netfilter: flowtable: dedicated slab for flow entry

The size of `struct flow_offload` has grown beyond 256 bytes on 64-bit
kernels (currently 280 bytes) because of the `flow_offload_tunnel`
member added recently. So kmalloc() allocates from the kmalloc-512 slab,
causing significant memory waste per entry.

Introduce a dedicated slab cache for flow entries to reduce memory
footprint. Results in a reduction from 512 bytes to 320 bytes per entry
on x86_64 kernels.

Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>

Author: LGA1150

net/netfilter/nf_flow_table_core.c

@@ -16,6 +16,7 @@
 
 static DEFINE_MUTEX(flowtable_lock);
 static LIST_HEAD(flowtables);
+static __read_mostly struct kmem_cache *flow_offload_cachep;
 
 static void
 flow_offload_fill_dir(struct flow_offload *flow,
@@ -56,7 +57,7 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct)
 	if (unlikely(nf_ct_is_dying(ct)))
 		return NULL;
 
-	flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
+	flow = kmem_cache_zalloc(flow_offload_cachep, GFP_ATOMIC);
 	if (!flow)
 		return NULL;
 
@@ -812,9 +813,13 @@ static int __init nf_flow_table_module_init(void)
 {
 	int ret;
 
+	flow_offload_cachep = KMEM_CACHE(flow_offload, SLAB_HWCACHE_ALIGN);
+	if (!flow_offload_cachep)
+		return -ENOMEM;
+
 	ret = register_pernet_subsys(&nf_flow_table_net_ops);
 	if (ret < 0)
-		return ret;
+		goto out_pernet;
 
 	ret = nf_flow_table_offload_init();
 	if (ret)
@@ -830,13 +835,16 @@ static int __init nf_flow_table_module_init(void)
 	nf_flow_table_offload_exit();
 out_offload:
 	unregister_pernet_subsys(&nf_flow_table_net_ops);
+out_pernet:
+	kmem_cache_destroy(flow_offload_cachep);
 	return ret;
 }
 
 static void __exit nf_flow_table_module_exit(void)
 {
 	nf_flow_table_offload_exit();
 	unregister_pernet_subsys(&nf_flow_table_net_ops);
+	kmem_cache_destroy(flow_offload_cachep);
 }
 
 module_init(nf_flow_table_module_init);