Commit 9e4e948a authored by Julian Anastasov's avatar Julian Anastasov Committed by Simon Horman
Browse files

ipvs: avoid rcu_barrier during netns cleanup 



commit 578bc3ef ("ipvs: reorganize dest trash") added
rcu_barrier() on cleanup to wait dest users and schedulers
like LBLC and LBLCR to put their last dest reference.
Using rcu_barrier with many namespaces is problematic.

Trying to fix it by freeing dest with kfree_rcu is not
a solution, RCU callbacks can run in parallel and execution
order is random.

Fix it by creating new function ip_vs_dest_put_and_free()
which is heavier than ip_vs_dest_put(). We will use it just
for schedulers like LBLC, LBLCR that can delay their dest
release.

By default, dests reference is above 0 if they are present in
service and it is 0 when deleted but still in trash list.
Change the dest trash code to use ip_vs_dest_put_and_free(),
so that refcnt -1 can be used for freeing. As result,
such checks remain in slow path and the rcu_barrier() from
netns cleanup can be removed.

Signed-off-by: default avatarJulian Anastasov <ja@ssi.bg>
Signed-off-by: default avatarSimon Horman <horms@verge.net.au>
parent 120c9794

include/net/ip_vs.h

+6 −0
Original line number Diff line number Diff line
@@ -1442,6 +1442,12 @@ static inline void ip_vs_dest_put(struct ip_vs_dest *dest) 
	atomic_dec(&dest->refcnt);

}



static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)

{

	if (atomic_dec_return(&dest->refcnt) < 0)

		kfree(dest);

}



/*

 *      IPVS sync daemon data and function prototypes

 *      (from ip_vs_sync.c)

net/netfilter/ipvs/ip_vs_ctl.c

+1 −5
Original line number Diff line number Diff line
@@ -704,7 +704,7 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest) 
	__ip_vs_dst_cache_reset(dest);

	__ip_vs_svc_put(svc, false);

	free_percpu(dest->stats.cpustats);

	kfree(dest);

	ip_vs_dest_put_and_free(dest);

}



/*
@@ -3820,10 +3820,6 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net) 
{

	struct netns_ipvs *ipvs = net_ipvs(net);



	/* Some dest can be in grace period even before cleanup, we have to

	 * defer ip_vs_trash_cleanup until ip_vs_dest_wait_readers is called.

	 */

	rcu_barrier();

	ip_vs_trash_cleanup(net);

	ip_vs_stop_estimator(net, &ipvs->tot_stats);

	ip_vs_control_net_cleanup_sysctl(net);

net/netfilter/ipvs/ip_vs_lblc.c

+1 −1
Original line number Diff line number Diff line
@@ -136,7 +136,7 @@ static void ip_vs_lblc_rcu_free(struct rcu_head *head) 
						   struct ip_vs_lblc_entry,

						   rcu_head);



	ip_vs_dest_put(en->dest);

	ip_vs_dest_put_and_free(en->dest);

	kfree(en);

}

net/netfilter/ipvs/ip_vs_lblcr.c

+1 −1
Original line number Diff line number Diff line
@@ -130,7 +130,7 @@ static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) 
	struct ip_vs_dest_set_elem *e;



	e = container_of(head, struct ip_vs_dest_set_elem, rcu_head);

	ip_vs_dest_put(e->dest);

	ip_vs_dest_put_and_free(e->dest);

	kfree(e);

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE