Merge branch 'ipmr-nl'

Nikolay Aleksandrov says:

====================
net: ipmr: more cleanups and mfc netlink support

This set continues with the minor cleanups in the first 6 patches and
patch 7 adds the first new feature - MFC manipulation via netlink. It
registers NEWROUTE/DELROUTE for that purpose and uses the same semantics
as the already present netlink dump. The only new attribute that is used
is RTA_PREFSRC to denote an MFC_PROXY entry. Currently the table must
exist before adding an entry, and new tables can be created only via
setsockopt, but that will be changed in the future.
This set was tested with modified iproute2 which supports NEWROUTE/DELROUTE
for RTNL_FAMILY_IPMR.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 188 insertions, 68 deletions

diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 79aaa9fc1a15..bf9b322cb0b0 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -9,38 +9,28 @@
 #ifdef CONFIG_IP_MROUTE
 static inline int ip_mroute_opt(int opt)
 {
-	return (opt >= MRT_BASE) && (opt <= MRT_MAX);
+	return opt >= MRT_BASE && opt <= MRT_MAX;
 }
-#else
-static inline int ip_mroute_opt(int opt)
-{
-	return 0;
-}
-#endif
 
-#ifdef CONFIG_IP_MROUTE
-extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int);
-extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
-extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
-extern int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
-extern int ip_mr_init(void);
+int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int);
+int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
+int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
+int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
+int ip_mr_init(void);
 #else
-static inline
-int ip_mroute_setsockopt(struct sock *sock,
-			 int optname, char __user *optval, unsigned int optlen)
+static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
+				       char __user *optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }
 
-static inline
-int ip_mroute_getsockopt(struct sock *sock,
-			 int optname, char __user *optval, int __user *optlen)
+static inline int ip_mroute_getsockopt(struct sock *sock, int optname,
+				       char __user *optval, int __user *optlen)
 {
 	return -ENOPROTOOPT;
 }
 
-static inline
-int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
+static inline int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 {
 	return -ENOIOCTLCMD;
 }
@@ -49,6 +39,11 @@ static inline int ip_mr_init(void)
 {
 	return 0;
 }
+
+static inline int ip_mroute_opt(int opt)
+{
+	return 0;
+}
 #endif
 
 struct vif_device {
@@ -64,6 +59,32 @@ struct vif_device {
 
 #define VIFF_STATIC 0x8000
 
+#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
+#define MFC_LINES 64
+
+struct mr_table {
+	struct list_head	list;
+	possible_net_t		net;
+	u32			id;
+	struct sock __rcu	*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;
+	bool			mroute_do_assert;
+	bool			mroute_do_pim;
+	int			mroute_reg_vif_num;
+};
+
+/* mfc_flags:
+ * MFC_STATIC - the entry was added statically (not by a routing daemon)
+ */
+enum {
+	MFC_STATIC = BIT(0),
+};
+
 struct mfc_cache {
 	struct list_head list;
 	__be32 mfc_mcastgrp;			/* Group the entry belongs to 	*/
@@ -89,19 +110,14 @@ struct mfc_cache {
 	struct rcu_head	rcu;
 };
 
-#define MFC_STATIC		1
-#define MFC_NOTIFY		2
-
-#define MFC_LINES		64
-
 #ifdef __BIG_ENDIAN
 #define MFC_HASH(a,b)	(((((__force u32)(__be32)a)>>24)^(((__force u32)(__be32)b)>>26))&(MFC_LINES-1))
 #else
 #define MFC_HASH(a,b)	((((__force u32)(__be32)a)^(((__force u32)(__be32)b)>>2))&(MFC_LINES-1))
-#endif		
+#endif
 
 struct rtmsg;
-extern int ipmr_get_route(struct net *net, struct sk_buff *skb,
-			  __be32 saddr, __be32 daddr,
-			  struct rtmsg *rtm, int nowait);
+int ipmr_get_route(struct net *net, struct sk_buff *skb,
+		   __be32 saddr, __be32 daddr,
+		   struct rtmsg *rtm, int nowait);
 #endif
diff --git a/include/linux/pim.h b/include/linux/pim.h
index 252bf6644c51..e1d756f81348 100644
--- a/include/linux/pim.h
+++ b/include/linux/pim.h
@@ -13,6 +13,11 @@
 
 #define PIM_NULL_REGISTER	cpu_to_be32(0x40000000)
 
+static inline bool ipmr_pimsm_enabled(void)
+{
+	return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2);
+}
+
 /* PIMv2 register message header layout (ietf-draft-idmr-pimvsm-v2-00.ps */
 struct pimreghdr
 {
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 614521437e30..04a48c0159cc 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -24,7 +24,6 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/if_arp.h>
-#include <linux/mroute.h>
 #include <linux/if_vlan.h>
 #include <linux/init.h>
 #include <linux/in6.h>
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4233cbe47052..e0b94cd843d7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -76,7 +76,6 @@
 #include <linux/igmp.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_bridge.h>
-#include <linux/mroute.h>
 #include <linux/netlink.h>
 #include <linux/tcp.h>
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index cbb51f3fac06..0f6e9ee031c4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -30,7 +30,6 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/if_arp.h>
-#include <linux/mroute.h>
 #include <linux/init.h>
 #include <linux/in6.h>
 #include <linux/inetdevice.h>
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6cb9009c3d96..1db8418aa62e 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -24,7 +24,6 @@
 #include <linux/netdevice.h>
 #include <linux/in.h>
 #include <linux/if_arp.h>
-#include <linux/mroute.h>
 #include <linux/init.h>
 #include <linux/in6.h>
 #include <linux/inetdevice.h>
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 4d8f0b698777..02d9c21e2953 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -30,7 +30,6 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/if_arp.h>
-#include <linux/mroute.h>
 #include <linux/init.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/if_ether.h>
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index f34c31defafe..1f067294cbc5 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -103,7 +103,6 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/if_arp.h>
-#include <linux/mroute.h>
 #include <linux/init.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/if_ether.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a2d248d9c35c..4c10ee771648 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -66,22 +66,7 @@
 #include <net/netlink.h>
 #include <net/fib_rules.h>
 #include <linux/netconf.h>
-
-struct mr_table {
-	struct list_head	list;
-	possible_net_t		net;
-	u32			id;
-	struct sock __rcu	*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;
-	bool			mroute_do_assert;
-	bool			mroute_do_pim;
-	int			mroute_reg_vif_num;
-};
+#include <net/nexthop.h>
 
 struct ipmr_rule {
 	struct fib_rule		common;
@@ -91,11 +76,6 @@ struct ipmr_result {
 	struct mr_table		*mrt;
 };
 
-static inline bool pimsm_enabled(void)
-{
-	return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2);
-}
-
 /* Big lock, protecting vif table, mrt cache and mroute socket state.
  * Note that the changes are semaphored via rtnl_lock.
  */
@@ -104,8 +84,6 @@ static DEFINE_RWLOCK(mrt_lock);
 
 /* Multicast router control variables */
 
-#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
-
 /* Special spinlock for queue of unresolved entries */
 static DEFINE_SPINLOCK(mfc_unres_lock);
 
@@ -769,7 +747,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 
 	switch (vifc->vifc_flags) {
 	case VIFF_REGISTER:
-		if (!pimsm_enabled())
+		if (!ipmr_pimsm_enabled())
 			return -EINVAL;
 		/* Special Purpose VIF in PIM
 		 * All the packets will be sent to the daemon
@@ -1307,12 +1285,14 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 
 	switch (optname) {
 	case MRT_INIT:
-		if (optlen != sizeof(int))
+		if (optlen != sizeof(int)) {
 			ret = -EINVAL;
-		if (rtnl_dereference(mrt->mroute_sk))
+			break;
+		}
+		if (rtnl_dereference(mrt->mroute_sk)) {
 			ret = -EADDRINUSE;
-		if (ret)
 			break;
+		}
 
 		ret = ip_ra_control(sk, 1, mrtsock_destruct);
 		if (ret == 0) {
@@ -1395,7 +1375,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 		mrt->mroute_do_assert = val;
 		break;
 	case MRT_PIM:
-		if (!pimsm_enabled()) {
+		if (!ipmr_pimsm_enabled()) {
 			ret = -ENOPROTOOPT;
 			break;
 		}
@@ -1469,7 +1449,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 		val = 0x0305;
 		break;
 	case MRT_PIM:
-		if (!pimsm_enabled())
+		if (!ipmr_pimsm_enabled())
 			return -ENOPROTOOPT;
 		val = mrt->mroute_do_pim;
 		break;
@@ -2199,8 +2179,6 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 	}
 
 	read_lock(&mrt_lock);
-	if (!nowait && (rtm->rtm_flags & RTM_F_NOTIFY))
-		cache->mfc_flags |= MFC_NOTIFY;
 	err = __ipmr_fill_mroute(mrt, skb, cache, rtm);
 	read_unlock(&mrt_lock);
 	rcu_read_unlock();
@@ -2362,6 +2340,130 @@ done:
 	return skb->len;
 }
 
+static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = {
+	[RTA_SRC]	= { .type = NLA_U32 },
+	[RTA_DST]	= { .type = NLA_U32 },
+	[RTA_IIF]	= { .type = NLA_U32 },
+	[RTA_TABLE]	= { .type = NLA_U32 },
+	[RTA_MULTIPATH]	= { .len = sizeof(struct rtnexthop) },
+};
+
+static bool ipmr_rtm_validate_proto(unsigned char rtm_protocol)
+{
+	switch (rtm_protocol) {
+	case RTPROT_STATIC:
+	case RTPROT_MROUTED:
+		return true;
+	}
+	return false;
+}
+
+static int ipmr_nla_get_ttls(const struct nlattr *nla, struct mfcctl *mfcc)
+{
+	struct rtnexthop *rtnh = nla_data(nla);
+	int remaining = nla_len(nla), vifi = 0;
+
+	while (rtnh_ok(rtnh, remaining)) {
+		mfcc->mfcc_ttls[vifi] = rtnh->rtnh_hops;
+		if (++vifi == MAXVIFS)
+			break;
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	return remaining > 0 ? -EINVAL : vifi;
+}
+
+/* returns < 0 on error, 0 for ADD_MFC and 1 for ADD_MFC_PROXY */
+static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
+			    struct mfcctl *mfcc, int *mrtsock,
+			    struct mr_table **mrtret)
+{
+	struct net_device *dev = NULL;
+	u32 tblid = RT_TABLE_DEFAULT;
+	struct mr_table *mrt;
+	struct nlattr *attr;
+	struct rtmsg *rtm;
+	int ret, rem;
+
+	ret = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy);
+	if (ret < 0)
+		goto out;
+	rtm = nlmsg_data(nlh);
+
+	ret = -EINVAL;
+	if (rtm->rtm_family != RTNL_FAMILY_IPMR || rtm->rtm_dst_len != 32 ||
+	    rtm->rtm_type != RTN_MULTICAST ||
+	    rtm->rtm_scope != RT_SCOPE_UNIVERSE ||
+	    !ipmr_rtm_validate_proto(rtm->rtm_protocol))
+		goto out;
+
+	memset(mfcc, 0, sizeof(*mfcc));
+	mfcc->mfcc_parent = -1;
+	ret = 0;
+	nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), rem) {
+		switch (nla_type(attr)) {
+		case RTA_SRC:
+			mfcc->mfcc_origin.s_addr = nla_get_be32(attr);
+			break;
+		case RTA_DST:
+			mfcc->mfcc_mcastgrp.s_addr = nla_get_be32(attr);
+			break;
+		case RTA_IIF:
+			dev = __dev_get_by_index(net, nla_get_u32(attr));
+			if (!dev) {
+				ret = -ENODEV;
+				goto out;
+			}
+			break;
+		case RTA_MULTIPATH:
+			if (ipmr_nla_get_ttls(attr, mfcc) < 0) {
+				ret = -EINVAL;
+				goto out;
+			}
+			break;
+		case RTA_PREFSRC:
+			ret = 1;
+			break;
+		case RTA_TABLE:
+			tblid = nla_get_u32(attr);
+			break;
+		}
+	}
+	mrt = ipmr_get_table(net, tblid);
+	if (!mrt) {
+		ret = -ENOENT;
+		goto out;
+	}
+	*mrtret = mrt;
+	*mrtsock = rtm->rtm_protocol == RTPROT_MROUTED ? 1 : 0;
+	if (dev)
+		mfcc->mfcc_parent = ipmr_find_vif(mrt, dev);
+
+out:
+	return ret;
+}
+
+/* takes care of both newroute and delroute */
+static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	int ret, mrtsock, parent;
+	struct mr_table *tbl;
+	struct mfcctl mfcc;
+
+	mrtsock = 0;
+	tbl = NULL;
+	ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl);
+	if (ret < 0)
+		return ret;
+
+	parent = ret ? mfcc.mfcc_parent : -1;
+	if (nlh->nlmsg_type == RTM_NEWROUTE)
+		return ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent);
+	else
+		return ipmr_mfc_delete(tbl, &mfcc, parent);
+}
+
 #ifdef CONFIG_PROC_FS
 /* The /proc interfaces to multicast routing :
  * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif
@@ -2715,6 +2817,10 @@ int __init ip_mr_init(void)
 #endif
 	rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE,
 		      NULL, ipmr_rtm_dumproute, NULL);
+	rtnl_register(RTNL_FAMILY_IPMR, RTM_NEWROUTE,
+		      ipmr_rtm_route, NULL, NULL);
+	rtnl_register(RTNL_FAMILY_IPMR, RTM_DELROUTE,
+		      ipmr_rtm_route, NULL, NULL);
 	return 0;
 
 #ifdef CONFIG_IP_PIMSM_V2
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3c7b9310b33f..938d03ce5e4b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -24,7 +24,6 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/if_arp.h>
-#include <linux/mroute.h>
 #include <linux/init.h>
 #include <linux/in6.h>
 #include <linux/inetdevice.h>