return res;
}
rcu_read_unlock();
- IP6_INC_STATS_BH(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ IP6_INC_STATS(dev_net(dst->dev),
+ ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
{
- static atomic_t ipv6_fragmentation_id;
- int old, new;
+ static u32 ip6_idents_hashrnd __read_mostly;
+ static bool hashrnd_initialized = false;
+ u32 hash, id;
- if (rt && !(rt->dst.flags & DST_NOPEER)) {
- struct inet_peer *peer;
-
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
- peer = rt->rt6i_peer;
- if (peer) {
- fhdr->identification = htonl(inet_getid(peer, 0));
- return;
- }
+ if (unlikely(!hashrnd_initialized)) {
+ hashrnd_initialized = true;
+ get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
}
- do {
- old = atomic_read(&ipv6_fragmentation_id);
- new = old + 1;
- if (!new)
- new = 1;
- } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
- fhdr->identification = htonl(new);
+ hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+ hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+ id = ip_idents_reserve(hash, 1);
+ fhdr->identification = htonl(id);
}
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
+ int hroom, troom;
__be32 frag_id = 0;
int ptr, offset = 0, err=0;
u8 *prevhdr, nexthdr = 0;
*/
*prevhdr = NEXTHDR_FRAGMENT;
+ hroom = LL_RESERVED_SPACE(rt->dst.dev);
+ troom = rt->dst.dev->needed_tailroom;
/*
* Keep copying data until we run out.
* Allocate buffer.
*/
- if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) {
+ if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
+ hroom + troom, 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->dst.dev));
+ skb_reserve(frag, hroom);
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
skb_reset_network_header(frag);
fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
const struct flowi6 *fl6)
{
struct ipv6_pinfo *np = inet6_sk(sk);
- struct rt6_info *rt = (struct rt6_info *)dst;
+ struct rt6_info *rt;
if (!dst)
goto out;
+ if (dst->ops->family != AF_INET6) {
+ dst_release(dst);
+ return NULL;
+ }
+
+ rt = (struct rt6_info *)dst;
/* Yes, checking route validity in not connected
* case is not very simple. Take into account,
* that we do not support routing by source, TOS,
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,
- struct rt6_info *rt)
-
+ int exthdrlen, int transhdrlen, int mtu,
+ unsigned int flags, struct rt6_info *rt)
{
struct sk_buff *skb;
int err;
* udp datagram
*/
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
+ struct frag_hdr fhdr;
+
skb = sock_alloc_send_skb(sk,
hh_len + fragheaderlen + transhdrlen + 20,
(flags & MSG_DONTWAIT), &err);
skb_put(skb,fragheaderlen + transhdrlen);
/* initialize network header pointer */
- skb_reset_network_header(skb);
+ skb_set_network_header(skb, exthdrlen);
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
- }
-
- err = skb_append_datato_frags(sk,skb, getfrag, from,
- (length - transhdrlen));
- if (!err) {
- struct frag_hdr fhdr;
/* Specify the length of each IPv6 datagram fragment.
* It has to be a multiple of 8.
ipv6_select_ident(&fhdr, rt);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
-
- return 0;
}
- /* There is not enough support do UPD LSO,
- * so follow normal path
- */
- kfree_skb(skb);
- return err;
+ return skb_append_datato_frags(sk, skb, getfrag, from,
+ (length - transhdrlen));
}
static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
}
+static void ip6_append_data_mtu(unsigned int *mtu,
+ int *maxfraglen,
+ unsigned int fragheaderlen,
+ struct sk_buff *skb,
+ struct rt6_info *rt,
+ unsigned int orig_mtu)
+{
+ if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
+ if (skb == NULL) {
+ /* first fragment, reserve header_len */
+ *mtu = orig_mtu - rt->dst.header_len;
+
+ } else {
+ /*
+ * this fragment is not first, the headers
+ * space is regarded as data space.
+ */
+ *mtu = orig_mtu;
+ }
+ *maxfraglen = ((*mtu - fragheaderlen) & ~7)
+ + fragheaderlen - sizeof(struct frag_hdr);
+ }
+}
+
int ip6_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 inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
- struct sk_buff *skb;
- unsigned int maxfraglen, fragheaderlen;
+ struct sk_buff *skb, *skb_prev = NULL;
+ unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
- int mtu;
int copy;
int err;
int offset = 0;
if (WARN_ON(np->cork.opt))
return -EINVAL;
- np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
+ np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
inet->cork.fl.u.ip6 = *fl6;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
- mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
- rt->dst.dev->mtu : dst_mtu(&rt->dst);
+ if (rt->dst.flags & DST_XFRM_TUNNEL)
+ mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+ rt->dst.dev->mtu : dst_mtu(&rt->dst);
+ else
+ mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+ rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
cork->length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
- exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len;
+ exthdrlen = (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
- dst_exthdrlen = rt->dst.header_len;
+ dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
} else {
rt = (struct rt6_info *)cork->dst;
fl6 = &inet->cork.fl.u.ip6;
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
+ orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
* --yoshfuji
*/
- cork->length += length;
- if (length > mtu) {
- int proto = sk->sk_protocol;
- if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
- ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
- return -EMSGSIZE;
- }
-
- if (proto == IPPROTO_UDP &&
- (rt->dst.dev->features & NETIF_F_UFO)) {
+ if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
+ sk->sk_protocol == IPPROTO_RAW)) {
+ ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
+ return -EMSGSIZE;
+ }
- err = ip6_ufo_append_data(sk, getfrag, from, length,
- hh_len, fragheaderlen,
- transhdrlen, mtu, flags, rt);
- if (err)
- goto error;
- return 0;
- }
+ skb = skb_peek_tail(&sk->sk_write_queue);
+ cork->length += length;
+ if (((length > mtu) ||
+ (skb && skb_has_frags(skb))) &&
+ (sk->sk_protocol == IPPROTO_UDP) &&
+ (rt->dst.dev->features & NETIF_F_UFO) &&
+ (sk->sk_type == SOCK_DGRAM)) {
+ err = ip6_ufo_append_data(sk, getfrag, from, length,
+ hh_len, fragheaderlen, exthdrlen,
+ transhdrlen, mtu, flags, rt);
+ if (err)
+ goto error;
+ return 0;
}
- if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+ if (!skb)
goto alloc_new_skb;
while (length > 0) {
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
- struct sk_buff *skb_prev;
alloc_new_skb:
- skb_prev = skb;
-
/* There's no room in the current skb */
- if (skb_prev)
- fraggap = skb_prev->len - maxfraglen;
+ if (skb)
+ fraggap = skb->len - maxfraglen;
else
fraggap = 0;
+ /* update mtu and maxfraglen if necessary */
+ if (skb == NULL || skb_prev == NULL)
+ ip6_append_data_mtu(&mtu, &maxfraglen,
+ fragheaderlen, skb, rt,
+ orig_mtu);
+
+ skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
- if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
- datalen = maxfraglen - fragheaderlen;
- fraglen = datalen + fragheaderlen;
+ if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+ datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
alloclen += dst_exthdrlen;
- /*
- * The last fragment gets additional space at tail.
- * Note: we overallocate on fragments with MSG_MODE
- * because we have no idea if we're the last one.
- */
- if (datalen == length + fraggap)
- alloclen += rt->dst.trailer_len;
+ if (datalen != length + fraggap) {
+ /*
+ * this is not the last fragment, the trailer
+ * space is regarded as data space.
+ */
+ datalen += rt->dst.trailer_len;
+ }
+
+ alloclen += rt->dst.trailer_len;
+ fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
*/
skb->ip_summed = csummode;
skb->csum = 0;
- /* reserve for fragmentation */
- skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
+ /* reserve for fragmentation and ipsec header */
+ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
+ dst_exthdrlen);
if (sk->sk_type == SOCK_DGRAM)
skb_shinfo(skb)->tx_flags = tx_flags;
/*
* Find where to start putting bytes
*/
- data = skb_put(skb, fraglen + dst_exthdrlen);
- skb_set_network_header(skb, exthdrlen + dst_exthdrlen);
- data += fragheaderlen + dst_exthdrlen;
+ data = skb_put(skb, fraglen);
+ skb_set_network_header(skb, exthdrlen);
+ data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
- ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
- ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+ ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
err = ip6_local_out(skb);