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

Pull networking updates from David Miller: 1) More iov_iter conversion work from Al Viro. [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was wrong, and this pull actually adds an extra commit on top of the branch I'm pulling to fix that up, so that the pre-merge state is ok. - Linus ] 2) Various optimizations to the ipv4 forwarding information base trie lookup implementation. From Alexander Duyck. 3) Remove sock_iocb altogether, from CHristoph Hellwig. 4) Allow congestion control algorithm selection via routing metrics. From Daniel Borkmann. 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet. 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet. 7) Add xmit_more support to r8169, e1000, and e1000e drivers. From Florian Westphal. 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross. 9) Add BPF packet actions to packet scheduler, from Jiri Pirko. 10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer. 11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman Kwok. 12) More sanely handle out-of-window dupacks, which can result in serious ACK storms. From Neal Cardwell. 13) Various rhashtable bug fixes and enhancements, from Herbert Xu, Patrick McHardy, and Thomas Graf. 14) Support xmit_more in be2net, from Sathya Perla. 15) Group Policy extensions for vxlan, from Thomas Graf. 16) Remove Checksum Offload support for vxlan, from Tom Herbert. 17) Like ipv4, support lockless transmit over ipv6 UDP sockets. From Vlad Yasevich. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits) crypto: fix af_alg_make_sg() conversion to iov_iter ipv4: Namespecify TCP PMTU mechanism i40e: Fix for stats init function call in Rx setup tcp: don't include Fast Open option in SYN-ACK on pure SYN-data openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set ipv6: Make __ipv6_select_ident static ipv6: Fix fragment id assignment on LE arches. bridge: Fix inability to add non-vlan fdb entry net: Mellanox: Delete unnecessary checks before the function call "vunmap" cxgb4: Add support in cxgb4 to get expansion rom version via ethtool ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version net: dsa: Remove redundant phy_attach() IB/mlx4: Reset flow support for IB kernel ULPs IB/mlx4: Always use the correct port for mirrored multicast attachments net/bonding: Fix potential bad memory access during bonding events tipc: remove tipc_snprintf tipc: nl compat add noop and remove legacy nl framework tipc: convert legacy nl stats show to nl compat tipc: convert legacy nl net id get to nl compat tipc: convert legacy nl net id set to nl compat ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2015-02-10 20:01:30 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2015-02-10 20:01:30 -0800
commit: c5ce28df0e7c01a1de23c36ebdefcd803f2b6cbb (patch)
tree: 9830baf38832769e1cf621708889111bbe3c93df /net/ipv6
parent: 29afc4e9a408f2304e09c6dd0dbcfbd2356d0faa (diff)
parent: 9399f0c51489ae8c16d6559b82a452fdc1895e91 (diff)
20 files changed, 508 insertions, 244 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f7c8bbeb27b7..98e4a63d72bb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -201,6 +201,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.disable_ipv6		= 0,
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
+	.accept_ra_mtu		= 1,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -238,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.disable_ipv6		= 0,
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
+	.accept_ra_mtu		= 1,
 };
 
 /* Check if a valid qdisc is available */
@@ -489,7 +491,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -619,7 +622,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 						       cb->nlh->nlmsg_seq,
 						       RTM_NEWNETCONF,
 						       NLM_F_MULTI,
-						       -1) <= 0) {
+						       -1) < 0) {
 				rcu_read_unlock();
 				goto done;
 			}
@@ -635,7 +638,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) <= 0)
+					       -1) < 0)
 			goto done;
 		else
 			h++;
@@ -646,7 +649,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) <= 0)
+					       -1) < 0)
 			goto done;
 		else
 			h++;
@@ -1519,15 +1522,30 @@ static int ipv6_count_addresses(struct inet6_dev *idev)
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  const struct net_device *dev, int strict)
 {
+	return ipv6_chk_addr_and_flags(net, addr, dev, strict, IFA_F_TENTATIVE);
+}
+EXPORT_SYMBOL(ipv6_chk_addr);
+
+int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+			    const struct net_device *dev, int strict,
+			    u32 banned_flags)
+{
 	struct inet6_ifaddr *ifp;
 	unsigned int hash = inet6_addr_hash(addr);
+	u32 ifp_flags;
 
 	rcu_read_lock_bh();
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
+		/* Decouple optimistic from tentative for evaluation here.
+		 * Ban optimistic addresses explicitly, when required.
+		 */
+		ifp_flags = (ifp->flags&IFA_F_OPTIMISTIC)
+			    ? (ifp->flags&~IFA_F_TENTATIVE)
+			    : ifp->flags;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
-		    !(ifp->flags&IFA_F_TENTATIVE) &&
+		    !(ifp_flags&banned_flags) &&
 		    (dev == NULL || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
 			rcu_read_unlock_bh();
@@ -1538,7 +1556,7 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 	rcu_read_unlock_bh();
 	return 0;
 }
-EXPORT_SYMBOL(ipv6_chk_addr);
+EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
 static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 			       struct net_device *dev)
@@ -4047,7 +4065,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0)
 		goto error;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 error:
 	nlmsg_cancel(skb, nlh);
@@ -4076,7 +4095,8 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
@@ -4101,7 +4121,8 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 enum addr_type_t {
@@ -4134,7 +4155,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						cb->nlh->nlmsg_seq,
 						RTM_NEWADDR,
 						NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 		}
@@ -4151,7 +4172,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETMULTICAST,
 						  NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		break;
@@ -4166,7 +4187,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETANYCAST,
 						  NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		break;
@@ -4209,7 +4230,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 				goto cont;
 
 			if (in6_dump_addrs(idev, skb, cb, type,
-					   s_ip_idx, &ip_idx) <= 0)
+					   s_ip_idx, &ip_idx) < 0)
 				goto done;
 cont:
 			idx++;
@@ -4376,6 +4397,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify;
 	array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
 	array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
+	array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -4572,6 +4594,22 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	return 0;
 }
 
+static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = {
+	[IFLA_INET6_ADDR_GEN_MODE]	= { .type = NLA_U8 },
+	[IFLA_INET6_TOKEN]		= { .len = sizeof(struct in6_addr) },
+};
+
+static int inet6_validate_link_af(const struct net_device *dev,
+				  const struct nlattr *nla)
+{
+	struct nlattr *tb[IFLA_INET6_MAX + 1];
+
+	if (dev && !__in6_dev_get(dev))
+		return -EAFNOSUPPORT;
+
+	return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy);
+}
+
 static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 {
 	int err = -EINVAL;
@@ -4638,7 +4676,8 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
 		goto nla_put_failure;
 
 	nla_nest_end(skb, protoinfo);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -4670,7 +4709,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			if (inet6_fill_ifinfo(skb, idev,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
-					      RTM_NEWLINK, NLM_F_MULTI) <= 0)
+					      RTM_NEWLINK, NLM_F_MULTI) < 0)
 				goto out;
 cont:
 			idx++;
@@ -4747,7 +4786,8 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	ci.valid_time = ntohl(pinfo->valid);
 	if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -5253,6 +5293,13 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "accept_ra_mtu",
+			.data		= &ipv6_devconf.accept_ra_mtu,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			/* sentinel */
 		}
 	},
@@ -5389,10 +5436,11 @@ static struct pernet_operations addrconf_ops = {
 	.exit = addrconf_exit_net,
 };
 
-static struct rtnl_af_ops inet6_ops = {
+static struct rtnl_af_ops inet6_ops __read_mostly = {
 	.family		  = AF_INET6,
 	.fill_link_af	  = inet6_fill_link_af,
 	.get_link_af_size = inet6_get_link_af_size,
+	.validate_link_af = inet6_validate_link_af,
 	.set_link_af	  = inet6_set_link_af,
 };
 
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index fd0dc47f471d..e43e79d0a612 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -490,7 +490,8 @@ static int ip6addrlbl_fill(struct sk_buff *skb,
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
@@ -510,7 +511,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWADDRLABEL,
 					      NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		idx++;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 49f5e73db122..c215be70cac0 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -369,7 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin) {
+	if (sin && skb->len) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
@@ -394,8 +394,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
 	memset(sin, 0, sizeof(*sin));
-
-	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
+	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL && skb->len) {
 		sin->sin6_family = AF_INET6;
 		if (np->rxopt.all) {
 			if (serr->ee.ee_origin != SO_EE_ORIGIN_ICMP &&
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index d674152b6ede..a5e95199585e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -427,7 +427,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 *	Dest addr check
 	 */
 
-	if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
+	if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
 		if (type != ICMPV6_PKT_TOOBIG &&
 		    !(type == ICMPV6_PARAMPROB &&
 		      code == ICMPV6_UNK_OPTION &&
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f1c6d5e98322..263ef4143bff 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -277,7 +277,6 @@ static int fib6_dump_node(struct fib6_walker *w)
 			w->leaf = rt;
 			return 1;
 		}
-		WARN_ON(res == 0);
 	}
 	w->leaf = NULL;
 	return 0;
@@ -630,32 +629,35 @@ static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 	       RTF_GATEWAY;
 }
 
-static int fib6_commit_metrics(struct dst_entry *dst,
-			       struct nlattr *mx, int mx_len)
+static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
 {
-	struct nlattr *nla;
-	int remaining;
-	u32 *mp;
+	int i;
 
-	if (dst->flags & DST_HOST) {
-		mp = dst_metrics_write_ptr(dst);
-	} else {
-		mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
-		if (!mp)
-			return -ENOMEM;
-		dst_init_metrics(dst, mp, 0);
+	for (i = 0; i < RTAX_MAX; i++) {
+		if (test_bit(i, mxc->mx_valid))
+			mp[i] = mxc->mx[i];
 	}
+}
 
-	nla_for_each_attr(nla, mx, mx_len, remaining) {
-		int type = nla_type(nla);
+static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
+{
+	if (!mxc->mx)
+		return 0;
 
-		if (type) {
-			if (type > RTAX_MAX)
-				return -EINVAL;
+	if (dst->flags & DST_HOST) {
+		u32 *mp = dst_metrics_write_ptr(dst);
 
-			mp[type - 1] = nla_get_u32(nla);
-		}
+		if (unlikely(!mp))
+			return -ENOMEM;
+
+		fib6_copy_metrics(mp, mxc);
+	} else {
+		dst_init_metrics(dst, mxc->mx, false);
+
+		/* We've stolen mx now. */
+		mxc->mx = NULL;
 	}
+
 	return 0;
 }
 
@@ -687,7 +689,7 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info, struct nlattr *mx, int mx_len)
+			    struct nl_info *info, struct mx6_config *mxc)
 {
 	struct rt6_info *iter = NULL;
 	struct rt6_info **ins;
@@ -796,11 +798,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			pr_warn("NLM_F_CREATE should be set when creating new route\n");
 
 add:
-		if (mx) {
-			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
-			if (err)
-				return err;
-		}
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		rt->dst.rt6_next = iter;
 		*ins = rt;
 		rt->rt6i_node = fn;
@@ -820,11 +821,11 @@ add:
 			pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
 			return -ENOENT;
 		}
-		if (mx) {
-			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
-			if (err)
-				return err;
-		}
+
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		*ins = rt;
 		rt->rt6i_node = fn;
 		rt->dst.rt6_next = iter->dst.rt6_next;
@@ -862,8 +863,8 @@ void fib6_force_start_gc(struct net *net)
  *	with source addr info in sub-trees
  */
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
-	     struct nlattr *mx, int mx_len)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+	     struct nl_info *info, struct mx6_config *mxc)
 {
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
@@ -958,7 +959,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
+	err = fib6_add_rt2node(fn, rt, info, mxc);
 	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 01ccc28a686f..bc28b7d42a6d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1662,6 +1662,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.dellink	= ip6gre_dellink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
@@ -1675,6 +1676,7 @@ static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
 	.changelink	= ip6gre_changelink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 /*
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d28f2a2efb32..d33df4cbd872 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1027,6 +1027,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
 static inline int ip6_ufo_append_data(struct sock *sk,
+			struct sk_buff_head *queue,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
@@ -1042,7 +1043,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 	 * device, so create one single skb packet containing complete
 	 * udp datagram
 	 */
-	skb = skb_peek_tail(&sk->sk_write_queue);
+	skb = skb_peek_tail(queue);
 	if (skb == NULL) {
 		skb = sock_alloc_send_skb(sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
@@ -1065,7 +1066,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb->protocol = htons(ETH_P_IPV6);
 		skb->csum = 0;
 
-		__skb_queue_tail(&sk->sk_write_queue, skb);
+		__skb_queue_tail(queue, skb);
 	} else if (skb_is_gso(skb)) {
 		goto append;
 	}
@@ -1121,99 +1122,106 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 	}
 }
 
-int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
-	int offset, int len, int odd, struct sk_buff *skb),
-	void *from, int length, int transhdrlen,
-	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
-	struct rt6_info *rt, unsigned int flags, int dontfrag)
+static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
+			  struct inet6_cork *v6_cork,
+			  int hlimit, int tclass, struct ipv6_txoptions *opt,
+			  struct rt6_info *rt, struct flowi6 *fl6)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct inet_cork *cork;
+	unsigned int mtu;
+
+	/*
+	 * setup for corking
+	 */
+	if (opt) {
+		if (WARN_ON(v6_cork->opt))
+			return -EINVAL;
+
+		v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation);
+		if (unlikely(v6_cork->opt == NULL))
+			return -ENOBUFS;
+
+		v6_cork->opt->tot_len = opt->tot_len;
+		v6_cork->opt->opt_flen = opt->opt_flen;
+		v6_cork->opt->opt_nflen = opt->opt_nflen;
+
+		v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt,
+						    sk->sk_allocation);
+		if (opt->dst0opt && !v6_cork->opt->dst0opt)
+			return -ENOBUFS;
+
+		v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt,
+						    sk->sk_allocation);
+		if (opt->dst1opt && !v6_cork->opt->dst1opt)
+			return -ENOBUFS;
+
+		v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt,
+						   sk->sk_allocation);
+		if (opt->hopopt && !v6_cork->opt->hopopt)
+			return -ENOBUFS;
+
+		v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt,
+						    sk->sk_allocation);
+		if (opt->srcrt && !v6_cork->opt->srcrt)
+			return -ENOBUFS;
+
+		/* need source address above miyazawa*/
+	}
+	dst_hold(&rt->dst);
+	cork->base.dst = &rt->dst;
+	cork->fl.u.ip6 = *fl6;
+	v6_cork->hop_limit = hlimit;
+	v6_cork->tclass = tclass;
+	if (rt->dst.flags & DST_XFRM_TUNNEL)
+		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+	else
+		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+	if (np->frag_size < mtu) {
+		if (np->frag_size)
+			mtu = np->frag_size;
+	}
+	cork->base.fragsize = mtu;
+	if (dst_allfrag(rt->dst.path))
+		cork->base.flags |= IPCORK_ALLFRAG;
+	cork->base.length = 0;
+
+	return 0;
+}
+
+static int __ip6_append_data(struct sock *sk,
+			     struct flowi6 *fl6,
+			     struct sk_buff_head *queue,
+			     struct inet_cork *cork,
+			     struct inet6_cork *v6_cork,
+			     struct page_frag *pfrag,
+			     int getfrag(void *from, char *to, int offset,
+					 int len, int odd, struct sk_buff *skb),
+			     void *from, int length, int transhdrlen,
+			     unsigned int flags, int dontfrag)
+{
 	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
-	int exthdrlen;
-	int dst_exthdrlen;
+	int exthdrlen = 0;
+	int dst_exthdrlen = 0;
 	int hh_len;
 	int copy;
 	int err;
 	int offset = 0;
 	__u8 tx_flags = 0;
 	u32 tskey = 0;
+	struct rt6_info *rt = (struct rt6_info *)cork->dst;
+	struct ipv6_txoptions *opt = v6_cork->opt;
+	int csummode = CHECKSUM_NONE;
 
-	if (flags&MSG_PROBE)
-		return 0;
-	cork = &inet->cork.base;
-	if (skb_queue_empty(&sk->sk_write_queue)) {
-		/*
-		 * setup for corking
-		 */
-		if (opt) {
-			if (WARN_ON(np->cork.opt))
-				return -EINVAL;
-
-			np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
-			if (unlikely(np->cork.opt == NULL))
-				return -ENOBUFS;
-
-			np->cork.opt->tot_len = opt->tot_len;
-			np->cork.opt->opt_flen = opt->opt_flen;
-			np->cork.opt->opt_nflen = opt->opt_nflen;
-
-			np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
-							    sk->sk_allocation);
-			if (opt->dst0opt && !np->cork.opt->dst0opt)
-				return -ENOBUFS;
-
-			np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
-							    sk->sk_allocation);
-			if (opt->dst1opt && !np->cork.opt->dst1opt)
-				return -ENOBUFS;
-
-			np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
-							   sk->sk_allocation);
-			if (opt->hopopt && !np->cork.opt->hopopt)
-				return -ENOBUFS;
-
-			np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
-							    sk->sk_allocation);
-			if (opt->srcrt && !np->cork.opt->srcrt)
-				return -ENOBUFS;
-
-			/* need source address above miyazawa*/
-		}
-		dst_hold(&rt->dst);
-		cork->dst = &rt->dst;
-		inet->cork.fl.u.ip6 = *fl6;
-		np->cork.hop_limit = hlimit;
-		np->cork.tclass = tclass;
-		if (rt->dst.flags & DST_XFRM_TUNNEL)
-			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
-		else
-			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
-		if (np->frag_size < mtu) {
-			if (np->frag_size)
-				mtu = np->frag_size;
-		}
-		cork->fragsize = mtu;
-		if (dst_allfrag(rt->dst.path))
-			cork->flags |= IPCORK_ALLFRAG;
-		cork->length = 0;
-		exthdrlen = (opt ? opt->opt_flen : 0);
-		length += exthdrlen;
-		transhdrlen += exthdrlen;
+	skb = skb_peek_tail(queue);
+	if (!skb) {
+		exthdrlen = opt ? opt->opt_flen : 0;
 		dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
-	} else {
-		rt = (struct rt6_info *)cork->dst;
-		fl6 = &inet->cork.fl.u.ip6;
-		opt = np->cork.opt;
-		transhdrlen = 0;
-		exthdrlen = 0;
-		dst_exthdrlen = 0;
-		mtu = cork->fragsize;
 	}
+
+	mtu = cork->fragsize;
 	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1262,6 +1270,14 @@ emsgsize:
 			tskey = sk->sk_tskey++;
 	}
 
+	/* If this is the first and only packet and device
+	 * supports checksum offloading, let's use it.
+	 */
+	if (!skb &&
+	    length + fragheaderlen < mtu &&
+	    rt->dst.dev->features & NETIF_F_V6_CSUM &&
+	    !exthdrlen)
+		csummode = CHECKSUM_PARTIAL;
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1278,13 +1294,12 @@ emsgsize:
 	 * --yoshfuji
 	 */
 
-	skb = skb_peek_tail(&sk->sk_write_queue);
 	cork->length += length;
 	if (((length > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
-		err = ip6_ufo_append_data(sk, getfrag, from, length,
+		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, rt);
 		if (err)
@@ -1375,7 +1390,7 @@ alloc_new_skb:
 			 *	Fill in the control structures
 			 */
 			skb->protocol = htons(ETH_P_IPV6);
-			skb->ip_summed = CHECKSUM_NONE;
+			skb->ip_summed = csummode;
 			skb->csum = 0;
 			/* reserve for fragmentation and ipsec header */
 			skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
@@ -1425,7 +1440,7 @@ alloc_new_skb:
 			/*
 			 * Put the packet on the pending queue
 			 */
-			__skb_queue_tail(&sk->sk_write_queue, skb);
+			__skb_queue_tail(queue, skb);
 			continue;
 		}
 
@@ -1444,7 +1459,6 @@ alloc_new_skb:
 			}
 		} else {
 			int i = skb_shinfo(skb)->nr_frags;
-			struct page_frag *pfrag = sk_page_frag(sk);
 
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
@@ -1487,43 +1501,81 @@ error:
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
+
+int ip6_append_data(struct sock *sk,
+		    int getfrag(void *from, char *to, int offset, int len,
+				int odd, struct sk_buff *skb),
+		    void *from, int length, int transhdrlen, int hlimit,
+		    int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
+		    struct rt6_info *rt, unsigned int flags, int dontfrag)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	int exthdrlen;
+	int err;
+
+	if (flags&MSG_PROBE)
+		return 0;
+	if (skb_queue_empty(&sk->sk_write_queue)) {
+		/*
+		 * setup for corking
+		 */
+		err = ip6_setup_cork(sk, &inet->cork, &np->cork, hlimit,
+				     tclass, opt, rt, fl6);
+		if (err)
+			return err;
+
+		exthdrlen = (opt ? opt->opt_flen : 0);
+		length += exthdrlen;
+		transhdrlen += exthdrlen;
+	} else {
+		fl6 = &inet->cork.fl.u.ip6;
+		transhdrlen = 0;
+	}
+
+	return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
+				 &np->cork, sk_page_frag(sk), getfrag,
+				 from, length, transhdrlen, flags, dontfrag);
+}
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
-static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
+static void ip6_cork_release(struct inet_cork_full *cork,
+			     struct inet6_cork *v6_cork)
 {
-	if (np->cork.opt) {
-		kfree(np->cork.opt->dst0opt);
-		kfree(np->cork.opt->dst1opt);
-		kfree(np->cork.opt->hopopt);
-		kfree(np->cork.opt->srcrt);
-		kfree(np->cork.opt);
-		np->cork.opt = NULL;
+	if (v6_cork->opt) {
+		kfree(v6_cork->opt->dst0opt);
+		kfree(v6_cork->opt->dst1opt);
+		kfree(v6_cork->opt->hopopt);
+		kfree(v6_cork->opt->srcrt);
+		kfree(v6_cork->opt);
+		v6_cork->opt = NULL;
 	}
 
-	if (inet->cork.base.dst) {
-		dst_release(inet->cork.base.dst);
-		inet->cork.base.dst = NULL;
-		inet->cork.base.flags &= ~IPCORK_ALLFRAG;
+	if (cork->base.dst) {
+		dst_release(cork->base.dst);
+		cork->base.dst = NULL;
+		cork->base.flags &= ~IPCORK_ALLFRAG;
 	}
-	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
+	memset(&cork->fl, 0, sizeof(cork->fl));
 }
 
-int ip6_push_pending_frames(struct sock *sk)
+struct sk_buff *__ip6_make_skb(struct sock *sk,
+			       struct sk_buff_head *queue,
+			       struct inet_cork_full *cork,
+			       struct inet6_cork *v6_cork)
 {
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
 	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
-	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
-	struct ipv6_txoptions *opt = np->cork.opt;
-	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
-	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+	struct ipv6_txoptions *opt = v6_cork->opt;
+	struct rt6_info *rt = (struct rt6_info *)cork->base.dst;
+	struct flowi6 *fl6 = &cork->fl.u.ip6;
 	unsigned char proto = fl6->flowi6_proto;
-	int err = 0;
 
-	skb = __skb_dequeue(&sk->sk_write_queue);
+	skb = __skb_dequeue(queue);
 	if (skb == NULL)
 		goto out;
 	tail_skb = &(skb_shinfo(skb)->frag_list);
@@ -1531,7 +1583,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	/* move skb->data to ip header from ext header */
 	if (skb->data < skb_network_header(skb))
 		__skb_pull(skb, skb_network_offset(skb));
-	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+	while ((tmp_skb = __skb_dequeue(queue)) != NULL) {
 		__skb_pull(tmp_skb, skb_network_header_len(skb));
 		*tail_skb = tmp_skb;
 		tail_skb = &(tmp_skb->next);
@@ -1556,10 +1608,10 @@ int ip6_push_pending_frames(struct sock *sk)
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	ip6_flow_hdr(hdr, np->cork.tclass,
+	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
 					np->autoflowlabel));
-	hdr->hop_limit = np->cork.hop_limit;
+	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
@@ -1576,34 +1628,104 @@ int ip6_push_pending_frames(struct sock *sk)
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
+	ip6_cork_release(cork, v6_cork);
+out:
+	return skb;
+}
+
+int ip6_send_skb(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+	int err;
+
 	err = ip6_local_out(skb);
 	if (err) {
 		if (err > 0)
 			err = net_xmit_errno(err);
 		if (err)
-			goto error;
+			IP6_INC_STATS(net, rt->rt6i_idev,
+				      IPSTATS_MIB_OUTDISCARDS);
 	}
 
-out:
-	ip6_cork_release(inet, np);
 	return err;
-error:
-	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
-	goto out;
+}
+
+int ip6_push_pending_frames(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	skb = ip6_finish_skb(sk);
+	if (!skb)
+		return 0;
+
+	return ip6_send_skb(skb);
 }
 EXPORT_SYMBOL_GPL(ip6_push_pending_frames);
 
-void ip6_flush_pending_frames(struct sock *sk)
+static void __ip6_flush_pending_frames(struct sock *sk,
+				       struct sk_buff_head *queue,
+				       struct inet_cork_full *cork,
+				       struct inet6_cork *v6_cork)
 {
 	struct sk_buff *skb;
 
-	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
+	while ((skb = __skb_dequeue_tail(queue)) != NULL) {
 		if (skb_dst(skb))
 			IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 	}
 
-	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
+	ip6_cork_release(cork, v6_cork);
+}
+
+void ip6_flush_pending_frames(struct sock *sk)
+{
+	__ip6_flush_pending_frames(sk, &sk->sk_write_queue,
+				   &inet_sk(sk)->cork, &inet6_sk(sk)->cork);
 }
 EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
+
+struct sk_buff *ip6_make_skb(struct sock *sk,
+			     int getfrag(void *from, char *to, int offset,
+					 int len, int odd, struct sk_buff *skb),
+			     void *from, int length, int transhdrlen,
+			     int hlimit, int tclass,
+			     struct ipv6_txoptions *opt, struct flowi6 *fl6,
+			     struct rt6_info *rt, unsigned int flags,
+			     int dontfrag)
+{
+	struct inet_cork_full cork;
+	struct inet6_cork v6_cork;
+	struct sk_buff_head queue;
+	int exthdrlen = (opt ? opt->opt_flen : 0);
+	int err;
+
+	if (flags & MSG_PROBE)
+		return NULL;
+
+	__skb_queue_head_init(&queue);
+
+	cork.base.flags = 0;
+	cork.base.addr = 0;
+	cork.base.opt = NULL;
+	v6_cork.opt = NULL;
+	err = ip6_setup_cork(sk, &cork, &v6_cork, hlimit, tclass, opt, rt, fl6);
+	if (err)
+		return ERR_PTR(err);
+
+	if (dontfrag < 0)
+		dontfrag = inet6_sk(sk)->dontfrag;
+
+	err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork,
+				&current->task_frag, getfrag, from,
+				length + exthdrlen, transhdrlen + exthdrlen,
+				flags, dontfrag);
+	if (err) {
+		__ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork);
+		return ERR_PTR(err);
+	}
+
+	return __ip6_make_skb(sk, &queue, &cork, &v6_cork);
+}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 92b3da571980..266a264ec212 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1760,6 +1760,14 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+struct net *ip6_tnl_get_link_net(const struct net_device *dev)
+{
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+
+	return tunnel->net;
+}
+EXPORT_SYMBOL(ip6_tnl_get_link_net);
+
 static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_LINK]		= { .type = NLA_U32 },
 	[IFLA_IPTUN_LOCAL]		= { .len = sizeof(struct in6_addr) },
@@ -1783,6 +1791,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = {
 	.dellink	= ip6_tnl_dellink,
 	.get_size	= ip6_tnl_get_size,
 	.fill_info	= ip6_tnl_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index 8db6c98fe218..32d9b268e7d8 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -62,14 +62,14 @@ error:
 }
 EXPORT_SYMBOL_GPL(udp_sock_create6);
 
-int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
-			 struct sk_buff *skb, struct net_device *dev,
-			 struct in6_addr *saddr, struct in6_addr *daddr,
-			 __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port)
+int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
+			 struct net_device *dev, struct in6_addr *saddr,
+			 struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port,
+			 __be16 dst_port, bool nocheck)
 {
 	struct udphdr *uh;
 	struct ipv6hdr *ip6h;
-	struct sock *sk = sock->sk;
 
 	__skb_push(skb, sizeof(*uh));
 	skb_reset_transport_header(skb);
@@ -85,7 +85,7 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
 			    | IPSKB_REROUTED);
 	skb_dst_set(skb, dst);
 
-	udp6_set_csum(udp_get_no_check6_tx(sk), skb, saddr, daddr, skb->len);
+	udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);
 
 	__skb_push(skb, sizeof(*ip6h));
 	skb_reset_network_header(skb);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ace10d0b3aac..5fb9e212eca8 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1016,6 +1016,7 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.changelink	= vti6_changelink,
 	.get_size	= vti6_get_size,
 	.fill_info	= vti6_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 722669754bbf..34b682617f50 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2388,7 +2388,8 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	if (err < 0 && err != -ENOENT)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 66980d8d98d1..8d766d9100cb 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -996,13 +996,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		lock_sock(sk);
 		skb = np->pktoptions;
 		if (skb)
-			atomic_inc(&skb->users);
-		release_sock(sk);
-
-		if (skb) {
 			ip6_datagram_recv_ctl(sk, &msg, skb);
-			kfree_skb(skb);
-		} else {
+		release_sock(sk);
+		if (!skb) {
 			if (np->rxopt.bits.rxinfo) {
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 682866777d53..471ed24aabae 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -655,7 +655,9 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
 	struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
 	int probes = atomic_read(&neigh->probes);
 
-	if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1))
+	if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr,
+					   dev, 1,
+					   IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))
 		saddr = &ipv6_hdr(skb)->saddr;
 	probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
 	if (probes < 0) {
@@ -1348,7 +1350,7 @@ skip_routeinfo:
 		}
 	}
 
-	if (ndopts.nd_opts_mtu) {
+	if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) {
 		__be32 n;
 		u32 mtu;
 
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 54520a0bd5e3..74581f706c4d 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,7 +9,8 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
-u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+static u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			       struct in6_addr *src)
 {
 	u32 hash, id;
 
@@ -54,7 +55,7 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 
 	id = __ipv6_select_ident(ip6_proxy_idents_hashrnd,
 				 &addrs[1], &addrs[0]);
-	skb_shinfo(skb)->ip6_frag_id = id;
+	skb_shinfo(skb)->ip6_frag_id = htonl(id);
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 2d3148378a1f..bd46f736f61d 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -163,8 +163,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
-	/* XXX: stripping const */
-	pfh.iov = (struct iovec *)msg->msg_iter.iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ee25631f8c29..dae7f1a1e464 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -609,7 +609,7 @@ out:
 	return err;
 }
 
-static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
+static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 			struct flowi6 *fl6, struct dst_entry **dstp,
 			unsigned int flags)
 {
@@ -648,7 +648,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	skb->transport_header = skb->network_header;
-	err = memcpy_fromiovecend((void *)iph, from, 0, length);
+	err = memcpy_from_msg(iph, msg, length);
 	if (err)
 		goto error_fault;
 
@@ -886,8 +886,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	if (inet->hdrincl)
-		/* XXX: stripping const */
-		err = rawv6_send_hdrinc(sk, (struct iovec *)msg->msg_iter.iov, len, &fl6, &dst, msg->msg_flags);
+		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
 	else {
 		lock_sock(sk);
 		err = ip6_append_data(sk, raw6_getfrag, &rfv,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 495965358d22..98565ce0ebcd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -499,7 +499,7 @@ static void rt6_probe_deferred(struct work_struct *w)
 	addrconf_addr_solict_mult(&work->target, &mcaddr);
 	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
 	dev_put(work->dev);
-	kfree(w);
+	kfree(work);
 }
 
 static void rt6_probe(struct rt6_info *rt)
@@ -853,14 +853,14 @@ EXPORT_SYMBOL(rt6_lookup);
  */
 
 static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
-			struct nlattr *mx, int mx_len)
+			struct mx6_config *mxc)
 {
 	int err;
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
-	err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
+	err = fib6_add(&table->tb6_root, rt, info, mxc);
 	write_unlock_bh(&table->tb6_lock);
 
 	return err;
@@ -868,10 +868,10 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
 
 int ip6_ins_rt(struct rt6_info *rt)
 {
-	struct nl_info info = {
-		.nl_net = dev_net(rt->dst.dev),
-	};
-	return __ip6_ins_rt(rt, &info, NULL, 0);
+	struct nl_info info = {	.nl_net = dev_net(rt->dst.dev), };
+	struct mx6_config mxc = { .mx = NULL, };
+
+	return __ip6_ins_rt(rt, &info, &mxc);
 }
 
 static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1471,9 +1471,51 @@ out:
 	return entries > rt_max_size;
 }
 
-/*
- *
- */
+static int ip6_convert_metrics(struct mx6_config *mxc,
+			       const struct fib6_config *cfg)
+{
+	struct nlattr *nla;
+	int remaining;
+	u32 *mp;
+
+	if (cfg->fc_mx == NULL)
+		return 0;
+
+	mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+	if (unlikely(!mp))
+		return -ENOMEM;
+
+	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+		int type = nla_type(nla);
+
+		if (type) {
+			u32 val;
+
+			if (unlikely(type > RTAX_MAX))
+				goto err;
+			if (type == RTAX_CC_ALGO) {
+				char tmp[TCP_CA_NAME_MAX];
+
+				nla_strlcpy(tmp, nla, sizeof(tmp));
+				val = tcp_ca_get_key_by_name(tmp);
+				if (val == TCP_CA_UNSPEC)
+					goto err;
+			} else {
+				val = nla_get_u32(nla);
+			}
+
+			mp[type - 1] = val;
+			__set_bit(type - 1, mxc->mx_valid);
+		}
+	}
+
+	mxc->mx = mp;
+
+	return 0;
+ err:
+	kfree(mp);
+	return -EINVAL;
+}
 
 int ip6_route_add(struct fib6_config *cfg)
 {
@@ -1483,6 +1525,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
+	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1678,8 +1721,14 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
+	err = ip6_convert_metrics(&mxc, cfg);
+	if (err)
+		goto out;
 
+	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
+
+	kfree(mxc.mx);
+	return err;
 out:
 	if (dev)
 		dev_put(dev);
@@ -2535,7 +2584,8 @@ static inline size_t rt6_nlmsg_size(void)
 	       + nla_total_size(4) /* RTA_OIF */
 	       + nla_total_size(4) /* RTA_PRIORITY */
 	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
-	       + nla_total_size(sizeof(struct rta_cacheinfo));
+	       + nla_total_size(sizeof(struct rta_cacheinfo))
+	       + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
 }
 
 static int rt6_fill_node(struct net *net,
@@ -2676,7 +2726,8 @@ static int rt6_fill_node(struct net *net,
 	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cdbfe5af6187..e4cbd5798eba 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1763,6 +1763,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.get_size	= ipip6_get_size,
 	.fill_info	= ipip6_fill_info,
 	.dellink	= ipip6_dellink,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9c0b54e87b47..5d46832c6f72 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1199,6 +1199,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
 						     newnp->opt->opt_flen);
 
+	tcp_ca_openreq_child(newsk, dst);
+
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 189dc4ae3eca..d048d46779fc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -909,7 +909,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto csum_error;
 		}
 
-		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
 			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 						 ip6_compute_pseudo);
 
@@ -990,9 +990,10 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 {
 	unsigned int offset;
 	struct udphdr *uh = udp_hdr(skb);
+	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
 	__wsum csum = 0;
 
-	if (skb_queue_len(&sk->sk_write_queue) == 1) {
+	if (!frags) {
 		/* Only one fragment on the socket.  */
 		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct udphdr, check);
@@ -1008,9 +1009,9 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 
 		skb->ip_summed = CHECKSUM_NONE;
 
-		skb_queue_walk(&sk->sk_write_queue, skb) {
-			csum = csum_add(csum, skb->csum);
-		}
+		do {
+			csum = csum_add(csum, frags->csum);
+		} while ((frags = frags->next));
 
 		uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP,
 					    csum);
@@ -1023,26 +1024,15 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
  *	Sending
  */
 
-static int udp_v6_push_pending_frames(struct sock *sk)
+static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6)
 {
-	struct sk_buff *skb;
+	struct sock *sk = skb->sk;
 	struct udphdr *uh;
-	struct udp_sock  *up = udp_sk(sk);
-	struct inet_sock *inet = inet_sk(sk);
-	struct flowi6 *fl6;
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
 	__wsum csum = 0;
-
-	if (up->pending == AF_INET)
-		return udp_push_pending_frames(sk);
-
-	fl6 = &inet->cork.fl.u.ip6;
-
-	/* Grab the skbuff where UDP header space exists. */
-	skb = skb_peek(&sk->sk_write_queue);
-	if (skb == NULL)
-		goto out;
+	int offset = skb_transport_offset(skb);
+	int len = skb->len - offset;
 
 	/*
 	 * Create a UDP header
@@ -1050,29 +1040,28 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	uh = udp_hdr(skb);
 	uh->source = fl6->fl6_sport;
 	uh->dest = fl6->fl6_dport;
-	uh->len = htons(up->len);
+	uh->len = htons(len);
 	uh->check = 0;
 
 	if (is_udplite)
-		csum = udplite_csum_outgoing(sk, skb);
-	else if (up->no_check6_tx) {   /* UDP csum disabled */
+		csum = udplite_csum(skb);
+	else if (udp_sk(sk)->no_check6_tx) {   /* UDP csum disabled */
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
-		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr,
-				     up->len);
+		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len);
 		goto send;
 	} else
-		csum = udp_csum_outgoing(sk, skb);
+		csum = udp_csum(skb);
 
 	/* add protocol-dependent pseudo-header */
 	uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
-				    up->len, fl6->flowi6_proto, csum);
+				    len, fl6->flowi6_proto, csum);
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
 send:
-	err = ip6_push_pending_frames(sk);
+	err = ip6_send_skb(skb);
 	if (err) {
 		if (err == -ENOBUFS && !inet6_sk(sk)->recverr) {
 			UDP6_INC_STATS_USER(sock_net(sk),
@@ -1082,6 +1071,30 @@ send:
 	} else
 		UDP6_INC_STATS_USER(sock_net(sk),
 				    UDP_MIB_OUTDATAGRAMS, is_udplite);
+	return err;
+}
+
+static int udp_v6_push_pending_frames(struct sock *sk)
+{
+	struct sk_buff *skb;
+	struct udp_sock  *up = udp_sk(sk);
+	struct flowi6 fl6;
+	int err = 0;
+
+	if (up->pending == AF_INET)
+		return udp_push_pending_frames(sk);
+
+	/* ip6_finish_skb will release the cork, so make a copy of
+	 * fl6 here.
+	 */
+	fl6 = inet_sk(sk)->cork.fl.u.ip6;
+
+	skb = ip6_finish_skb(sk);
+	if (!skb)
+		goto out;
+
+	err = udp_v6_send_skb(skb, &fl6);
+
 out:
 	up->len = 0;
 	up->pending = 0;
@@ -1164,6 +1177,7 @@ do_udp_sendmsg:
 	if (len > INT_MAX - sizeof(struct udphdr))
 		return -EMSGSIZE;
 
+	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
 	if (up->pending) {
 		/*
 		 * There are pending frames.
@@ -1294,6 +1308,20 @@ do_udp_sendmsg:
 		goto do_confirm;
 back_from_confirm:
 
+	/* Lockless fast path for the non-corking case */
+	if (!corkreq) {
+		struct sk_buff *skb;
+
+		skb = ip6_make_skb(sk, getfrag, msg, ulen,
+				   sizeof(struct udphdr), hlimit, tclass, opt,
+				   &fl6, (struct rt6_info *)dst,
+				   msg->msg_flags, dontfrag);
+		err = PTR_ERR(skb);
+		if (!IS_ERR_OR_NULL(skb))
+			err = udp_v6_send_skb(skb, &fl6);
+		goto release_dst;
+	}
+
 	lock_sock(sk);
 	if (unlikely(up->pending)) {
 		/* The socket is already corked while preparing it. */
@@ -1311,7 +1339,6 @@ do_append_data:
 	if (dontfrag < 0)
 		dontfrag = np->dontfrag;
 	up->len += ulen;
-	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
 	err = ip6_append_data(sk, getfrag, msg, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
 		(struct rt6_info *)dst,
@@ -1323,6 +1350,11 @@ do_append_data:
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
 		up->pending = 0;
 
+	if (err > 0)
+		err = np->recverr ? net_xmit_errno(err) : 0;
+	release_sock(sk);
+
+release_dst:
 	if (dst) {
 		if (connected) {
 			ip6_dst_store(sk, dst,
@@ -1339,9 +1371,6 @@ do_append_data:
 		dst = NULL;
 	}
 
-	if (err > 0)
-		err = np->recverr ? net_xmit_errno(err) : 0;
-	release_sock(sk);
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
author	Linus Torvalds <torvalds@linux-foundation.org>	2015-02-10 20:01:30 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2015-02-10 20:01:30 -0800
commit	c5ce28df0e7c01a1de23c36ebdefcd803f2b6cbb (patch)
tree	9830baf38832769e1cf621708889111bbe3c93df /net/ipv6
parent	29afc4e9a408f2304e09c6dd0dbcfbd2356d0faa (diff)
parent	9399f0c51489ae8c16d6559b82a452fdc1895e91 (diff)