alistair23-linux/include/linux/tc_ematch/tc_em_meta.h

95 lines
1.9 KiB
C
Raw Normal View History

#ifndef __LINUX_TC_EM_META_H
#define __LINUX_TC_EM_META_H
#include <linux/pkt_cls.h>
enum
{
TCA_EM_META_UNSPEC,
TCA_EM_META_HDR,
TCA_EM_META_LVALUE,
TCA_EM_META_RVALUE,
__TCA_EM_META_MAX
};
#define TCA_EM_META_MAX (__TCA_EM_META_MAX - 1)
struct tcf_meta_val
{
__u16 kind;
__u8 shift;
__u8 op;
};
#define TCF_META_TYPE_MASK (0xf << 12)
#define TCF_META_TYPE(kind) (((kind) & TCF_META_TYPE_MASK) >> 12)
#define TCF_META_ID_MASK 0x7ff
#define TCF_META_ID(kind) ((kind) & TCF_META_ID_MASK)
enum
{
TCF_META_TYPE_VAR,
TCF_META_TYPE_INT,
__TCF_META_TYPE_MAX
};
#define TCF_META_TYPE_MAX (__TCF_META_TYPE_MAX - 1)
enum
{
TCF_META_ID_VALUE,
TCF_META_ID_RANDOM,
TCF_META_ID_LOADAVG_0,
TCF_META_ID_LOADAVG_1,
TCF_META_ID_LOADAVG_2,
TCF_META_ID_DEV,
TCF_META_ID_PRIORITY,
TCF_META_ID_PROTOCOL,
TCF_META_ID_PKTTYPE,
TCF_META_ID_PKTLEN,
TCF_META_ID_DATALEN,
TCF_META_ID_MACLEN,
TCF_META_ID_NFMARK,
TCF_META_ID_TCINDEX,
TCF_META_ID_RTCLASSID,
TCF_META_ID_RTIIF,
TCF_META_ID_SK_FAMILY,
TCF_META_ID_SK_STATE,
TCF_META_ID_SK_REUSE,
TCF_META_ID_SK_BOUND_IF,
TCF_META_ID_SK_REFCNT,
TCF_META_ID_SK_SHUTDOWN,
TCF_META_ID_SK_PROTO,
TCF_META_ID_SK_TYPE,
TCF_META_ID_SK_RCVBUF,
TCF_META_ID_SK_RMEM_ALLOC,
TCF_META_ID_SK_WMEM_ALLOC,
TCF_META_ID_SK_OMEM_ALLOC,
TCF_META_ID_SK_WMEM_QUEUED,
TCF_META_ID_SK_RCV_QLEN,
TCF_META_ID_SK_SND_QLEN,
TCF_META_ID_SK_ERR_QLEN,
TCF_META_ID_SK_FORWARD_ALLOCS,
TCF_META_ID_SK_SNDBUF,
TCF_META_ID_SK_ALLOCS,
TCF_META_ID_SK_ROUTE_CAPS,
[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>
2005-10-03 15:13:38 -06:00
TCF_META_ID_SK_HASH,
TCF_META_ID_SK_LINGERTIME,
TCF_META_ID_SK_ACK_BACKLOG,
TCF_META_ID_SK_MAX_ACK_BACKLOG,
TCF_META_ID_SK_PRIO,
TCF_META_ID_SK_RCVLOWAT,
TCF_META_ID_SK_RCVTIMEO,
TCF_META_ID_SK_SNDTIMEO,
TCF_META_ID_SK_SENDMSG_OFF,
TCF_META_ID_SK_WRITE_PENDING,
__TCF_META_ID_MAX
};
#define TCF_META_ID_MAX (__TCF_META_ID_MAX - 1)
struct tcf_meta_hdr
{
struct tcf_meta_val left;
struct tcf_meta_val right;
};
#endif