d297653dd6
fdb dumps spanning multiple skb's currently restart from the first
interface again for every skb. This results in unnecessary
iterations on the already visited interfaces and their fdb
entries. In large scale setups, we have seen this to slow
down fdb dumps considerably. On a system with 30k macs we
see fdb dumps spanning across more than 300 skbs.
To fix the problem, this patch replaces the existing single fdb
marker with three markers: netdev hash entries, netdevs and fdb
index to continue where we left off instead of restarting from the
first netdev. This is consistent with link dumps.
In the process of fixing the performance issue, this patch also
re-implements fix done by
commit 472681d57a ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump")
(with an internal fix from Wilson Kok) in the following ways:
- change ndo_fdb_dump handlers to return error code instead
of the last fdb index
- use cb->args strictly for dump frag markers and not error codes.
This is consistent with other dump functions.
Below results were taken on a system with 1000 netdevs
and 35085 fdb entries:
before patch:
$time bridge fdb show | wc -l
15065
real 1m11.791s
user 0m0.070s
sys 1m8.395s
(existing code does not return all macs)
after patch:
$time bridge fdb show | wc -l
35085
real 0m2.017s
user 0m0.113s
sys 0m1.942s
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
129 lines
4 KiB
C
129 lines
4 KiB
C
#ifndef __LINUX_RTNETLINK_H
|
|
#define __LINUX_RTNETLINK_H
|
|
|
|
|
|
#include <linux/mutex.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/wait.h>
|
|
#include <uapi/linux/rtnetlink.h>
|
|
|
|
extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
|
|
extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid);
|
|
extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid,
|
|
u32 group, struct nlmsghdr *nlh, gfp_t flags);
|
|
extern void rtnl_set_sk_err(struct net *net, u32 group, int error);
|
|
extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics);
|
|
extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
|
|
u32 id, long expires, u32 error);
|
|
|
|
void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
|
|
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
|
|
unsigned change, gfp_t flags);
|
|
void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev,
|
|
gfp_t flags);
|
|
|
|
|
|
/* RTNL is used as a global lock for all changes to network configuration */
|
|
extern void rtnl_lock(void);
|
|
extern void rtnl_unlock(void);
|
|
extern int rtnl_trylock(void);
|
|
extern int rtnl_is_locked(void);
|
|
|
|
extern wait_queue_head_t netdev_unregistering_wq;
|
|
extern struct mutex net_mutex;
|
|
|
|
#ifdef CONFIG_PROVE_LOCKING
|
|
extern bool lockdep_rtnl_is_held(void);
|
|
#else
|
|
static inline bool lockdep_rtnl_is_held(void)
|
|
{
|
|
return true;
|
|
}
|
|
#endif /* #ifdef CONFIG_PROVE_LOCKING */
|
|
|
|
/**
|
|
* rcu_dereference_rtnl - rcu_dereference with debug checking
|
|
* @p: The pointer to read, prior to dereferencing
|
|
*
|
|
* Do an rcu_dereference(p), but check caller either holds rcu_read_lock()
|
|
* or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference()
|
|
*/
|
|
#define rcu_dereference_rtnl(p) \
|
|
rcu_dereference_check(p, lockdep_rtnl_is_held())
|
|
|
|
/**
|
|
* rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking
|
|
* @p: The pointer to read, prior to dereference
|
|
*
|
|
* Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh()
|
|
* or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh()
|
|
*/
|
|
#define rcu_dereference_bh_rtnl(p) \
|
|
rcu_dereference_bh_check(p, lockdep_rtnl_is_held())
|
|
|
|
/**
|
|
* rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL
|
|
* @p: The pointer to read, prior to dereferencing
|
|
*
|
|
* Return the value of the specified RCU-protected pointer, but omit
|
|
* both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
|
|
* caller holds RTNL.
|
|
*/
|
|
#define rtnl_dereference(p) \
|
|
rcu_dereference_protected(p, lockdep_rtnl_is_held())
|
|
|
|
static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
|
|
{
|
|
return rtnl_dereference(dev->ingress_queue);
|
|
}
|
|
|
|
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev);
|
|
|
|
#ifdef CONFIG_NET_INGRESS
|
|
void net_inc_ingress_queue(void);
|
|
void net_dec_ingress_queue(void);
|
|
#endif
|
|
|
|
#ifdef CONFIG_NET_EGRESS
|
|
void net_inc_egress_queue(void);
|
|
void net_dec_egress_queue(void);
|
|
#endif
|
|
|
|
void rtnetlink_init(void);
|
|
void __rtnl_unlock(void);
|
|
void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail);
|
|
|
|
#define ASSERT_RTNL() do { \
|
|
if (unlikely(!rtnl_is_locked())) { \
|
|
printk(KERN_ERR "RTNL: assertion failed at %s (%d)\n", \
|
|
__FILE__, __LINE__); \
|
|
dump_stack(); \
|
|
} \
|
|
} while(0)
|
|
|
|
extern int ndo_dflt_fdb_dump(struct sk_buff *skb,
|
|
struct netlink_callback *cb,
|
|
struct net_device *dev,
|
|
struct net_device *filter_dev,
|
|
int *idx);
|
|
extern int ndo_dflt_fdb_add(struct ndmsg *ndm,
|
|
struct nlattr *tb[],
|
|
struct net_device *dev,
|
|
const unsigned char *addr,
|
|
u16 vid,
|
|
u16 flags);
|
|
extern int ndo_dflt_fdb_del(struct ndmsg *ndm,
|
|
struct nlattr *tb[],
|
|
struct net_device *dev,
|
|
const unsigned char *addr,
|
|
u16 vid);
|
|
|
|
extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
|
|
struct net_device *dev, u16 mode,
|
|
u32 flags, u32 mask, int nlflags,
|
|
u32 filter_mask,
|
|
int (*vlan_fill)(struct sk_buff *skb,
|
|
struct net_device *dev,
|
|
u32 filter_mask));
|
|
#endif /* __LINUX_RTNETLINK_H */
|