In case almost or all available ports are taken, clash resolution can
take a very long time, resulting in soft lockup.
This can happen when many to-be-natted hosts connect to same
destination:port (e.g. a proxy) and all connections pass the same SNAT.
Pick a random offset in the acceptable range, then try ever smaller
number of adjacent port numbers, until either the limit is reached or a
useable port was found. This results in at most 248 attempts
(128 + 64 + 32 + 16 + 8, i.e. 4 restarts with new search offset)
instead of 64000+,
Signed-off-by: Florian Westphal <fw@xxxxxxxxx>
---
Pablo,
this will unfortunately result in a nf-next merge conflict
due to *rover removal in nf-next.
I can send a patch vs. nf-next instead if you prefer.
net/netfilter/nf_nat_proto_common.c | 26 ++++++++++++++++++++++----
1 file changed, 22 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index 5d849d835561..0e3321660624 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -41,9 +41,10 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
const struct nf_conn *ct,
u16 *rover)
{
- unsigned int range_size, min, max, i;
+ unsigned int range_size, min, max, i, attempts;
__be16 *portptr;
- u_int16_t off;
+ u16 off;
+ static const unsigned int max_attempts = 128;
if (maniptype == NF_NAT_MANIP_SRC)
portptr = &tuple->src.u.all;
@@ -89,15 +90,32 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
off = *rover;
}
- for (i = 0; ; ++off) {
+ attempts = range_size;
+ if (attempts > max_attempts)
+ attempts = max_attempts;
+
+ /* We are in softirq; doing a search of the entire range risks
+ * soft lockup when all tuples are already used.
+ *
+ * If we can't find any free port from first offset, pick a new
+ * one and try again, with ever smaller search window.
+ */
+another_round:
+ for (i = 0; i < attempts; ++off) {
*portptr = htons(min + off % range_size);
- if (++i != range_size && nf_nat_used_tuple(tuple, ct))
+ if (nf_nat_used_tuple(tuple, ct))
continue;
if (!(range->flags & (NF_NAT_RANGE_PROTO_RANDOM_ALL|
NF_NAT_RANGE_PROTO_OFFSET)))
*rover = off;
return;
}
+
+ if (attempts >= range_size || attempts < 16)
+ return;
+ attempts /= 2;
+ off = prandom_u32();
+ goto another_round;
}
EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple);
--
2.19.2
