netfilter: ipset: references are protected by rwlock instead of mutex

The timeout variant of the list:set type must reference the member sets.
However, its garbage collector runs at timer interrupt so the mutex
protection of the references is a no go. Therefore the reference protection
is converted to rwlock.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>

7 files changed, 73 insertions, 56 deletions

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index ec333d83f3b4..5a262e3ae715 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -293,7 +293,7 @@ struct ip_set {
         /* Lock protecting the set data */
         rwlock_t lock;
         /* References to the set */
-        atomic_t ref;
+        u32 ref;
         /* The core set type */
         struct ip_set_type *type;
         /* The type variant doing the real job */
diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
index ec9d9bea1e37..a0196ac79051 100644
--- a/include/linux/netfilter/ipset/ip_set_ahash.h
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -515,8 +515,7 @@ type_pf_head(struct ip_set *set, struct sk_buff *skb)
         if (h->netmask != HOST_MASK)
                 NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask);
 #endif
-        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-                      htonl(atomic_read(&set->ref) - 1));
+        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
         NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize));
         if (with_timeout(h->timeout))
                 NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout));
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index bca96990218d..a113ff066928 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -338,8 +338,7 @@ bitmap_ip_head(struct ip_set *set, struct sk_buff *skb)
         NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip));
         if (map->netmask != 32)
                 NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask);
-        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-                      htonl(atomic_read(&set->ref) - 1));
+        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
         NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
                       htonl(sizeof(*map) + map->memsize));
         if (with_timeout(map->timeout))
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 5e790172deff..00a33242e90c 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -434,8 +434,7 @@ bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb)
                 goto nla_put_failure;
         NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip));
         NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip));
-        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-                      htonl(atomic_read(&set->ref) - 1));
+        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
         NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
                       htonl(sizeof(*map)
                             + (map->last_ip - map->first_ip + 1) * map->dsize));
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 165f09b1a9cb..6b38eb8f6ed8 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -320,8 +320,7 @@ bitmap_port_head(struct ip_set *set, struct sk_buff *skb)
                 goto nla_put_failure;
         NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port));
         NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port));
-        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-                      htonl(atomic_read(&set->ref) - 1));
+        NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
         NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
                       htonl(sizeof(*map) + map->memsize));
         if (with_timeout(map->timeout))
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index d6b48230a540..e88ac3c3ed07 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -26,6 +26,7 @@
 
 static LIST_HEAD(ip_set_type_list);             /* all registered set types */
 static DEFINE_MUTEX(ip_set_type_mutex);         /* protects ip_set_type_list */
+static DEFINE_RWLOCK(ip_set_ref_lock);          /* protects the set refs */
 
 static struct ip_set **ip_set_list;             /* all individual sets */
 static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */
@@ -301,13 +302,18 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
 static inline void
 __ip_set_get(ip_set_id_t index)
 {
-        atomic_inc(&ip_set_list[index]->ref);
+        write_lock_bh(&ip_set_ref_lock);
+        ip_set_list[index]->ref++;
+        write_unlock_bh(&ip_set_ref_lock);
 }
 
 static inline void
 __ip_set_put(ip_set_id_t index)
 {
-        atomic_dec(&ip_set_list[index]->ref);
+        write_lock_bh(&ip_set_ref_lock);
+        BUG_ON(ip_set_list[index]->ref == 0);
+        ip_set_list[index]->ref--;
+        write_unlock_bh(&ip_set_ref_lock);
 }
 
 /*
@@ -324,7 +330,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
         struct ip_set *set = ip_set_list[index];
         int ret = 0;
 
-        BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+        BUG_ON(set == NULL);
         pr_debug("set %s, index %u\n", set->name, index);
 
         if (dim < set->type->dimension ||
@@ -356,7 +362,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
         struct ip_set *set = ip_set_list[index];
         int ret;
 
-        BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+        BUG_ON(set == NULL);
         pr_debug("set %s, index %u\n", set->name, index);
 
         if (dim < set->type->dimension ||
@@ -378,7 +384,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
         struct ip_set *set = ip_set_list[index];
         int ret = 0;
 
-        BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+        BUG_ON(set == NULL);
         pr_debug("set %s, index %u\n", set->name, index);
 
         if (dim < set->type->dimension ||
@@ -397,7 +403,6 @@ EXPORT_SYMBOL_GPL(ip_set_del);
  * Find set by name, reference it once. The reference makes sure the
  * thing pointed to, does not go away under our feet.
  *
- * The nfnl mutex must already be activated.
  */
 ip_set_id_t
 ip_set_get_byname(const char *name, struct ip_set **set)
@@ -423,15 +428,12 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname);
  * reference count by 1. The caller shall not assume the index
  * to be valid, after calling this function.
  *
- * The nfnl mutex must already be activated.
  */
 void
 ip_set_put_byindex(ip_set_id_t index)
 {
-        if (ip_set_list[index] != NULL) {
-                BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0);
+        if (ip_set_list[index] != NULL)
                 __ip_set_put(index);
-        }