[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, 3 insertions, 2 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 8c48fbecb7c..b6440805c42 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -99,6 +99,7 @@ struct proto;
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_bind_node: bind hash linkage for various protocol lookup tables
  *	@skc_refcnt: reference count
+ *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_prot: protocol handlers inside a network family
  *
  *	This is the minimal network layer representation of sockets, the header
@@ -112,6 +113,7 @@ struct sock_common {
 	struct hlist_node	skc_node;
 	struct hlist_node	skc_bind_node;
 	atomic_t		skc_refcnt;
+	unsigned int		skc_hash;
 	struct proto		*skc_prot;
 };
 
@@ -139,7 +141,6 @@ struct sock_common {
   *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_lingertime: %SO_LINGER l_linger setting
-  *	@sk_hashent: hash entry in several tables (e.g. inet_hashinfo.ehash)
   *	@sk_backlog: always used with the per-socket spinlock held
   *	@sk_callback_lock: used with the callbacks in the end of this struct
   *	@sk_error_queue: rarely used
@@ -186,6 +187,7 @@ struct sock {
 #define sk_node			__sk_common.skc_node
 #define sk_bind_node		__sk_common.skc_bind_node
 #define sk_refcnt		__sk_common.skc_refcnt
+#define sk_hash			__sk_common.skc_hash
 #define sk_prot			__sk_common.skc_prot
 	unsigned char		sk_shutdown : 2,
 				sk_no_check : 2,
@@ -208,7 +210,6 @@ struct sock {
 	unsigned int		sk_allocation;
 	int			sk_sndbuf;
 	int			sk_route_caps;
-	int			sk_hashent;
 	unsigned long 		sk_flags;
 	unsigned long	        sk_lingertime;
 	/*