Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 274 insertions, 200 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 7649d7750075..84f26e8e6c60 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -82,6 +82,7 @@
 #include <linux/tcp.h>
 
 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)
@@ -130,7 +131,7 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
         int ttl = inet->uc_ttl;
 
         if (ttl < 0)
-                ttl = dst_metric(dst, RTAX_HOPLIMIT);
+                ttl = ip4_dst_hoplimit(dst);
         return ttl;
 }
 
@@ -139,14 +140,14 @@ 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;
@@ -157,14 +158,14 @@ 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);
 
-        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;
@@ -311,11 +312,12 @@ int ip_output(struct sk_buff *skb)
                             !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_queue_xmit(struct sk_buff *skb)
+int ip_queue_xmit(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;
@@ -324,6 +326,8 @@ 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;
@@ -335,40 +339,32 @@ 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;
-
-                {
-                        struct flowi fl = { .oif = sk->sk_bound_dev_if,
-                                            .mark = sk->sk_mark,
-                                            .nl_u = { .ip4_u =
-                                                      { .daddr = daddr,
-                                                        .saddr = inet->inet_saddr,
-                                                        .tos = RT_CONN_FLAGS(sk) } },
-                                            .proto = sk->sk_protocol,
-                                            .flags = inet_sk_flowi_flags(sk),
-                                            .uli_u = { .ports =
-                                                       { .sport = inet->inet_sport,
-                                                         .dport = inet->inet_dport } } };
-
-                        /* If this fails, retransmit mechanism of transport layer will
-                         * keep trying until route appears or the connection times
-                         * itself out.
-                         */
-                        security_sk_classify_flow(sk, &fl);
-                        if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0))
-                                goto no_route;
-                }
+                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), fl4, sk,
+                                           daddr, inet->inet_saddr,
+                                           inet->inet_dport,
+                                           inet->inet_sport,
+                                           sk->sk_protocol,
+                                           RT_CONN_FLAGS(sk),
+                                           sk->sk_bound_dev_if);
+                if (IS_ERR(rt))
+                        goto no_route;
                 sk_setup_caps(sk, &rt->dst);
         }
         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 && fl4->daddr != rt->rt_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));
@@ -378,13 +374,13 @@ packet_routed:
                 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;
+        iph->saddr    = fl4->saddr;
+        iph->daddr    = fl4->daddr;
         /* 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,
@@ -487,7 +483,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
          * LATER: this step can be merged to real generation of fragments,
          * we can switch to copy when see the first bad fragment.
          */
-        if (skb_has_frags(skb)) {
+        if (skb_has_frag_list(skb)) {
                 struct sk_buff *frag, *frag2;
                 int first_len = skb_pagelen(skb);
 
@@ -610,7 +606,7 @@ slow_path:
                 /* IF: it doesn't fit, use 'mtu' - the data space left */
                 if (len > mtu)
                         len = mtu;
-                /* IF: we are not sending upto and including the packet end
+                /* IF: we are not sending up to and including the packet end
                    then align the next start on an eight byte boundary */
                 if (len < left) {
                         len &= ~7;
@@ -734,6 +730,7 @@ csum_page(struct page *page, int offset, int copy)
 }
 
 static inline int ip_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,
@@ -746,7 +743,7 @@ static inline int ip_ufo_append_data(struct sock *sk,
          * device, so create one single skb packet containing complete
          * udp datagram
          */
-        if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
+        if ((skb = skb_peek_tail(queue)) == NULL) {
                 skb = sock_alloc_send_skb(sk,
                         hh_len + fragheaderlen + transhdrlen + 20,
                         (flags & MSG_DONTWAIT), &err);
@@ -768,40 +765,30 @@ static inline int ip_ufo_append_data(struct sock *sk,
 
                 skb->ip_summed = CHECKSUM_PARTIAL;
                 skb->csum = 0;
-                sk->sk_sndmsg_off = 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(&sk->sk_write_queue, skb);
+                __skb_queue_tail(queue, skb);
         }
 
         return skb_append_datato_frags(sk, skb, getfrag, from,
                                        (length - transhdrlen));
 }
 
-/*
- *      ip_append_data() and ip_append_page() can make one large IP datagram
- *      from many pieces of data. Each pieces will be holded on the socket
- *      until ip_push_pending_frames() is called. Each piece can be a page
- *      or non-page data.
- *
- *      Not only UDP, other transport protocols - e.g. raw sockets - can use
- *      this interface potentially.
- *
- *      LATER: length must be adjusted by pad at tail, when it is required.
- */
-int ip_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,
-                   struct ipcm_cookie *ipc, struct rtable **rtp,
-                   unsigned int flags)
+static int __ip_append_data(struct sock *sk,
+                            struct flowi4 *fl4,
+                            struct sk_buff_head *queue,
+                            struct inet_cork *cork,
+                            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)
 {
         struct inet_sock *inet = inet_sk(sk);
         struct sk_buff *skb;
 
-        struct ip_options *opt = NULL;
+        struct ip_options *opt = cork->opt;
         int hh_len;
         int exthdrlen;
         int mtu;
@@ -810,60 +797,20 @@ int ip_append_data(struct sock *sk,
         int offset = 0;
         unsigned int maxfraglen, fragheaderlen;
         int csummode = CHECKSUM_NONE;
-        struct rtable *rt;
+        struct rtable *rt = (struct rtable *)cork->dst;
 
-        if (flags&MSG_PROBE)
-                return 0;
+        skb = skb_peek_tail(queue);
 
-        if (skb_queue_empty(&sk->sk_write_queue)) {
-                /*
-                 * setup for corking.
-                 */
-                opt = ipc->opt;
-                if (opt) {
-                        if (inet->cork.opt == NULL) {
-                                inet->cork.opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation);
-                                if (unlikely(inet->cork.opt == NULL))
-                                        return -ENOBUFS;
-                        }
-                        memcpy(inet->cork.opt, opt, sizeof(struct ip_options)+opt->optlen);
-                        inet->cork.flags |= IPCORK_OPT;
-                        inet->cork.addr = ipc->addr;
-                }
-                rt = *rtp;
-                if (unlikely(!rt))
-                        return -EFAULT;
-                /*
-                 * We steal reference to this route, caller should not release it
-                 */
-                *rtp = NULL;
-                inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ?
-                                            rt->dst.dev->mtu :
-                                            dst_mtu(rt->dst.path);
-                inet->cork.dst = &rt->dst;
-                inet->cork.length = 0;
-                sk->sk_sndmsg_page = NULL;
-                sk->sk_sndmsg_off = 0;
-                if ((exthdrlen = rt->dst.header_len) != 0) {
-                        length += exthdrlen;
-                        transhdrlen += exthdrlen;
-                }
-        } else {
-                rt = (struct rtable *)inet->cork.dst;
-                if (inet->cork.flags & IPCORK_OPT)
-                        opt = inet->cork.opt;
+        exthdrlen = !skb ? rt->dst.header_len : 0;
+        mtu = cork->fragsize;
 
-                transhdrlen = 0;
-                exthdrlen = 0;
-                mtu = inet->cork.fragsize;
-        }
         hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
         fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
         maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
 
-        if (inet->cork.length + length > 0xFFFF - fragheaderlen) {
-                ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport,
+        if (cork->length + length > 0xFFFF - fragheaderlen) {
+                ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
                                mtu-exthdrlen);
                 return -EMSGSIZE;
         }
@@ -878,15 +825,13 @@ int ip_append_data(struct sock *sk,
             !exthdrlen)
                 csummode = CHECKSUM_PARTIAL;
 
-        skb = skb_peek_tail(&sk->sk_write_queue);
-
-        inet->cork.length += length;
+        cork->length += length;
         if (((length > mtu) || (skb && skb_is_gso(skb))) &&
             (sk->sk_protocol == IPPROTO_UDP) &&
-            (rt->dst.dev->features & NETIF_F_UFO)) {
-                err = ip_ufo_append_data(sk, getfrag, from, length, hh_len,
-                                         fragheaderlen, transhdrlen, mtu,
-                                         flags);
+            (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);
                 if (err)
                         goto error;
                 return 0;
@@ -934,7 +879,9 @@ alloc_new_skb:
                             !(rt->dst.dev->features&NETIF_F_SG))
                                 alloclen = mtu;
                         else
-                                alloclen = datalen + fragheaderlen;
+                                alloclen = fraglen;
+
+                        alloclen += exthdrlen;
 
                         /* The last fragment gets additional space at tail.
                          * Note, with MSG_MORE we overallocate on fragments,
@@ -960,7 +907,7 @@ alloc_new_skb:
                                 else
                                         /* only the initial fragment is
                                            time stamped */
-                                        ipc->shtx.flags = 0;
+                                        cork->tx_flags = 0;
                         }
                         if (skb == NULL)
                                 goto error;
@@ -971,16 +918,16 @@ alloc_new_skb:
                         skb->ip_summed = csummode;
                         skb->csum = 0;
                         skb_reserve(skb, hh_len);
-                        *skb_tx(skb) = ipc->shtx;
+                        skb_shinfo(skb)->tx_flags = cork->tx_flags;
 
                         /*
                          *      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(
@@ -1008,7 +955,7 @@ alloc_new_skb:
                         /*
                          * Put the packet on the pending queue.
                          */
-                        __skb_queue_tail(&sk->sk_write_queue, skb);
+                        __skb_queue_tail(queue, skb);
                         continue;
                 }
 
@@ -1028,8 +975,8 @@ alloc_new_skb:
                 } else {
                         int i = skb_shinfo(skb)->nr_frags;
                         skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
-                        struct page *page = sk->sk_sndmsg_page;
-                        int off = sk->sk_sndmsg_off;
+                        struct page *page = cork->page;
+                        int off = cork->off;
                         unsigned int left;
 
                         if (page && (left = PAGE_SIZE - off) > 0) {
@@ -1041,7 +988,7 @@ alloc_new_skb:
                                                 goto error;
                                         }
                                         get_page(page);
-                                        skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
+                                        skb_fill_page_desc(skb, i, page, off, 0);
                                         frag = &skb_shinfo(skb)->frags[i];
                                 }
                         } else if (i < MAX_SKB_FRAGS) {
@@ -1052,8 +999,8 @@ alloc_new_skb:
                                         err = -ENOMEM;
                                         goto error;
                                 }
-                                sk->sk_sndmsg_page = page;
-                                sk->sk_sndmsg_off = 0;
+                                cork->page = page;
+                                cork->off = 0;
 
                                 skb_fill_page_desc(skb, i, page, 0, 0);
                                 frag = &skb_shinfo(skb)->frags[i];
@@ -1065,7 +1012,7 @@ alloc_new_skb:
                                 err = -EFAULT;
                                 goto error;
                         }
-                        sk->sk_sndmsg_off += copy;
+                        cork->off += copy;
                         frag->size += copy;
                         skb->len += copy;
                         skb->data_len += copy;
@@ -1079,18 +1026,95 @@ alloc_new_skb:
         return 0;
 
 error:
-        inet->cork.length -= length;
+        cork->length -= length;
         IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
         return err;
 }
 
-ssize_t ip_append_page(struct sock *sk, struct page *page,
+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_rcu *opt;
+        struct rtable *rt;
+
+        /*
+         * setup for corking.
+         */
+        opt = ipc->opt;
+        if (opt) {
+                if (cork->opt == NULL) {
+                        cork->opt = kmalloc(sizeof(struct ip_options) + 40,
+                                            sk->sk_allocation);
+                        if (unlikely(cork->opt == NULL))
+                                return -ENOBUFS;
+                }
+                memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
+                cork->flags |= IPCORK_OPT;
+                cork->addr = ipc->addr;
+        }
+        rt = *rtp;
+        if (unlikely(!rt))
+                return -EFAULT;
+        /*
+         * 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);
+        cork->dst = &rt->dst;
+        cork->length = 0;
+        cork->tx_flags = ipc->tx_flags;
+        cork->page = NULL;
+        cork->off = 0;
+
+        return 0;
+}
+
+/*
+ *      ip_append_data() and ip_append_page() can make one large IP datagram
+ *      from many pieces of data. Each pieces will be holded on the socket
+ *      until ip_push_pending_frames() is called. Each piece can be a page
+ *      or non-page data.
+ *
+ *      Not only UDP, other transport protocols - e.g. raw sockets - can use
+ *      this interface potentially.
+ *
+ *      LATER: length must be adjusted by pad at tail, when it is required.
+ */
+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,
+                   struct ipcm_cookie *ipc, struct rtable **rtp,
+                   unsigned int flags)
+{
+        struct inet_sock *inet = inet_sk(sk);
+        int err;
+
+        if (flags&MSG_PROBE)
+                return 0;
+
+        if (skb_queue_empty(&sk->sk_write_queue)) {
+                err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp);
+                if (err)
+                        return err;
+        } else {
+                transhdrlen = 0;
+        }
+
+        return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, getfrag,
+                                from, length, transhdrlen, flags);
+}
+
+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;
@@ -1106,28 +1130,29 @@ 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;
 
-        if (inet->cork.length + size > 0xFFFF - fragheaderlen) {
-                ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu);
+        if (cork->length + size > 0xFFFF - fragheaderlen) {
+                ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
                 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)) {
@@ -1222,45 +1247,47 @@ 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;
 }
 
-static void ip_cork_release(struct inet_sock *inet)
+static void ip_cork_release(struct inet_cork *cork)
 {
-        inet->cork.flags &= ~IPCORK_OPT;
-        kfree(inet->cork.opt);
-        inet->cork.opt = NULL;
-        dst_release(inet->cork.dst);
-        inet->cork.dst = NULL;
+        cork->flags &= ~IPCORK_OPT;
+        kfree(cork->opt);
+        cork->opt = NULL;
+        dst_release(cork->dst);
+        cork->dst = NULL;
 }
 
 /*
  *      Combined all pending IP fragments on the socket as one IP datagram
  *      and push them out.
  */
-int ip_push_pending_frames(struct sock *sk)
+struct sk_buff *__ip_make_skb(struct sock *sk,
+                              struct flowi4 *fl4,
+                              struct sk_buff_head *queue,
+                              struct inet_cork *cork)
 {
         struct sk_buff *skb, *tmp_skb;
         struct sk_buff **tail_skb;
         struct inet_sock *inet = inet_sk(sk);
         struct net *net = sock_net(sk);
         struct ip_options *opt = NULL;
-        struct rtable *rt = (struct rtable *)inet->cork.dst;
+        struct rtable *rt = (struct rtable *)cork->dst;
         struct iphdr *iph;
         __be16 df = 0;
         __u8 ttl;
-        int err = 0;
 
-        if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
+        if ((skb = __skb_dequeue(queue)) == NULL)
                 goto out;
         tail_skb = &(skb_shinfo(skb)->frag_list);
 
         /* 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);
@@ -1286,8 +1313,8 @@ int ip_push_pending_frames(struct sock *sk)
              ip_dont_fragment(sk, &rt->dst)))
                 df = htons(IP_DF);
 
-        if (inet->cork.flags & IPCORK_OPT)
-                opt = inet->cork.opt;
+        if (cork->flags & IPCORK_OPT)
+                opt = cork->opt;
 
         if (rt->rt_type == RTN_MULTICAST)
                 ttl = inet->mc_ttl;
@@ -1297,17 +1324,18 @@ int ip_push_pending_frames(struct sock *sk)
         iph = (struct iphdr *)skb->data;
         iph->version = 4;
         iph->ihl = 5;
-        if (opt) {
-                iph->ihl += opt->optlen>>2;
-                ip_options_build(skb, opt, inet->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;
+        iph->saddr = fl4->saddr;
+        iph->daddr = fl4->daddr;
+
+        if (opt) {
+                iph->ihl += opt->optlen>>2;
+                ip_options_build(skb, opt, cork->addr, rt, 0);
+        }
 
         skb->priority = sk->sk_priority;
         skb->mark = sk->sk_mark;
@@ -1315,44 +1343,99 @@ int ip_push_pending_frames(struct sock *sk)
          * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
          * on dst refcount
          */
-        inet->cork.dst = NULL;
+        cork->dst = NULL;
         skb_dst_set(skb, &rt->dst);
 
         if (iph->protocol == IPPROTO_ICMP)
                 icmp_out_count(net, ((struct icmphdr *)
                         skb_transport_header(skb))->type);
 
-        /* Netfilter gets whole the not fragmented skb. */
+        ip_cork_release(cork);
+out:
+        return skb;
+}
+
+int ip_send_skb(struct sk_buff *skb)
+{
+        struct net *net = sock_net(skb->sk);
+        int err;
+
         err = ip_local_out(skb);
         if (err) {
                 if (err > 0)
                         err = net_xmit_errno(err);
                 if (err)
-                        goto error;
+                        IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
         }
 
-out:
-        ip_cork_release(inet);
         return err;
+}
 
-error:
-        IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
-        goto out;
+int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)
+{
+        struct sk_buff *skb;
+
+        skb = ip_finish_skb(sk, fl4);
+        if (!skb)
+                return 0;
+
+        /* Netfilter gets whole the not fragmented skb. */
+        return ip_send_skb(skb);
 }
 
 /*
  *      Throw away all pending data on the socket.
  */
-void ip_flush_pending_frames(struct sock *sk)
+static void __ip_flush_pending_frames(struct sock *sk,
+                                      struct sk_buff_head *queue,
+                                      struct inet_cork *cork)
 {
         struct sk_buff *skb;
 
-        while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
+        while ((skb = __skb_dequeue_tail(queue)) != NULL)
                 kfree_skb(skb);
 
-        ip_cork_release(inet_sk(sk));
+        ip_cork_release(cork);
 }
 
+void ip_flush_pending_frames(struct sock *sk)
+{
+        __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 sk_buff_head queue;
+        int err;
+
+        if (flags & MSG_PROBE)
+                return NULL;
+
+        __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, fl4, &queue, &cork, getfrag,
+                               from, length, transhdrlen, flags);
+        if (err) {
+                __ip_flush_pending_frames(sk, &queue, &cork);
+                return ERR_PTR(err);
+        }
+
+        return __ip_make_skb(sk, fl4, &queue, &cork);
+}
 
 /*
  *      Fetch data from kernel space and fill in checksum if needed.
@@ -1374,48 +1457,39 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
  *      Should run single threaded per socket because it uses the sock
  *      structure to pass arguments.
  */
-void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg,
-                   unsigned int len)
+void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
+                   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);
 
-        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.shtx.flags = 0;
+        ipc.tx_flags = 0;
 
-        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 flowi fl = { .oif = arg->bound_dev_if,
-                                    .nl_u = { .ip4_u =
-                                              { .daddr = daddr,
-                                                .saddr = rt->rt_spec_dst,
-                                                .tos = RT_TOS(ip_hdr(skb)->tos) } },
-                                    /* Not quite clean, but right. */
-                                    .uli_u = { .ports =
-                                               { .sport = tcp_hdr(skb)->dest,
-                                                 .dport = tcp_hdr(skb)->source } },
-                                    .proto = sk->sk_protocol,
-                                    .flags = ip_reply_arg_flowi_flags(arg) };
-                security_skb_classify_flow(skb, &fl);
-                if (ip_route_output_key(sock_net(sk), &rt, &fl))
-                        return;
-        }
+        flowi4_init_output(&fl4, arg->bound_dev_if, 0,
+                           RT_TOS(ip_hdr(skb)->tos),
+                           RT_SCOPE_UNIVERSE, sk->sk_protocol,
+                           ip_reply_arg_flowi_flags(arg),
+                           daddr, rt->rt_spec_dst,
+                           tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+        security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+        rt = ip_route_output_key(sock_net(sk), &fl4);
+        if (IS_ERR(rt))
+                return;
 
         /* And let IP do all the hard work.
 
@@ -1428,7 +1502,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
         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,
+        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) {
                 if (arg->csumoffset >= 0)
@@ -1436,7 +1510,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
                           arg->csumoffset) = csum_fold(csum_add(skb->csum,
                                                                 arg->csum));
                 skb->ip_summed = CHECKSUM_NONE;
-                ip_push_pending_frames(sk);
+                ip_push_pending_frames(sk, &fl4);
         }
 
         bh_unlock_sock(sk);