*
* The Internet Protocol (IP) output module.
*
- * Version: $Id: ip_output.c,v 1.100 2002/02/01 22:01:03 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@super.org>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/highmem.h>
+#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/sockios.h>
iph->tot_len = htons(skb->len);
ip_send_check(iph);
- return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb->dst->dev,
+ return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
dst_output);
}
__skb_pull(newskb, skb_network_offset(newskb));
newskb->pkt_type = PACKET_LOOPBACK;
newskb->ip_summed = CHECKSUM_UNNECESSARY;
- BUG_TRAP(newskb->dst);
- netif_rx(newskb);
+ WARN_ON(!skb_dst(newskb));
+ netif_rx_ni(newskb);
return 0;
}
__be32 saddr, __be32 daddr, struct ip_options *opt)
{
struct inet_sock *inet = inet_sk(sk);
- struct rtable *rt = (struct rtable *)skb->dst;
+ struct rtable *rt = skb_rtable(skb);
struct iphdr *iph;
/* Build the IP header. */
}
skb->priority = sk->sk_priority;
+ skb->mark = sk->sk_mark;
/* Send it out. */
return ip_local_out(skb);
static inline int ip_finish_output2(struct sk_buff *skb)
{
- struct dst_entry *dst = skb->dst;
+ struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
- if (rt->rt_type == RTN_MULTICAST)
- IP_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS);
- else if (rt->rt_type == RTN_BROADCAST)
- IP_INC_STATS(IPSTATS_MIB_OUTBCASTPKTS);
+ if (rt->rt_type == RTN_MULTICAST) {
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len);
+ } else if (rt->rt_type == RTN_BROADCAST)
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTBCAST, skb->len);
/* Be paranoid, rather than too clever. */
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL;
return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ?
- skb->dst->dev->mtu : dst_mtu(skb->dst);
+ skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
}
static int ip_finish_output(struct sk_buff *skb)
{
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
- if (skb->dst->xfrm != NULL) {
+ if (skb_dst(skb)->xfrm != NULL) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(skb);
}
int ip_mc_output(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
- struct rtable *rt = (struct rtable*)skb->dst;
+ struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->u.dst.dev;
/*
* If the indicated interface is up and running, send the packet.
*/
- IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
*/
if (rt->rt_flags&RTCF_MULTICAST) {
- if ((!sk || inet_sk(sk)->mc_loop)
+ if (sk_mc_loop(sk)
#ifdef CONFIG_IP_MROUTE
/* Small optimization: do not loopback not local frames,
which returned after forwarding; they will be dropped
This check is duplicated in ip_mr_input at the moment.
*/
- && ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED))
+ &&
+ ((rt->rt_flags & RTCF_LOCAL) ||
+ !(IPCB(skb)->flags & IPSKB_FORWARDED))
#endif
- ) {
+ ) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb,
int ip_output(struct sk_buff *skb)
{
- struct net_device *dev = skb->dst->dev;
+ struct net_device *dev = skb_dst(skb)->dev;
- IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
/* Skip all of this if the packet is already routed,
* f.e. by something like SCTP.
*/
- rt = (struct rtable *) skb->dst;
+ rt = skb_rtable(skb);
if (rt != NULL)
goto packet_routed;
__be32 daddr;
/* Use correct destination address if we have options. */
- daddr = inet->daddr;
+ 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->saddr,
+ .saddr = inet->inet_saddr,
.tos = RT_CONN_FLAGS(sk) } },
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = { .ports =
- { .sport = inet->sport,
- .dport = inet->dport } } };
+ { .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(&rt, &fl, sk, 0))
+ if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0))
goto no_route;
}
sk_setup_caps(sk, &rt->u.dst);
}
- skb->dst = dst_clone(&rt->u.dst);
+ skb_dst_set(skb, dst_clone(&rt->u.dst));
packet_routed:
if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
if (opt && opt->optlen) {
iph->ihl += opt->optlen >> 2;
- ip_options_build(skb, opt, inet->daddr, rt, 0);
+ ip_options_build(skb, opt, inet->inet_daddr, rt, 0);
}
ip_select_ident_more(iph, &rt->u.dst, sk,
(skb_shinfo(skb)->gso_segs ?: 1) - 1);
skb->priority = sk->sk_priority;
+ skb->mark = sk->sk_mark;
return ip_local_out(skb);
no_route:
- IP_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EHOSTUNREACH;
}
to->pkt_type = from->pkt_type;
to->priority = from->priority;
to->protocol = from->protocol;
- dst_release(to->dst);
- to->dst = dst_clone(from->dst);
+ skb_dst_drop(to);
+ skb_dst_set(to, dst_clone(skb_dst(from)));
to->dev = from->dev;
to->mark = from->mark;
* single device frame, and queue such a frame for sending.
*/
-int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
+int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct iphdr *iph;
int raw = 0;
unsigned int mtu, hlen, left, len, ll_rs, pad;
int offset;
__be16 not_last_frag;
- struct rtable *rt = (struct rtable*)skb->dst;
+ struct rtable *rt = skb_rtable(skb);
int err = 0;
dev = rt->u.dst.dev;
iph = ip_hdr(skb);
if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
- IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(ip_skb_dst_mtu(skb)));
kfree_skb(skb);
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
- if (skb_shinfo(skb)->frag_list) {
+ if (skb_has_frags(skb)) {
struct sk_buff *frag;
int first_len = skb_pagelen(skb);
+ int truesizes = 0;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
skb_cloned(skb))
goto slow_path;
- for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
+ skb_walk_frags(skb, frag) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
BUG_ON(frag->sk);
if (skb->sk) {
- sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
- skb->truesize -= frag->truesize;
}
+ truesizes += frag->truesize;
}
/* Everything is OK. Generate! */
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
- skb_shinfo(skb)->frag_list = NULL;
+ skb_frag_list_init(skb);
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);
err = output(skb);
if (!err)
- IP_INC_STATS(IPSTATS_MIB_FRAGCREATES);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
}
if (err == 0) {
- IP_INC_STATS(IPSTATS_MIB_FRAGOKS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
return 0;
}
kfree_skb(frag);
frag = skb;
}
- IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
if (err)
goto fail;
- IP_INC_STATS(IPSTATS_MIB_FRAGCREATES);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
}
kfree_skb(skb);
- IP_INC_STATS(IPSTATS_MIB_FRAGOKS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
- IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
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 mtu, unsigned int flags)
{
struct sk_buff *skb;
int err;
skb_reserve(skb, hh_len);
/* create space for UDP/IP header */
- skb_put(skb,fragheaderlen + transhdrlen);
+ skb_put(skb, fragheaderlen + transhdrlen);
/* initialize network header pointer */
skb_reset_network_header(skb);
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
sk->sk_sndmsg_off = 0;
- }
- err = skb_append_datato_frags(sk,skb, getfrag, from,
- (length - transhdrlen));
- if (!err) {
- /* specify the length of each IP datagram fragment*/
+ /* 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);
-
- return 0;
}
- /* There is not enough support do UFO ,
- * so follow normal path
- */
- kfree_skb(skb);
- return err;
+
+ return skb_append_datato_frags(sk, skb, getfrag, from,
+ (length - transhdrlen));
}
/*
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 *rt,
+ struct ipcm_cookie *ipc, struct rtable **rtp,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
int offset = 0;
unsigned int maxfraglen, fragheaderlen;
int csummode = CHECKSUM_NONE;
+ struct rtable *rt;
if (flags&MSG_PROBE)
return 0;
inet->cork.flags |= IPCORK_OPT;
inet->cork.addr = ipc->addr;
}
- dst_hold(&rt->u.dst);
+ 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->u.dst.dev->mtu :
dst_mtu(rt->u.dst.path);
- inet->cork.rt = rt;
+ inet->cork.dst = &rt->u.dst;
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
transhdrlen += exthdrlen;
}
} else {
- rt = inet->cork.rt;
+ rt = (struct rtable *)inet->cork.dst;
if (inet->cork.flags & IPCORK_OPT)
opt = inet->cork.opt;
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
if (inet->cork.length + length > 0xFFFF - fragheaderlen) {
- ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu-exthdrlen);
+ ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport,
+ mtu-exthdrlen);
return -EMSGSIZE;
}
csummode = CHECKSUM_PARTIAL;
inet->cork.length += length;
- if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
- (rt->u.dst.dev->features & NETIF_F_UFO)) {
-
+ if (((length> mtu) || !skb_queue_empty(&sk->sk_write_queue)) &&
+ (sk->sk_protocol == IPPROTO_UDP) &&
+ (rt->u.dst.dev->features & NETIF_F_UFO)) {
err = ip_ufo_append_data(sk, getfrag, from, length, hh_len,
fragheaderlen, transhdrlen, mtu,
flags);
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
+ else
+ /* only the initial fragment is
+ time stamped */
+ ipc->shtx.flags = 0;
}
if (skb == NULL)
goto error;
skb->ip_summed = csummode;
skb->csum = 0;
skb_reserve(skb, hh_len);
+ *skb_tx(skb) = ipc->shtx;
/*
* Find where to start putting bytes.
error:
inet->cork.length -= length;
- IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
return err;
}
if (skb_queue_empty(&sk->sk_write_queue))
return -EINVAL;
- rt = inet->cork.rt;
+ rt = (struct rtable *)inet->cork.dst;
if (inet->cork.flags & IPCORK_OPT)
opt = inet->cork.opt;
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
if (inet->cork.length + size > 0xFFFF - fragheaderlen) {
- ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu);
+ ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu);
return -EMSGSIZE;
}
error:
inet->cork.length -= size;
- IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
return err;
}
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;
- }
+ dst_release(inet->cork.dst);
+ inet->cork.dst = NULL;
}
/*
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 = inet->cork.rt;
+ struct rtable *rt = (struct rtable *)inet->cork.dst;
struct iphdr *iph;
__be16 df = 0;
__u8 ttl;
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
- __sock_put(tmp_skb->sk);
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
}
iph->daddr = rt->rt_dst;
skb->priority = sk->sk_priority;
- skb->dst = dst_clone(&rt->u.dst);
+ skb->mark = sk->sk_mark;
+ /*
+ * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
+ * on dst refcount
+ */
+ inet->cork.dst = NULL;
+ skb_dst_set(skb, &rt->u.dst);
if (iph->protocol == IPPROTO_ICMP)
- icmp_out_count(((struct icmphdr *)
+ icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
/* Netfilter gets whole the not fragmented skb. */
err = ip_local_out(skb);
if (err) {
if (err > 0)
- err = inet->recverr ? net_xmit_errno(err) : 0;
+ err = net_xmit_errno(err);
if (err)
goto error;
}
return err;
error:
- IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
goto out;
}
*
* 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)
} replyopts;
struct ipcm_cookie ipc;
__be32 daddr;
- struct rtable *rt = (struct rtable*)skb->dst;
+ struct rtable *rt = skb_rtable(skb);
if (ip_options_echo(&replyopts.opt, skb))
return;
daddr = ipc.addr = rt->rt_src;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (replyopts.opt.optlen) {
ipc.opt = &replyopts.opt;
.uli_u = { .ports =
{ .sport = tcp_hdr(skb)->dest,
.dport = tcp_hdr(skb)->source } },
- .proto = sk->sk_protocol };
+ .proto = sk->sk_protocol,
+ .flags = ip_reply_arg_flowi_flags(arg) };
security_skb_classify_flow(skb, &fl);
- if (ip_route_output_key(&rt, &fl))
+ if (ip_route_output_key(sock_net(sk), &rt, &fl))
return;
}
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,
- &ipc, rt, MSG_DONTWAIT);
+ &ipc, &rt, MSG_DONTWAIT);
if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
if (arg->csumoffset >= 0)
*((__sum16 *)skb_transport_header(skb) +