ipv4: Cap ADVMSS metric in the FIB rather than the routing cache.
It makes no sense to execute this limit test every time we create a
routing cache entry.
We can't simply error out on these things since we've silently
accepted and truncated them forever.
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e5b7182..415f823 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -779,9 +779,14 @@
int type = nla_type(nla);
if (type) {
+ u32 val;
+
if (type > RTAX_MAX)
goto err_inval;
- fi->fib_metrics[type - 1] = nla_get_u32(nla);
+ val = nla_get_u32(nla);
+ if (type == RTAX_ADVMSS && val > 65535 - 40)
+ val = 65535 - 40;
+ fi->fib_metrics[type - 1] = val;
}
}
}