leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
3072b90c47
linux/include/net/ip_fib.h
Eric Dumazet ebc0ffae5d fib: RCU conversion of fib_lookup() 
fib_lookup() converted to be called in RCU protected context, no
reference taken and released on a contended cache line (fib_clntref)

fib_table_lookup() and fib_semantic_match() get an additional parameter.

struct fib_info gets an rcu_head field, and is freed after an rcu grace
period.

Stress test :
(Sending 160.000.000 UDP frames on same neighbour,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_HASH) (about same results for FIB_TRIE)

Before patch :

real	1m31.199s
user	0m13.761s
sys	23m24.780s

After patch:

real	1m5.375s
user	0m14.997s
sys	15m50.115s

Before patch Profile :

13044.00 15.4% __ip_route_output_key vmlinux
 8438.00 10.0% dst_destroy           vmlinux
 5983.00  7.1% fib_semantic_match    vmlinux
 5410.00  6.4% fib_rules_lookup      vmlinux
 4803.00  5.7% neigh_lookup          vmlinux
 4420.00  5.2% _raw_spin_lock        vmlinux
 3883.00  4.6% rt_set_nexthop        vmlinux
 3261.00  3.9% _raw_read_lock        vmlinux
 2794.00  3.3% fib_table_lookup      vmlinux
 2374.00  2.8% neigh_resolve_output  vmlinux
 2153.00  2.5% dst_alloc             vmlinux
 1502.00  1.8% _raw_read_lock_bh     vmlinux
 1484.00  1.8% kmem_cache_alloc      vmlinux
 1407.00  1.7% eth_header            vmlinux
 1406.00  1.7% ipv4_dst_destroy      vmlinux
 1298.00  1.5% __copy_from_user_ll   vmlinux
 1174.00  1.4% dev_queue_xmit        vmlinux
 1000.00  1.2% ip_output             vmlinux

After patch Profile :

13712.00 15.8% dst_destroy             vmlinux
 8548.00  9.9% __ip_route_output_key   vmlinux
 7017.00  8.1% neigh_lookup            vmlinux
 4554.00  5.3% fib_semantic_match      vmlinux
 4067.00  4.7% _raw_read_lock          vmlinux
 3491.00  4.0% dst_alloc               vmlinux
 3186.00  3.7% neigh_resolve_output    vmlinux
 3103.00  3.6% fib_table_lookup        vmlinux
 2098.00  2.4% _raw_read_lock_bh       vmlinux
 2081.00  2.4% kmem_cache_alloc        vmlinux
 2013.00  2.3% _raw_spin_lock          vmlinux
 1763.00  2.0% __copy_from_user_ll     vmlinux
 1763.00  2.0% ip_output               vmlinux
 1761.00  2.0% ipv4_dst_destroy        vmlinux
 1631.00  1.9% eth_header              vmlinux
 1440.00  1.7% _raw_read_unlock_bh     vmlinux

Reference results, if IP route cache is enabled :

real	0m29.718s
user	0m10.845s
sys	7m37.341s

25213.00 29.5% __ip_route_output_key   vmlinux
 9011.00 10.5% dst_release             vmlinux
 4817.00  5.6% ip_push_pending_frames  vmlinux
 4232.00  5.0% ip_finish_output        vmlinux
 3940.00  4.6% udp_sendmsg             vmlinux
 3730.00  4.4% __copy_from_user_ll     vmlinux
 3716.00  4.4% ip_route_output_flow    vmlinux
 2451.00  2.9% __xfrm_lookup           vmlinux
 2221.00  2.6% ip_append_data          vmlinux
 1718.00  2.0% _raw_spin_lock_bh       vmlinux
 1655.00  1.9% __alloc_skb             vmlinux
 1572.00  1.8% sock_wfree              vmlinux
 1345.00  1.6% kfree                   vmlinux

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 20:39:38 -07:00

272 lines
6.8 KiB
C
Raw Blame History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the Forwarding Information Base.
*
* Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _NET_IP_FIB_H
#define _NET_IP_FIB_H
#include <net/flow.h>
#include <linux/seq_file.h>
#include <net/fib_rules.h>
struct fib_config {
u8 fc_dst_len;
u8 fc_tos;
u8 fc_protocol;
u8 fc_scope;
u8 fc_type;
/* 3 bytes unused */
u32 fc_table;
__be32 fc_dst;
__be32 fc_gw;
int fc_oif;
u32 fc_flags;
u32 fc_priority;
__be32 fc_prefsrc;
struct nlattr *fc_mx;
struct rtnexthop *fc_mp;
int fc_mx_len;
int fc_mp_len;
u32 fc_flow;
u32 fc_nlflags;
struct nl_info fc_nlinfo;
};
struct fib_info;
struct fib_nh {
struct net_device *nh_dev;
struct hlist_node nh_hash;
struct fib_info *nh_parent;
unsigned nh_flags;
unsigned char nh_scope;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int nh_weight;
int nh_power;
#endif
#ifdef CONFIG_NET_CLS_ROUTE
__u32 nh_tclassid;
#endif
int nh_oif;
__be32 nh_gw;
};
/*
* This structure contains data shared by many of routes.
*/
struct fib_info {
struct hlist_node fib_hash;
struct hlist_node fib_lhash;
struct net *fib_net;
int fib_treeref;
atomic_t fib_clntref;
int fib_dead;
unsigned fib_flags;
int fib_protocol;
__be32 fib_prefsrc;
u32 fib_priority;
u32 fib_metrics[RTAX_MAX];
#define fib_mtu fib_metrics[RTAX_MTU-1]
#define fib_window fib_metrics[RTAX_WINDOW-1]
#define fib_rtt fib_metrics[RTAX_RTT-1]
#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
int fib_nhs;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int fib_power;
#endif
struct rcu_head rcu;
struct fib_nh fib_nh[0];
#define fib_dev fib_nh[0].nh_dev
};
#ifdef CONFIG_IP_MULTIPLE_TABLES
struct fib_rule;
#endif
struct fib_result {
unsigned char prefixlen;
unsigned char nh_sel;
unsigned char type;
unsigned char scope;
struct fib_info *fi;
#ifdef CONFIG_IP_MULTIPLE_TABLES
struct fib_rule *r;
#endif
};
struct fib_result_nl {
__be32 fl_addr; /* To be looked up*/
u32 fl_mark;
unsigned char fl_tos;
unsigned char fl_scope;
unsigned char tb_id_in;
unsigned char tb_id; /* Results */
unsigned char prefixlen;
unsigned char nh_sel;
unsigned char type;
unsigned char scope;
int err;
};
#ifdef CONFIG_IP_ROUTE_MULTIPATH
#define FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel])
#define FIB_TABLE_HASHSZ 2
#else /* CONFIG_IP_ROUTE_MULTIPATH */
#define FIB_RES_NH(res) ((res).fi->fib_nh[0])
#define FIB_TABLE_HASHSZ 256
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
#define FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : __fib_res_prefsrc(&res))
#define FIB_RES_GW(res) (FIB_RES_NH(res).nh_gw)
#define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev)
#define FIB_RES_OIF(res) (FIB_RES_NH(res).nh_oif)
struct fib_table {
struct hlist_node tb_hlist;
u32 tb_id;
int tb_default;
unsigned char tb_data[0];
};
extern int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
struct fib_result *res, int fib_flags);
extern int fib_table_insert(struct fib_table *, struct fib_config *);
extern int fib_table_delete(struct fib_table *, struct fib_config *);
extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
struct netlink_callback *cb);
extern int fib_table_flush(struct fib_table *table);
extern void fib_table_select_default(struct fib_table *table,
const struct flowi *flp,
struct fib_result *res);
#ifndef CONFIG_IP_MULTIPLE_TABLES
#define TABLE_LOCAL_INDEX 0
#define TABLE_MAIN_INDEX 1
static inline struct fib_table *fib_get_table(struct net *net, u32 id)
{
struct hlist_head *ptr;
ptr = id == RT_TABLE_LOCAL ?
&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] :
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX];
return hlist_entry(ptr->first, struct fib_table, tb_hlist);
}
static inline struct fib_table *fib_new_table(struct net *net, u32 id)
{
return fib_get_table(net, id);
}
static inline int fib_lookup(struct net *net, const struct flowi *flp,
struct fib_result *res)
{
struct fib_table *table;
table = fib_get_table(net, RT_TABLE_LOCAL);
if (!fib_table_lookup(table, flp, res, FIB_LOOKUP_NOREF))
return 0;
table = fib_get_table(net, RT_TABLE_MAIN);
if (!fib_table_lookup(table, flp, res, FIB_LOOKUP_NOREF))
return 0;
return -ENETUNREACH;
}
#else /* CONFIG_IP_MULTIPLE_TABLES */
extern int __net_init fib4_rules_init(struct net *net);
extern void __net_exit fib4_rules_exit(struct net *net);
#ifdef CONFIG_NET_CLS_ROUTE
extern u32 fib_rules_tclass(struct fib_result *res);
#endif
extern int fib_lookup(struct net *n, struct flowi *flp, struct fib_result *res);
extern struct fib_table *fib_new_table(struct net *net, u32 id);
extern struct fib_table *fib_get_table(struct net *net, u32 id);
#endif /* CONFIG_IP_MULTIPLE_TABLES */
/* Exported by fib_frontend.c */
extern const struct nla_policy rtm_ipv4_policy[];
extern void ip_fib_init(void);
extern int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
struct net_device *dev, __be32 *spec_dst,
u32 *itag, u32 mark);
extern void fib_select_default(struct net *net, const struct flowi *flp,
struct fib_result *res);
/* Exported by fib_semantics.c */
extern int ip_fib_check_default(__be32 gw, struct net_device *dev);
extern int fib_sync_down_dev(struct net_device *dev, int force);
extern int fib_sync_down_addr(struct net *net, __be32 local);
extern int fib_sync_up(struct net_device *dev);
extern __be32 __fib_res_prefsrc(struct fib_result *res);
extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res);
/* Exported by fib_{hash|trie}.c */
extern void fib_hash_init(void);
extern struct fib_table *fib_hash_table(u32 id);
static inline void fib_combine_itag(u32 *itag, struct fib_result *res)
{
#ifdef CONFIG_NET_CLS_ROUTE
#ifdef CONFIG_IP_MULTIPLE_TABLES
u32 rtag;
#endif
*itag = FIB_RES_NH(*res).nh_tclassid<<16;
#ifdef CONFIG_IP_MULTIPLE_TABLES
rtag = fib_rules_tclass(res);
if (*itag == 0)
*itag = (rtag<<16);
*itag |= (rtag>>16);
#endif
#endif
}
extern void free_fib_info(struct fib_info *fi);
static inline void fib_info_put(struct fib_info *fi)
{
if (atomic_dec_and_test(&fi->fib_clntref))
free_fib_info(fi);
}
#ifdef CONFIG_PROC_FS
extern int __net_init fib_proc_init(struct net *net);
extern void __net_exit fib_proc_exit(struct net *net);
#else
static inline int fib_proc_init(struct net *net)
{
return 0;
}
static inline void fib_proc_exit(struct net *net)
{
}
#endif
#endif /* _NET_FIB_H */
Reference in New Issue View Git Blame Copy Permalink