Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 121 insertions, 16 deletions

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3eab2b2ffd34..a9454cbd953c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -65,6 +65,7 @@
 #include <net/checksum.h>
 #include <net/netlink.h>
 #include <net/fib_rules.h>
+#include <linux/netconf.h>
 
 #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
 #define CONFIG_IP_PIMSM	1
@@ -83,8 +84,8 @@ struct mr_table {
 	struct vif_device	vif_table[MAXVIFS];
 	int			maxvif;
 	atomic_t		cache_resolve_queue_len;
-	int			mroute_do_assert;
-	int			mroute_do_pim;
+	bool			mroute_do_assert;
+	bool			mroute_do_pim;
 #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
 	int			mroute_reg_vif_num;
 #endif
@@ -133,6 +134,8 @@ 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 mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
+				 int cmd);
 static void mroute_clean_tables(struct mr_table *mrt);
 static void ipmr_expire_process(unsigned long arg);
 
@@ -582,6 +585,9 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev) {
 		IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--;
+		inet_netconf_notify_devconf(dev_net(dev),
+					    NETCONFA_MC_FORWARDING,
+					    dev->ifindex, &in_dev->cnf);
 		ip_rt_multicast_event(in_dev);
 	}
 
@@ -665,6 +671,7 @@ static void ipmr_expire_process(unsigned long arg)
 		}
 
 		list_del(&c->list);
+		mroute_netlink_event(mrt, c, RTM_DELROUTE);
 		ipmr_destroy_unres(mrt, c);
 	}
 
@@ -772,6 +779,8 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		return -EADDRNOTAVAIL;
 	}
 	IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++;
+	inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex,
+				    &in_dev->cnf);
 	ip_rt_multicast_event(in_dev);
 
 	/* Fill in the VIF structures */
@@ -1020,6 +1029,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb)
 
 		atomic_inc(&mrt->cache_resolve_queue_len);
 		list_add(&c->list, &mrt->mfc_unres_queue);
+		mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 
 		if (atomic_read(&mrt->cache_resolve_queue_len) == 1)
 			mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires);
@@ -1054,7 +1064,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
 		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
 			list_del_rcu(&c->list);
-
+			mroute_netlink_event(mrt, c, RTM_DELROUTE);
 			ipmr_cache_free(c);
 			return 0;
 		}
@@ -1089,6 +1099,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
+		mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 		return 0;
 	}
 
@@ -1131,6 +1142,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		ipmr_cache_resolve(net, mrt, uc, c);
 		ipmr_cache_free(uc);
 	}
+	mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 	return 0;
 }
 
@@ -1159,6 +1171,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 			if (c->mfc_flags & MFC_STATIC)
 				continue;
 			list_del_rcu(&c->list);
+			mroute_netlink_event(mrt, c, RTM_DELROUTE);
 			ipmr_cache_free(c);
 		}
 	}
@@ -1167,6 +1180,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 		spin_lock_bh(&mfc_unres_lock);
 		list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
+			mroute_netlink_event(mrt, c, RTM_DELROUTE);
 			ipmr_destroy_unres(mrt, c);
 		}
 		spin_unlock_bh(&mfc_unres_lock);
@@ -1185,6 +1199,9 @@ static void mrtsock_destruct(struct sock *sk)
 	ipmr_for_each_table(mrt, net) {
 		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
+			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+						    NETCONFA_IFINDEX_ALL,
+						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
 			mroute_clean_tables(mrt);
 		}
@@ -1207,23 +1224,24 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 	struct net *net = sock_net(sk);
 	struct mr_table *mrt;
 
+	if (sk->sk_type != SOCK_RAW ||
+	    inet_sk(sk)->inet_num != IPPROTO_IGMP)
+		return -EOPNOTSUPP;
+
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
 	if (mrt == NULL)
 		return -ENOENT;
 
 	if (optname != MRT_INIT) {
 		if (sk != rcu_access_pointer(mrt->mroute_sk) &&
-		    !capable(CAP_NET_ADMIN))
+		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EACCES;
 	}
 
 	switch (optname) {
 	case MRT_INIT:
-		if (sk->sk_type != SOCK_RAW ||
-		    inet_sk(sk)->inet_num != IPPROTO_IGMP)
-			return -EOPNOTSUPP;
 		if (optlen != sizeof(int))
-			return -ENOPROTOOPT;
+			return -EINVAL;
 
 		rtnl_lock();
 		if (rtnl_dereference(mrt->mroute_sk)) {
@@ -1235,6 +1253,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		if (ret == 0) {
 			rcu_assign_pointer(mrt->mroute_sk, sk);
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
+			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+						    NETCONFA_IFINDEX_ALL,
+						    net->ipv4.devconf_all);
 		}
 		rtnl_unlock();
 		return ret;
@@ -1284,9 +1305,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 	case MRT_ASSERT:
 	{
 		int v;
+		if (optlen != sizeof(v))
+			return -EINVAL;
 		if (get_user(v, (int __user *)optval))
 			return -EFAULT;
-		mrt->mroute_do_assert = (v) ? 1 : 0;
+		mrt->mroute_do_assert = v;
 		return 0;
 	}
 #ifdef CONFIG_IP_PIMSM
@@ -1294,9 +1317,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 	{
 		int v;
 
+		if (optlen != sizeof(v))
+			return -EINVAL;
 		if (get_user(v, (int __user *)optval))
 			return -EFAULT;
-		v = (v) ? 1 : 0;
+		v = !!v;
 
 		rtnl_lock();
 		ret = 0;
@@ -1329,7 +1354,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		} else {
 			if (!ipmr_new_table(net, v))
 				ret = -ENOMEM;
-			raw_sk(sk)->ipmr_table = v;
+			else
+				raw_sk(sk)->ipmr_table = v;
 		}
 		rtnl_unlock();
 		return ret;
@@ -1355,6 +1381,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 	struct net *net = sock_net(sk);
 	struct mr_table *mrt;
 
+	if (sk->sk_type != SOCK_RAW ||
+	    inet_sk(sk)->inet_num != IPPROTO_IGMP)
+		return -EOPNOTSUPP;
+
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
 	if (mrt == NULL)
 		return -ENOENT;
@@ -2024,6 +2054,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	int ct;
 	struct rtnexthop *nhp;
 	struct nlattr *mp_attr;
+	struct rta_mfc_stats mfcs;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
 	if (c->mfc_parent >= MAXVIFS)
@@ -2052,6 +2083,12 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 	nla_nest_end(skb, mp_attr);
 
+	mfcs.mfcs_packets = c->mfc_un.res.pkt;
+	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
+	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
+	if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0)
+		return -EMSGSIZE;
+
 	rtm->rtm_type = RTN_MULTICAST;
 	return 1;
 }
@@ -2121,12 +2158,13 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 }
 
 static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
-			    u32 portid, u32 seq, struct mfc_cache *c)
+			    u32 portid, u32 seq, struct mfc_cache *c, int cmd)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
+	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2140,13 +2178,18 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 		goto nla_put_failure;
 	rtm->rtm_type     = RTN_MULTICAST;
 	rtm->rtm_scope    = RT_SCOPE_UNIVERSE;
-	rtm->rtm_protocol = RTPROT_UNSPEC;
+	if (c->mfc_flags & MFC_STATIC)
+		rtm->rtm_protocol = RTPROT_STATIC;
+	else
+		rtm->rtm_protocol = RTPROT_MROUTED;
 	rtm->rtm_flags    = 0;
 
 	if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) ||
 	    nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp))
 		goto nla_put_failure;
-	if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0)
+	err = __ipmr_fill_mroute(mrt, skb, c, rtm);
+	/* do not break the dump if cache is unresolved */
+	if (err < 0 && err != -ENOENT)
 		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
@@ -2156,6 +2199,52 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static size_t mroute_msgsize(bool unresolved, int maxvif)
+{
+	size_t len =
+		NLMSG_ALIGN(sizeof(struct rtmsg))
+		+ nla_total_size(4)	/* RTA_TABLE */
+		+ nla_total_size(4)	/* RTA_SRC */
+		+ nla_total_size(4)	/* RTA_DST */
+		;
+
+	if (!unresolved)
+		len = len
+		      + nla_total_size(4)	/* RTA_IIF */
+		      + nla_total_size(0)	/* RTA_MULTIPATH */
+		      + maxvif * NLA_ALIGN(sizeof(struct rtnexthop))
+						/* RTA_MFC_STATS */
+		      + nla_total_size(sizeof(struct rta_mfc_stats))
+		;
+
+	return len;
+}
+
+static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
+				 int cmd)
+{
+	struct net *net = read_pnet(&mrt->net);
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif),
+			GFP_ATOMIC);
+	if (skb == NULL)
+		goto errout;
+
+	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	if (err < 0)
+		goto errout;
+
+	rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC);
+	return;
+
+errout:
+	kfree_skb(skb);
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err);
+}
+
 static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2182,13 +2271,29 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 				if (ipmr_fill_mroute(mrt, skb,
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
-						     mfc) < 0)
+						     mfc, RTM_NEWROUTE) < 0)
 					goto done;
 next_entry:
 				e++;
 			}
 			e = s_e = 0;
 		}
+		spin_lock_bh(&mfc_unres_lock);
+		list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
+			if (e < s_e)
+				goto next_entry2;
+			if (ipmr_fill_mroute(mrt, skb,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     mfc, RTM_NEWROUTE) < 0) {
+				spin_unlock_bh(&mfc_unres_lock);
+				goto done;
+			}
+next_entry2:
+			e++;
+		}
+		spin_unlock_bh(&mfc_unres_lock);
+		e = s_e = 0;
 		s_h = 0;
 next_table:
 		t++;