1 files changed, 291 insertions, 222 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 459c011b1d4..8d3b6b0e985 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -43,7 +43,6 @@
  */
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -85,7 +84,7 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
 EXPORT_SYMBOL(sysctl_ip_default_ttl);
 
 /* Generate a checksum for an outgoing IP datagram. */
-__inline__ void ip_send_check(struct iphdr *iph)
+void ip_send_check(struct iphdr *iph)
 {
 	iph->check = 0;
 	iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
@@ -102,29 +101,17 @@ int __ip_local_out(struct sk_buff *skb)
 		       skb_dst(skb)->dev, dst_output);
 }
 
-int ip_local_out(struct sk_buff *skb)
+int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
 
 	err = __ip_local_out(skb);
 	if (likely(err == 1))
-		err = dst_output(skb);
+		err = dst_output_sk(sk, skb);
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(ip_local_out);
-
-/* dev_loopback_xmit for use with netfilter. */
-static int ip_dev_loopback_xmit(struct sk_buff *newskb)
-{
-	skb_reset_mac_header(newskb);
-	__skb_pull(newskb, skb_network_offset(newskb));
-	newskb->pkt_type = PACKET_LOOPBACK;
-	newskb->ip_summed = CHECKSUM_UNNECESSARY;
-	WARN_ON(!skb_dst(newskb));
-	netif_rx_ni(newskb);
-	return 0;
-}
+EXPORT_SYMBOL_GPL(ip_local_out_sk);
 
 static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
 {
@@ -140,14 +127,14 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
  *
  */
 int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
-			  __be32 saddr, __be32 daddr, struct ip_options *opt)
+			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct rtable *rt = skb_rtable(skb);
 	struct iphdr *iph;
 
 	/* Build the IP header. */
-	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
+	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	iph->version  = 4;
@@ -158,14 +145,14 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	else
 		iph->frag_off = 0;
 	iph->ttl      = ip_select_ttl(inet, &rt->dst);
-	iph->daddr    = rt->rt_dst;
-	iph->saddr    = rt->rt_src;
+	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
+	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(iph, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
-	if (opt && opt->optlen) {
-		iph->ihl += opt->optlen>>2;
-		ip_options_build(skb, opt, daddr, rt, 0);
+	if (opt && opt->opt.optlen) {
+		iph->ihl += opt->opt.optlen>>2;
+		ip_options_build(skb, &opt->opt, daddr, rt, 0);
 	}
 
 	skb->priority = sk->sk_priority;
@@ -182,6 +169,8 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	struct rtable *rt = (struct rtable *)dst;
 	struct net_device *dev = dst->dev;
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
+	struct neighbour *neigh;
+	u32 nexthop;
 
 	if (rt->rt_type == RTN_MULTICAST) {
 		IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len);
@@ -199,27 +188,69 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 		}
 		if (skb->sk)
 			skb_set_owner_w(skb2, skb->sk);
-		kfree_skb(skb);
+		consume_skb(skb);
 		skb = skb2;
 	}
 
-	if (dst->hh)
-		return neigh_hh_output(dst->hh, skb);
-	else if (dst->neighbour)
-		return dst->neighbour->output(skb);
+	rcu_read_lock_bh();
+	nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
+	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
+	if (unlikely(!neigh))
+		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+	if (!IS_ERR(neigh)) {
+		int res = dst_neigh_output(dst, neigh, skb);
+
+		rcu_read_unlock_bh();
+		return res;
+	}
+	rcu_read_unlock_bh();
 
-	if (net_ratelimit())
-		printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n");
+	net_dbg_ratelimited("%s: No header cache and no neighbour!\n",
+			    __func__);
 	kfree_skb(skb);
 	return -EINVAL;
 }
 
-static inline int ip_skb_dst_mtu(struct sk_buff *skb)
+static int ip_finish_output_gso(struct sk_buff *skb)
 {
-	struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL;
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	/* common case: locally created skb or seglen is <= mtu */
+	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+		return ip_finish_output2(skb);
+
+	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	 *
+	 * This can happen in two cases:
+	 * 1) TCP GRO packet, DF bit not set
+	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+	 * from host network stack.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = ip_fragment(segs, ip_finish_output2);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
 
-	return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ?
-	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
+	return ret;
 }
 
 static int ip_finish_output(struct sk_buff *skb)
@@ -231,15 +262,17 @@ static int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+	if (skb_is_gso(skb))
+		return ip_finish_output_gso(skb);
+
+	if (skb->len > ip_skb_dst_mtu(skb))
 		return ip_fragment(skb, ip_finish_output2);
-	else
-		return ip_finish_output2(skb);
+
+	return ip_finish_output2(skb);
 }
 
-int ip_mc_output(struct sk_buff *skb)
+int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
 	struct rtable *rt = skb_rtable(skb);
 	struct net_device *dev = rt->dst.dev;
 
@@ -275,7 +308,7 @@ int ip_mc_output(struct sk_buff *skb)
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
 					newskb, NULL, newskb->dev,
-					ip_dev_loopback_xmit);
+					dev_loopback_xmit);
 		}
 
 		/* Multicasts with ttl 0 must not go beyond the host */
@@ -290,7 +323,7 @@ int ip_mc_output(struct sk_buff *skb)
 		struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 		if (newskb)
 			NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb,
-				NULL, newskb->dev, ip_dev_loopback_xmit);
+				NULL, newskb->dev, dev_loopback_xmit);
 	}
 
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL,
@@ -298,7 +331,7 @@ int ip_mc_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_output(struct sk_buff *skb)
+int ip_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
 
@@ -312,11 +345,26 @@ int ip_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_queue_xmit(struct sk_buff *skb)
+/*
+ * copy saddr and daddr, possibly using 64bit load/stores
+ * Equivalent to :
+ *   iph->saddr = fl4->saddr;
+ *   iph->daddr = fl4->daddr;
+ */
+static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
+{
+	BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
+		     offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
+	memcpy(&iph->saddr, &fl4->saddr,
+	       sizeof(fl4->saddr) + sizeof(fl4->daddr));
+}
+
+/* Note: skb->sk can be different from sk, in case of tunnels */
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 {
-	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
-	struct ip_options *opt = inet->opt;
+	struct ip_options_rcu *inet_opt;
+	struct flowi4 *fl4;
 	struct rtable *rt;
 	struct iphdr *iph;
 	int res;
@@ -325,6 +373,8 @@ int ip_queue_xmit(struct sk_buff *skb)
 	 * f.e. by something like SCTP.
 	 */
 	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	fl4 = &fl->u.ip4;
 	rt = skb_rtable(skb);
 	if (rt != NULL)
 		goto packet_routed;
@@ -336,14 +386,14 @@ int ip_queue_xmit(struct sk_buff *skb)
 
 		/* Use correct destination address if we have options. */
 		daddr = inet->inet_daddr;
-		if(opt && opt->srr)
-			daddr = opt->faddr;
+		if (inet_opt && inet_opt->opt.srr)
+			daddr = inet_opt->opt.faddr;
 
 		/* If this fails, retransmit mechanism of transport layer will
 		 * keep trying until route appears or the connection times
 		 * itself out.
 		 */
-		rt = ip_route_output_ports(sock_net(sk), sk,
+		rt = ip_route_output_ports(sock_net(sk), fl4, sk,
 					   daddr, inet->inet_saddr,
 					   inet->inet_dport,
 					   inet->inet_sport,
@@ -357,32 +407,32 @@ int ip_queue_xmit(struct sk_buff *skb)
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
-	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
+	skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
-	if (ip_dont_fragment(sk, &rt->dst) && !skb->local_df)
+	if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
 		iph->frag_off = htons(IP_DF);
 	else
 		iph->frag_off = 0;
 	iph->ttl      = ip_select_ttl(inet, &rt->dst);
 	iph->protocol = sk->sk_protocol;
-	iph->saddr    = rt->rt_src;
-	iph->daddr    = rt->rt_dst;
+	ip_copy_addrs(iph, fl4);
+
 	/* Transport layer set skb->h.foo itself. */
 
-	if (opt && opt->optlen) {
-		iph->ihl += opt->optlen >> 2;
-		ip_options_build(skb, opt, inet->inet_daddr, rt, 0);
+	if (inet_opt && inet_opt->opt.optlen) {
+		iph->ihl += inet_opt->opt.optlen >> 2;
+		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(iph, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
+	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
@@ -416,10 +466,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
-    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-	to->nf_trace = from->nf_trace;
-#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	to->ipvs_property = from->ipvs_property;
 #endif
@@ -453,10 +499,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	iph = ip_hdr(skb);
 
-	if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
+	mtu = ip_skb_dst_mtu(skb);
+	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
+		     (IPCB(skb)->frag_max_size &&
+		      IPCB(skb)->frag_max_size > mtu))) {
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(ip_skb_dst_mtu(skb)));
+			  htonl(mtu));
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	}
@@ -466,7 +515,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 */
 
 	hlen = iph->ihl * 4;
-	mtu = dst_mtu(&rt->dst) - hlen;	/* Size of data space */
+	mtu = mtu - hlen;	/* Size of data space */
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge)
 		mtu -= nf_bridge_mtu_reduction(skb);
@@ -486,7 +535,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
-		    (iph->frag_off & htons(IP_MF|IP_OFFSET)) ||
+		    ip_is_fragment(iph) ||
 		    skb_cloned(skb))
 			goto slow_path;
 
@@ -579,6 +628,11 @@ slow_path_clean:
 	}
 
 slow_path:
+	/* for offloaded checksums cleanup checksum before fragmentation */
+	if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb))
+		goto fail;
+	iph = ip_hdr(skb);
+
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;		/* Where to start from */
 
@@ -686,7 +740,7 @@ slow_path:
 
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
 	}
-	kfree_skb(skb);
+	consume_skb(skb);
 	IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
 	return err;
 
@@ -731,7 +785,7 @@ static inline int ip_ufo_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 hh_len, int fragheaderlen,
-			int transhdrlen, int mtu, unsigned int flags)
+			int transhdrlen, int maxfraglen, unsigned int flags)
 {
 	struct sk_buff *skb;
 	int err;
@@ -760,21 +814,29 @@ static inline int ip_ufo_append_data(struct sock *sk,
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
 
-		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
 
-		/* specify the length of each IP datagram fragment */
-		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
 		__skb_queue_tail(queue, skb);
+	} else if (skb_is_gso(skb)) {
+		goto append;
 	}
 
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	/* specify the length of each IP datagram fragment */
+	skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
+	skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
+append:
 	return skb_append_datato_frags(sk, skb, getfrag, from,
 				       (length - transhdrlen));
 }
 
-static int __ip_append_data(struct sock *sk, struct sk_buff_head *queue,
+static int __ip_append_data(struct sock *sk,
+			    struct flowi4 *fl4,
+			    struct sk_buff_head *queue,
 			    struct inet_cork *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,
@@ -790,23 +852,24 @@ static int __ip_append_data(struct sock *sk, struct sk_buff_head *queue,
 	int copy;
 	int err;
 	int offset = 0;
-	unsigned int maxfraglen, fragheaderlen;
+	unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
 
-	exthdrlen = transhdrlen ? rt->dst.header_len : 0;
-	length += exthdrlen;
-	transhdrlen += exthdrlen;
+	skb = skb_peek_tail(queue);
+
+	exthdrlen = !skb ? rt->dst.header_len : 0;
 	mtu = cork->fragsize;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
-	if (cork->length + length > 0xFFFF - fragheaderlen) {
-		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport,
-			       mtu-exthdrlen);
+	if (cork->length + length > maxnonfragsize - fragheaderlen) {
+		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
@@ -820,15 +883,13 @@ static int __ip_append_data(struct sock *sk, struct sk_buff_head *queue,
 	    !exthdrlen)
 		csummode = CHECKSUM_PARTIAL;
 
-	skb = skb_peek_tail(queue);
-
 	cork->length += length;
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO)) {
+	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
-					 mtu, flags);
+					 maxfraglen, flags);
 		if (err)
 			goto error;
 		return 0;
@@ -878,17 +939,16 @@ alloc_new_skb:
 			else
 				alloclen = fraglen;
 
+			alloclen += exthdrlen;
+
 			/* The last fragment gets additional space at tail.
 			 * Note, with MSG_MORE we overallocate on fragments,
 			 * because we have no idea what fragment will be
 			 * the last.
 			 */
-			if (datalen == length + fraggap) {
+			if (datalen == length + fraggap)
 				alloclen += rt->dst.trailer_len;
-				/* make sure mtu is not reached */
-				if (datalen > mtu - fragheaderlen - rt->dst.trailer_len)
-					datalen -= ALIGN(rt->dst.trailer_len, 8);
-			}
+
 			if (transhdrlen) {
 				skb = sock_alloc_send_skb(sk,
 						alloclen + hh_len + 15,
@@ -921,11 +981,11 @@ alloc_new_skb:
 			/*
 			 *	Find where to start putting bytes.
 			 */
-			data = skb_put(skb, fraglen);
+			data = skb_put(skb, fraglen + exthdrlen);
 			skb_set_network_header(skb, exthdrlen);
 			skb->transport_header = (skb->network_header +
 						 fragheaderlen);
-			data += fragheaderlen;
+			data += fragheaderlen + exthdrlen;
 
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
@@ -972,46 +1032,30 @@ alloc_new_skb:
 			}
 		} else {
 			int i = skb_shinfo(skb)->nr_frags;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
-			struct page *page = cork->page;
-			int off = cork->off;
-			unsigned int left;
-
-			if (page && (left = PAGE_SIZE - off) > 0) {
-				if (copy >= left)
-					copy = left;
-				if (page != frag->page) {
-					if (i == MAX_SKB_FRAGS) {
-						err = -EMSGSIZE;
-						goto error;
-					}
-					get_page(page);
-					skb_fill_page_desc(skb, i, page, off, 0);
-					frag = &skb_shinfo(skb)->frags[i];
-				}
-			} else if (i < MAX_SKB_FRAGS) {
-				if (copy > PAGE_SIZE)
-					copy = PAGE_SIZE;
-				page = alloc_pages(sk->sk_allocation, 0);
-				if (page == NULL)  {
-					err = -ENOMEM;
-					goto error;
-				}
-				cork->page = page;
-				cork->off = 0;
 
-				skb_fill_page_desc(skb, i, page, 0, 0);
-				frag = &skb_shinfo(skb)->frags[i];
-			} else {
-				err = -EMSGSIZE;
-				goto error;
-			}
-			if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
-				err = -EFAULT;
+			err = -ENOMEM;
+			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
+
+			if (!skb_can_coalesce(skb, i, pfrag->page,
+					      pfrag->offset)) {
+				err = -EMSGSIZE;
+				if (i == MAX_SKB_FRAGS)
+					goto error;
+
+				__skb_fill_page_desc(skb, i, pfrag->page,
+						     pfrag->offset, 0);
+				skb_shinfo(skb)->nr_frags = ++i;
+				get_page(pfrag->page);
 			}
-			cork->off += copy;
-			frag->size += copy;
+			copy = min_t(int, copy, pfrag->size - pfrag->offset);
+			if (getfrag(from,
+				    page_address(pfrag->page) + pfrag->offset,
+				    offset, copy, skb->len, skb) < 0)
+				goto error_efault;
+
+			pfrag->offset += copy;
+			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 			skb->len += copy;
 			skb->data_len += copy;
 			skb->truesize += copy;
@@ -1023,6 +1067,8 @@ alloc_new_skb:
 
 	return 0;
 
+error_efault:
+	err = -EFAULT;
 error:
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
@@ -1032,8 +1078,7 @@ error:
 static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			 struct ipcm_cookie *ipc, struct rtable **rtp)
 {
-	struct inet_sock *inet = inet_sk(sk);
-	struct ip_options *opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
 	/*
@@ -1047,7 +1092,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			if (unlikely(cork->opt == NULL))
 				return -ENOBUFS;
 		}
-		memcpy(cork->opt, opt, sizeof(struct ip_options) + opt->optlen);
+		memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
 		cork->flags |= IPCORK_OPT;
 		cork->addr = ipc->addr;
 	}
@@ -1058,13 +1103,14 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	 * We steal reference to this route, caller should not release it
 	 */
 	*rtp = NULL;
-	cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ?
-			 rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
 	cork->dst = &rt->dst;
 	cork->length = 0;
+	cork->ttl = ipc->ttl;
+	cork->tos = ipc->tos;
+	cork->priority = ipc->priority;
 	cork->tx_flags = ipc->tx_flags;
-	cork->page = NULL;
-	cork->off = 0;
 
 	return 0;
 }
@@ -1080,7 +1126,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
  *
  *	LATER: length must be adjusted by pad at tail, when it is required.
  */
-int ip_append_data(struct sock *sk,
+int ip_append_data(struct sock *sk, struct flowi4 *fl4,
 		   int getfrag(void *from, char *to, int offset, int len,
 			       int odd, struct sk_buff *skb),
 		   void *from, int length, int transhdrlen,
@@ -1094,29 +1140,31 @@ int ip_append_data(struct sock *sk,
 		return 0;
 
 	if (skb_queue_empty(&sk->sk_write_queue)) {
-		err = ip_setup_cork(sk, &inet->cork, ipc, rtp);
+		err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp);
 		if (err)
 			return err;
 	} else {
 		transhdrlen = 0;
 	}
 
-	return __ip_append_data(sk, &sk->sk_write_queue, &inet->cork, getfrag,
+	return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base,
+				sk_page_frag(sk), getfrag,
 				from, length, transhdrlen, flags);
 }
 
-ssize_t	ip_append_page(struct sock *sk, struct page *page,
+ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		       int offset, size_t size, int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sk_buff *skb;
 	struct rtable *rt;
 	struct ip_options *opt = NULL;
+	struct inet_cork *cork;
 	int hh_len;
 	int mtu;
 	int len;
 	int err;
-	unsigned int maxfraglen, fragheaderlen, fraggap;
+	unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
 
 	if (inet->hdrincl)
 		return -EPERM;
@@ -1127,28 +1175,31 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 	if (skb_queue_empty(&sk->sk_write_queue))
 		return -EINVAL;
 
-	rt = (struct rtable *)inet->cork.dst;
-	if (inet->cork.flags & IPCORK_OPT)
-		opt = inet->cork.opt;
+	cork = &inet->cork.base;
+	rt = (struct rtable *)cork->dst;
+	if (cork->flags & IPCORK_OPT)
+		opt = cork->opt;
 
 	if (!(rt->dst.dev->features&NETIF_F_SG))
 		return -EOPNOTSUPP;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
-	mtu = inet->cork.fragsize;
+	mtu = cork->fragsize;
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
-	if (inet->cork.length + size > 0xFFFF - fragheaderlen) {
-		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu);
+	if (cork->length + size > maxnonfragsize - fragheaderlen) {
+		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
 	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
 		return -EINVAL;
 
-	inet->cork.length += size;
+	cork->length += size;
 	if ((size + skb->len > mtu) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
@@ -1218,7 +1269,7 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 		if (len > size)
 			len = size;
 		if (skb_can_coalesce(skb, i, page, offset)) {
-			skb_shinfo(skb)->frags[i-1].size += len;
+			skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], len);
 		} else if (i < MAX_SKB_FRAGS) {
 			get_page(page);
 			skb_fill_page_desc(skb, i, page, offset, len);
@@ -1243,7 +1294,7 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 	return 0;
 
 error:
-	inet->cork.length -= size;
+	cork->length -= size;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
@@ -1262,6 +1313,7 @@ static void ip_cork_release(struct inet_cork *cork)
  *	and push them out.
  */
 struct sk_buff *__ip_make_skb(struct sock *sk,
+			      struct flowi4 *fl4,
 			      struct sk_buff_head *queue,
 			      struct inet_cork *cork)
 {
@@ -1297,13 +1349,13 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	 * to fragment the frame generated here. No matter, what transforms
 	 * how transforms change size of the packet, it will come out.
 	 */
-	if (inet->pmtudisc < IP_PMTUDISC_DO)
-		skb->local_df = 1;
+	skb->ignore_df = ip_sk_ignore_df(sk);
 
 	/* DF bit is set when we want to see DF on outgoing frames.
-	 * If local_df is set too, we still allow to fragment this frame
+	 * If ignore_df is set too, we still allow to fragment this frame
 	 * locally. */
-	if (inet->pmtudisc >= IP_PMTUDISC_DO ||
+	if (inet->pmtudisc == IP_PMTUDISC_DO ||
+	    inet->pmtudisc == IP_PMTUDISC_PROBE ||
 	    (skb->len <= dst_mtu(&rt->dst) &&
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
@@ -1311,27 +1363,29 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	if (cork->flags & IPCORK_OPT)
 		opt = cork->opt;
 
-	if (rt->rt_type == RTN_MULTICAST)
+	if (cork->ttl != 0)
+		ttl = cork->ttl;
+	else if (rt->rt_type == RTN_MULTICAST)
 		ttl = inet->mc_ttl;
 	else
 		ttl = ip_select_ttl(inet, &rt->dst);
 
-	iph = (struct iphdr *)skb->data;
+	iph = ip_hdr(skb);
 	iph->version = 4;
 	iph->ihl = 5;
+	iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
+	iph->frag_off = df;
+	iph->ttl = ttl;
+	iph->protocol = sk->sk_protocol;
+	ip_copy_addrs(iph, fl4);
+	ip_select_ident(skb, sk);
+
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
 		ip_options_build(skb, opt, cork->addr, rt, 0);
 	}
-	iph->tos = inet->tos;
-	iph->frag_off = df;
-	ip_select_ident(iph, &rt->dst, sk);
-	iph->ttl = ttl;
-	iph->protocol = sk->sk_protocol;
-	iph->saddr = rt->rt_src;
-	iph->daddr = rt->rt_dst;
 
-	skb->priority = sk->sk_priority;
+	skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
 	skb->mark = sk->sk_mark;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1349,9 +1403,8 @@ out:
 	return skb;
 }
 
-int ip_send_skb(struct sk_buff *skb)
+int ip_send_skb(struct net *net, struct sk_buff *skb)
 {
-	struct net *net = sock_net(skb->sk);
 	int err;
 
 	err = ip_local_out(skb);
@@ -1365,16 +1418,16 @@ int ip_send_skb(struct sk_buff *skb)
 	return err;
 }
 
-int ip_push_pending_frames(struct sock *sk)
+int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)
 {
 	struct sk_buff *skb;
 
-	skb = ip_finish_skb(sk);
+	skb = ip_finish_skb(sk, fl4);
 	if (!skb)
 		return 0;
 
 	/* Netfilter gets whole the not fragmented skb. */
-	return ip_send_skb(skb);
+	return ip_send_skb(sock_net(sk), skb);
 }
 
 /*
@@ -1394,17 +1447,18 @@ static void __ip_flush_pending_frames(struct sock *sk,
 
 void ip_flush_pending_frames(struct sock *sk)
 {
-	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
+	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
 
 struct sk_buff *ip_make_skb(struct sock *sk,
+			    struct flowi4 *fl4,
 			    int getfrag(void *from, char *to, int offset,
 					int len, int odd, struct sk_buff *skb),
 			    void *from, int length, int transhdrlen,
 			    struct ipcm_cookie *ipc, struct rtable **rtp,
 			    unsigned int flags)
 {
-	struct inet_cork cork = {};
+	struct inet_cork cork;
 	struct sk_buff_head queue;
 	int err;
 
@@ -1413,18 +1467,22 @@ struct sk_buff *ip_make_skb(struct sock *sk,
 
 	__skb_queue_head_init(&queue);
 
+	cork.flags = 0;
+	cork.addr = 0;
+	cork.opt = NULL;
 	err = ip_setup_cork(sk, &cork, ipc, rtp);
 	if (err)
 		return ERR_PTR(err);
 
-	err = __ip_append_data(sk, &queue, &cork, getfrag,
+	err = __ip_append_data(sk, fl4, &queue, &cork,
+			       &current->task_frag, getfrag,
 			       from, length, transhdrlen, flags);
 	if (err) {
 		__ip_flush_pending_frames(sk, &queue, &cork);
 		return ERR_PTR(err);
 	}
 
-	return __ip_make_skb(sk, &queue, &cork);
+	return __ip_make_skb(sk, fl4, &queue, &cork);
 }
 
 /*
@@ -1442,77 +1500,88 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 
 /*
  *	Generic function to send a packet as reply to another packet.
- *	Used to send TCP resets so far. ICMP should use this function too.
+ *	Used to send some TCP resets/acks so far.
  *
- *	Should run single threaded per socket because it uses the sock
- *     	structure to pass arguments.
+ *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg,
-		   unsigned int len)
+static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
+	.sk = {
+		.__sk_common = {
+			.skc_refcnt = ATOMIC_INIT(1),
+		},
+		.sk_wmem_alloc	= ATOMIC_INIT(1),
+		.sk_allocation	= GFP_ATOMIC,
+		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
+	},
+	.pmtudisc	= IP_PMTUDISC_WANT,
+	.uc_ttl		= -1,
+};
+
+void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
+			   __be32 saddr, const struct ip_reply_arg *arg,
+			   unsigned int len)
 {
-	struct inet_sock *inet = inet_sk(sk);
-	struct {
-		struct ip_options	opt;
-		char			data[40];
-	} replyopts;
+	struct ip_options_data replyopts;
 	struct ipcm_cookie ipc;
-	__be32 daddr;
+	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct sk_buff *nskb;
+	struct sock *sk;
+	struct inet_sock *inet;
 
-	if (ip_options_echo(&replyopts.opt, skb))
+	if (ip_options_echo(&replyopts.opt.opt, skb))
 		return;
 
-	daddr = ipc.addr = rt->rt_src;
+	ipc.addr = daddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
-	if (replyopts.opt.optlen) {
+	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;
 
-		if (ipc.opt->srr)
-			daddr = replyopts.opt.faddr;
+		if (replyopts.opt.opt.srr)
+			daddr = replyopts.opt.opt.faddr;
 	}
 
-	{
-		struct flowi4 fl4 = {
-			.flowi4_oif = arg->bound_dev_if,
-			.daddr = daddr,
-			.saddr = rt->rt_spec_dst,
-			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
-			.fl4_sport = tcp_hdr(skb)->dest,
-			.fl4_dport = tcp_hdr(skb)->source,
-			.flowi4_proto = sk->sk_protocol,
-			.flowi4_flags = ip_reply_arg_flowi_flags(arg),
-		};
-		security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
-		rt = ip_route_output_key(sock_net(sk), &fl4);
-		if (IS_ERR(rt))
-			return;
-	}
+	flowi4_init_output(&fl4, arg->bound_dev_if,
+			   IP4_REPLY_MARK(net, skb->mark),
+			   RT_TOS(arg->tos),
+			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
+			   ip_reply_arg_flowi_flags(arg),
+			   daddr, saddr,
+			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt))
+		return;
 
-	/* And let IP do all the hard work.
+	inet = &get_cpu_var(unicast_sock);
 
-	   This chunk is not reenterable, hence spinlock.
-	   Note that it uses the fact, that this function is called
-	   with locally disabled BH and that sk cannot be already spinlocked.
-	 */
-	bh_lock_sock(sk);
-	inet->tos = ip_hdr(skb)->tos;
+	inet->tos = arg->tos;
+	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	ip_append_data(sk, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
+	sock_net_set(sk, net);
+	__skb_queue_head_init(&sk->sk_write_queue);
+	sk->sk_sndbuf = sysctl_wmem_default;
+	ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
 		       &ipc, &rt, MSG_DONTWAIT);
-	if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
+	nskb = skb_peek(&sk->sk_write_queue);
+	if (nskb) {
 		if (arg->csumoffset >= 0)
-			*((__sum16 *)skb_transport_header(skb) +
-			  arg->csumoffset) = csum_fold(csum_add(skb->csum,
+			*((__sum16 *)skb_transport_header(nskb) +
+			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
-		skb->ip_summed = CHECKSUM_NONE;
-		ip_push_pending_frames(sk);
+		nskb->ip_summed = CHECKSUM_NONE;
+		skb_orphan(nskb);
+		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
+		ip_push_pending_frames(sk, &fl4);
 	}
 
-	bh_unlock_sock(sk);
+	put_cpu_var(unicast_sock);
 
 	ip_rt_put(rt);
 }
@@ -1522,7 +1591,7 @@ void __init ip_init(void)
 	ip_rt_init();
 	inet_initpeers();
 
-#if defined(CONFIG_IP_MULTICAST) && defined(CONFIG_PROC_FS)
-	igmp_mc_proc_init();
+#if defined(CONFIG_IP_MULTICAST)
+	igmp_mc_init();
 #endif
 }