netfilter: allow NFQUEUE bypass if no listener is available

[pandora-kernel.git] / net / netfilter / nf_queue.c

diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 74aebed..5ab22e2 100644 (file)
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -27,14 +27,17 @@ static DEFINE_MUTEX(queue_handler_mutex);
 int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
 {
        int ret;
+       const struct nf_queue_handler *old;
 
        if (pf >= ARRAY_SIZE(queue_handler))
                return -EINVAL;
 
        mutex_lock(&queue_handler_mutex);
-       if (queue_handler[pf] == qh)
+       old = rcu_dereference_protected(queue_handler[pf],
+                                       lockdep_is_held(&queue_handler_mutex));
+       if (old == qh)
                ret = -EEXIST;
-       else if (queue_handler[pf])
+       else if (old)
                ret = -EBUSY;
        else {
                rcu_assign_pointer(queue_handler[pf], qh);
@@ -49,11 +52,15 @@ EXPORT_SYMBOL(nf_register_queue_handler);
 /* The caller must flush their queue before this */
 int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
 {
+       const struct nf_queue_handler *old;
+
        if (pf >= ARRAY_SIZE(queue_handler))
                return -EINVAL;
 
        mutex_lock(&queue_handler_mutex);
-       if (queue_handler[pf] && queue_handler[pf] != qh) {
+       old = rcu_dereference_protected(queue_handler[pf],
+                                       lockdep_is_held(&queue_handler_mutex));
+       if (old && old != qh) {
                mutex_unlock(&queue_handler_mutex);
                return -EINVAL;
        }
@@ -73,7 +80,10 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh)
 
        mutex_lock(&queue_handler_mutex);
        for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++)  {
-               if (queue_handler[pf] == qh)
+               if (rcu_dereference_protected(
+                               queue_handler[pf],
+                               lockdep_is_held(&queue_handler_mutex)
+                               ) == qh)
                        rcu_assign_pointer(queue_handler[pf], NULL);
        }
        mutex_unlock(&queue_handler_mutex);
@@ -115,7 +125,7 @@ static int __nf_queue(struct sk_buff *skb,
                      int (*okfn)(struct sk_buff *),
                      unsigned int queuenum)
 {
-       int status;
+       int status = -ENOENT;
        struct nf_queue_entry *entry = NULL;
 #ifdef CONFIG_BRIDGE_NETFILTER
        struct net_device *physindev;
@@ -128,16 +138,20 @@ static int __nf_queue(struct sk_buff *skb,
        rcu_read_lock();
 
        qh = rcu_dereference(queue_handler[pf]);
-       if (!qh)
+       if (!qh) {
+               status = -ESRCH;
                goto err_unlock;
+       }
 
        afinfo = nf_get_afinfo(pf);
        if (!afinfo)
                goto err_unlock;
 
        entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC);
-       if (!entry)
+       if (!entry) {
+               status = -ENOMEM;
                goto err_unlock;
+       }
 
        *entry = (struct nf_queue_entry) {
                .skb    = skb,
@@ -151,11 +165,9 @@ static int __nf_queue(struct sk_buff *skb,
 
        /* If it's going away, ignore hook. */
        if (!try_module_get(entry->elem->owner)) {
-               rcu_read_unlock();
-               kfree(entry);
-               return 0;
+               status = -ECANCELED;
+               goto err_unlock;
        }
-
        /* Bump dev refs so they don't vanish while packet is out */
        if (indev)
                dev_hold(indev);
@@ -182,14 +194,13 @@ static int __nf_queue(struct sk_buff *skb,
                goto err;
        }
 
-       return 1;
+       return 0;
 
 err_unlock:
        rcu_read_unlock();
 err:
-       kfree_skb(skb);
        kfree(entry);
-       return 1;
+       return status;
 }
 
 int nf_queue(struct sk_buff *skb,
@@ -201,6 +212,8 @@ int nf_queue(struct sk_buff *skb,
             unsigned int queuenum)
 {
        struct sk_buff *segs;
+       int err;
+       unsigned int queued;
 
        if (!skb_is_gso(skb))
                return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
@@ -216,20 +229,35 @@ int nf_queue(struct sk_buff *skb,
        }
 
        segs = skb_gso_segment(skb, 0);
-       kfree_skb(skb);
+       /* Does not use PTR_ERR to limit the number of error codes that can be
+        * returned by nf_queue.  For instance, callers rely on -ECANCELED to mean
+        * 'ignore this hook'.
+        */
        if (IS_ERR(segs))
-               return 1;
+               return -EINVAL;
 
+       queued = 0;
+       err = 0;
        do {
                struct sk_buff *nskb = segs->next;
 
                segs->next = NULL;
-               if (!__nf_queue(segs, elem, pf, hook, indev, outdev, okfn,
-                               queuenum))
+               if (err == 0)
+                       err = __nf_queue(segs, elem, pf, hook, indev,
+                                          outdev, okfn, queuenum);
+               if (err == 0)
+                       queued++;
+               else
                        kfree_skb(segs);
                segs = nskb;
        } while (segs);
-       return 1;
+
+       /* also free orig skb if only some segments were queued */
+       if (unlikely(err && queued))
+               err = 0;
+       if (err == 0)
+               kfree_skb(skb);
+       return err;
 }
 
 void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
@@ -237,6 +265,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
        struct sk_buff *skb = entry->skb;
        struct list_head *elem = &entry->elem->list;
        const struct nf_afinfo *afinfo;
+       int err;
 
        rcu_read_lock();
 
@@ -270,10 +299,17 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
                local_bh_enable();
                break;
        case NF_QUEUE:
-               if (!__nf_queue(skb, elem, entry->pf, entry->hook,
-                               entry->indev, entry->outdev, entry->okfn,
-                               verdict >> NF_VERDICT_BITS))
-                       goto next_hook;
+               err = __nf_queue(skb, elem, entry->pf, entry->hook,
+                                entry->indev, entry->outdev, entry->okfn,
+                                verdict >> NF_VERDICT_QBITS);
+               if (err < 0) {
+                       if (err == -ECANCELED)
+                               goto next_hook;
+                       if (err == -ESRCH &&
+                          (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+                               goto next_hook;
+                       kfree_skb(skb);
+               }
                break;
        case NF_STOLEN:
        default: