[IPVS]: Close race conditions on ip_vs_conn_tab list modification

In an smp system, it is possible for an connection timer to expire, calling
ip_vs_conn_expire while the connection table is being flushed, before
ct_write_lock_bh is acquired.

Since the list iterator loop in ip_vs_con_flush releases and re-acquires the
spinlock (even though it doesn't re-enable softirqs), it is possible for the
expiration function to modify the connection list, while it is being traversed
in ip_vs_conn_flush.

The result is that the next pointer gets set to NULL, and subsequently
dereferenced, resulting in an oops.

Signed-off-by: Neil Horman <nhorman@redhat.com>
Acked-by: JulianAnastasov
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 4 insertions, 21 deletions

diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c
index fd6feb5499fe..9f16ab309106 100644
--- a/net/ipv4/ipvs/ip_vs_conn.c
+++ b/net/ipv4/ipvs/ip_vs_conn.c
@@ -548,7 +548,6 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
 {
         if (del_timer(&cp->timer))
                 mod_timer(&cp->timer, jiffies);
-        __ip_vs_conn_put(cp);
 }
 
 
@@ -764,7 +763,6 @@ void ip_vs_random_dropentry(void)
 {
         int idx;
         struct ip_vs_conn *cp;
-        struct ip_vs_conn *ct;
 
         /*
          * Randomly scan 1/32 of the whole table every second
@@ -801,21 +799,12 @@ void ip_vs_random_dropentry(void)
                                         continue;
                         }
 
-                        /*
-                         * Drop the entry, and drop its ct if not referenced
-                         */
-                        atomic_inc(&cp->refcnt);
-                        ct_write_unlock(hash);
-
-                        if ((ct = cp->control))
-                                atomic_inc(&ct->refcnt);
                         IP_VS_DBG(4, "del connection\n");
                         ip_vs_conn_expire_now(cp);
-                        if (ct) {
+                        if (cp->control) {
                                 IP_VS_DBG(4, "del conn template\n");
-                                ip_vs_conn_expire_now(ct);
+                                ip_vs_conn_expire_now(cp->control);
                         }
-                        ct_write_lock(hash);
                 }
                 ct_write_unlock(hash);
         }
@@ -829,7 +818,6 @@ static void ip_vs_conn_flush(void)
 {
         int idx;
         struct ip_vs_conn *cp;
-        struct ip_vs_conn *ct;
 
   flush_again:
         for (idx=0; idx<IP_VS_CONN_TAB_SIZE; idx++) {
@@ -839,18 +827,13 @@ static void ip_vs_conn_flush(void)
                 ct_write_lock_bh(idx);
 
                 list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-                        atomic_inc(&cp->refcnt);
-                        ct_write_unlock(idx);
 
-                        if ((ct = cp->control))
-                                atomic_inc(&ct->refcnt);
                         IP_VS_DBG(4, "del connection\n");
                         ip_vs_conn_expire_now(cp);
-                        if (ct) {
+                        if (cp->control) {
                                 IP_VS_DBG(4, "del conn template\n");
-                                ip_vs_conn_expire_now(ct);
+                                ip_vs_conn_expire_now(cp->control);
                         }
-                        ct_write_lock(idx);
                 }
                 ct_write_unlock_bh(idx);
         }