1 files changed, 140 insertions, 279 deletions

diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 0cef1433d66..5d24b1fdb59 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -1,4 +1,10 @@
+/*
+ * Rusty Russell (C)2000 -- This code is GPL.
+ * Patrick McHardy (c) 2006-2012
+ */
+
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
@@ -7,361 +13,216 @@
 #include <linux/seq_file.h>
 #include <linux/rcupdate.h>
 #include <net/protocol.h>
+#include <net/netfilter/nf_queue.h>
+#include <net/dst.h>
 
 #include "nf_internals.h"
 
 /*
- * A queue handler may be registered for each protocol.  Each is protected by
- * long term mutex.  The handler must provide an an outfn() to accept packets
- * for queueing and must reinject all packets it receives, no matter what.
+ * Hook for nfnetlink_queue to register its queue handler.
+ * We do this so that most of the NFQUEUE code can be modular.
+ *
+ * Once the queue is registered it must reinject all packets it
+ * receives, no matter what.
  */
-static struct nf_queue_handler *queue_handler[NPROTO];
-
-static DEFINE_MUTEX(queue_handler_mutex);
+static const struct nf_queue_handler __rcu *queue_handler __read_mostly;
 
 /* return EBUSY when somebody else is registered, return EEXIST if the
  * same handler is registered, return 0 in case of success. */
-int nf_register_queue_handler(int pf, struct nf_queue_handler *qh)
+void nf_register_queue_handler(const struct nf_queue_handler *qh)
 {
-	int ret;
-
-	if (pf >= NPROTO)
-		return -EINVAL;
-
-	mutex_lock(&queue_handler_mutex);
-	if (queue_handler[pf] == qh)
-		ret = -EEXIST;
-	else if (queue_handler[pf])
-		ret = -EBUSY;
-	else {
-		rcu_assign_pointer(queue_handler[pf], qh);
-		ret = 0;
-	}
-	mutex_unlock(&queue_handler_mutex);
-
-	return ret;
+	/* should never happen, we only have one queueing backend in kernel */
+	WARN_ON(rcu_access_pointer(queue_handler));
+	rcu_assign_pointer(queue_handler, qh);
 }
 EXPORT_SYMBOL(nf_register_queue_handler);
 
 /* The caller must flush their queue before this */
-int nf_unregister_queue_handler(int pf, struct nf_queue_handler *qh)
+void nf_unregister_queue_handler(void)
 {
-	if (pf >= NPROTO)
-		return -EINVAL;
-
-	mutex_lock(&queue_handler_mutex);
-	if (queue_handler[pf] != qh) {
-		mutex_unlock(&queue_handler_mutex);
-		return -EINVAL;
-	}
-
-	rcu_assign_pointer(queue_handler[pf], NULL);
-	mutex_unlock(&queue_handler_mutex);
-
+	RCU_INIT_POINTER(queue_handler, NULL);
 	synchronize_rcu();
-
-	return 0;
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
-void nf_unregister_queue_handlers(struct nf_queue_handler *qh)
+void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 {
-	int pf;
+	/* Release those devices we held, or Alexey will kill me. */
+	if (entry->indev)
+		dev_put(entry->indev);
+	if (entry->outdev)
+		dev_put(entry->outdev);
+#ifdef CONFIG_BRIDGE_NETFILTER
+	if (entry->skb->nf_bridge) {
+		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
 
-	mutex_lock(&queue_handler_mutex);
-	for (pf = 0; pf < NPROTO; pf++)  {
-		if (queue_handler[pf] == qh)
-			rcu_assign_pointer(queue_handler[pf], NULL);
+		if (nf_bridge->physindev)
+			dev_put(nf_bridge->physindev);
+		if (nf_bridge->physoutdev)
+			dev_put(nf_bridge->physoutdev);
 	}
-	mutex_unlock(&queue_handler_mutex);
+#endif
+	/* Drop reference to owner of hook which queued us. */
+	module_put(entry->elem->owner);
+}
+EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs);
 
-	synchronize_rcu();
+/* Bump dev refs so they don't vanish while packet is out */
+bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
+{
+	if (!try_module_get(entry->elem->owner))
+		return false;
+
+	if (entry->indev)
+		dev_hold(entry->indev);
+	if (entry->outdev)
+		dev_hold(entry->outdev);
+#ifdef CONFIG_BRIDGE_NETFILTER
+	if (entry->skb->nf_bridge) {
+		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
+		struct net_device *physdev;
+
+		physdev = nf_bridge->physindev;
+		if (physdev)
+			dev_hold(physdev);
+		physdev = nf_bridge->physoutdev;
+		if (physdev)
+			dev_hold(physdev);
+	}
+#endif
+
+	return true;
 }
-EXPORT_SYMBOL_GPL(nf_unregister_queue_handlers);
+EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
 
 /*
  * Any packet that leaves via this function must come back
  * through nf_reinject().
  */
-static int __nf_queue(struct sk_buff *skb,
-		      struct list_head *elem,
-		      int pf, unsigned int hook,
+int nf_queue(struct sk_buff *skb,
+		      struct nf_hook_ops *elem,
+		      u_int8_t pf, unsigned int hook,
 		      struct net_device *indev,
 		      struct net_device *outdev,
 		      int (*okfn)(struct sk_buff *),
 		      unsigned int queuenum)
 {
-	int status;
-	struct nf_info *info;
-#ifdef CONFIG_BRIDGE_NETFILTER
-	struct net_device *physindev = NULL;
-	struct net_device *physoutdev = NULL;
-#endif
-	struct nf_afinfo *afinfo;
-	struct nf_queue_handler *qh;
+	int status = -ENOENT;
+	struct nf_queue_entry *entry = NULL;
+	const struct nf_afinfo *afinfo;
+	const struct nf_queue_handler *qh;
 
-	/* QUEUE == DROP if noone is waiting, to be safe. */
+	/* QUEUE == DROP if no one is waiting, to be safe. */
 	rcu_read_lock();
 
-	qh = rcu_dereference(queue_handler[pf]);
+	qh = rcu_dereference(queue_handler);
 	if (!qh) {
-		rcu_read_unlock();
-		kfree_skb(skb);
-		return 1;
+		status = -ESRCH;
+		goto err_unlock;
 	}
 
 	afinfo = nf_get_afinfo(pf);
-	if (!afinfo) {
-		rcu_read_unlock();
-		kfree_skb(skb);
-		return 1;
-	}
-
-	info = kmalloc(sizeof(*info) + afinfo->route_key_size, GFP_ATOMIC);
-	if (!info) {
-		if (net_ratelimit())
-			printk(KERN_ERR "OOM queueing packet %p\n",
-			       skb);
-		rcu_read_unlock();
-		kfree_skb(skb);
-		return 1;
-	}
-
-	*info = (struct nf_info) {
-		(struct nf_hook_ops *)elem, pf, hook, indev, outdev, okfn };
-
-	/* If it's going away, ignore hook. */
-	if (!try_module_get(info->elem->owner)) {
-		rcu_read_unlock();
-		kfree(info);
-		return 0;
-	}
-
-	/* Bump dev refs so they don't vanish while packet is out */
-	if (indev) dev_hold(indev);
-	if (outdev) dev_hold(outdev);
-
-#ifdef CONFIG_BRIDGE_NETFILTER
-	if (skb->nf_bridge) {
-		physindev = skb->nf_bridge->physindev;
-		if (physindev) dev_hold(physindev);
-		physoutdev = skb->nf_bridge->physoutdev;
-		if (physoutdev) dev_hold(physoutdev);
-	}
-#endif
-	afinfo->saveroute(skb, info);
-	status = qh->outfn(skb, info, queuenum, qh->data);
+	if (!afinfo)
+		goto err_unlock;
+
+	entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC);
+	if (!entry) {
+		status = -ENOMEM;
+		goto err_unlock;
+	}
+
+	*entry = (struct nf_queue_entry) {
+		.skb	= skb,
+		.elem	= elem,
+		.pf	= pf,
+		.hook	= hook,
+		.indev	= indev,
+		.outdev	= outdev,
+		.okfn	= okfn,
+		.size	= sizeof(*entry) + afinfo->route_key_size,
+	};
+
+	if (!nf_queue_entry_get_refs(entry)) {
+		status = -ECANCELED;
+		goto err_unlock;
+	}
+	skb_dst_force(skb);
+	afinfo->saveroute(skb, entry);
+	status = qh->outfn(entry, queuenum);
 
 	rcu_read_unlock();
 
 	if (status < 0) {
-		/* James M doesn't say fuck enough. */
-		if (indev) dev_put(indev);
-		if (outdev) dev_put(outdev);
-#ifdef CONFIG_BRIDGE_NETFILTER
-		if (physindev) dev_put(physindev);
-		if (physoutdev) dev_put(physoutdev);
-#endif
-		module_put(info->elem->owner);
-		kfree(info);
-		kfree_skb(skb);
-
-		return 1;
+		nf_queue_entry_release_refs(entry);
+		goto err;
 	}
 
-	return 1;
-}
-
-int nf_queue(struct sk_buff *skb,
-	     struct list_head *elem,
-	     int pf, unsigned int hook,
-	     struct net_device *indev,
-	     struct net_device *outdev,
-	     int (*okfn)(struct sk_buff *),
-	     unsigned int queuenum)
-{
-	struct sk_buff *segs;
-
-	if (!skb_is_gso(skb))
-		return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
-				  queuenum);
-
-	switch (pf) {
-	case AF_INET:
-		skb->protocol = htons(ETH_P_IP);
-		break;
-	case AF_INET6:
-		skb->protocol = htons(ETH_P_IPV6);
-		break;
-	}
-
-	segs = skb_gso_segment(skb, 0);
-	kfree_skb(skb);
-	if (unlikely(IS_ERR(segs)))
-		return 1;
-
-	do {
-		struct sk_buff *nskb = segs->next;
+	return 0;
 
-		segs->next = NULL;
-		if (!__nf_queue(segs, elem, pf, hook, indev, outdev, okfn,
-				queuenum))
-			kfree_skb(segs);
-		segs = nskb;
-	} while (segs);
-	return 1;
+err_unlock:
+	rcu_read_unlock();
+err:
+	kfree(entry);
+	return status;
 }
 
-void nf_reinject(struct sk_buff *skb, struct nf_info *info,
-		 unsigned int verdict)
+void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 {
-	struct list_head *elem = &info->elem->list;
-	struct list_head *i;
-	struct nf_afinfo *afinfo;
+	struct sk_buff *skb = entry->skb;
+	struct nf_hook_ops *elem = entry->elem;
+	const struct nf_afinfo *afinfo;
+	int err;
 
 	rcu_read_lock();
 
-	/* Release those devices we held, or Alexey will kill me. */
-	if (info->indev) dev_put(info->indev);
-	if (info->outdev) dev_put(info->outdev);
-#ifdef CONFIG_BRIDGE_NETFILTER
-	if (skb->nf_bridge) {
-		if (skb->nf_bridge->physindev)
-			dev_put(skb->nf_bridge->physindev);
-		if (skb->nf_bridge->physoutdev)
-			dev_put(skb->nf_bridge->physoutdev);
-	}
-#endif
-
-	/* Drop reference to owner of hook which queued us. */
-	module_put(info->elem->owner);
-
-	list_for_each_rcu(i, &nf_hooks[info->pf][info->hook]) {
-		if (i == elem)
-			break;
-	}
-
-	if (i == &nf_hooks[info->pf][info->hook]) {
-		/* The module which sent it to userspace is gone. */
-		NFDEBUG("%s: module disappeared, dropping packet.\n",
-			__FUNCTION__);
-		verdict = NF_DROP;
-	}
+	nf_queue_entry_release_refs(entry);
 
 	/* Continue traversal iff userspace said ok... */
 	if (verdict == NF_REPEAT) {
-		elem = elem->prev;
+		elem = list_entry(elem->list.prev, struct nf_hook_ops, list);
 		verdict = NF_ACCEPT;
 	}
 
 	if (verdict == NF_ACCEPT) {
-		afinfo = nf_get_afinfo(info->pf);
-		if (!afinfo || afinfo->reroute(skb, info) < 0)
+		afinfo = nf_get_afinfo(entry->pf);
+		if (!afinfo || afinfo->reroute(skb, entry) < 0)
 			verdict = NF_DROP;
 	}
 
 	if (verdict == NF_ACCEPT) {
 	next_hook:
-		verdict = nf_iterate(&nf_hooks[info->pf][info->hook],
-				     skb, info->hook,
-				     info->indev, info->outdev, &elem,
-				     info->okfn, INT_MIN);
+		verdict = nf_iterate(&nf_hooks[entry->pf][entry->hook],
+				     skb, entry->hook,
+				     entry->indev, entry->outdev, &elem,
+				     entry->okfn, INT_MIN);
 	}
 
 	switch (verdict & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_STOP:
-		info->okfn(skb);
-	case NF_STOLEN:
+		local_bh_disable();
+		entry->okfn(skb);
+		local_bh_enable();
 		break;
 	case NF_QUEUE:
-		if (!__nf_queue(skb, elem, info->pf, info->hook,
-				info->indev, info->outdev, info->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:
 		break;
 	default:
 		kfree_skb(skb);
 	}
 	rcu_read_unlock();
-	kfree(info);
-	return;
+	kfree(entry);
 }
 EXPORT_SYMBOL(nf_reinject);
-
-#ifdef CONFIG_PROC_FS
-static void *seq_start(struct seq_file *seq, loff_t *pos)
-{
-	if (*pos >= NPROTO)
-		return NULL;
-
-	return pos;
-}
-
-static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
-{
-	(*pos)++;
-
-	if (*pos >= NPROTO)
-		return NULL;
-
-	return pos;
-}
-
-static void seq_stop(struct seq_file *s, void *v)
-{
-
-}
-
-static int seq_show(struct seq_file *s, void *v)
-{
-	int ret;
-	loff_t *pos = v;
-	struct nf_queue_handler *qh;
-
-	rcu_read_lock();
-	qh = rcu_dereference(queue_handler[*pos]);
-	if (!qh)
-		ret = seq_printf(s, "%2lld NONE\n", *pos);
-	else
-		ret = seq_printf(s, "%2lld %s\n", *pos, qh->name);
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static const struct seq_operations nfqueue_seq_ops = {
-	.start	= seq_start,
-	.next	= seq_next,
-	.stop	= seq_stop,
-	.show	= seq_show,
-};
-
-static int nfqueue_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &nfqueue_seq_ops);
-}
-
-static const struct file_operations nfqueue_file_ops = {
-	.owner	 = THIS_MODULE,
-	.open	 = nfqueue_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-#endif /* PROC_FS */
-
-
-int __init netfilter_queue_init(void)
-{
-#ifdef CONFIG_PROC_FS
-	struct proc_dir_entry *pde;
-
-	pde = create_proc_entry("nf_queue", S_IRUGO, proc_net_netfilter);
-	if (!pde)
-		return -1;
-	pde->proc_fops = &nfqueue_file_ops;
-#endif
-	return 0;
-}
-