*
* 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>
* Fixes:
* Alan Cox : Missing nonblock feature in ip_build_xmit.
* Mike Kilburn : htons() missing in ip_build_xmit.
- * Bradford Johnson: Fix faulty handling of some frames when
+ * Bradford Johnson: Fix faulty handling of some frames when
* no route is found.
* Alexander Demenshin: Missing sk/skb free in ip_queue_xmit
* (in case if packet not accepted by
* some redundant tests.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Andi Kleen : Replace ip_reply with ip_send_reply.
- * Andi Kleen : Split fast and slow ip_build_xmit path
- * for decreased register pressure on x86
- * and more readibility.
+ * Andi Kleen : Split fast and slow ip_build_xmit path
+ * for decreased register pressure on x86
+ * and more readibility.
* Marc Boucher : When call_out_firewall returns FW_QUEUE,
* silently drop skb instead of failing with -EPERM.
* Detlev Wengorz : Copy protocol for fragments.
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
-#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
-#include <net/checksum.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
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(skb)->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)
{
- newskb->mac.raw = newskb->data;
- __skb_pull(newskb, newskb->nh.raw - newskb->data);
+ skb_reset_mac_header(newskb);
+ __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;
}
return ttl;
}
-/*
+/*
* Add an ip header to a skbuff and send it out.
*
*/
__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. */
- if (opt)
- iph=(struct iphdr *)skb_push(skb,sizeof(struct iphdr) + opt->optlen);
- else
- iph=(struct iphdr *)skb_push(skb,sizeof(struct iphdr));
-
+ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
+ skb_reset_network_header(skb);
+ iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
iph->tos = inet->tos;
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);
- skb->nh.iph = iph;
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);
static inline int ip_finish_output2(struct sk_buff *skb)
{
- struct dst_entry *dst = skb->dst;
- struct hh_cache *hh = dst->hh;
+ struct dst_entry *dst = skb_dst(skb);
+ struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
- int hh_len = LL_RESERVED_SPACE(dev);
+ unsigned int hh_len = LL_RESERVED_SPACE(dev);
+
+ 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->hard_header)) {
+ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
struct sk_buff *skb2;
skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
skb = skb2;
}
- if (hh) {
- int hh_alen;
-
- read_lock_bh(&hh->hh_lock);
- hh_alen = HH_DATA_ALIGN(hh->hh_len);
- memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
- read_unlock_bh(&hh->hh_lock);
- skb_push(skb, hh->hh_len);
- return hh->hh_output(skb);
- } else if (dst->neighbour)
+ if (dst->hh)
+ return neigh_hh_output(dst->hh, skb);
+ else if (dst->neighbour)
return dst->neighbour->output(skb);
if (net_ratelimit())
return -EINVAL;
}
-static inline int ip_finish_output(struct sk_buff *skb)
+static inline int ip_skb_dst_mtu(struct sk_buff *skb)
+{
+ struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL;
+
+ return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ?
+ 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);
}
#endif
- if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb))
+ if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
return ip_fragment(skb, ip_finish_output2);
else
return ip_finish_output2(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_IP_POST_ROUTING, newskb, NULL,
- newskb->dev,
+ NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb,
+ NULL, newskb->dev,
ip_dev_loopback_xmit);
}
/* Multicasts with ttl 0 must not go beyond the host */
- if (skb->nh.iph->ttl == 0) {
+ if (ip_hdr(skb)->ttl == 0) {
kfree_skb(skb);
return 0;
}
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));
}
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);
- return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev,
- ip_finish_output,
+ return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, dev,
+ ip_finish_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
/* 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)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
- iph = (struct iphdr *) skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
- *((__u16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
- iph->tot_len = htons(skb->len);
+ skb_push(skb, sizeof(struct iphdr) + (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->u.dst) && !ipfragok)
iph->frag_off = htons(IP_DF);
else
iph->protocol = sk->sk_protocol;
iph->saddr = rt->rt_src;
iph->daddr = rt->rt_dst;
- skb->nh.iph = iph;
/* Transport layer set skb->h.foo itself. */
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);
- /* 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);
+ 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;
#ifdef CONFIG_NET_SCHED
to->tc_index = from->tc_index;
#endif
-#ifdef CONFIG_NETFILTER
- /* Connection association is same as pre-frag packet */
- nf_conntrack_put(to->nfct);
- to->nfct = from->nfct;
- nf_conntrack_get(to->nfct);
- to->nfctinfo = from->nfctinfo;
+ 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
-#ifdef CONFIG_BRIDGE_NETFILTER
- nf_bridge_put(to->nf_bridge);
- to->nf_bridge = from->nf_bridge;
- nf_bridge_get(to->nf_bridge);
-#endif
-#endif
skb_copy_secmark(to, from);
}
* 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;
* Point into the IP datagram header.
*/
- iph = skb->nh.iph;
+ 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(dst_mtu(&rt->u.dst)));
+ htonl(ip_skb_dst_mtu(skb)));
kfree_skb(skb);
return -EMSGSIZE;
}
* 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);
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
- frag->h.raw = frag->data;
- frag->nh.raw = __skb_push(frag, hlen);
- memcpy(frag->nh.raw, iph, hlen);
- iph = frag->nh.iph;
+ skb_reset_transport_header(frag);
+ __skb_push(frag, hlen);
+ skb_reset_network_header(frag);
+ memcpy(skb_network_header(frag), iph, hlen);
+ iph = ip_hdr(frag);
iph->tot_len = htons(frag->len);
ip_copy_metadata(frag, skb);
if (offset == 0)
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;
}
* Keep copying data until we run out.
*/
- while(left > 0) {
+ while (left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
ip_copy_metadata(skb2, skb);
skb_reserve(skb2, ll_rs);
skb_put(skb2, len + hlen);
- skb2->nh.raw = skb2->data;
- skb2->h.raw = skb2->data + hlen;
+ skb_reset_network_header(skb2);
+ skb2->transport_header = skb2->network_header + hlen;
/*
* Charge the memory for the fragment to any owner
* Copy the packet header into the new buffer.
*/
- memcpy(skb2->nh.raw, skb->data, hlen);
+ skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen);
/*
* Copy a block of the IP datagram.
*/
- if (skb_copy_bits(skb, ptr, skb2->h.raw, len))
+ if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
BUG();
left -= len;
/*
* Fill in the new header fields.
*/
- iph = skb2->nh.iph;
+ iph = ip_hdr(skb2);
iph->frag_off = htons((offset >> 3));
/* ANK: dirty, but effective trick. Upgrade options only if
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);
+ kfree_skb(skb);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
if (memcpy_fromiovecend(to, iov, offset, len) < 0)
return -EFAULT;
} else {
- unsigned int csum = 0;
+ __wsum csum = 0;
if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0)
return -EFAULT;
skb->csum = csum_block_add(skb->csum, csum, odd);
return 0;
}
-static inline unsigned int
+static inline __wsum
csum_page(struct page *page, int offset, int copy)
{
char *kaddr;
- unsigned int csum;
+ __wsum csum;
kaddr = kmap(page);
csum = csum_partial(kaddr + offset, copy, 0);
kunmap(page);
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->nh.raw = skb->data;
+ skb_reset_network_header(skb);
/* initialize protocol header pointer */
- skb->h.raw = skb->data + fragheaderlen;
+ skb->transport_header = skb->network_header + fragheaderlen;
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));
}
/*
* 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.
*
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);
- inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
- inet->cork.rt = rt;
+ 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.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;
}
*/
if (transhdrlen &&
length + fragheaderlen <= mtu &&
- rt->u.dst.dev->features & NETIF_F_ALL_CSUM &&
+ rt->u.dst.dev->features & NETIF_F_V4_CSUM &&
!exthdrlen)
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);
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
- if ((flags & MSG_MORE) &&
+ if ((flags & MSG_MORE) &&
!(rt->u.dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen += rt->u.dst.trailer_len;
if (transhdrlen) {
- skb = sock_alloc_send_skb(sk,
+ skb = sock_alloc_send_skb(sk,
alloclen + hh_len + 15,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
- skb = sock_wmalloc(sk,
+ skb = sock_wmalloc(sk,
alloclen + hh_len + 15, 1,
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.
*/
data = skb_put(skb, fraglen);
- skb->nh.raw = data + exthdrlen;
+ skb_set_network_header(skb, exthdrlen);
+ skb->transport_header = (skb->network_header +
+ fragheaderlen);
data += fragheaderlen;
- skb->h.raw = data + exthdrlen;
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
unsigned int off;
off = skb->len;
- if (getfrag(from, skb_put(skb, copy),
+ if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
get_page(page);
- skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
+ skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if (i < MAX_SKB_FRAGS) {
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;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
+ skb->truesize += copy;
+ atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
error:
inet->cork.length -= length;
- IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
- return err;
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
+ return err;
}
ssize_t ip_append_page(struct sock *sk, struct page *page,
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;
}
}
if (len <= 0) {
struct sk_buff *skb_prev;
- char *data;
- struct iphdr *iph;
int alloclen;
skb_prev = skb;
/*
* Find where to start putting bytes.
*/
- data = skb_put(skb, fragheaderlen + fraggap);
- skb->nh.iph = iph = (struct iphdr *)data;
- data += fragheaderlen;
- skb->h.raw = data;
-
+ skb_put(skb, fragheaderlen + fraggap);
+ skb_reset_network_header(skb);
+ skb->transport_header = (skb->network_header +
+ fragheaderlen);
if (fraggap) {
- skb->csum = skb_copy_and_csum_bits(
- skb_prev, maxfraglen,
- data, fraggap, 0);
+ skb->csum = skb_copy_and_csum_bits(skb_prev,
+ maxfraglen,
+ skb_transport_header(skb),
+ fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
pskb_trim_unique(skb_prev, maxfraglen);
}
if (skb->ip_summed == CHECKSUM_NONE) {
- unsigned int csum;
+ __wsum csum;
csum = csum_page(page, offset, len);
skb->csum = csum_block_add(skb->csum, csum, skb->len);
}
skb->len += len;
skb->data_len += len;
+ skb->truesize += len;
+ atomic_add(len, &sk->sk_wmem_alloc);
offset += len;
size -= len;
}
error:
inet->cork.length -= size;
- IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
return err;
}
+static void ip_cork_release(struct inet_sock *inet)
+{
+ inet->cork.flags &= ~IPCORK_OPT;
+ kfree(inet->cork.opt);
+ inet->cork.opt = NULL;
+ dst_release(inet->cork.dst);
+ inet->cork.dst = NULL;
+}
+
/*
* Combined all pending IP fragments on the socket as one IP datagram
* and push them out.
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;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
- if (skb->data < skb->nh.raw)
- __skb_pull(skb, skb->nh.raw - skb->data);
+ if (skb->data < skb_network_header(skb))
+ __skb_pull(skb, skb_network_offset(skb));
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
- __skb_pull(tmp_skb, skb->h.raw - skb->nh.raw);
+ __skb_pull(tmp_skb, skb_network_header_len(skb));
*tail_skb = tmp_skb;
tail_skb = &(tmp_skb->next);
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;
}
* 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)
+ if (inet->pmtudisc < IP_PMTUDISC_DO)
skb->local_df = 1;
/* 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
* locally. */
- if (inet->pmtudisc == IP_PMTUDISC_DO ||
+ if (inet->pmtudisc >= IP_PMTUDISC_DO ||
(skb->len <= dst_mtu(&rt->u.dst) &&
ip_dont_fragment(sk, &rt->u.dst)))
df = htons(IP_DF);
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->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(net, ((struct icmphdr *)
+ 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;
+ err = net_xmit_errno(err);
if (err)
goto error;
}
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:
- IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
goto out;
}
*/
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));
}
/*
* Fetch data from kernel space and fill in checksum if needed.
*/
-static int ip_reply_glue_bits(void *dptr, char *to, int offset,
+static int ip_reply_glue_bits(void *dptr, char *to, int offset,
int len, int odd, struct sk_buff *skb)
{
- unsigned int csum;
+ __wsum csum;
csum = csum_partial_copy_nocheck(dptr+offset, to, len, 0);
skb->csum = csum_block_add(skb->csum, csum, odd);
- return 0;
+ return 0;
}
-/*
+/*
* Generic function to send a packet as reply to another packet.
* Used to send TCP resets so far. ICMP should use this function too.
*
- * Should run single threaded per socket because it uses the sock
+ * 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;
}
{
- struct flowi fl = { .nl_u = { .ip4_u =
+ struct flowi fl = { .oif = arg->bound_dev_if,
+ .nl_u = { .ip4_u =
{ .daddr = daddr,
.saddr = rt->rt_spec_dst,
- .tos = RT_TOS(skb->nh.iph->tos) } },
+ .tos = RT_TOS(ip_hdr(skb)->tos) } },
/* Not quite clean, but right. */
.uli_u = { .ports =
- { .sport = skb->h.th->dest,
- .dport = skb->h.th->source } },
- .proto = sk->sk_protocol };
+ { .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(&rt, &fl))
+ if (ip_route_output_key(sock_net(sk), &rt, &fl))
return;
}
with locally disabled BH and that sk cannot be already spinlocked.
*/
bh_lock_sock(sk);
- inet->tos = skb->nh.iph->tos;
+ inet->tos = ip_hdr(skb)->tos;
sk->sk_priority = skb->priority;
- sk->sk_protocol = skb->nh.iph->protocol;
+ 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)
- *((u16 *)skb->h.raw + arg->csumoffset) = csum_fold(csum_add(skb->csum, arg->csum));
+ *((__sum16 *)skb_transport_header(skb) +
+ arg->csumoffset) = csum_fold(csum_add(skb->csum,
+ arg->csum));
skb->ip_summed = CHECKSUM_NONE;
ip_push_pending_frames(sk);
}