summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/ip_forward.c71
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/route.c13
3 files changed, 79 insertions, 7 deletions
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e9f1217..f3869c1 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
#include <net/route.h>
#include <net/xfrm.h>
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+ return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+ !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+ unsigned int mtu;
+
+ if (skb->local_df || !skb_is_gso(skb))
+ return false;
+
+ mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+ /* if seglen > mtu, do software segmentation for IP fragmentation on
+ * output. DF bit cannot be set since ip_forward would have sent
+ * icmp error.
+ */
+ return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ features = netif_skb_dev_features(skb, dst->dev);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = dst_output(segs);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ if (ip_gso_exceeds_dst_mtu(skb))
+ return ip_forward_finish_gso(skb);
+
return dst_output(skb);
}
@@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb)
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
- (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+ if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index efa1138..b3e86ea 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -273,7 +273,7 @@ static int __init ic_open_devs(void)
msleep(1);
- if time_before(jiffies, next_msg)
+ if (time_before(jiffies, next_msg))
continue;
elapsed = jiffies_to_msecs(jiffies - start);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25071b4..4c011ec 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1597,6 +1597,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1695,10 +1696,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
- if (err != 0)
+ if (err != 0) {
+ if (!IN_DEV_FORWARD(in_dev))
+ err = -EHOSTUNREACH;
goto no_route;
-
- RT_CACHE_STAT_INC(in_slow_tot);
+ }
if (res.type == RTN_BROADCAST)
goto brd_input;
@@ -1712,8 +1714,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
goto local_input;
}
- if (!IN_DEV_FORWARD(in_dev))
+ if (!IN_DEV_FORWARD(in_dev)) {
+ err = -EHOSTUNREACH;
goto no_route;
+ }
if (res.type != RTN_UNICAST)
goto martian_destination;
@@ -1768,6 +1772,7 @@ local_input:
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;