Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland...

[linux.git] / net / ipv4 / ip_output.c

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e5f7dc2de30349c8045bdadc5e77940bcf97680d..341779e685d913d41ac14ae59a141ab32dca847f 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -91,6 +91,28 @@ __inline__ void ip_send_check(struct iphdr *iph)
        iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 }
 
+int __ip_local_out(struct sk_buff *skb)
+{
+       struct iphdr *iph = ip_hdr(skb);
+
+       iph->tot_len = htons(skb->len);
+       ip_send_check(iph);
+       return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb->dst->dev,
+                      dst_output);
+}
+
+int ip_local_out(struct sk_buff *skb)
+{
+       int err;
+
+       err = __ip_local_out(skb);
+       if (likely(err == 1))
+               err = dst_output(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)
 {
@@ -138,20 +160,18 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
        iph->daddr    = rt->rt_dst;
        iph->saddr    = rt->rt_src;
        iph->protocol = sk->sk_protocol;
-       iph->tot_len  = htons(skb->len);
        ip_select_ident(iph, &rt->u.dst, sk);
 
        if (opt && opt->optlen) {
                iph->ihl += opt->optlen>>2;
                ip_options_build(skb, opt, daddr, rt, 0);
        }
-       ip_send_check(iph);
 
        skb->priority = sk->sk_priority;
+       skb->mark = sk->sk_mark;
 
        /* Send it out. */
-       return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
-                      dst_output);
+       return ip_local_out(skb);
 }
 
 EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
@@ -251,8 +271,8 @@ int ip_mc_output(struct sk_buff *skb)
                ) {
                        struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
                        if (newskb)
-                               NF_HOOK(PF_INET, NF_IP_POST_ROUTING, newskb, NULL,
-                                       newskb->dev,
+                               NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb,
+                                       NULL, newskb->dev,
                                        ip_dev_loopback_xmit);
                }
 
@@ -267,11 +287,11 @@ int ip_mc_output(struct sk_buff *skb)
        if (rt->rt_flags&RTCF_BROADCAST) {
                struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
                if (newskb)
-                       NF_HOOK(PF_INET, NF_IP_POST_ROUTING, newskb, NULL,
+                       NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb, NULL,
                                newskb->dev, ip_dev_loopback_xmit);
        }
 
-       return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev,
+       return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
                            ip_finish_output,
                            !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
@@ -285,7 +305,7 @@ int ip_output(struct sk_buff *skb)
        skb->dev = dev;
        skb->protocol = htons(ETH_P_IP);
 
-       return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev,
+       return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, dev,
                            ip_finish_output,
                            !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
@@ -331,7 +351,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok)
                         * itself out.
                         */
                        security_sk_classify_flow(sk, &fl);
-                       if (ip_route_output_flow(&rt, &fl, sk, 0))
+                       if (ip_route_output_flow(&init_net, &rt, &fl, sk, 0))
                                goto no_route;
                }
                sk_setup_caps(sk, &rt->u.dst);
@@ -347,7 +367,6 @@ packet_routed:
        skb_reset_network_header(skb);
        iph = ip_hdr(skb);
        *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
-       iph->tot_len = htons(skb->len);
        if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok)
                iph->frag_off = htons(IP_DF);
        else
@@ -366,13 +385,10 @@ packet_routed:
        ip_select_ident_more(iph, &rt->u.dst, sk,
                             (skb_shinfo(skb)->gso_segs ?: 1) - 1);
 
-       /* Add an IP checksum. */
-       ip_send_check(iph);
-
        skb->priority = sk->sk_priority;
+       skb->mark = sk->sk_mark;
 
-       return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
-                      dst_output);
+       return ip_local_out(skb);
 
 no_route:
        IP_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
@@ -462,6 +478,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
        if (skb_shinfo(skb)->frag_list) {
                struct sk_buff *frag;
                int first_len = skb_pagelen(skb);
+               int truesizes = 0;
 
                if (first_len - hlen > mtu ||
                    ((first_len - hlen) & 7) ||
@@ -485,7 +502,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
                                sock_hold(skb->sk);
                                frag->sk = skb->sk;
                                frag->destructor = sock_wfree;
-                               skb->truesize -= frag->truesize;
+                               truesizes += frag->truesize;
                        }
                }
 
@@ -496,6 +513,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
                frag = skb_shinfo(skb)->frag_list;
                skb_shinfo(skb)->frag_list = NULL;
                skb->data_len = first_len - skb_headlen(skb);
+               skb->truesize -= truesizes;
                skb->len = first_len;
                iph->tot_len = htons(first_len);
                iph->frag_off = htons(IP_MF);
@@ -1016,8 +1034,6 @@ alloc_new_skb:
 
                                skb_fill_page_desc(skb, i, page, 0, 0);
                                frag = &skb_shinfo(skb)->frags[i];
-                               skb->truesize += PAGE_SIZE;
-                               atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
                        } else {
                                err = -EMSGSIZE;
                                goto error;
@@ -1030,6 +1046,8 @@ alloc_new_skb:
                        frag->size += copy;
                        skb->len += copy;
                        skb->data_len += copy;
+                       skb->truesize += copy;
+                       atomic_add(copy, &sk->sk_wmem_alloc);
                }
                offset += copy;
                length -= copy;
@@ -1172,6 +1190,8 @@ ssize_t   ip_append_page(struct sock *sk, struct page *page,
 
                skb->len += len;
                skb->data_len += len;
+               skb->truesize += len;
+               atomic_add(len, &sk->sk_wmem_alloc);
                offset += len;
                size -= len;
        }
@@ -1183,6 +1203,17 @@ error:
        return err;
 }
 
+static void ip_cork_release(struct inet_sock *inet)
+{
+       inet->cork.flags &= ~IPCORK_OPT;
+       kfree(inet->cork.opt);
+       inet->cork.opt = NULL;
+       if (inet->cork.rt) {
+               ip_rt_put(inet->cork.rt);
+               inet->cork.rt = NULL;
+       }
+}
+
 /*
  *     Combined all pending IP fragments on the socket as one IP datagram
  *     and push them out.
@@ -1249,16 +1280,15 @@ int ip_push_pending_frames(struct sock *sk)
                ip_options_build(skb, opt, inet->cork.addr, rt, 0);
        }
        iph->tos = inet->tos;
-       iph->tot_len = htons(skb->len);
        iph->frag_off = df;
        ip_select_ident(iph, &rt->u.dst, sk);
        iph->ttl = ttl;
        iph->protocol = sk->sk_protocol;
        iph->saddr = rt->rt_src;
        iph->daddr = rt->rt_dst;
-       ip_send_check(iph);
 
        skb->priority = sk->sk_priority;
+       skb->mark = sk->sk_mark;
        skb->dst = dst_clone(&rt->u.dst);
 
        if (iph->protocol == IPPROTO_ICMP)
@@ -1266,8 +1296,7 @@ int ip_push_pending_frames(struct sock *sk)
                        skb_transport_header(skb))->type);
 
        /* Netfilter gets whole the not fragmented skb. */
-       err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL,
-                     skb->dst->dev, dst_output);
+       err = ip_local_out(skb);
        if (err) {
                if (err > 0)
                        err = inet->recverr ? net_xmit_errno(err) : 0;
@@ -1276,13 +1305,7 @@ int ip_push_pending_frames(struct sock *sk)
        }
 
 out:
-       inet->cork.flags &= ~IPCORK_OPT;
-       kfree(inet->cork.opt);
-       inet->cork.opt = NULL;
-       if (inet->cork.rt) {
-               ip_rt_put(inet->cork.rt);
-               inet->cork.rt = NULL;
-       }
+       ip_cork_release(inet);
        return err;
 
 error:
@@ -1295,19 +1318,12 @@ error:
  */
 void ip_flush_pending_frames(struct sock *sk)
 {
-       struct inet_sock *inet = inet_sk(sk);
        struct sk_buff *skb;
 
        while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
                kfree_skb(skb);
 
-       inet->cork.flags &= ~IPCORK_OPT;
-       kfree(inet->cork.opt);
-       inet->cork.opt = NULL;
-       if (inet->cork.rt) {
-               ip_rt_put(inet->cork.rt);
-               inet->cork.rt = NULL;
-       }
+       ip_cork_release(inet_sk(sk));
 }
 
 
@@ -1330,8 +1346,6 @@ 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.
- *
- *     LATER: switch from ip_build_xmit to ip_append_*
  */
 void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg,
                   unsigned int len)
@@ -1370,7 +1384,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
                                                 .dport = tcp_hdr(skb)->source } },
                                    .proto = sk->sk_protocol };
                security_skb_classify_flow(skb, &fl);
-               if (ip_route_output_key(&rt, &fl))
+               if (ip_route_output_key(sk->sk_net, &rt, &fl))
                        return;
        }