1) Using jhash2() instead of jhash() is a litle bit faster if applicable.
2) 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: Eric Dumazet <dada1@xxxxxxxxxxxxx>
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 033d448..7cc04e8 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -105,7 +105,16 @@ static inline bool dst_cmp(const struct dsthash_ent *ent,
static u_int32_t
hash_dst(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst)
{
- return jhash(dst, sizeof(*dst), ht->rnd) % ht->cfg.size;
+ u_int32_t hash = jhash2((const u32 *)dst,
+ sizeof(*dst)/sizeof(u32),
+ ht->rnd);
+ /*
+ * Instead of returning hash % ht->cfg.size (implying a divide)
+ * we return the high 32 bits of the (hash * ht->cfg.size) that will
+ * give results between [0 and cfg.size-1] and same hash distribution,
+ * but using a multiply, less expensive than a divide
+ */
+ return ((u64)hash * ht->cfg.size) >> 32;
}
static struct dsthash_ent *
