[PATCH net] net: free ip_vs_dest structs when refcnt=0

[David Windsor]

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 Juilan 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 <dwind...@gmail.com>
---
 include/net/ip_vs.h            | 2 +-
 net/netfilter/ipvs/ip_vs_ctl.c | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cd6018a..a3e78ad 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 55e0169..6b5492e 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;
                }
        }
@@ -1084,7 +1083,6 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, 
struct ip_vs_dest *dest,
        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 +
-- 
2.7.4