netfilter: nf_conntrack: nf_conntrack_alloc() fixes

When a slab cache uses SLAB_DESTROY_BY_RCU, we must be careful when allocating
objects, since slab allocator could give a freed object still used by lockless
readers.

In particular, nf_conntrack RCU lookups rely on ct->tuplehash[xxx].hnnode.next
being always valid (ie containing a valid 'nulls' value, or a valid pointer to next
object in hash chain.)

kmem_cache_zalloc() setups object with NULL values, but a NULL value is not valid
for ct->tuplehash[xxx].hnnode.next.

Fix is to call kmem_cache_alloc() and do the zeroing ourself.

As spotted by Patrick, we also need to make sure lookup keys are committed to
memory before setting refcount to 1, or a lockless reader could get a reference
on the old version of the object. Its key re-check could then pass the barrier.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt
index 93cb28d05dcd92da30dde47ec58205e2b0851022..18f9651ff23d411e96737ec070d4fc6bc29c50fe 100644 (file)
--- a/Documentation/RCU/rculist_nulls.txt
+++ b/Documentation/RCU/rculist_nulls.txt
@@ -83,11 +83,12 @@ not detect it missed following items in original chain.
 obj = kmem_cache_alloc(...);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
-atomic_inc(&obj->refcnt);
 /*
  * we need to make sure obj->key is updated before obj->next
+ * or obj->refcnt
  */
 smp_wmb();
+atomic_set(&obj->refcnt, 1);
 hlist_add_head_rcu(&obj->obj_node, list);
 unlock_chain(); // typically a spin_unlock()
 
@@ -159,6 +160,10 @@ out:
 obj = kmem_cache_alloc(cachep);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
+/*
+ * changes to obj->key must be visible before refcnt one
+ */
+smp_wmb();
 atomic_set(&obj->refcnt, 1);
 /*
  * insert obj in RCU way (readers might be traversing chain)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7508f11c5b3952a05ed9b41682f50d7827b3c4e6..b5869b9574b08a52c4c16f04cdb3f17336f9d762 100644 (file)
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -561,23 +561,38 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
                }
        }
 
-       ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp);
+       /*
+        * Do not use kmem_cache_zalloc(), as this cache uses
+        * SLAB_DESTROY_BY_RCU.
+        */
+       ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
        if (ct == NULL) {
                pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
                atomic_dec(&net->ct.count);
                return ERR_PTR(-ENOMEM);
        }
-
+       /*
+        * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
+        * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
+        */
+       memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
+              sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
        spin_lock_init(&ct->lock);
-       atomic_set(&ct->ct_general.use, 1);
        ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
+       ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
        ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
+       ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL;
        /* Don't set timer yet: wait for confirmation */
        setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
 #ifdef CONFIG_NET_NS
        ct->ct_net = net;
 #endif
 
+       /*
+        * changes to lookup keys must be done before setting refcnt to 1
+        */
+       smp_wmb();
+       atomic_set(&ct->ct_general.use, 1);
        return ct;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_alloc);