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>
}
/* node numbers are 1..n, not 0..n */
}
/* node numbers are 1..n, not 0..n */
- return (hashval % config->num_total_nodes) + 1;
+ return (((u64)hashval * config->num_total_nodes) >> 32) + 1;
static inline unsigned int
hash_by_src(const struct nf_conntrack_tuple *tuple)
{
static inline unsigned int
hash_by_src(const struct nf_conntrack_tuple *tuple)
{
/* Original src, to ensure we map it consistently if poss. */
/* Original src, to ensure we map it consistently if poss. */
- return jhash_3words((__force u32)tuple->src.u3.ip,
+ hash = jhash_3words((__force u32)tuple->src.u3.ip,
(__force u32)tuple->src.u.all,
(__force u32)tuple->src.u.all,
- tuple->dst.protonum, 0) % nf_nat_htable_size;
+ tuple->dst.protonum, 0);
+ return ((u64)hash * nf_nat_htable_size) >> 32;
}
/* Is this tuple already taken? (not by us) */
}
/* Is this tuple already taken? (not by us) */
maxip = ntohl(range->max_ip);
j = jhash_2words((__force u32)tuple->src.u3.ip,
(__force u32)tuple->dst.u3.ip, 0);
maxip = ntohl(range->max_ip);
j = jhash_2words((__force u32)tuple->src.u3.ip,
(__force u32)tuple->dst.u3.ip, 0);
- *var_ipp = htonl(minip + j % (maxip - minip + 1));
+ j = ((u64)j * (maxip - minip + 1)) >> 32;
+ *var_ipp = htonl(minip + j);
}
/* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING,
}
/* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING,
((__force __u16)tuple->src.u.all << 16) |
(__force __u16)tuple->dst.u.all);
((__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)
}
static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple)
static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple)
{
static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple)
{
if (unlikely(!nf_ct_expect_hash_rnd_initted)) {
get_random_bytes(&nf_ct_expect_hash_rnd, 4);
nf_ct_expect_hash_rnd_initted = 1;
}
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) |
(((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 *
}
struct nf_conntrack_expect *