From 90c1aff702d449a1a248c4829d51c0bc677f968e Mon Sep 17 00:00:00 2001 From: David Windsor Date: Mon, 23 Jan 2017 22:24:29 -0500 Subject: [PATCH] ipvs: free ip_vs_dest structs when refcnt=0 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 Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- 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 +