#include <net/checksum.h>
#include <linux/mroute6.h>
-static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
+int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
int __ip6_local_out(struct sk_buff *skb)
{
len = 0;
ipv6_hdr(skb)->payload_len = htons(len);
- return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
- dst_output);
+ return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+ skb_dst(skb)->dev, dst_output);
}
int ip6_local_out(struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(ip6_local_out);
-static int ip6_output_finish(struct sk_buff *skb)
-{
- struct dst_entry *dst = skb_dst(skb);
-
- if (dst->hh)
- return neigh_hh_output(dst->hh, skb);
- else if (dst->neighbour)
- return dst->neighbour->output(skb);
-
- IP6_INC_STATS_BH(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
- kfree_skb(skb);
- return -EINVAL;
-
-}
-
/* dev_loopback_xmit for use with netfilter. */
static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
{
newskb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(newskb));
- netif_rx(newskb);
+ netif_rx_ni(newskb);
return 0;
}
-
-static int ip6_output2(struct sk_buff *skb)
+static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
- ((mroute6_socket(dev_net(dev)) &&
+ ((mroute6_socket(dev_net(dev), skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
is not supported in any case.
*/
if (newskb)
- NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, newskb,
- NULL, newskb->dev,
+ NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+ newskb, NULL, newskb->dev,
ip6_dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
skb->len);
}
- return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
- ip6_output_finish);
+ if (dst->hh)
+ return neigh_hh_output(dst->hh, skb);
+ else if (dst->neighbour)
+ return dst->neighbour->output(skb);
+
+ IP6_INC_STATS_BH(dev_net(dst->dev),
+ ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ kfree_skb(skb);
+ return -EINVAL;
}
-static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
+static int ip6_finish_output(struct sk_buff *skb)
{
- struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
-
- return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ?
- skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
+ if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+ dst_allfrag(skb_dst(skb)))
+ return ip6_fragment(skb, ip6_finish_output2);
+ else
+ return ip6_finish_output2(skb);
}
int ip6_output(struct sk_buff *skb)
{
+ struct net_device *dev = skb_dst(skb)->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (unlikely(idev->cnf.disable_ipv6)) {
- IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev,
+ IP6_INC_STATS(dev_net(dev), idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
- if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
- dst_allfrag(skb_dst(skb)))
- return ip6_fragment(skb, ip6_output2);
- else
- return ip6_output2(skb);
+ return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+ ip6_finish_output,
+ !(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
/*
- * xmit an sk_buff (used by TCP)
+ * xmit an sk_buff (used by TCP, SCTP and DCCP)
*/
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
- struct ipv6_txoptions *opt, int ipfragok)
+ struct ipv6_txoptions *opt)
{
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
}
kfree_skb(skb);
skb = skb2;
- if (sk)
- skb_set_owner_w(skb, sk);
+ skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
- /* Allow local fragmentation. */
- if (ipfragok)
- skb->local_df = 1;
-
/*
* Fill in the IPv6 header
*/
if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
- return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
- dst_output);
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+ dst->dev, dst_output);
}
if (net_ratelimit())
goto drop;
}
+ if (skb->pkt_type != PACKET_HOST)
+ goto drop;
+
skb_forward_csum(skb);
/*
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if (skb->len > mtu) {
+ if (skb->len > mtu && !skb_is_gso(skb)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
- return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
return offset;
}
-static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
+static u32 hashidentrnd __read_mostly;
+#define FID_HASH_SZ 16
+static u32 ipv6_fragmentation_id[FID_HASH_SZ];
+
+void __init initialize_hashidentrnd(void)
+{
+ get_random_bytes(&hashidentrnd, sizeof(hashidentrnd));
+}
+
+static u32 __ipv6_select_ident(const struct in6_addr *addr)
+{
+ u32 newid, oldid, hash = jhash2((u32 *)addr, 4, hashidentrnd);
+ u32 *pid = &ipv6_fragmentation_id[hash % FID_HASH_SZ];
+
+ do {
+ oldid = *pid;
+ newid = oldid + 1;
+ if (!(hash + newid))
+ newid++;
+ } while (cmpxchg(pid, oldid, newid) != oldid);
+
+ return hash + newid;
+}
+
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+ fhdr->identification = htonl(__ipv6_select_ident(&rt->rt6i_dst.addr));
+}
+
+int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket.
*/
- if (!skb->local_df) {
+ if (!skb->local_df && skb->len > mtu) {
skb->dev = skb_dst(skb)->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
}
mtu -= hlen + sizeof(struct frag_hdr);
- if (skb_has_frags(skb)) {
+ if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
- int truesizes = 0;
+ struct sk_buff *frag2;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
- goto slow_path;
+ goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
- goto slow_path;
+ goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
- truesizes += frag->truesize;
}
+ skb->truesize -= frag->truesize;
}
err = 0;
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
- ipv6_select_ident(fh);
+ ipv6_select_ident(fh, rt);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
- skb->truesize -= truesizes;
skb->len = first_len;
ipv6_hdr(skb)->payload_len = htons(first_len -
sizeof(struct ipv6hdr));
- dst_hold(&rt->u.dst);
+ dst_hold(&rt->dst);
for (;;) {
/* Prepare header of the next frame,
err = output(skb);
if(!err)
- IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+ IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
kfree(tmp_hdr);
if (err == 0) {
- IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+ IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGOKS);
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
return 0;
}
frag = skb;
}
- IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+ IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGFAILS);
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
return err;
+
+slow_path_clean:
+ skb_walk_frags(skb, frag2) {
+ if (frag2 == frag)
+ break;
+ frag2->sk = NULL;
+ frag2->destructor = NULL;
+ skb->truesize += frag2->truesize;
+ }
}
slow_path:
* Allocate buffer.
*/
- if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) {
+ if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) {
NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
*/
ip6_copy_metadata(frag, skb);
- skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev));
+ skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev));
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
skb_reset_network_header(frag);
fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
fh->nexthdr = nexthdr;
fh->reserved = 0;
if (!frag_id) {
- ipv6_select_ident(fh);
+ ipv6_select_ident(fh, rt);
frag_id = fh->identification;
} else
fh->identification = frag_id;
struct in6_addr *fl_addr,
struct in6_addr *addr_cache)
{
- return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
- (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)));
+ return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
+ (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache));
}
static struct dst_entry *ip6_sk_dst_check(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 mtu,unsigned int flags,
+ struct rt6_info *rt)
{
struct sk_buff *skb;
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
- ipv6_select_ident(&fhdr);
+ ipv6_select_ident(&fhdr, rt);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
- struct rt6_info *rt, unsigned int flags)
+ struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
/* need source address above miyazawa*/
}
- dst_hold(&rt->u.dst);
- inet->cork.dst = &rt->u.dst;
+ dst_hold(&rt->dst);
+ inet->cork.dst = &rt->dst;
inet->cork.fl = *fl;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
- rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path);
+ rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
inet->cork.fragsize = mtu;
- if (dst_allfrag(rt->u.dst.path))
+ if (dst_allfrag(rt->dst.path))
inet->cork.flags |= IPCORK_ALLFRAG;
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
- exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0) -
+ exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) -
rt->rt6i_nfheader_len;
length += exthdrlen;
transhdrlen += exthdrlen;
mtu = inet->cork.fragsize;
}
- hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
+ hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
*/
inet->cork.length += length;
- if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
- (rt->u.dst.dev->features & NETIF_F_UFO)) {
+ if (length > mtu) {
+ int proto = sk->sk_protocol;
+ if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
+ ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
+ return -EMSGSIZE;
+ }
- err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
- fragheaderlen, transhdrlen, mtu,
- flags);
- if (err)
- goto error;
- return 0;
+ if (proto == IPPROTO_UDP &&
+ (rt->dst.dev->features & NETIF_F_UFO)) {
+
+ err = ip6_ufo_append_data(sk, getfrag, from, length,
+ hh_len, fragheaderlen,
+ transhdrlen, mtu, flags, rt);
+ if (err)
+ goto error;
+ return 0;
+ }
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
fraglen = datalen + fragheaderlen;
if ((flags & MSG_MORE) &&
- !(rt->u.dst.dev->features&NETIF_F_SG))
+ !(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
* because we have no idea if we're the last one.
*/
if (datalen == length + fraggap)
- alloclen += rt->u.dst.trailer_len;
+ alloclen += rt->dst.trailer_len;
/*
* We just reserve space for fragment header.
if (copy > length)
copy = length;
- if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
- skb_dst_set(skb, dst_clone(&rt->u.dst));
+ skb_dst_set(skb, dst_clone(&rt->dst));
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));