[PATCH 0/4] net: ipmr netlink interface for route dumping

[PATCH 0/4] net: ipmr netlink interface for route dumping

[Patrick, McHardy, kaber]

These patches add support to ipmr to dump routes of all tables over
netlink. The /proc interface contains an unterminated list of oifs
at the end of a line, therefore it can't be extended to print the
routing table number without breaking backwards compatibility.

These patches fully decouple rtnetlink families from real address
families and add a new family RTNL_FAMILY_IPMR for ipmr as well as
a RTM_GETROUTE handler.

The first patch additionally marks the fib_rules_ops templates as
const __net_initdata. This is not directly related to the netlink
interface, but was already queued in my tree.

Please apply or pull from:

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

Thanks!

[PATCH 1/3] net: fib_rules: mark arguments to fib_rules_register const and __net_initdata

[Patrick, McHardy, kaber]

From: Patrick McHardy <kaber@trash.net>

fib_rules_register() duplicates the template passed to it without modification,
mark the argument as const. Additionally the templates are only needed when
instantiating a new namespace, so mark them as __net_initdata, which means
they can be discarded when CONFIG_NET_NS=n.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/fib_rules.h |    2 +-
 net/core/fib_rules.c    |    2 +-
 net/decnet/dn_rules.c   |    2 +-
 net/ipv4/fib_rules.c    |    2 +-
 net/ipv4/ipmr.c         |    2 +-
 net/ipv6/fib6_rules.c   |    2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 52bd9e6..e8923bc 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -104,7 +104,7 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 	return frh->table;
 }
 
-extern struct fib_rules_ops *fib_rules_register(struct fib_rules_ops *, struct net *);
+extern struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *, struct net *);
 extern void fib_rules_unregister(struct fib_rules_ops *);
 extern void                     fib_rules_cleanup_ops(struct fib_rules_ops *);
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 1bc6659..42e84e0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -122,7 +122,7 @@ errout:
 }
 
 struct fib_rules_ops *
-fib_rules_register(struct fib_rules_ops *tmpl, struct net *net)
+fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net)
 {
 	struct fib_rules_ops *ops;
 	int err;
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index af28dcc..1226bca 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -216,7 +216,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops)
 	dn_rt_cache_flush(-1);
 }
 
-static struct fib_rules_ops dn_fib_rules_ops_template = {
+static const struct fib_rules_ops __net_initdata dn_fib_rules_ops_template = {
 	.family		= FIB_RULES_DECNET,
 	.rule_size	= sizeof(struct dn_fib_rule),
 	.addr_size	= sizeof(u16),
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 3ec84fe..8ab62a5 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -245,7 +245,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
 	rt_cache_flush(ops->fro_net, -1);
 }
 
-static struct fib_rules_ops fib4_rules_ops_template = {
+static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
 	.family		= FIB_RULES_IPV4,
 	.rule_size	= sizeof(struct fib4_rule),
 	.addr_size	= sizeof(u32),
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a2df501..7d3e382 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -216,7 +216,7 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	return 0;
 }
 
-static struct fib_rules_ops ipmr_rules_ops_template = {
+static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
 	.family		= FIB_RULES_IPMR,
 	.rule_size	= sizeof(struct ipmr_rule),
 	.addr_size	= sizeof(u32),
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 8124f16..35f6949 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -237,7 +237,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
 	       + nla_total_size(16); /* src */
 }
 
-static struct fib_rules_ops fib6_rules_ops_template = {
+static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = {
 	.family			= FIB_RULES_IPV6,
 	.rule_size		= sizeof(struct fib6_rule),
 	.addr_size		= sizeof(struct in6_addr),
-- 
1.7.0.4

[PATCH 2/3] net: rtnetlink: decouple rtnetlink address families from real address families

[Patrick, McHardy, kaber]

From: Patrick McHardy <kaber@trash.net>

Decouple rtnetlink address families from real address families in socket.h to
be able to add rtnetlink interfaces to code that is not a real address family
without increasing AF_MAX/NPROTO.

This will be used to add support for multicast route dumping from all tables
as the proc interface can't be extended to support anything but the main table
without breaking compatibility.

This partialy undoes the patch to introduce independant families for routing
rules and converts ipmr routing rules to a new rtnetlink family. Similar to
that patch, values up to 127 are reserved for real address families, values
above that may be used arbitrarily.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/fib_rules.h |    8 --------
 include/linux/rtnetlink.h |    6 ++++++
 net/core/rtnetlink.c      |   14 +++++++-------
 net/decnet/dn_rules.c     |    2 +-
 net/ipv4/fib_rules.c      |    2 +-
 net/ipv4/ipmr.c           |    2 +-
 net/ipv6/fib6_rules.c     |    2 +-
 7 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h
index 04a3976..51da65b 100644
--- a/include/linux/fib_rules.h
+++ b/include/linux/fib_rules.h
@@ -15,14 +15,6 @@
 /* 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
-#define FIB_RULES_IPMR		128
-
 struct fib_rule_hdr {
 	__u8		family;
 	__u8		dst_len;
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index d1c7c90..5a42c36 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -7,6 +7,12 @@
 #include <linux/if_addr.h>
 #include <linux/neighbour.h>
 
+/* rtnetlink families. Values up to 127 are reserved for real address
+ * families, values above 128 may be used arbitrarily.
+ */
+#define RTNL_FAMILY_IPMR		128
+#define RTNL_FAMILY_MAX			128
+
 /****
  *		Routing/neighbour discovery messages.
  ****/
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 78c8598..fd781b6 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -98,7 +98,7 @@ int lockdep_rtnl_is_held(void)
 EXPORT_SYMBOL(lockdep_rtnl_is_held);
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 
-static struct rtnl_link *rtnl_msg_handlers[NPROTO];
+static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
 
 static inline int rtm_msgindex(int msgtype)
 {
@@ -118,7 +118,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
 {
 	struct rtnl_link *tab;
 
-	if (protocol < NPROTO)
+	if (protocol <= RTNL_FAMILY_MAX)
 		tab = rtnl_msg_handlers[protocol];
 	else
 		tab = NULL;
@@ -133,7 +133,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
 {
 	struct rtnl_link *tab;
 
-	if (protocol < NPROTO)
+	if (protocol <= RTNL_FAMILY_MAX)
 		tab = rtnl_msg_handlers[protocol];
 	else
 		tab = NULL;
@@ -167,7 +167,7 @@ int __rtnl_register(int protocol, int msgtype,
 	struct rtnl_link *tab;
 	int msgindex;
 
-	BUG_ON(protocol < 0 || protocol >= NPROTO);
+	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 	msgindex = rtm_msgindex(msgtype);
 
 	tab = rtnl_msg_handlers[protocol];
@@ -219,7 +219,7 @@ int rtnl_unregister(int protocol, int msgtype)
 {
 	int msgindex;
 
-	BUG_ON(protocol < 0 || protocol >= NPROTO);
+	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 	msgindex = rtm_msgindex(msgtype);
 
 	if (rtnl_msg_handlers[protocol] == NULL)
@@ -241,7 +241,7 @@ EXPORT_SYMBOL_GPL(rtnl_unregister);
  */
 void rtnl_unregister_all(int protocol)
 {
-	BUG_ON(protocol < 0 || protocol >= NPROTO);
+	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 
 	kfree(rtnl_msg_handlers[protocol]);
 	rtnl_msg_handlers[protocol] = NULL;
@@ -1384,7 +1384,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 
 	if (s_idx == 0)
 		s_idx = 1;
-	for (idx = 1; idx < NPROTO; idx++) {
+	for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
 		int type = cb->nlh->nlmsg_type-RTM_BASE;
 		if (idx < s_idx || idx == PF_PACKET)
 			continue;
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index 1226bca..48fdf10 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 const struct fib_rules_ops __net_initdata dn_fib_rules_ops_template = {
-	.family		= FIB_RULES_DECNET,
+	.family		= AF_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 8ab62a5..76daeb5 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 const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
-	.family		= FIB_RULES_IPV4,
+	.family		= AF_INET,
 	.rule_size	= sizeof(struct fib4_rule),
 	.addr_size	= sizeof(u32),
 	.action		= fib4_rule_action,
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 7d3e382..41e8fc0 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -217,7 +217,7 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 }
 
 static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
-	.family		= FIB_RULES_IPMR,
+	.family		= RTNL_FAMILY_IPMR,
 	.rule_size	= sizeof(struct ipmr_rule),
 	.addr_size	= sizeof(u32),
 	.action		= ipmr_rule_action,
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 35f6949..8e44f8f 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 const struct fib_rules_ops __net_initdata fib6_rules_ops_template = {
-	.family			= FIB_RULES_IPV6,
+	.family			= AF_INET6,
 	.rule_size		= sizeof(struct fib6_rule),
 	.addr_size		= sizeof(struct in6_addr),
 	.action			= fib6_rule_action,
-- 
1.7.0.4

[PATCH 3/3] net: ipmr: add support for dumping routing tables over netlink

[Patrick, McHardy, kaber]

From: Patrick McHardy <kaber@trash.net>

The ipmr /proc interface (ip_mr_cache) can't be extended to dump routes
from any tables but the main table in a backwards compatible fashion since
the output format ends in a variable amount of output interfaces.

Introduce a new netlink interface to dump multicast routes from all tables,
similar to the netlink interface for regular routes.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/ipv4/ipmr.c |   96 +++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 files changed, 89 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 41e8fc0..eddfd12 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -128,8 +128,8 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
 			 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 mr_table *mrt, struct sk_buff *skb,
-			    struct mfc_cache *c, struct rtmsg *rtm);
+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
@@ -831,7 +831,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
 		if (ip_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
 
-			if (ipmr_fill_mroute(mrt, 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 {
@@ -1904,9 +1904,8 @@ drop:
 }
 #endif
 
-static int
-ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c,
-		 struct rtmsg *rtm)
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+			      struct mfc_cache *c, struct rtmsg *rtm)
 {
 	int ct;
 	struct rtnexthop *nhp;
@@ -1994,11 +1993,93 @@ int ipmr_get_route(struct net *net,
 
 	if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
 		cache->mfc_flags |= MFC_NOTIFY;
-	err = ipmr_fill_mroute(mrt, skb, cache, rtm);
+	err = __ipmr_fill_mroute(mrt, skb, cache, rtm);
 	read_unlock(&mrt_lock);
 	return err;
 }
 
+static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+			    u32 pid, u32 seq, struct mfc_cache *c)
+{
+	struct nlmsghdr *nlh;
+	struct rtmsg *rtm;
+
+	nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	rtm = nlmsg_data(nlh);
+	rtm->rtm_family   = RTNL_FAMILY_IPMR;
+	rtm->rtm_dst_len  = 32;
+	rtm->rtm_src_len  = 32;
+	rtm->rtm_tos      = 0;
+	rtm->rtm_table    = mrt->id;
+	NLA_PUT_U32(skb, RTA_TABLE, mrt->id);
+	rtm->rtm_type     = RTN_MULTICAST;
+	rtm->rtm_scope    = RT_SCOPE_UNIVERSE;
+	rtm->rtm_protocol = RTPROT_UNSPEC;
+	rtm->rtm_flags    = 0;
+
+	NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin);
+	NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp);
+
+	if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0)
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct mr_table *mrt;
+	struct mfc_cache *mfc;
+	unsigned int t = 0, s_t;
+	unsigned int h = 0, s_h;
+	unsigned int e = 0, s_e;
+
+	s_t = cb->args[0];
+	s_h = cb->args[1];
+	s_e = cb->args[2];
+
+	read_lock(&mrt_lock);
+	ipmr_for_each_table(mrt, net) {
+		if (t < s_t)
+			goto next_table;
+		if (t > s_t)
+			s_h = 0;
+		for (h = s_h; h < MFC_LINES; h++) {
+			list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) {
+				if (e < s_e)
+					goto next_entry;
+				if (ipmr_fill_mroute(mrt, skb,
+						     NETLINK_CB(cb->skb).pid,
+						     cb->nlh->nlmsg_seq,
+						     mfc) < 0)
+					goto done;
+next_entry:
+				e++;
+			}
+			e = s_e = 0;
+		}
+		s_h = 0;
+next_table:
+		t++;
+	}
+done:
+	read_unlock(&mrt_lock);
+
+	cb->args[2] = e;
+	cb->args[1] = h;
+	cb->args[0] = t;
+
+	return skb->len;
+}
+
 #ifdef CONFIG_PROC_FS
 /*
  *	The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
@@ -2355,6 +2436,7 @@ int __init ip_mr_init(void)
 		goto add_proto_fail;
 	}
 #endif
+	rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute);
 	return 0;
 
 #ifdef CONFIG_IP_PIMSM_V2
-- 
1.7.0.4

Re: [PATCH 0/4] net: ipmr netlink interface for route dumping

[David Miller]

Whoa, there are three of you now?!?!?!

:-)

Re: [PATCH 0/4] net: ipmr netlink interface for route dumping

[Patrick McHardy]

David Miller wrote:
> Whoa, there are three of you now?!?!?!
> 
> :-)
> 

That would be nice, I'd have my two clones do all the work :)

Not sure what happened, some mishandling of git send-email
apparently :)

Re: [PATCH 0/4] net: ipmr netlink interface for route dumping

[David Miller]

From: Patrick@trash.net, McHardy@trash.net, kaber@trash.net
Date: Tue, 27 Apr 2010 15:26:22 +0200

> Please apply or pull from:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/kaber/ipmr-2.6.git master
> 

Pulled, thanks Patrick.

And good luck finding those missing quotes in your git send-email
scripting :-)