#include <net/xfrm.h>
#include <net/checksum.h>
#include <linux/mroute6.h>
+#include <net/l3mdev.h>
-static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output2(struct net *net, struct sock *sk, 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(sk) &&
- ((mroute6_socket(dev_net(dev), skb) &&
+ ((mroute6_socket(net, skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
*/
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
- sk, newskb, NULL, newskb->dev,
+ net, sk, newskb, NULL, newskb->dev,
dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
- IP6_INC_STATS(dev_net(dev), idev,
+ IP6_INC_STATS(net, idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
}
- IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
- skb->len);
+ IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len);
if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
IPV6_ADDR_SCOPE_NODELOCAL &&
}
rcu_read_lock_bh();
- nexthop = rt6_nexthop((struct rt6_info *)dst);
+ nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
}
rcu_read_unlock_bh();
- IP6_INC_STATS(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
-static int ip6_finish_output(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
- return ip6_fragment(sk, skb, ip6_finish_output2);
+ return ip6_fragment(net, sk, skb, ip6_finish_output2);
else
- return ip6_finish_output2(sk, skb);
+ return ip6_finish_output2(net, sk, skb);
}
-int ip6_output(struct sock *sk, struct sk_buff *skb)
+int ip6_output(struct net *net, struct sock *sk, 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(dev), idev,
- IPSTATS_MIB_OUTDISCARDS);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
- return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb,
- NULL, dev,
+ return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, dev,
ip6_finish_output,
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
/*
- * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * Note : socket lock is not held for SYNACK packets, but might be modified
+ * by calls to skb_set_owner_w() and ipv6_local_error(),
+ * which are using proper atomic operations or spinlocks.
*/
-
-int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
+int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt, int tclass)
{
struct net *net = sock_net(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
+ const struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
}
consume_skb(skb);
skb = skb2;
- skb_set_owner_w(skb, sk);
+ /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
+ * it is safe to call in our context (socket lock not held)
+ */
+ skb_set_owner_w(skb, (struct sock *)sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel));
+ np->autoflowlabel, fl6));
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
- return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
- NULL, dst->dev, dst_output_sk);
+ /* hooks should never assume socket lock is held.
+ * we promote our socket to non const
+ */
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+ net, (struct sock *)sk, skb, NULL, dst->dev,
+ dst_output);
}
skb->dev = dst->dev;
- ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
+ /* ipv6_local_error() does not require socket lock,
+ * we promote our socket to non const
+ */
+ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);
+
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
return 0;
}
-static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb)
+static inline int ip6_forward_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
{
skb_sender_cpu_clear(skb);
- return dst_output_sk(sk, skb);
+ return dst_output(net, sk, skb);
}
static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
if (skb->pkt_type != PACKET_HOST)
goto drop;
+ if (unlikely(skb->sk))
+ goto drop;
+
if (skb_warn_if_lro(skb))
goto drop;
else
target = &hdr->daddr;
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+ peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
- return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb,
- skb->dev, dst->dev,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
+ net, NULL, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
skb_copy_secmark(to, from);
}
-int ip6_fragment(struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *))
+int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
int hroom, troom;
- __be32 frag_id = 0;
+ __be32 frag_id;
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
- struct net *net = dev_net(skb_dst(skb)->dev);
hlen = ip6_find_1stfragopt(skb, &prevhdr);
nexthdr = *prevhdr;
/* 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 (unlikely(!skb->ignore_df && skb->len > mtu) ||
- (IP6CB(skb)->frag_max_size &&
- IP6CB(skb)->frag_max_size > mtu)) {
- if (skb->sk && dst_allfrag(skb_dst(skb)))
- sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+ if (unlikely(!skb->ignore_df && skb->len > mtu))
+ goto fail_toobig;
- skb->dev = skb_dst(skb)->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_FRAGFAILS);
- kfree_skb(skb);
- return -EMSGSIZE;
+ if (IP6CB(skb)->frag_max_size) {
+ if (IP6CB(skb)->frag_max_size > mtu)
+ goto fail_toobig;
+
+ /* don't send fragments larger than what we received */
+ mtu = IP6CB(skb)->frag_max_size;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
}
if (np && np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
+ if (mtu < hlen + sizeof(struct frag_hdr) + 8)
+ goto fail_toobig;
mtu -= hlen + sizeof(struct frag_hdr);
+ frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
+ &ipv6_hdr(skb)->saddr);
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (err = skb_checksum_help(skb)))
+ goto fail;
+
+ hroom = LL_RESERVED_SPACE(rt->dst.dev);
if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
struct sk_buff *frag2;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
- skb_cloned(skb))
+ skb_cloned(skb) ||
+ skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
goto slow_path;
skb_walk_frags(skb, frag) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
- skb_headroom(frag) < hlen)
+ skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr)))
goto slow_path_clean;
/* Partially cloned skb? */
err = 0;
offset = 0;
- frag = skb_shinfo(skb)->frag_list;
- skb_frag_list_init(skb);
/* BUILD HEADER */
*prevhdr = NEXTHDR_FRAGMENT;
if (!tmp_hdr) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto fail;
}
+ frag = skb_shinfo(skb)->frag_list;
+ skb_frag_list_init(skb);
__skb_pull(skb, hlen);
fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr));
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
- ipv6_select_ident(net, fh, rt);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
- frag_id = fh->identification;
+ fh->identification = frag_id;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
ip6_copy_metadata(frag, skb);
}
- err = output(sk, skb);
+ err = output(net, sk, skb);
if (!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
}
slow_path:
- if ((skb->ip_summed == CHECKSUM_PARTIAL) &&
- skb_checksum_help(skb))
- goto fail;
-
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
*/
*prevhdr = NEXTHDR_FRAGMENT;
- hroom = LL_RESERVED_SPACE(rt->dst.dev);
troom = rt->dst.dev->needed_tailroom;
/*
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
- if (!frag_id) {
- ipv6_select_ident(net, fh, rt);
- frag_id = fh->identification;
- } else
- fh->identification = frag_id;
+ fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
/*
* Put this fragment into the sending queue.
*/
- err = output(sk, frag);
+ err = output(net, sk, frag);
if (err)
goto fail;
consume_skb(skb);
return err;
+fail_toobig:
+ if (skb->sk && dst_allfrag(skb_dst(skb)))
+ sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+
+ skb->dev = skb_dst(skb)->dev;
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ err = -EMSGSIZE;
+
fail:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
#ifdef CONFIG_IPV6_SUBTREES
ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
#endif
- (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
+ (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) &&
+ (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) {
dst_release(dst);
dst = NULL;
}
return dst;
}
-static int ip6_dst_lookup_tail(struct sock *sk,
+static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
- struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
struct rt6_info *rt;
#endif
int err;
+ int flags = 0;
/* The correct way to handle this would be to do
* ip6_route_get_saddr, and then ip6_route_output; however,
dst_release(*dst);
*dst = NULL;
}
+
+ if (fl6->flowi6_oif)
+ flags |= RT6_LOOKUP_F_IFACE;
}
if (!*dst)
- *dst = ip6_route_output(net, sk, fl6);
+ *dst = ip6_route_output_flags(net, sk, fl6, flags);
err = (*dst)->error;
if (err)
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
- n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev,
+ rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
*
* It returns zero on success, or a standard errno code on error.
*/
-int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6)
+int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
+ struct flowi6 *fl6)
{
*dst = NULL;
- return ip6_dst_lookup_tail(sk, dst, fl6);
+ return ip6_dst_lookup_tail(net, sk, dst, fl6);
}
EXPORT_SYMBOL_GPL(ip6_dst_lookup);
* It returns a valid dst pointer on success, or a pointer encoded
* error code.
*/
-struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst)
{
struct dst_entry *dst = NULL;
int err;
- err = ip6_dst_lookup_tail(sk, &dst, fl6);
+ err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
if (err)
return ERR_PTR(err);
if (final_dst)
fl6->daddr = *final_dst;
+ if (!fl6->flowi6_oif)
+ fl6->flowi6_oif = l3mdev_fib_oif(dst->dev);
return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
dst = ip6_sk_dst_check(sk, dst, fl6);
- err = ip6_dst_lookup_tail(sk, &dst, fl6);
+ err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
if (err)
return ERR_PTR(err);
if (final_dst)
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)
+ const struct flowi6 *fl6)
{
struct sk_buff *skb;
- struct frag_hdr fhdr;
int err;
/* There is support for UDP large send offload by network
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
- ipv6_select_ident(sock_net(sk), &fhdr, rt);
- skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
+ skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk),
+ &fl6->daddr,
+ &fl6->saddr);
append:
return skb_append_datato_frags(sk, skb, getfrag, from,
struct rt6_info *rt = (struct rt6_info *)cork->dst;
struct ipv6_txoptions *opt = v6_cork->opt;
int csummode = CHECKSUM_NONE;
+ unsigned int maxnonfragsize, headersize;
skb = skb_peek_tail(queue);
if (!skb) {
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
sizeof(struct frag_hdr);
- if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
- unsigned int maxnonfragsize, headersize;
-
- headersize = sizeof(struct ipv6hdr) +
- (opt ? opt->opt_flen + opt->opt_nflen : 0) +
- (dst_allfrag(&rt->dst) ?
- sizeof(struct frag_hdr) : 0) +
- rt->rt6i_nfheader_len;
-
- if (ip6_sk_ignore_df(sk))
- maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
- else
- maxnonfragsize = mtu;
+ headersize = sizeof(struct ipv6hdr) +
+ (opt ? opt->opt_flen + opt->opt_nflen : 0) +
+ (dst_allfrag(&rt->dst) ?
+ sizeof(struct frag_hdr) : 0) +
+ rt->rt6i_nfheader_len;
+
+ if (cork->length + length > mtu - headersize && dontfrag &&
+ (sk->sk_protocol == IPPROTO_UDP ||
+ sk->sk_protocol == IPPROTO_RAW)) {
+ ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+ sizeof(struct ipv6hdr));
+ goto emsgsize;
+ }
- /* dontfrag active */
- if ((cork->length + length > mtu - headersize) && dontfrag &&
- (sk->sk_protocol == IPPROTO_UDP ||
- sk->sk_protocol == IPPROTO_RAW)) {
- ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
- sizeof(struct ipv6hdr));
- goto emsgsize;
- }
+ if (ip6_sk_ignore_df(sk))
+ maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+ else
+ maxnonfragsize = mtu;
- if (cork->length + length > maxnonfragsize - headersize) {
+ if (cork->length + length > maxnonfragsize - headersize) {
emsgsize:
- ipv6_local_error(sk, EMSGSIZE, fl6,
- mtu - headersize +
- sizeof(struct ipv6hdr));
- return -EMSGSIZE;
- }
+ ipv6_local_error(sk, EMSGSIZE, fl6,
+ mtu - headersize +
+ sizeof(struct ipv6hdr));
+ return -EMSGSIZE;
}
+ /* CHECKSUM_PARTIAL only with no extension headers and when
+ * we are not going to fragment
+ */
+ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
+ headersize == sizeof(struct ipv6hdr) &&
+ length < mtu - headersize &&
+ !(flags & MSG_MORE) &&
+ rt->dst.dev->features & NETIF_F_V6_CSUM)
+ csummode = CHECKSUM_PARTIAL;
+
if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
sock_tx_timestamp(sk, &tx_flags);
if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
tskey = sk->sk_tskey++;
}
- /* If this is the first and only packet and device
- * supports checksum offloading, let's use it.
- * Use transhdrlen, same as IPv4, because partial
- * sums only work when transhdrlen is set.
- */
- if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
- length + fragheaderlen < mtu &&
- rt->dst.dev->features & NETIF_F_V6_CSUM &&
- !exthdrlen)
- csummode = CHECKSUM_PARTIAL;
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) &&
- (sk->sk_type == SOCK_DGRAM)) {
+ (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen,
- transhdrlen, mtu, flags, rt);
+ transhdrlen, mtu, flags, fl6);
if (err)
goto error;
return 0;
ip6_flow_hdr(hdr, v6_cork->tclass,
ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel));
+ np->autoflowlabel, fl6));
hdr->hop_limit = v6_cork->hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
int err;
- err = ip6_local_out(skb);
+ err = ip6_local_out(net, skb->sk, skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
Code Review / kvmfornfv.git / blobdiff