summaryrefslogtreecommitdiff
path: root/net/ipv6/ip6_output.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/ip6_output.c')
-rw-r--r--net/ipv6/ip6_output.c98
1 files changed, 61 insertions, 37 deletions
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e6f931997996..64d6073731d3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -321,6 +321,41 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
return dst_output(skb);
}
+static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+ unsigned int mtu;
+ struct inet6_dev *idev;
+
+ if (dst_metric_locked(dst, RTAX_MTU)) {
+ mtu = dst_metric_raw(dst, RTAX_MTU);
+ if (mtu)
+ return mtu;
+ }
+
+ mtu = IPV6_MIN_MTU;
+ rcu_read_lock();
+ idev = __in6_dev_get(dst->dev);
+ if (idev)
+ mtu = idev->cnf.mtu6;
+ rcu_read_unlock();
+
+ return mtu;
+}
+
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+ return true;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -336,7 +371,8 @@ int ip6_forward(struct sk_buff *skb)
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
- IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_INDISCARDS);
goto drop;
}
@@ -370,8 +406,8 @@ int ip6_forward(struct sk_buff *skb)
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
- IP6_INC_STATS_BH(net,
- ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
@@ -384,14 +420,15 @@ int ip6_forward(struct sk_buff *skb)
if (proxied > 0)
return ip6_input(skb);
else if (proxied < 0) {
- IP6_INC_STATS(net, ip6_dst_idev(dst),
- IPSTATS_MIB_INDISCARDS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
- IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb_dst(skb);
@@ -439,25 +476,25 @@ int ip6_forward(struct sk_buff *skb)
}
}
- mtu = dst_mtu(dst);
+ mtu = ip6_dst_mtu_forward(dst);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
- (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+ if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP6_INC_STATS_BH(net,
- ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
- IP6_INC_STATS_BH(net,
- ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_INTOOBIGERRORS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (skb_cow(skb, dst->dev->hard_header_len)) {
- IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+ IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
@@ -493,9 +530,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- to->nf_trace = from->nf_trace;
-#endif
skb_copy_secmark(to, from);
}
@@ -938,7 +972,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
* @sk: socket which provides route info
* @fl6: flow to lookup
* @final_dst: final destination address for ipsec lookup
- * @can_sleep: we are in a sleepable context
*
* This function performs a route lookup on the given flow.
*
@@ -946,8 +979,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
* error code.
*/
struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
- const struct in6_addr *final_dst,
- bool can_sleep)
+ const struct in6_addr *final_dst)
{
struct dst_entry *dst = NULL;
int err;
@@ -957,8 +989,6 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
return ERR_PTR(err);
if (final_dst)
fl6->daddr = *final_dst;
- if (can_sleep)
- fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
@@ -969,7 +999,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
* @sk: socket which provides the dst cache and route info
* @fl6: flow to lookup
* @final_dst: final destination address for ipsec lookup
- * @can_sleep: we are in a sleepable context
*
* This function performs a route lookup on the given flow with the
* possibility of using the cached route in the socket if it is valid.
@@ -980,8 +1009,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
* error code.
*/
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
- const struct in6_addr *final_dst,
- bool can_sleep)
+ const struct in6_addr *final_dst)
{
struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
int err;
@@ -993,8 +1021,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
return ERR_PTR(err);
if (final_dst)
fl6->daddr = *final_dst;
- if (can_sleep)
- fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
@@ -1075,21 +1101,19 @@ static void ip6_append_data_mtu(unsigned int *mtu,
unsigned int fragheaderlen,
struct sk_buff *skb,
struct rt6_info *rt,
- bool pmtuprobe)
+ unsigned int orig_mtu)
{
if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
if (skb == NULL) {
/* first fragment, reserve header_len */
- *mtu = *mtu - rt->dst.header_len;
+ *mtu = orig_mtu - rt->dst.header_len;
} else {
/*
* this fragment is not first, the headers
* space is regarded as data space.
*/
- *mtu = min(*mtu, pmtuprobe ?
- rt->dst.dev->mtu :
- dst_mtu(rt->dst.path));
+ *mtu = orig_mtu;
}
*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+ fragheaderlen - sizeof(struct frag_hdr);
@@ -1106,7 +1130,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
- unsigned int maxfraglen, fragheaderlen, mtu;
+ unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
@@ -1162,10 +1186,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
- mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+ mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
- mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+ mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
@@ -1188,6 +1212,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
+ orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1285,8 +1310,7 @@ alloc_new_skb:
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt,
- np->pmtudisc ==
- IPV6_PMTUDISC_PROBE);
+ orig_mtu);
skb_prev = skb;
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-04-07 02:57:34 +0000