ipvs: make the service replacement more robust

commit 578bc3ef1e473a ("ipvs: reorganize dest trash") added
IP_VS_DEST_STATE_REMOVING flag and RCU callback named
ip_vs_dest_wait_readers() to keep dests and services after
removal for at least a RCU grace period. But we have the
following corner cases:

- we can not reuse the same dest if its service is removed
while IP_VS_DEST_STATE_REMOVING is still set because another dest
removal in the first grace period can not extend this period.
It can happen when ipvsadm -C && ipvsadm -R is used.

- dest->svc can be replaced but ip_vs_in_stats() and
ip_vs_out_stats() have no explicit read memory barriers
when accessing dest->svc. It can happen that dest->svc
was just freed (replaced) while we use it to update
the stats.

We solve the problems as follows:

- IP_VS_DEST_STATE_REMOVING is removed and we ensure a fixed
idle period for the dest (IP_VS_DEST_TRASH_PERIOD). idle_start
will remember when for first time after deletion we noticed
dest->refcnt=0. Later, the connections can grab a reference
while in RCU grace period but if refcnt becomes 0 we can
safely free the dest and its svc.

- dest->svc becomes RCU pointer. As result, we add explicit
RCU locking in ip_vs_in_stats() and ip_vs_out_stats().

- __ip_vs_unbind_svc is renamed to __ip_vs_svc_put(), it
now can free the service immediately or after a RCU grace
period. dest->svc is not set to NULL anymore.

	As result, unlinked dests and their services are
freed always after IP_VS_DEST_TRASH_PERIOD period, unused
services are freed after a RCU grace period.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

1 files changed, 2 insertions, 5 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index fe782ed..9c4d37e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -723,8 +723,6 @@ struct ip_vs_dest_dst {
 	struct rcu_head		rcu_head;
 };
 
-/* In grace period after removing */
-#define IP_VS_DEST_STATE_REMOVING	0x01
 /*
  *	The real server destination forwarding entry
  *	with ip address, port number, and so on.
@@ -742,7 +740,7 @@ struct ip_vs_dest {
 
 	atomic_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */
-	unsigned long		state;		/* state flags */
+	unsigned long		idle_start;	/* start time, jiffies */
 
 	/* connection counters and thresholds */
 	atomic_t		activeconns;	/* active connections */
@@ -756,14 +754,13 @@ struct ip_vs_dest {
 	struct ip_vs_dest_dst __rcu *dest_dst;	/* cached dst info */
 
 	/* for virtual service */
-	struct ip_vs_service	*svc;		/* service it belongs to */
+	struct ip_vs_service __rcu *svc;	/* service it belongs to */
 	__u16			protocol;	/* which protocol (TCP/UDP) */
 	__be16			vport;		/* virtual port number */
 	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__u32			vfwmark;	/* firewall mark of service */
 
 	struct list_head	t_list;		/* in dest_trash */
-	struct rcu_head		rcu_head;
 	unsigned int		in_rs_table:1;	/* we are in rs_table */
 };