[NETFILTER]: non-power-of-two jhash optimizations

Apply Eric Dumazet's jhash optimizations where applicable. Quoting Eric:

Thanks to jhash, hash value uses full 32 bits. Instead of returning
hash % size (implying a divide) we return the high 32 bits of the
(hash * size) that will give results between [0 and size-1] and same
hash distribution.

On most cpus, a multiply is less expensive than a divide, by an order
of magnitude.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 6 insertions, 4 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5920f953f782..25564073ee23 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -81,7 +81,7 @@ static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple,
                    ((__force __u16)tuple->src.u.all << 16) |
                     (__force __u16)tuple->dst.u.all);
 
-        return jhash_2words(a, b, rnd) % size;
+        return ((u64)jhash_2words(a, b, rnd) * size) >> 32;
 }
 
 static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 0efbf343eac8..e0cd9d00aa61 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -73,15 +73,17 @@ static void nf_ct_expectation_timed_out(unsigned long ul_expect)
 
 static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple)
 {
+        unsigned int hash;
+
         if (unlikely(!nf_ct_expect_hash_rnd_initted)) {
                 get_random_bytes(&nf_ct_expect_hash_rnd, 4);
                 nf_ct_expect_hash_rnd_initted = 1;
         }
 
-        return jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
+        hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
                       (((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
-                       (__force __u16)tuple->dst.u.all) ^ nf_ct_expect_hash_rnd) %
-               nf_ct_expect_hsize;
+                       (__force __u16)tuple->dst.u.all) ^ nf_ct_expect_hash_rnd);
+        return ((u64)hash * nf_ct_expect_hsize) >> 32;
 }
 
 struct nf_conntrack_expect *