netfilter: ipv4: propagate routing errors from ip_route_me_harder()

Propagate routing errors from ip_route_me_harder() when dropping a packet
using NF_DROP_ERR(). This makes userspace get the proper error instead of
EPERM for everything.

Example:

# ip r a unreachable default table 100
# ip ru add fwmark 0x1 lookup 100
# iptables -t mangle -A OUTPUT -d 8.8.8.8 -j MARK --set-mark 0x1

Current behaviour:

PING 8.8.8.8 (8.8.8.8) 56(84) bytes of data.
ping: sendmsg: Operation not permitted
ping: sendmsg: Operation not permitted
ping: sendmsg: Operation not permitted

New behaviour:

PING 8.8.8.8 (8.8.8.8) 56(84) bytes of data.
ping: sendmsg: Network is unreachable
ping: sendmsg: Network is unreachable
ping: sendmsg: Network is unreachable
ping: sendmsg: Network is unreachable

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

3 files changed, 14 insertions, 9 deletions

diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 4c0cf63dd92e..8b201e8095cd 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -40,14 +40,14 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
         fl4.flowi4_flags = flags;
         rt = ip_route_output_key(net, &fl4);
         if (IS_ERR(rt))
-                return -1;
+                return PTR_ERR(rt);
 
         /* Drop old route. */
         skb_dst_drop(skb);
         skb_dst_set(skb, &rt->dst);
 
         if (skb_dst(skb)->error)
-                return -1;
+                return skb_dst(skb)->error;
 
 #ifdef CONFIG_XFRM
         if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -56,7 +56,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
                 skb_dst_set(skb, NULL);
                 dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
                 if (IS_ERR(dst))
-                        return -1;
+                        return PTR_ERR(dst);;
                 skb_dst_set(skb, dst);
         }
 #endif
@@ -66,7 +66,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
         if (skb_headroom(skb) < hh_len &&
             pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
                                 0, GFP_ATOMIC))
-                return -1;
+                return -ENOMEM;
 
         return 0;
 }
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 85d88f206447..cba5658ec82c 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -44,6 +44,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
         u_int8_t tos;
         __be32 saddr, daddr;
         u_int32_t mark;
+        int err;
 
         /* root is playing with raw sockets. */
         if (skb->len < sizeof(struct iphdr) ||
@@ -66,9 +67,11 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
                 if (iph->saddr != saddr ||
                     iph->daddr != daddr ||
                     skb->mark != mark ||
-                    iph->tos != tos)
-                        if (ip_route_me_harder(skb, RTN_UNSPEC))
-                                ret = NF_DROP;
+                    iph->tos != tos) {
+                        err = ip_route_me_harder(skb, RTN_UNSPEC);
+                        if (err < 0)
+                                ret = NF_DROP_ERR(err);
+                }
         }
 
         return ret;
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index eeaff7e4acb5..c2937c81bb67 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -213,6 +213,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum,
         const struct nf_conn *ct;
         enum ip_conntrack_info ctinfo;
         unsigned int ret;
+        int err;
 
         /* root is playing with raw sockets. */
         if (skb->len < sizeof(struct iphdr) ||
@@ -226,8 +227,9 @@ nf_nat_ipv4_local_fn(unsigned int hooknum,
 
                 if (ct->tuplehash[dir].tuple.dst.u3.ip !=
                     ct->tuplehash[!dir].tuple.src.u3.ip) {
-                        if (ip_route_me_harder(skb, RTN_UNSPEC))
-                                ret = NF_DROP;
+                        err = ip_route_me_harder(skb, RTN_UNSPEC);
+                        if (err < 0)
+                                ret = NF_DROP_ERR(err);
                 }
 #ifdef CONFIG_XFRM
                 else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&