xsk: Store struct xdp_sock as a flexible array member of the XSKMAP

Prior this commit, the array storing XDP socket instances were stored
in a separate allocated array of the XSKMAP. Now, we store the sockets
as a flexible array member in a similar fashion as the arraymap. Doing
so, we do less pointer chasing in the lookup.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/20191101110346.15004-2-bjorn.topel@gmail.com

kernel/bpf/xskmap.c

@@ -11,9 +11,9 @@
 
 struct xsk_map {
 	struct bpf_map map;
-	struct xdp_sock **xsk_map;
 	struct list_head __percpu *flush_list;
 	spinlock_t lock; /* Synchronize map updates */
+	struct xdp_sock *xsk_map[];
 };
 
 int xsk_map_inc(struct xsk_map *map)
@@ -80,9 +80,10 @@ static void xsk_map_sock_delete(struct xdp_sock *xs,
 
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
+	struct bpf_map_memory mem;
+	int cpu, err, numa_node;
 	struct xsk_map *m;
-	int cpu, err;
-	u64 cost;
+	u64 cost, size;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -92,44 +93,35 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
 		return ERR_PTR(-EINVAL);
 
-	m = kzalloc(sizeof(*m), GFP_USER);
-	if (!m)
+	numa_node = bpf_map_attr_numa_node(attr);
+	size = struct_size(m, xsk_map, attr->max_entries);
+	cost = size + array_size(sizeof(*m->flush_list), num_possible_cpus());
+
+	err = bpf_map_charge_init(&mem, cost);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	m = bpf_map_area_alloc(size, numa_node);
+	if (!m) {
+		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	bpf_map_init_from_attr(&m->map, attr);
+	bpf_map_charge_move(&m->map.memory, &mem);
 	spin_lock_init(&m->lock);
 
-	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
-	cost += sizeof(struct list_head) * num_possible_cpus();
-
-	/* Notice returns -EPERM on if map size is larger than memlock limit */
-	err = bpf_map_charge_init(&m->map.memory, cost);
-	if (err)
-		goto free_m;
-
-	err = -ENOMEM;
-
 	m->flush_list = alloc_percpu(struct list_head);
-	if (!m->flush_list)
-		goto free_charge;
+	if (!m->flush_list) {
+		bpf_map_charge_finish(&m->map.memory);
+		bpf_map_area_free(m);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	for_each_possible_cpu(cpu)
 		INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));
 
-	m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
-					sizeof(struct xdp_sock *),
-					m->map.numa_node);
-	if (!m->xsk_map)
-		goto free_percpu;
 	return &m->map;
-
-free_percpu:
-	free_percpu(m->flush_list);
-free_charge:
-	bpf_map_charge_finish(&m->map.memory);
-free_m:
-	kfree(m);
-	return ERR_PTR(err);
 }
 
 static void xsk_map_free(struct bpf_map *map)
@@ -139,8 +131,7 @@ static void xsk_map_free(struct bpf_map *map)
 	bpf_clear_redirect_map(map);
 	synchronize_net();
 	free_percpu(m->flush_list);
-	bpf_map_area_free(m->xsk_map);
-	kfree(m);
+	bpf_map_area_free(m);
 }
 
 static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)