netfilter: add netfilter ingress hook after handle_ing() under unique static key

This patch adds the Netfilter ingress hook just after the existing tc ingress
hook, that seems to be the consensus solution for this.

Note that the Netfilter hook resides under the global static key that enables
ingress filtering. Nonetheless, Netfilter still also has its own static key for
minimal impact on the existing handle_ing().

* Without this patch:

Result: OK: 6216490(c6216338+d152) usec, 100000000 (60byte,0frags)
  16086246pps 7721Mb/sec (7721398080bps) errors: 100000000

    42.46%  kpktgend_0   [kernel.kallsyms]   [k] __netif_receive_skb_core
    25.92%  kpktgend_0   [kernel.kallsyms]   [k] kfree_skb
     7.81%  kpktgend_0   [pktgen]            [k] pktgen_thread_worker
     5.62%  kpktgend_0   [kernel.kallsyms]   [k] ip_rcv
     2.70%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_internal
     2.34%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_sk
     1.44%  kpktgend_0   [kernel.kallsyms]   [k] __build_skb

* With this patch:

Result: OK: 6214833(c6214731+d101) usec, 100000000 (60byte,0frags)
  16090536pps 7723Mb/sec (7723457280bps) errors: 100000000

    41.23%  kpktgend_0      [kernel.kallsyms]  [k] __netif_receive_skb_core
    26.57%  kpktgend_0      [kernel.kallsyms]  [k] kfree_skb
     7.72%  kpktgend_0      [pktgen]           [k] pktgen_thread_worker
     5.55%  kpktgend_0      [kernel.kallsyms]  [k] ip_rcv
     2.78%  kpktgend_0      [kernel.kallsyms]  [k] netif_receive_skb_internal
     2.06%  kpktgend_0      [kernel.kallsyms]  [k] netif_receive_skb_sk
     1.43%  kpktgend_0      [kernel.kallsyms]  [k] __build_skb

* Without this patch + tc ingress:

        tc filter add dev eth4 parent ffff: protocol ip prio 1 \
                u32 match ip dst 4.3.2.1/32

Result: OK: 9269001(c9268821+d179) usec, 100000000 (60byte,0frags)
  10788648pps 5178Mb/sec (5178551040bps) errors: 100000000

    40.99%  kpktgend_0   [kernel.kallsyms]  [k] __netif_receive_skb_core
    17.50%  kpktgend_0   [kernel.kallsyms]  [k] kfree_skb
    11.77%  kpktgend_0   [cls_u32]          [k] u32_classify
     5.62%  kpktgend_0   [kernel.kallsyms]  [k] tc_classify_compat
     5.18%  kpktgend_0   [pktgen]           [k] pktgen_thread_worker
     3.23%  kpktgend_0   [kernel.kallsyms]  [k] tc_classify
     2.97%  kpktgend_0   [kernel.kallsyms]  [k] ip_rcv
     1.83%  kpktgend_0   [kernel.kallsyms]  [k] netif_receive_skb_internal
     1.50%  kpktgend_0   [kernel.kallsyms]  [k] netif_receive_skb_sk
     0.99%  kpktgend_0   [kernel.kallsyms]  [k] __build_skb

* With this patch + tc ingress:

        tc filter add dev eth4 parent ffff: protocol ip prio 1 \
                u32 match ip dst 4.3.2.1/32

Result: OK: 9308218(c9308091+d126) usec, 100000000 (60byte,0frags)
  10743194pps 5156Mb/sec (5156733120bps) errors: 100000000

    42.01%  kpktgend_0   [kernel.kallsyms]   [k] __netif_receive_skb_core
    17.78%  kpktgend_0   [kernel.kallsyms]   [k] kfree_skb
    11.70%  kpktgend_0   [cls_u32]           [k] u32_classify
     5.46%  kpktgend_0   [kernel.kallsyms]   [k] tc_classify_compat
     5.16%  kpktgend_0   [pktgen]            [k] pktgen_thread_worker
     2.98%  kpktgend_0   [kernel.kallsyms]   [k] ip_rcv
     2.84%  kpktgend_0   [kernel.kallsyms]   [k] tc_classify
     1.96%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_internal
     1.57%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_sk

Note that the results are very similar before and after.

I can see gcc gets the code under the ingress static key out of the hot path.
Then, on that cold branch, it generates the code to accomodate the netfilter
ingress static key. My explanation for this is that this reduces the pressure
on the instruction cache for non-users as the new code is out of the hot path,
and it comes with minimal impact for tc ingress users.

Using gcc version 4.8.4 on:

Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                8
[...]
L1d cache:             16K
L1i cache:             64K
L2 cache:              2048K
L3 cache:              8192K

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -1656,6 +1656,9 @@ struct net_device {
 	struct tcf_proto __rcu  *ingress_cl_list;
 #endif
 	struct netdev_queue __rcu *ingress_queue;
+#ifdef CONFIG_NETFILTER_INGRESS
+	struct list_head	nf_hooks_ingress;
+#endif
 
 	unsigned char		broadcast[MAX_ADDR_LEN];
 #ifdef CONFIG_RFS_ACCEL

include/linux/netfilter.h

@@ -86,6 +86,7 @@ struct nf_hook_ops {
 
 	/* User fills in from here down. */
 	nf_hookfn		*hook;
+	struct net_device	*dev;
 	struct module		*owner;
 	void			*priv;
 	u_int8_t		pf;

include/linux/netfilter_ingress.h

@@ -0,0 +1,41 @@
+#ifndef _NETFILTER_INGRESS_H_
+#define _NETFILTER_INGRESS_H_
+
+#include <linux/netfilter.h>
+#include <linux/netdevice.h>
+
+#ifdef CONFIG_NETFILTER_INGRESS
+static inline int nf_hook_ingress_active(struct sk_buff *skb)
+{
+	return nf_hook_list_active(&skb->dev->nf_hooks_ingress,
+				   NFPROTO_NETDEV, NF_NETDEV_INGRESS);
+}
+
+static inline int nf_hook_ingress(struct sk_buff *skb)
+{
+	struct nf_hook_state state;
+
+	nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress,
+			   NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL,
+			   skb->dev, NULL, NULL);
+	return nf_hook_slow(skb, &state);
+}
+
+static inline void nf_hook_ingress_init(struct net_device *dev)
+{
+	INIT_LIST_HEAD(&dev->nf_hooks_ingress);
+}
+#else /* CONFIG_NETFILTER_INGRESS */
+static inline int nf_hook_ingress_active(struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline int nf_hook_ingress(struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline void nf_hook_ingress_init(struct net_device *dev) {}
+#endif /* CONFIG_NETFILTER_INGRESS */
+#endif /* _NETFILTER_INGRESS_H_ */

include/uapi/linux/netfilter.h

@@ -51,11 +51,17 @@ enum nf_inet_hooks {
 	NF_INET_NUMHOOKS
 };
 
+enum nf_dev_hooks {
+	NF_NETDEV_INGRESS,
+	NF_NETDEV_NUMHOOKS
+};
+
 enum {
 	NFPROTO_UNSPEC =  0,
 	NFPROTO_INET   =  1,
 	NFPROTO_IPV4   =  2,
 	NFPROTO_ARP    =  3,
+	NFPROTO_NETDEV =  5,
 	NFPROTO_BRIDGE =  7,
 	NFPROTO_IPV6   = 10,
 	NFPROTO_DECNET = 12,

net/core/dev.c

@@ -135,6 +135,7 @@
 #include <linux/if_macvlan.h>
 #include <linux/errqueue.h>
 #include <linux/hrtimer.h>
+#include <linux/netfilter_ingress.h>
 
 #include "net-sysfs.h"
 
@@ -3666,6 +3667,13 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 
 	return skb;
 }
+#else
+static inline struct sk_buff *handle_ing(struct sk_buff *skb,
+					 struct packet_type **pt_prev,
+					 int *ret, struct net_device *orig_dev)
+{
+	return skb;
+}
 #endif
 
 /**
@@ -3739,6 +3747,28 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
 	}
 }
 
+#ifdef CONFIG_NETFILTER_INGRESS
+static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
+			     int *ret, struct net_device *orig_dev)
+{
+	if (nf_hook_ingress_active(skb)) {
+		if (*pt_prev) {
+			*ret = deliver_skb(skb, *pt_prev, orig_dev);
+			*pt_prev = NULL;
+		}
+
+		return nf_hook_ingress(skb);
+	}
+	return 0;
+}
+#else
+static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
+			     int *ret, struct net_device *orig_dev)
+{
+	return 0;
+}
+#endif
+
 static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 {
 	struct packet_type *ptype, *pt_prev;
@@ -3803,6 +3833,9 @@ skip_taps:
 		skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 		if (!skb)
 			goto unlock;
+
+		if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
+			goto unlock;
 	}
 #endif
 #ifdef CONFIG_NET_CLS_ACT
@@ -6968,6 +7001,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->group = INIT_NETDEV_GROUP;
 	if (!dev->ethtool_ops)
 		dev->ethtool_ops = &default_ethtool_ops;
+
+	nf_hook_ingress_init(dev);
+
 	return dev;
 
 free_all:

net/netfilter/Kconfig

@@ -1,6 +1,13 @@
 menu "Core Netfilter Configuration"
 	depends on NET && INET && NETFILTER
 
+config NETFILTER_INGRESS
+	bool "Netfilter ingress support"
+	select NET_INGRESS
+	help
+	  This allows you to classify packets from ingress using the Netfilter
+	  infrastructure.
+
 config NETFILTER_NETLINK
 	tristate
 

net/netfilter/core.c

@@ -64,10 +64,27 @@ static DEFINE_MUTEX(nf_hook_mutex);
 
 int nf_register_hook(struct nf_hook_ops *reg)
 {
+	struct list_head *nf_hook_list;
 	struct nf_hook_ops *elem;
 
 	mutex_lock(&nf_hook_mutex);
-	list_for_each_entry(elem, &nf_hooks[reg->pf][reg->hooknum], list) {
+	switch (reg->pf) {
+	case NFPROTO_NETDEV:
+#ifdef CONFIG_NETFILTER_INGRESS
+		if (reg->hooknum == NF_NETDEV_INGRESS) {
+			BUG_ON(reg->dev == NULL);
+			nf_hook_list = &reg->dev->nf_hooks_ingress;
+			net_inc_ingress_queue();
+			break;
+		}
+#endif
+		/* Fall through. */
+	default:
+		nf_hook_list = &nf_hooks[reg->pf][reg->hooknum];
+		break;
+	}
+
+	list_for_each_entry(elem, nf_hook_list, list) {
 		if (reg->priority < elem->priority)
 			break;
 	}
@@ -85,6 +102,18 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
 	mutex_lock(&nf_hook_mutex);
 	list_del_rcu(&reg->list);
 	mutex_unlock(&nf_hook_mutex);
+	switch (reg->pf) {
+	case NFPROTO_NETDEV:
+#ifdef CONFIG_NETFILTER_INGRESS
+		if (reg->hooknum == NF_NETDEV_INGRESS) {
+			net_dec_ingress_queue();
+			break;
+		}
+		break;
+#endif
+	default:
+		break;
+	}
 #ifdef HAVE_JUMP_LABEL
 	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif