netfilter: nf_flow_table: hardware offload support

This patch adds the dataplane hardware offload to the flowtable
infrastructure. Three new flags represent the hardware state of this
flow:

* FLOW_OFFLOAD_HW: This flow entry resides in the hardware.
* FLOW_OFFLOAD_HW_DYING: This flow entry has been scheduled to be remove
  from hardware. This might be triggered by either packet path (via TCP
  RST/FIN packet) or via aging.
* FLOW_OFFLOAD_HW_DEAD: This flow entry has been already removed from
  the hardware, the software garbage collector can remove it from the
  software flowtable.

This patch supports for:

* IPv4 only.
* Aging via FLOW_CLS_STATS, no packet and byte counter synchronization
  at this stage.

This patch also adds the action callback that specifies how to convert
the flow entry into the flow_rule object that is passed to the driver.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -848,6 +848,7 @@ enum tc_setup_type {
 	TC_SETUP_ROOT_QDISC,
 	TC_SETUP_QDISC_GRED,
 	TC_SETUP_QDISC_TAPRIO,
+	TC_SETUP_FT,
 };
 
 /* These structures hold the attributes of bpf state that are being passed

include/net/netfilter/nf_flow_table.h

@@ -12,6 +12,9 @@
 #include <net/dst.h>
 
 struct nf_flowtable;
+struct nf_flow_rule;
+struct flow_offload;
+enum flow_offload_tuple_dir;
 
 struct nf_flowtable_type {
 	struct list_head		list;
@@ -20,6 +23,10 @@ struct nf_flowtable_type {
 	int				(*setup)(struct nf_flowtable *ft,
 						 struct net_device *dev,
 						 enum flow_block_command cmd);
+	int				(*action)(struct net *net,
+						  const struct flow_offload *flow,
+						  enum flow_offload_tuple_dir dir,
+						  struct nf_flow_rule *flow_rule);
 	void				(*free)(struct nf_flowtable *ft);
 	nf_hookfn			*hook;
 	struct module			*owner;
@@ -80,6 +87,9 @@ struct flow_offload_tuple_rhash {
 #define FLOW_OFFLOAD_DNAT	0x2
 #define FLOW_OFFLOAD_DYING	0x4
 #define FLOW_OFFLOAD_TEARDOWN	0x8
+#define FLOW_OFFLOAD_HW		0x10
+#define FLOW_OFFLOAD_HW_DYING	0x20
+#define FLOW_OFFLOAD_HW_DEAD	0x40
 
 enum flow_offload_type {
 	NF_FLOW_OFFLOAD_UNSPEC	= 0,
@@ -142,11 +152,22 @@ unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 #define MODULE_ALIAS_NF_FLOWTABLE(family)	\
 	MODULE_ALIAS("nf-flowtable-" __stringify(family))
 
-static inline int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
-					      struct net_device *dev,
-					      enum flow_block_command cmd)
-{
-	return 0;
-}
+void nf_flow_offload_add(struct nf_flowtable *flowtable,
+			 struct flow_offload *flow);
+void nf_flow_offload_del(struct nf_flowtable *flowtable,
+			 struct flow_offload *flow);
+void nf_flow_offload_stats(struct nf_flowtable *flowtable,
+			   struct flow_offload *flow);
+
+void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
+int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
+				struct net_device *dev,
+				enum flow_block_command cmd);
+int nf_flow_rule_route(struct net *net, const struct flow_offload *flow,
+		       enum flow_offload_tuple_dir dir,
+		       struct nf_flow_rule *flow_rule);
+
+int nf_flow_table_offload_init(void);
+void nf_flow_table_offload_exit(void);
 
 #endif /* _NF_FLOW_TABLE_H */

net/ipv4/netfilter/nf_flow_table_ipv4.c

@@ -10,6 +10,7 @@ static struct nf_flowtable_type flowtable_ipv4 = {
 	.family		= NFPROTO_IPV4,
 	.init		= nf_flow_table_init,
 	.setup		= nf_flow_table_offload_setup,
+	.action		= nf_flow_rule_route,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ip_hook,
 	.owner		= THIS_MODULE,

net/ipv6/netfilter/nf_flow_table_ipv6.c

@@ -11,6 +11,7 @@ static struct nf_flowtable_type flowtable_ipv6 = {
 	.family		= NFPROTO_IPV6,
 	.init		= nf_flow_table_init,
 	.setup		= nf_flow_table_offload_setup,
+	.action		= nf_flow_rule_route,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ipv6_hook,
 	.owner		= THIS_MODULE,

net/netfilter/Makefile

@@ -120,7 +120,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV)	+= nft_fwd_netdev.o
 
 # flow table infrastructure
 obj-$(CONFIG_NF_FLOW_TABLE)	+= nf_flow_table.o
-nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o
+nf_flow_table-objs		:= nf_flow_table_core.o nf_flow_table_ip.o \
+				   nf_flow_table_offload.o
 
 obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
 

net/netfilter/nf_flow_table_core.c

@@ -250,6 +250,9 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 		return err;
 	}
 
+	if (flow_table->flags & NF_FLOWTABLE_HW_OFFLOAD)
+		nf_flow_offload_add(flow_table, flow);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
@@ -350,9 +353,20 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
 	struct nf_flowtable *flow_table = data;
 
+	if (flow->flags & FLOW_OFFLOAD_HW)
+		nf_flow_offload_stats(flow_table, flow);
+
 	if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) ||
-	    (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)))
-		flow_offload_del(flow_table, flow);
+	    (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) {
+		if (flow->flags & FLOW_OFFLOAD_HW) {
+			if (!(flow->flags & FLOW_OFFLOAD_HW_DYING))
+				nf_flow_offload_del(flow_table, flow);
+			else if (flow->flags & FLOW_OFFLOAD_HW_DEAD)
+				flow_offload_del(flow_table, flow);
+		} else {
+			flow_offload_del(flow_table, flow);
+		}
+	}
 }
 
 static void nf_flow_offload_work_gc(struct work_struct *work)
@@ -485,6 +499,7 @@ int nf_flow_table_init(struct nf_flowtable *flowtable)
 	int err;
 
 	INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+	flow_block_init(&flowtable->flow_block);
 
 	err = rhashtable_init(&flowtable->rhashtable,
 			      &nf_flow_offload_rhash_params);
@@ -520,6 +535,7 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
 static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
 					  struct net_device *dev)
 {
+	nf_flow_table_offload_flush(flowtable);
 	nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
 	flush_delayed_work(&flowtable->gc_work);
 }
@@ -547,5 +563,18 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_free);
 
+static int __init nf_flow_table_module_init(void)
+{
+	return nf_flow_table_offload_init();
+}
+
+static void __exit nf_flow_table_module_exit(void)
+{
+	nf_flow_table_offload_exit();
+}
+
+module_init(nf_flow_table_module_init);
+module_exit(nf_flow_table_module_exit);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");

net/netfilter/nf_flow_table_inet.c

@@ -25,6 +25,7 @@ static struct nf_flowtable_type flowtable_inet = {
 	.family		= NFPROTO_INET,
 	.init		= nf_flow_table_init,
 	.setup		= nf_flow_table_offload_setup,
+	.action		= nf_flow_rule_route,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_inet_hook,
 	.owner		= THIS_MODULE,