[INET]: speedup inet (tcp/dccp) lookups

Arnaldo and I agreed it could be applied now, because I have other
pending patches depending on this one (Thank you Arnaldo)

(The other important patch moves skc_refcnt in a separate cache line,
so that the SMP/NUMA performance doesnt suffer from cache line ping pongs)

1) First some performance data :
--------------------------------

tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established()

The most time critical code is :

sk_for_each(sk, node, &head->chain) {
     if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif))
         goto hit; /* You sunk my battleship! */
}

The sk_for_each() does use prefetch() hints but only the begining of
"struct sock" is prefetched.

As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far
away from the begining of "struct sock", it has to bring into CPU
cache cold cache line. Each iteration has to use at least 2 cache
lines.

This can be problematic if some chains are very long.

2) The goal
-----------

The idea I had is to change things so that INET_MATCH() may return
FALSE in 99% of cases only using the data already in the CPU cache,
using one cache line per iteration.

3) Description of the patch
---------------------------

Adds a new 'unsigned int skc_hash' field in 'struct sock_common',
filling a 32 bits hole on 64 bits platform.

struct sock_common {
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
	struct hlist_node	skc_node;
	struct hlist_node	skc_bind_node;
	atomic_t		skc_refcnt;
+	unsigned int		skc_hash;
	struct proto		*skc_prot;
};

Store in this 32 bits field the full hash, not masked by (ehash_size -
1) Using this full hash as the first comparison done in INET_MATCH
permits us immediatly skip the element without touching a second cache
line in case of a miss.

Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to
sk_hash and tw_hash) already contains the slot number if we mask with
(ehash_size - 1)

File include/net/inet_hashtables.h

64 bits platforms :
#define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
     (((__sk)->sk_hash == (__hash))
     ((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie))   &&  \
     ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports))   &&  \
     (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))

32bits platforms:
#define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
     (((__sk)->sk_hash == (__hash))                 &&  \
     (inet_sk(__sk)->daddr          == (__saddr))   &&  \
     (inet_sk(__sk)->rcv_saddr      == (__daddr))   &&  \
     (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))


- Adds a prefetch(head->chain.first) in 
__inet_lookup_established()/__tcp_v4_check_established() and 
__inet6_lookup_established()/__tcp_v6_check_established() and 
__dccp_v4_check_established() to bring into cache the first element of the 
list, before the {read|write}_lock(&head->lock);

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 10 insertions, 11 deletions

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 03df3b157960..5a2beed5a770 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -26,19 +26,18 @@
 struct inet_hashinfo;
 
 /* I have no idea if this is a good hash for v6 or not. -DaveM */
-static inline int inet6_ehashfn(const struct in6_addr *laddr, const u16 lport,
-				const struct in6_addr *faddr, const u16 fport,
-				const int ehash_size)
+static inline unsigned int inet6_ehashfn(const struct in6_addr *laddr, const u16 lport,
+				const struct in6_addr *faddr, const u16 fport)
 {
-	int hashent = (lport ^ fport);
+	unsigned int hashent = (lport ^ fport);
 
 	hashent ^= (laddr->s6_addr32[3] ^ faddr->s6_addr32[3]);
 	hashent ^= hashent >> 16;
 	hashent ^= hashent >> 8;
-	return (hashent & (ehash_size - 1));
+	return hashent;
 }
 
-static inline int inet6_sk_ehashfn(const struct sock *sk, const int ehash_size)
+static inline int inet6_sk_ehashfn(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ipv6_pinfo *np = inet6_sk(sk);
@@ -46,7 +45,7 @@ static inline int inet6_sk_ehashfn(const struct sock *sk, const int ehash_size)
 	const struct in6_addr *faddr = &np->daddr;
 	const __u16 lport = inet->num;
 	const __u16 fport = inet->dport;
-	return inet6_ehashfn(laddr, lport, faddr, fport, ehash_size);
+	return inet6_ehashfn(laddr, lport, faddr, fport);
 }
 
 /*
@@ -69,14 +68,14 @@ static inline struct sock *
 	/* Optimize here for direct hit, only listening connections can
 	 * have wildcards anyways.
 	 */
-	const int hash = inet6_ehashfn(daddr, hnum, saddr, sport,
-				       hashinfo->ehash_size);
-	struct inet_ehash_bucket *head = &hashinfo->ehash[hash];
+	unsigned int hash = inet6_ehashfn(daddr, hnum, saddr, sport);
+	struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);
 
+	prefetch(head->chain.first);
 	read_lock(&head->lock);
 	sk_for_each(sk, node, &head->chain) {
 		/* For IPV6 do the cheaper port and family tests first. */
-		if (INET6_MATCH(sk, saddr, daddr, ports, dif))
+		if (INET6_MATCH(sk, hash, saddr, daddr, ports, dif))
 			goto hit; /* You sunk my battleship! */
 	}
 	/* Must check for a TIME_WAIT'er before going to listener hash. */