netfilter: convert hook list to an array

This converts the storage and layout of netfilter hook entries from a
linked list to an array.  After this commit, hook entries will be
stored adjacent in memory.  The next pointer is no longer required.

The ops pointers are stored at the end of the array as they are only
used in the register/unregister path and in the legacy br_netfilter code.

nf_unregister_net_hooks() is slower than needed as it just calls
nf_unregister_net_hook in a loop (i.e. at least n synchronize_net()
calls), this will be addressed in followup patch.

Test setup:
 - ixgbe 10gbit
 - netperf UDP_STREAM, 64 byte packets
 - 5 hooks: (raw + mangle prerouting, mangle+filter input, inet filter):
empty mangle and raw prerouting, mangle and filter input hooks:
353.9
this patch:
364.2

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

5 files changed, 28 insertions, 27 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 614642e..ca0a301 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1811,7 +1811,7 @@ struct net_device {
 #endif
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
-	struct nf_hook_entry __rcu *nf_hooks_ingress;
+	struct nf_hook_entries __rcu *nf_hooks_ingress;
 #endif
 
 	unsigned char		broadcast[MAX_ADDR_LEN];
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 22f0810..f84bca1 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -72,25 +72,32 @@ struct nf_hook_ops {
 };
 
 struct nf_hook_entry {
-	struct nf_hook_entry __rcu	*next;
 	nf_hookfn			*hook;
 	void				*priv;
-	const struct nf_hook_ops	*orig_ops;
 };
 
-static inline void
-nf_hook_entry_init(struct nf_hook_entry *entry,	const struct nf_hook_ops *ops)
-{
-	entry->next = NULL;
-	entry->hook = ops->hook;
-	entry->priv = ops->priv;
-	entry->orig_ops = ops;
-}
+struct nf_hook_entries {
+	u16				num_hook_entries;
+	/* padding */
+	struct nf_hook_entry		hooks[];
+
+	/* trailer: pointers to original orig_ops of each hook.
+	 *
+	 * This is not part of struct nf_hook_entry since its only
+	 * needed in slow path (hook register/unregister).
+	 *
+	 * const struct nf_hook_ops     *orig_ops[]
+	 */
+};
 
-static inline int
-nf_hook_entry_priority(const struct nf_hook_entry *entry)
+static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e)
 {
-	return entry->orig_ops->priority;
+	unsigned int n = e->num_hook_entries;
+	const void *hook_end;
+
+	hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */
+
+	return (struct nf_hook_ops **)hook_end;
 }
 
 static inline int
@@ -100,12 +107,6 @@ nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb,
 	return entry->hook(entry->priv, skb, state);
 }
 
-static inline const struct nf_hook_ops *
-nf_hook_entry_ops(const struct nf_hook_entry *entry)
-{
-	return entry->orig_ops;
-}
-
 static inline void nf_hook_state_init(struct nf_hook_state *p,
 				      unsigned int hook,
 				      u_int8_t pf,
@@ -168,7 +169,7 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 #endif
 
 int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
-		 struct nf_hook_entry *entry);
+		 const struct nf_hook_entries *e, unsigned int i);
 
 /**
  *	nf_hook - call a netfilter hook
@@ -182,7 +183,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
 			  struct net_device *indev, struct net_device *outdev,
 			  int (*okfn)(struct net *, struct sock *, struct sk_buff *))
 {
-	struct nf_hook_entry *hook_head;
+	struct nf_hook_entries *hook_head;
 	int ret = 1;
 
 #ifdef HAVE_JUMP_LABEL
@@ -200,7 +201,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
 		nf_hook_state_init(&state, hook, pf, indev, outdev,
 				   sk, net, okfn);
 
-		ret = nf_hook_slow(skb, &state, hook_head);
+		ret = nf_hook_slow(skb, &state, hook_head, 0);
 	}
 	rcu_read_unlock();
 
diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h
index 5947606..8d5dae1 100644
--- a/include/linux/netfilter_ingress.h
+++ b/include/linux/netfilter_ingress.h
@@ -17,7 +17,7 @@ static inline bool nf_hook_ingress_active(const struct sk_buff *skb)
 /* caller must hold rcu_read_lock */
 static inline int nf_hook_ingress(struct sk_buff *skb)
 {
-	struct nf_hook_entry *e = rcu_dereference(skb->dev->nf_hooks_ingress);
+	struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress);
 	struct nf_hook_state state;
 	int ret;
 
@@ -30,7 +30,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb)
 	nf_hook_state_init(&state, NF_NETDEV_INGRESS,
 			   NFPROTO_NETDEV, skb->dev, NULL, NULL,
 			   dev_net(skb->dev), NULL);
-	ret = nf_hook_slow(skb, &state, e);
+	ret = nf_hook_slow(skb, &state, e, 0);
 	if (ret == 0)
 		return -1;
 
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 4454719f..3946872 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -10,9 +10,9 @@ struct nf_queue_entry {
 	struct list_head	list;
 	struct sk_buff		*skb;
 	unsigned int		id;
+	unsigned int		hook_index;	/* index in hook_entries->hook[] */
 
 	struct nf_hook_state	state;
-	struct nf_hook_entry	*hook;
 	u16			size; /* sizeof(entry) + saved route keys */
 
 	/* extra space to store route keys */
diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h
index cea396b..72d66c8 100644
--- a/include/net/netns/netfilter.h
+++ b/include/net/netns/netfilter.h
@@ -16,7 +16,7 @@ struct netns_nf {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header *nf_log_dir_header;
 #endif
-	struct nf_hook_entry __rcu *hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+	struct nf_hook_entries __rcu *hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 	bool			defrag_ipv4;
 #endif