inet: change lport contribution to inet_ehashfn() and inet6_ehashfn()

In order to speedup __inet_hash_connect(), we want to ensure hash values
for <source address, port X, destination address, destination port>
are not randomly spread, but monotonically increasing.

Goal is to allow __inet_hash_connect() to derive the hash value
of a candidate 4-tuple with a single addition in the following
patch in the series.

Given :
  hash_0 = inet_ehashfn(saddr, 0, daddr, dport)
  hash_sport = inet_ehashfn(saddr, sport, daddr, dport)

Then (hash_sport == hash_0 + sport) for all sport values.

As far as I know, there is no security implication with this change.

After this patch, when __inet_hash_connect() has to try XXXX candidates,
the hash table buckets are contiguous and packed, allowing
a better use of cpu caches and hardware prefetchers.

Tested:

Server: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog
Client: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog -c -H server

Before this patch:

  utime_start=0.271607
  utime_end=3.847111
  stime_start=18.407684
  stime_end=1997.485557
  num_transactions=1350742
  latency_min=0.014131929
  latency_max=17.895073144
  latency_mean=0.505675853
  latency_stddev=2.125164772
  num_samples=307884
  throughput=139866.80

perf top on client:

 56.86%  [kernel]       [k] __inet6_check_established
 17.96%  [kernel]       [k] __inet_hash_connect
 13.88%  [kernel]       [k] inet6_ehashfn
  2.52%  [kernel]       [k] rcu_all_qs
  2.01%  [kernel]       [k] __cond_resched
  0.41%  [kernel]       [k] _raw_spin_lock

After this patch:

  utime_start=0.286131
  utime_end=4.378886
  stime_start=11.952556
  stime_end=1991.655533
  num_transactions=1446830
  latency_min=0.001061085
  latency_max=12.075275028
  latency_mean=0.376375302
  latency_stddev=1.361969596
  num_samples=306383
  throughput=151866.56

perf top:

 50.01%  [kernel]       [k] __inet6_check_established
 20.65%  [kernel]       [k] __inet_hash_connect
 15.81%  [kernel]       [k] inet6_ehashfn
  2.92%  [kernel]       [k] rcu_all_qs
  2.34%  [kernel]       [k] __cond_resched
  0.50%  [kernel]       [k] _raw_spin_lock
  0.34%  [kernel]       [k] sched_balance_trigger
  0.24%  [kernel]       [k] queued_spin_lock_slowpath

There is indeed an increase of throughput and reduction of latency.

Signed-off-by: Eric Dumazet <[email protected]>
Reviewed-by: Kuniyuki Iwashima <[email protected]>
Tested-by: Jason Xing <[email protected]>
Reviewed-by: Jason Xing <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: edumazet

net/ipv4/inet_hashtables.c

@@ -35,8 +35,8 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr,
 {
 	net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));
 
-	return __inet_ehashfn(laddr, lport, faddr, fport,
-			      inet_ehash_secret + net_hash_mix(net));
+	return lport + __inet_ehashfn(laddr, 0, faddr, fport,
+				      inet_ehash_secret + net_hash_mix(net));
 }
 EXPORT_SYMBOL_GPL(inet_ehashfn);
 

net/ipv6/inet6_hashtables.c

@@ -35,8 +35,8 @@ u32 inet6_ehashfn(const struct net *net,
 	lhash = (__force u32)laddr->s6_addr32[3];
 	fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret);
 
-	return __inet6_ehashfn(lhash, lport, fhash, fport,
-			       inet6_ehash_secret + net_hash_mix(net));
+	return lport + __inet6_ehashfn(lhash, 0, fhash, fport,
+				       inet6_ehash_secret + net_hash_mix(net));
 }
 EXPORT_SYMBOL_GPL(inet6_ehashfn);