 +1633,19 @@ ipmr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc_cache *c,
 	if (c->mfc_parent > MAXVIFS)
 		return -ENOENT;
 
-	if (VIF_EXISTS(net, c->mfc_parent))
-		RTA_PUT(skb, RTA_IIF, 4, &net->ipv4.vif_table[c->mfc_parent].dev->ifindex);
+	if (VIF_EXISTS(mrt, c->mfc_parent))
+		RTA_PUT(skb, RTA_IIF, 4, &mrt->vif_table[c->mfc_parent].dev->ifindex);
 
 	mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0));
 
 	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
-		if (VIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) {
+		if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
 			if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
 				goto rtattr_failure;
 			nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
 			nhp->rtnh_flags = 0;
 			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
-			nhp->rtnh_ifindex = net->ipv4.vif_table[ct].dev->ifindex;
+			nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex;
 			nhp->rtnh_len = sizeof(*nhp);
 		}
 	}
@@ -1634,11 +1663,12 @@ int ipmr_get_route(struct net *net,
 		   struct sk_buff *skb, struct rtmsg *rtm, int nowait)
 {
 	int err;
+	struct mr_table *mrt = net->ipv4.mrt;
 	struct mfc_cache *cache;
 	struct rtable *rt = skb_rtable(skb);
 
 	read_lock(&mrt_lock);
-	cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst);
+	cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst);
 
 	if (cache == NULL) {
 		struct sk_buff *skb2;
@@ -1652,7 +1682,7 @@ int ipmr_get_route(struct net *net,
 		}
 
 		dev = skb->dev;
-		if (dev == NULL || (vif = ipmr_find_vif(dev)) < 0) {
+		if (dev == NULL || (vif = ipmr_find_vif(mrt, dev)) < 0) {
 			read_unlock(&mrt_lock);
 			return -ENODEV;
 		}
@@ -1669,14 +1699,14 @@ int ipmr_get_route(struct net *net,
 		iph->saddr = rt->rt_src;
 		iph->daddr = rt->rt_dst;
 		iph->version = 0;
-		err = ipmr_cache_unresolved(net, vif, skb2);
+		err = ipmr_cache_unresolved(mrt, vif, skb2);
 		read_unlock(&mrt_lock);
 		return err;
 	}
 
 	if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
 		cache->mfc_flags |= MFC_NOTIFY;
-	err = ipmr_fill_mroute(net, skb, cache, rtm);
+	err = ipmr_fill_mroute(mrt, skb, cache, rtm);
 	read_unlock(&mrt_lock);
 	return err;
 }
@@ -1694,11 +1724,13 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net,
 					   struct ipmr_vif_iter *iter,
 					   loff_t pos)
 {
-	for (iter->ct = 0; iter->ct < net->ipv4.maxvif; ++iter->ct) {
-		if (!VIF_EXISTS(net, iter->ct))
+	struct mr_table *mrt = net->ipv4.mrt;
+
+	for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
+		if (!VIF_EXISTS(mrt, iter->ct))
 			continue;
 		if (pos-- == 0)
-			return &net->ipv4.vif_table[iter->ct];
+			return &mrt->vif_table[iter->ct];
 	}
 	return NULL;
 }
@@ -1717,15 +1749,16 @@ static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ipmr_vif_iter *iter = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
 		return ipmr_vif_seq_idx(net, iter, 0);
 
-	while (++iter->ct < net->ipv4.maxvif) {
-		if (!VIF_EXISTS(net, iter->ct))
+	while (++iter->ct < mrt->maxvif) {
+		if (!VIF_EXISTS(mrt, iter->ct))
 			continue;
-		return &net->ipv4.vif_table[iter->ct];
+		return &mrt->vif_table[iter->ct];
 	}
 	return NULL;
 }
@@ -1739,6 +1772,7 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
 static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -1749,7 +1783,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
 
 		seq_printf(seq,
 			   "%2Zd %-10s %8ld %7ld  %8ld %7ld %05X %08X %08X\n",
-			   vif - net->ipv4.vif_table,
+			   vif - mrt->vif_table,
 			   name, vif->bytes_in, vif->pkt_in,
 			   vif->bytes_out, vif->pkt_out,
 			   vif->flags, vif->local, vif->remote);
@@ -1788,11 +1822,12 @@ struct ipmr_mfc_iter {
 static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
 					  struct ipmr_mfc_iter *it, loff_t pos)
 {
+	struct mr_table *mrt = net->ipv4.mrt;
 	struct mfc_cache *mfc;
 
 	read_lock(&mrt_lock);
 	for (it->ct = 0; it->ct < MFC_LINES; it->ct++) {
-		it->cache = &net->ipv4.mfc_cache_array[it->ct];
+		it->cache = &mrt->mfc_cache_array[it->ct];
 		list_for_each_entry(mfc, it->cache, list)
 			if (pos-- == 0)
 				return mfc;
@@ -1800,7 +1835,7 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
 	read_unlock(&mrt_lock);
 
 	spin_lock_bh(&mfc_unres_lock);
-	it->cache = &net->ipv4.mfc_unres_queue;
+	it->cache = &mrt->mfc_unres_queue;
 	list_for_each_entry(mfc, it->cache, list)
 		if (pos-- == 0)
 			return mfc;
@@ -1827,6 +1862,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct mfc_cache *mfc = v;
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	++*pos;
 
@@ -1836,13 +1872,13 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (mfc->list.next != it->cache)
 		return list_entry(mfc->list.next, struct mfc_cache, list);
 
-	if (it->cache == &net->ipv4.mfc_unres_queue)
+	if (it->cache == &mrt->mfc_unres_queue)
 		goto end_of_list;
 
-	BUG_ON(it->cache != &net->ipv4.mfc_cache_array[it->ct]);
+	BUG_ON(it->cache != &mrt->mfc_cache_array[it->ct]);
 
 	while (++it->ct < MFC_LINES) {
-		it->cache = &net->ipv4.mfc_cache_array[it->ct];
+		it->cache = &mrt->mfc_cache_array[it->ct];
 		if (list_empty(it->cache))
 			continue;
 		return list_first_entry(it->cache, struct mfc_cache, list);
@@ -1850,7 +1886,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 	/* exhausted cache_array, show unresolved */
 	read_unlock(&mrt_lock);
-	it->cache = &net->ipv4.mfc_unres_queue;
+	it->cache = &mrt->mfc_unres_queue;
 	it->ct = 0;
 
 	spin_lock_bh(&mfc_unres_lock);
@@ -1868,10 +1904,11 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 {
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = net->ipv4.mrt;
 
-	if (it->cache == &net->ipv4.mfc_unres_queue)
+	if (it->cache == &mrt->mfc_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == &net->ipv4.mfc_cache_array[it->ct])
+	else if (it->cache == &mrt->mfc_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
@@ -1879,6 +1916,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
 {
 	int n;
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = net->ipv4.mrt;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -1892,14 +1930,14 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
 			   (unsigned long) mfc->mfc_origin,
 			   mfc->mfc_parent);
 
-		if (it->cache != &net->ipv4.mfc_unres_queue) {
+		if (it->cache != &mrt->mfc_unres_queue) {
 			seq_printf(seq, " %8lu %8lu %8lu",
 				   mfc->mfc_un.res.pkt,
 				   mfc->mfc_un.res.bytes,
 				   mfc->mfc_un.res.wrong_if);
 			for (n = mfc->mfc_un.res.minvif;
 			     n < mfc->mfc_un.res.maxvif; n++ ) {
-				if (VIF_EXISTS(net, n) &&
+				if (VIF_EXISTS(mrt, n) &&
 				    mfc->mfc_un.res.ttls[n] < 255)
 					seq_printf(seq,
 					   " %2d:%-3d",
@@ -1951,35 +1989,27 @@ static const struct net_protocol pim_protocol = {
  */
 static int __net_init ipmr_net_init(struct net *net)
 {
+	struct mr_table *mrt;
 	unsigned int i;
 	int err = 0;
 
-	net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device),
-				      GFP_KERNEL);
-	if (!net->ipv4.vif_table) {
+	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
+	if (mrt == NULL) {
 		err = -ENOMEM;
 		goto fail;
 	}
 
 	/* Forwarding cache */
-	net->ipv4.mfc_cache_array = kcalloc(MFC_LINES,
-					    sizeof(struct list_head),
-					    GFP_KERNEL);
-	if (!net->ipv4.mfc_cache_array) {
-		err = -ENOMEM;
-		goto fail_mfc_cache;
-	}
-
 	for (i = 0; i < MFC_LINES; i++)
-		INIT_LIST_HEAD(&net->ipv4.mfc_cache_array[i]);
+		INIT_LIST_HEAD(&mrt->mfc_cache_array[i]);
 
-	INIT_LIST_HEAD(&net->ipv4.mfc_unres_queue);
+	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
 
-	setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process,
+	setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
 		    (unsigned long)net);
 
 #ifdef CONFIG_IP_PIMSM
-	net->ipv4.mroute_reg_vif_num = -1;
+	mrt->mroute_reg_vif_num = -1;
 #endif
 
 #ifdef CONFIG_PROC_FS
@@ -1989,16 +2019,16 @@ static int __net_init ipmr_net_init(struct net *net)
 	if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops))
 		goto proc_cache_fail;
 #endif
+
+	net->ipv4.mrt = mrt;
 	return 0;
 
 #ifdef CONFIG_PROC_FS
 proc_cache_fail:
 	proc_net_remove(net, "ip_mr_vif");
 proc_vif_fail:
-	kfree(net->ipv4.mfc_cache_array);
+	kfree(mrt);
 #endif
-fail_mfc_cache:
-	kfree(net->ipv4.vif_table);
 fail:
 	return err;
 }
@@ -2009,8 +2039,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	proc_net_remove(net, "ip_mr_cache");
 	proc_net_remove(net, "ip_mr_vif");
 #endif
-	kfree(net->ipv4.mfc_cache_array);
-	kfree(net->ipv4.vif_table);
+	kfree(net->ipv4.mrt);
 }
 
 static struct pernet_operations ipmr_net_ops = {
-- 
1.7.0.4

[PATCH 9/9] ipv4: ipmr: support multiple tables

[Patrick McHardy]

This patch adds support for multiple independant multicast routing instances,
named "tables".

Userspace multicast routing daemons can bind to a specific table instance by
issuing a setsockopt call using a new option MRT_TABLE. The table number is
stored in the raw socket data and affects all following ipmr setsockopt(),
getsockopt() and ioctl() calls. By default, a single table (RT_TABLE_DEFAULT)
is created with a default routing rule pointing to it. Newly created pimreg
devices have the table number appended ("pimregX"), with the exception of
devices created in the default table, which are named just "pimreg" for
compatibility reasons.

Packets are directed to a specific table instance using routing rules,
similar to how regular routing rules work. Currently iif, oif and mark
are supported as keys, source and destination addresses could be supported
additionally.

Example usage:

- bind pimd/xorp/... to a specific table:

uint32_t table = 123;
setsockopt(fd, IPPROTO_IP, MRT_TABLE, &table, sizeof(table));

- create routing rules directing packets to the new table:

# ip mrule add iif eth0 lookup 123
# ip mrule add oif eth0 lookup 123

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/fib_rules.h |    1 +
 include/linux/mroute.h    |    3 +-
 include/net/netns/ipv4.h  |    5 +
 include/net/raw.h         |    1 +
 net/ipv4/Kconfig          |   14 ++
 net/ipv4/ipmr.c           |  399 ++++++++++++++++++++++++++++++++++++++-------
 6 files changed, 361 insertions(+), 62 deletions(-)

diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h
index 405e411..04a3976 100644
--- a/include/linux/fib_rules.h
+++ b/include/linux/fib_rules.h
@@ -21,6 +21,7 @@
 #define FIB_RULES_IPV4		AF_INET
 #define FIB_RULES_IPV6		AF_INET6
 #define FIB_RULES_DECNET	AF_DECnet
+#define FIB_RULES_IPMR		128
 
 struct fib_rule_hdr {
 	__u8		family;
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 7ff6c77..fa04b24 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -27,7 +27,8 @@
 #define MRT_DEL_MFC	(MRT_BASE+5)	/* Delete a multicast forwarding entry	*/
 #define MRT_VERSION	(MRT_BASE+6)	/* Get the kernel multicast version	*/
 #define MRT_ASSERT	(MRT_BASE+7)	/* Activate PIM assert mode		*/
-#define MRT_PIM		(MRT_BASE+8)	/* enable PIM code	*/
+#define MRT_PIM		(MRT_BASE+8)	/* enable PIM code			*/
+#define MRT_TABLE	(MRT_BASE+9)	/* Specify mroute table ID		*/
 
 #define SIOCGETVIFCNT	SIOCPROTOPRIVATE	/* IP protocol privates */
 #define SIOCGETSGCNT	(SIOCPROTOPRIVATE+1)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 72e762a..ae07fee 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -59,7 +59,12 @@ struct netns_ipv4 {
 	atomic_t rt_genid;
 
 #ifdef CONFIG_IP_MROUTE
+#ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES
 	struct mr_table		*mrt;
+#else
+	struct list_head	mr_tables;
+	struct fib_rules_ops	*mr_rules_ops;
+#endif
 #endif
 };
 #endif
diff --git a/include/net/raw.h b/include/net/raw.h
index 67cc643..43c5750 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -61,6 +61,7 @@ struct raw_sock {
 	/* inet_sock has to be the first member */
 	struct inet_sock   inet;
 	struct icmp_filter filter;
+	u32		   ipmr_table;
 };
 
 static inline struct raw_sock *raw_sk(const struct sock *sk)
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index c9a1c68..be59774 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -250,6 +250,20 @@ config IP_MROUTE
 	  <file:Documentation/networking/multicast.txt>. If you haven't heard
 	  about it, you don't need it.
 
+config IP_MROUTE_MULTIPLE_TABLES
+	bool "IP: multicast policy routing"
+	depends on IP_ADVANCED_ROUTER
+	select FIB_RULES
+	help
+	  Normally, a multicast router runs a userspace daemon and decides
+	  what to do with a multicast packet based on the source and
+	  destination addresses. If you say Y here, the multicast router
+	  will also be able to take interfaces and packet marks into
+	  account and run multiple instances of userspace daemons
+	  simultaneously, each one handling a single table.
+
+	  If unsure, say N.
+
 config IP_PIMSM_V1
 	bool "IP: PIM-SM version 1 support"
 	depends on IP_MROUTE
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 498f4e9..5df5fd7 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -63,12 +63,15 @@
 #include <net/ipip.h>
 #include <net/checksum.h>
 #include <net/netlink.h>
+#include <net/fib_rules.h>
 
 #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
 #define CONFIG_IP_PIMSM	1
 #endif
 
 struct mr_table {
+	struct list_head	list;
+	u32			id;
 	struct sock		*mroute_sk;
 	struct timer_list	ipmr_expire_timer;
 	struct list_head	mfc_unres_queue;
@@ -83,6 +86,14 @@ struct mr_table {
 #endif
 };
 
+struct ipmr_rule {
+	struct fib_rule		common;
+};
+
+struct ipmr_result {
+	struct mr_table		*mrt;
+};
+
 /* Big lock, protecting vif table, mrt cache and mroute socket state.
    Note that the changes are semaphored via rtnl_lock.
  */
@@ -108,6 +119,7 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
 
 static struct kmem_cache *mrt_cachep __read_mostly;
 
+static struct mr_table *ipmr_new_table(struct net *net, u32 id);
 static int ip_mr_forward(struct net *net, struct mr_table *mrt,
 			 struct sk_buff *skb, struct mfc_cache *cache,
 			 int local);
@@ -115,6 +127,206 @@ static int ipmr_cache_report(struct mr_table *mrt,
 			     struct sk_buff *pkt, vifi_t vifi, int assert);
 static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			    struct mfc_cache *c, struct rtmsg *rtm);
+static void ipmr_expire_process(unsigned long arg);
+
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+#define ipmr_for_each_table(mrt, net) \
+	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
+
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+	struct mr_table *mrt;
+
+	ipmr_for_each_table(mrt, net) {
+		if (mrt->id == id)
+			return mrt;
+	}
+	return NULL;
+}
+
+static int ipmr_fib_lookup(struct net *net, struct flowi *flp,
+			   struct mr_table **mrt)
+{
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = { .result = &res, };
+	int err;
+
+	err = fib_rules_lookup(net->ipv4.mr_rules_ops, flp, 0, &arg);
+	if (err < 0)
+		return err;
+	*mrt = res.mrt;
+	return 0;
+}
+
+static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp,
+			    int flags, struct fib_lookup_arg *arg)
+{
+	struct ipmr_result *res = arg->result;
+	struct mr_table *mrt;
+
+	switch (rule->action) {
+	case FR_ACT_TO_TBL:
+		break;
+	case FR_ACT_UNREACHABLE:
+		return -ENETUNREACH;
+	case FR_ACT_PROHIBIT:
+		return -EACCES;
+	case FR_ACT_BLACKHOLE:
+	default:
+		return -EINVAL;
+	}
+
+	mrt = ipmr_get_table(rule->fr_net, rule->table);
+	if (mrt == NULL)
+		return -EAGAIN;
+	res->mrt = mrt;
+	return 0;
+}
+
+static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
+{
+	return 1;
+}
+
+static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = {
+	FRA_GENERIC_POLICY,
+};
+
+static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+			       struct fib_rule_hdr *frh, struct nlattr **tb)
+{
+	return 0;
+}
+
+static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+			     struct nlattr **tb)
+{
+	return 1;
+}
+
+static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+			  struct fib_rule_hdr *frh)
+{
+	frh->dst_len = 0;
+	frh->src_len = 0;
+	frh->tos     = 0;
+	return 0;
+}
+
+static struct fib_rules_ops ipmr_rules_ops_template = {
+	.family		= FIB_RULES_IPMR,
+	.rule_size	= sizeof(struct ipmr_rule),
+	.addr_size	= sizeof(u32),
+	.action		= ipmr_rule_action,
+	.match		= ipmr_rule_match,
+	.configure	= ipmr_rule_configure,
+	.compare	= ipmr_rule_compare,
+	.default_pref	= fib_default_rule_pref,
+	.fill		= ipmr_rule_fill,
+	.nlgroup	= RTNLGRP_IPV4_RULE,
+	.policy		= ipmr_rule_policy,
+	.owner		= THIS_MODULE,
+};
+
+static int __net_init ipmr_rules_init(struct net *net)
+{
+	struct fib_rules_ops *ops;
+	struct mr_table *mrt;
+	int err;
+
+	ops = fib_rules_register(&ipmr_rules_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	INIT_LIST_HEAD(&net->ipv4.mr_tables);
+
+	mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
+	if (mrt == NULL) {
+		err = -ENOMEM;
+		goto err1;
+	}
+
+	err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0);
+	if (err < 0)
+		goto err2;
+
+	net->ipv4.mr_rules_ops = ops;
+	return 0;
+
+err2:
+	kfree(mrt);
+err1:
+	fib_rules_unregister(ops);
+	return err;
+}
+
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+	struct mr_table *mrt, *next;
+
+	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list)
+		kfree(mrt);
+	fib_rules_unregister(net->ipv4.mr_rules_ops);
+}
+#else
+#define ipmr_for_each_table(mrt, net) \
+	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
+
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+	return net->ipv4.mrt;
+}
+
+static int ipmr_fib_lookup(struct net *net, struct flowi *flp,
+			   struct mr_table **mrt)
+{
+	*mrt = net->ipv4.mrt;
+	return 0;
+}
+
+static int __net_init ipmr_rules_init(struct net *net)
+{
+	net->ipv4.mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
+	return net->ipv4.mrt ? 0 : -ENOMEM;
+}
+
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+	kfree(net->ipv4.mrt);
+}
+#endif
+
+static struct mr_table *ipmr_new_table(struct net *net, u32 id)
+{
+	struct mr_table *mrt;
+	unsigned int i;
+
+	mrt = ipmr_get_table(net, id);
+	if (mrt != NULL)
+		return mrt;
+
+	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
+	if (mrt == NULL)
+		return NULL;
+	mrt->id = id;
+
+	/* Forwarding cache */
+	for (i = 0; i < MFC_LINES; i++)
+		INIT_LIST_HEAD(&mrt->mfc_cache_array[i]);
+
+	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
+
+	setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
+		    (unsigned long)mrt);
+
+#ifdef CONFIG_IP_PIMSM
+	mrt->mroute_reg_vif_num = -1;
+#endif
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+	list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables);
+#endif
+	return mrt;
+}
 
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
 
@@ -215,7 +427,17 @@ failure:
 static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
+	struct flowi fl = {
+		.oif		= dev->ifindex,
+		.iif		= skb->skb_iif,
+		.mark		= skb->mark,
+	};
+	int err;
+
+	err = ipmr_fib_lookup(net, &fl, &mrt);
+	if (err < 0)
+		return err;
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
@@ -240,12 +462,18 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
-static struct net_device *ipmr_reg_vif(struct net *net)
+static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 {
 	struct net_device *dev;
 	struct in_device *in_dev;
+	char name[IFNAMSIZ];
+
+	if (mrt->id == RT_TABLE_DEFAULT)
+		sprintf(name, "pimreg");
+	else
+		sprintf(name, "pimreg%u", mrt->id);
 
-	dev = alloc_netdev(0, "pimreg", reg_vif_setup);
+	dev = alloc_netdev(0, name, reg_vif_setup);
 
 	if (dev == NULL)
 		return NULL;
@@ -461,7 +689,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		 */
 		if (mrt->mroute_reg_vif_num >= 0)
 			return -EADDRINUSE;
-		dev = ipmr_reg_vif(net);
+		dev = ipmr_reg_vif(net, mrt);
 		if (!dev)
 			return -ENOBUFS;
 		err = dev_set_allmulti(dev, 1);
@@ -928,17 +1156,19 @@ static void mroute_clean_tables(struct mr_table *mrt)
 static void mrtsock_destruct(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
 
 	rtnl_lock();
-	if (sk == mrt->mroute_sk) {
-		IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
+	ipmr_for_each_table(mrt, net) {
+		if (sk == mrt->mroute_sk) {
+			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
 
-		write_lock_bh(&mrt_lock);
-		mrt->mroute_sk = NULL;
-		write_unlock_bh(&mrt_lock);
+			write_lock_bh(&mrt_lock);
+			mrt->mroute_sk = NULL;
+			write_unlock_bh(&mrt_lock);
 
-		mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt);
+		}
 	}
 	rtnl_unlock();
 }
@@ -956,7 +1186,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 	struct vifctl vif;
 	struct mfcctl mfc;
 	struct net *net = sock_net(sk);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
 
 	if (optname != MRT_INIT) {
 		if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN))
@@ -1055,6 +1289,27 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		return ret;
 	}
 #endif
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+	case MRT_TABLE:
+	{
+		u32 v;
+
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+		if (get_user(v, (u32 __user *)optval))
+			return -EFAULT;
+		if (sk == mrt->mroute_sk)
+			return -EBUSY;
+
+		rtnl_lock();
+		ret = 0;
+		if (!ipmr_new_table(net, v))
+			ret = -ENOMEM;
+		raw_sk(sk)->ipmr_table = v;
+		rtnl_unlock();
+		return ret;
+	}
+#endif
 	/*
 	 *	Spurious command, or MRT_VERSION which you cannot
 	 *	set.
@@ -1073,7 +1328,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 	int olr;
 	int val;
 	struct net *net = sock_net(sk);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
 
 	if (optname != MRT_VERSION &&
 #ifdef CONFIG_IP_PIMSM
@@ -1115,7 +1374,11 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 	struct vif_device *vif;
 	struct mfc_cache *c;
 	struct net *net = sock_net(sk);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
 
 	switch (cmd) {
 	case SIOCGETVIFCNT:
@@ -1166,17 +1429,20 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
 {
 	struct net_device *dev = ptr;
 	struct net *net = dev_net(dev);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
 	struct vif_device *v;
 	int ct;
 	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
-	v = &mrt->vif_table[0];
-	for (ct = 0; ct < mrt->maxvif; ct++, v++) {
-		if (v->dev == dev)
-			vif_delete(mrt, ct, 1, &list);
+
+	ipmr_for_each_table(mrt, net) {
+		v = &mrt->vif_table[0];
+		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
+			if (v->dev == dev)
+				vif_delete(mrt, ct, 1, &list);
+		}
 	}
 	unregister_netdevice_many(&list);
 	return NOTIFY_DONE;
@@ -1443,8 +1709,9 @@ int ip_mr_input(struct sk_buff *skb)
 {
 	struct mfc_cache *cache;
 	struct net *net = dev_net(skb->dev);
-	struct mr_table *mrt = net->ipv4.mrt;
 	int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
+	struct mr_table *mrt;
+	int err;
 
 	/* Packet is looped back after forward, it should not be
 	   forwarded second time, but still can be delivered locally.
@@ -1452,6 +1719,10 @@ int ip_mr_input(struct sk_buff *skb)
 	if (IPCB(skb)->flags&IPSKB_FORWARDED)
 		goto dont_forward;
 
+	err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt);
+	if (err < 0)
+		return err;
+
 	if (!local) {
 		    if (IPCB(skb)->opt.router_alert) {
 			    if (ip_call_ra_chain(skb))
@@ -1522,12 +1793,11 @@ dont_forward:
 }
 
 #ifdef CONFIG_IP_PIMSM
-static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
+static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb,
+		     unsigned int pimlen)
 {
 	struct net_device *reg_dev = NULL;
 	struct iphdr *encap;
-	struct net *net = dev_net(skb->dev);
-	struct mr_table *mrt = net->ipv4.mrt;
 
 	encap = (struct iphdr *)(skb_transport_header(skb) + pimlen);
 	/*
@@ -1578,18 +1848,21 @@ int pim_rcv_v1(struct sk_buff * skb)
 {
 	struct igmphdr *pim;
 	struct net *net = dev_net(skb->dev);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
 
 	if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
 		goto drop;
 
 	pim = igmp_hdr(skb);
 
+	if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0)
+		goto drop;
+
 	if (!mrt->mroute_do_pim ||
 	    pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER)
 		goto drop;
 
-	if (__pim_rcv(skb, sizeof(*pim))) {
+	if (__pim_rcv(mrt, skb, sizeof(*pim))) {
 drop:
 		kfree_skb(skb);
 	}
@@ -1601,6 +1874,8 @@ drop:
 static int pim_rcv(struct sk_buff * skb)
 {
 	struct pimreghdr *pim;
+	struct net *net = dev_net(skb->dev);
+	struct mr_table *mrt;
 
 	if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
 		goto drop;
@@ -1612,7 +1887,10 @@ static int pim_rcv(struct sk_buff * skb)
 	     csum_fold(skb_checksum(skb, 0, skb->len, 0))))
 		goto drop;
 
-	if (__pim_rcv(skb, sizeof(*pim))) {
+	if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0)
+		goto drop;
+
+	if (__pim_rcv(mrt, skb, sizeof(*pim))) {
 drop:
 		kfree_skb(skb);
 	}
@@ -1663,10 +1941,14 @@ int ipmr_get_route(struct net *net,
 		   struct sk_buff *skb, struct rtmsg *rtm, int nowait)
 {
 	int err;
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt;
 	struct mfc_cache *cache;
 	struct rtable *rt = skb_rtable(skb);
 
+	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
+
 	read_lock(&mrt_lock);
 	cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst);
 
@@ -1717,6 +1999,7 @@ int ipmr_get_route(struct net *net,
  */
 struct ipmr_vif_iter {
 	struct seq_net_private p;
+	struct mr_table *mrt;
 	int ct;
 };
 
@@ -1724,7 +2007,7 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net,
 					   struct ipmr_vif_iter *iter,
 					   loff_t pos)
 {
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt = iter->mrt;
 
 	for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
 		if (!VIF_EXISTS(mrt, iter->ct))
@@ -1738,7 +2021,15 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net,
 static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(mrt_lock)
 {
+	struct ipmr_vif_iter *iter = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return ERR_PTR(-ENOENT);
+
+	iter->mrt = mrt;
 
 	read_lock(&mrt_lock);
 	return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1)
@@ -1749,7 +2040,7 @@ static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ipmr_vif_iter *iter = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt = iter->mrt;
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
@@ -1771,8 +2062,8 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
 
 static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
 {
-	struct net *net = seq_file_net(seq);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct ipmr_vif_iter *iter = seq->private;
+	struct mr_table *mrt = iter->mrt;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -1814,6 +2105,7 @@ static const struct file_operations ipmr_vif_fops = {
 
 struct ipmr_mfc_iter {
 	struct seq_net_private p;
+	struct mr_table *mrt;
 	struct list_head *cache;
 	int ct;
 };
@@ -1822,7 +2114,7 @@ struct ipmr_mfc_iter {
 static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
 					  struct ipmr_mfc_iter *it, loff_t pos)
 {
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt = it->mrt;
 	struct mfc_cache *mfc;
 
 	read_lock(&mrt_lock);
@@ -1850,7 +2142,13 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return ERR_PTR(-ENOENT);
 
+	it->mrt = mrt;
 	it->cache = NULL;
 	it->ct = 0;
 	return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
@@ -1862,7 +2160,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct mfc_cache *mfc = v;
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt = it->mrt;
 
 	++*pos;
 
@@ -1903,8 +2201,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 {
 	struct ipmr_mfc_iter *it = seq->private;
-	struct net *net = seq_file_net(seq);
-	struct mr_table *mrt = net->ipv4.mrt;
+	struct mr_table *mrt = it->mrt;
 
 	if (it->cache == &mrt->mfc_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
@@ -1915,8 +2212,6 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
 {
 	int n;
-	struct net *net = seq_file_net(seq);
-	struct mr_table *mrt = net->ipv4.mrt;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -1924,6 +2219,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
 	} else {
 		const struct mfc_cache *mfc = v;
 		const struct ipmr_mfc_iter *it = seq->private;
+		const struct mr_table *mrt = it->mrt;
 
 		seq_printf(seq, "%08lX %08lX %-3hd",
 			   (unsigned long) mfc->mfc_mcastgrp,
@@ -1989,28 +2285,11 @@ static const struct net_protocol pim_protocol = {
  */
 static int __net_init ipmr_net_init(struct net *net)
 {
-	struct mr_table *mrt;
-	unsigned int i;
-	int err = 0;
+	int err;
 
-	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
-	if (mrt == NULL) {
-		err = -ENOMEM;
+	err = ipmr_rules_init(net);
+	if (err < 0)
 		goto fail;
-	}
-
-	/* Forwarding cache */
-	for (i = 0; i < MFC_LINES; i++)
-		INIT_LIST_HEAD(&mrt->mfc_cache_array[i]);
-
-	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
-
-	setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
-		    (unsigned long)net);
-
-#ifdef CONFIG_IP_PIMSM
-	mrt->mroute_reg_vif_num = -1;
-#endif
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
@@ -2019,15 +2298,13 @@ static int __net_init ipmr_net_init(struct net *net)
 	if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops))
 		goto proc_cache_fail;
 #endif
-
-	net->ipv4.mrt = mrt;
 	return 0;
 
 #ifdef CONFIG_PROC_FS
 proc_cache_fail:
 	proc_net_remove(net, "ip_mr_vif");
 proc_vif_fail:
-	kfree(mrt);
+	ipmr_rules_exit(net);
 #endif
 fail:
 	return err;
@@ -2039,7 +2316,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	proc_net_remove(net, "ip_mr_cache");
 	proc_net_remove(net, "ip_mr_vif");
 #endif
-	kfree(net->ipv4.mrt);
+	ipmr_rules_exit(net);
 }
 
 static struct pernet_operations ipmr_net_ops = {
-- 
1.7.0.4

Re: [PATCH 0/9] net: support multiple independant multicast routing instances

[David Miller]

From: Patrick McHardy <kaber@trash.net>
Date: Tue, 13 Apr 2010 17:03:14 +0200

> this is an updated patchset of my patches to support multiple independant
> multicast routing instances. Changes since the last posting are:
> 
> - rebase to the current net-next-2.6.git tree
> - fix up patch subjects to consistently refer to "ipv4: ipmr:"
> - fix up list_head conversion patch to add new elements at the head of
>   the list instead of at the tail
> 
> Please apply or pull from:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/kaber/ipmr-2.6.git master

I applied the patches instead of pulling just to check your email
patch submission format, and it was perfect! :-)

I'll do a git pull next time.

All applied to net-next-2.6, thanks!