mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 03:50:54 +07:00
32b293a53d
During some debugging I needed to look into how /proc/net/ipv6_route operated and in my digging I found its calling fib6_clean_all() which uses "write_lock_bh(&table->tb6_lock)" before doing the walk of the table. I found this on 2.6.32, but reading the code I believe the same basic idea exists currently. Looking at the rtnetlink code they are only calling "read_lock_bh(&table->tb6_lock);" via fib6_dump_table(). While I realize reading from proc isn't the recommended way of fetching the ipv6 route table; taking a write lock seems unnecessary and would probably cause network performance issues. To verify this I loaded up the ipv6 route table and then ran iperf in 3 cases: * doing nothing * reading ipv6 route table via proc (while :; do cat /proc/net/ipv6_route > /dev/null; done) * reading ipv6 route table via rtnetlink (while :; do ip -6 route show table all > /dev/null; done) * Load the ipv6 route table up with: * for ((i = 0;i < 4000;i++)); do ip route add unreachable 2000::$i; done * iperf commands: * client: iperf -i 1 -V -c <ipv6 addr> * server: iperf -V -s * iperf results - 3 runs each (in Mbits/sec) * nothing: client: 927,927,927 server: 927,927,927 * proc: client: 179,97,96,113 server: 142,112,133 * iproute: client: 928,927,928 server: 927,927,927 lock_stat shows taking the write lock is causing the slowdown. Using this info I decided to write a version of fib6_clean_all() which replaces write_lock_bh(&table->tb6_lock) with read_lock_bh(&table->tb6_lock). With this new function I see the same results as with my rtnetlink iperf test. Signed-off-by: Josh Hunt <joshhunt00@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
241 lines
5.3 KiB
C
241 lines
5.3 KiB
C
/*
|
|
* Linux INET6 implementation
|
|
*
|
|
* Authors:
|
|
* Pedro Roque <roque@di.fc.ul.pt>
|
|
*
|
|
* 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 _IP6_FIB_H
|
|
#define _IP6_FIB_H
|
|
|
|
#include <linux/ipv6_route.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/spinlock.h>
|
|
#include <net/dst.h>
|
|
#include <net/flow.h>
|
|
#include <net/netlink.h>
|
|
#include <net/inetpeer.h>
|
|
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
#define FIB6_TABLE_HASHSZ 256
|
|
#else
|
|
#define FIB6_TABLE_HASHSZ 1
|
|
#endif
|
|
|
|
struct rt6_info;
|
|
|
|
struct fib6_config {
|
|
u32 fc_table;
|
|
u32 fc_metric;
|
|
int fc_dst_len;
|
|
int fc_src_len;
|
|
int fc_ifindex;
|
|
u32 fc_flags;
|
|
u32 fc_protocol;
|
|
|
|
struct in6_addr fc_dst;
|
|
struct in6_addr fc_src;
|
|
struct in6_addr fc_prefsrc;
|
|
struct in6_addr fc_gateway;
|
|
|
|
unsigned long fc_expires;
|
|
struct nlattr *fc_mx;
|
|
int fc_mx_len;
|
|
|
|
struct nl_info fc_nlinfo;
|
|
};
|
|
|
|
struct fib6_node {
|
|
struct fib6_node *parent;
|
|
struct fib6_node *left;
|
|
struct fib6_node *right;
|
|
#ifdef CONFIG_IPV6_SUBTREES
|
|
struct fib6_node *subtree;
|
|
#endif
|
|
struct rt6_info *leaf;
|
|
|
|
__u16 fn_bit; /* bit key */
|
|
__u16 fn_flags;
|
|
__u32 fn_sernum;
|
|
struct rt6_info *rr_ptr;
|
|
};
|
|
|
|
#ifndef CONFIG_IPV6_SUBTREES
|
|
#define FIB6_SUBTREE(fn) NULL
|
|
#else
|
|
#define FIB6_SUBTREE(fn) ((fn)->subtree)
|
|
#endif
|
|
|
|
/*
|
|
* routing information
|
|
*
|
|
*/
|
|
|
|
struct rt6key {
|
|
struct in6_addr addr;
|
|
int plen;
|
|
};
|
|
|
|
struct fib6_table;
|
|
|
|
struct rt6_info {
|
|
struct dst_entry dst;
|
|
|
|
/*
|
|
* Tail elements of dst_entry (__refcnt etc.)
|
|
* and these elements (rarely used in hot path) are in
|
|
* the same cache line.
|
|
*/
|
|
struct fib6_table *rt6i_table;
|
|
struct fib6_node *rt6i_node;
|
|
|
|
struct in6_addr rt6i_gateway;
|
|
|
|
atomic_t rt6i_ref;
|
|
|
|
/* These are in a separate cache line. */
|
|
struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
|
|
u32 rt6i_flags;
|
|
struct rt6key rt6i_src;
|
|
struct rt6key rt6i_prefsrc;
|
|
u32 rt6i_metric;
|
|
u32 rt6i_peer_genid;
|
|
|
|
struct inet6_dev *rt6i_idev;
|
|
struct inet_peer *rt6i_peer;
|
|
|
|
#ifdef CONFIG_XFRM
|
|
u32 rt6i_flow_cache_genid;
|
|
#endif
|
|
/* more non-fragment space at head required */
|
|
unsigned short rt6i_nfheader_len;
|
|
|
|
u8 rt6i_protocol;
|
|
};
|
|
|
|
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
|
|
{
|
|
return ((struct rt6_info *)dst)->rt6i_idev;
|
|
}
|
|
|
|
struct fib6_walker_t {
|
|
struct list_head lh;
|
|
struct fib6_node *root, *node;
|
|
struct rt6_info *leaf;
|
|
unsigned char state;
|
|
unsigned char prune;
|
|
unsigned int skip;
|
|
unsigned int count;
|
|
int (*func)(struct fib6_walker_t *);
|
|
void *args;
|
|
};
|
|
|
|
struct rt6_statistics {
|
|
__u32 fib_nodes;
|
|
__u32 fib_route_nodes;
|
|
__u32 fib_rt_alloc; /* permanent routes */
|
|
__u32 fib_rt_entries; /* rt entries in table */
|
|
__u32 fib_rt_cache; /* cache routes */
|
|
__u32 fib_discarded_routes;
|
|
};
|
|
|
|
#define RTN_TL_ROOT 0x0001
|
|
#define RTN_ROOT 0x0002 /* tree root node */
|
|
#define RTN_RTINFO 0x0004 /* node with valid routing info */
|
|
|
|
/*
|
|
* priority levels (or metrics)
|
|
*
|
|
*/
|
|
|
|
|
|
struct fib6_table {
|
|
struct hlist_node tb6_hlist;
|
|
u32 tb6_id;
|
|
rwlock_t tb6_lock;
|
|
struct fib6_node tb6_root;
|
|
};
|
|
|
|
#define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC
|
|
#define RT6_TABLE_MAIN RT_TABLE_MAIN
|
|
#define RT6_TABLE_DFLT RT6_TABLE_MAIN
|
|
#define RT6_TABLE_INFO RT6_TABLE_MAIN
|
|
#define RT6_TABLE_PREFIX RT6_TABLE_MAIN
|
|
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
#define FIB6_TABLE_MIN 1
|
|
#define FIB6_TABLE_MAX RT_TABLE_MAX
|
|
#define RT6_TABLE_LOCAL RT_TABLE_LOCAL
|
|
#else
|
|
#define FIB6_TABLE_MIN RT_TABLE_MAIN
|
|
#define FIB6_TABLE_MAX FIB6_TABLE_MIN
|
|
#define RT6_TABLE_LOCAL RT6_TABLE_MAIN
|
|
#endif
|
|
|
|
typedef struct rt6_info *(*pol_lookup_t)(struct net *,
|
|
struct fib6_table *,
|
|
struct flowi6 *, int);
|
|
|
|
/*
|
|
* exported functions
|
|
*/
|
|
|
|
extern struct fib6_table *fib6_get_table(struct net *net, u32 id);
|
|
extern struct fib6_table *fib6_new_table(struct net *net, u32 id);
|
|
extern struct dst_entry *fib6_rule_lookup(struct net *net,
|
|
struct flowi6 *fl6, int flags,
|
|
pol_lookup_t lookup);
|
|
|
|
extern struct fib6_node *fib6_lookup(struct fib6_node *root,
|
|
const struct in6_addr *daddr,
|
|
const struct in6_addr *saddr);
|
|
|
|
struct fib6_node *fib6_locate(struct fib6_node *root,
|
|
const struct in6_addr *daddr, int dst_len,
|
|
const struct in6_addr *saddr, int src_len);
|
|
|
|
extern void fib6_clean_all_ro(struct net *net,
|
|
int (*func)(struct rt6_info *, void *arg),
|
|
int prune, void *arg);
|
|
|
|
extern void fib6_clean_all(struct net *net,
|
|
int (*func)(struct rt6_info *, void *arg),
|
|
int prune, void *arg);
|
|
|
|
extern int fib6_add(struct fib6_node *root,
|
|
struct rt6_info *rt,
|
|
struct nl_info *info);
|
|
|
|
extern int fib6_del(struct rt6_info *rt,
|
|
struct nl_info *info);
|
|
|
|
extern void inet6_rt_notify(int event, struct rt6_info *rt,
|
|
struct nl_info *info);
|
|
|
|
extern void fib6_run_gc(unsigned long expires,
|
|
struct net *net);
|
|
|
|
extern void fib6_gc_cleanup(void);
|
|
|
|
extern int fib6_init(void);
|
|
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
extern int fib6_rules_init(void);
|
|
extern void fib6_rules_cleanup(void);
|
|
#else
|
|
static inline int fib6_rules_init(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void fib6_rules_cleanup(void)
|
|
{
|
|
return ;
|
|
}
|
|
#endif
|
|
#endif
|