From: David Windsor <dwindsor@xxxxxxxxx>
Currently, the ip_vs_dest cache frees ip_vs_dest objects when their
reference count becomes < 0. Aside from not being semantically sound,
this is problematic for the new type refcount_t, which will be introduced
shortly in a separate patch. refcount_t is the new kernel type for
holding reference counts, and provides overflow protection and a
constrained interface relative to atomic_t (the type currently being
used for kernel reference counts).
Per Julian Anastasov: "The problem is that dest_trash currently holds
deleted dests (unlinked from RCU lists) with refcnt=0." Changing
dest_trash to hold dest with refcnt=1 will allow us to free ip_vs_dest
structs when their refcnt=0, in ip_vs_dest_put_and_free().
Signed-off-by: David Windsor <dwindsor@xxxxxxxxx>
Signed-off-by: Julian Anastasov <ja@xxxxxx>
Signed-off-by: Simon Horman <horms@xxxxxxxxxxxx>
Signed-off-by: Pablo Neira Ayuso <pablo@xxxxxxxxxxxxx>
---
include/net/ip_vs.h | 2 +-
net/netfilter/ipvs/ip_vs_ctl.c | 8 +++-----
2 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4b46c591b542..7bdfa7d78363 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1421,7 +1421,7 @@ static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
{
- if (atomic_dec_return(&dest->refcnt) < 0)
+ if (atomic_dec_and_test(&dest->refcnt))
kfree(dest);
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 55e0169caa4c..5fc4836e7c79 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -711,7 +711,6 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
dest->vport == svc->port))) {
/* HIT */
list_del(&dest->t_list);
- ip_vs_dest_hold(dest);
goto out;
}
}
@@ -741,7 +740,7 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest)
* When the ip_vs_control_clearup is activated by ipvs module exit,
* the service tables must have been flushed and all the connections
* are expired, and the refcnt of each destination in the trash must
- * be 0, so we simply release them here.
+ * be 1, so we simply release them here.
*/
static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs)
{
@@ -1080,11 +1079,10 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
if (list_empty(&ipvs->dest_trash) && !cleanup)
mod_timer(&ipvs->dest_trash_timer,
jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
- /* dest lives in trash without reference */
+ /* dest lives in trash with reference */
list_add(&dest->t_list, &ipvs->dest_trash);
dest->idle_start = 0;
spin_unlock_bh(&ipvs->dest_trash_lock);
- ip_vs_dest_put(dest);
}
@@ -1160,7 +1158,7 @@ static void ip_vs_dest_trash_expire(unsigned long data)
spin_lock(&ipvs->dest_trash_lock);
list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
- if (atomic_read(&dest->refcnt) > 0)
+ if (atomic_read(&dest->refcnt) > 1)
continue;
if (dest->idle_start) {
if (time_before(now, dest->idle_start +
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
