cgroup: bpf: Add bpf_skb_in_cgroup_proto

Adds a bpf helper, bpf_skb_in_cgroup, to decide if a skb->sk
belongs to a descendant of a cgroup2.  It is similar to the
feature added in netfilter:
commit c38c459 ("netfilter: implement xt_cgroup cgroup2 path match")

The user is expected to populate a BPF_MAP_TYPE_CGROUP_ARRAY
which will be used by the bpf_skb_in_cgroup.

Modifications to the bpf verifier is to ensure BPF_MAP_TYPE_CGROUP_ARRAY
and bpf_skb_in_cgroup() are always used together.

Signed-off-by: Martin KaFai Lau <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Daniel Borkmann <[email protected]>
Cc: Tejun Heo <[email protected]>
Acked-by: Alexei Starovoitov <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: iamkafai

Diff for: include/uapi/linux/bpf.h

@@ -337,6 +337,17 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_skb_change_type,
 
+	/**
+	 * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+	 * @skb: pointer to skb
+	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+	 * @index: index of the cgroup in the bpf_map
+	 * Return:
+	 *   == 0 skb failed the cgroup2 descendant test
+	 *   == 1 skb succeeded the cgroup2 descendant test
+	 *    < 0 error
+	 */
+	BPF_FUNC_skb_in_cgroup,
 	__BPF_FUNC_MAX_ID,
 };
 

Diff for: kernel/bpf/verifier.c

@@ -1036,7 +1036,9 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_CGROUP_ARRAY:
-		goto error;
+		if (func_id != BPF_FUNC_skb_in_cgroup)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -1056,6 +1058,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
 			goto error;
 		break;
+	case BPF_FUNC_skb_in_cgroup:
+		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
+			goto error;
+		break;
 	default:
 		break;
 	}

Diff for: net/core/filter.c

@@ -2239,6 +2239,40 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
 	}
 }
 
+#ifdef CONFIG_SOCK_CGROUP_DATA
+static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(long)r1;
+	struct bpf_map *map = (struct bpf_map *)(long)r2;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct cgroup *cgrp;
+	struct sock *sk;
+	u32 i = (u32)r3;
+
+	sk = skb->sk;
+	if (!sk || !sk_fullsock(sk))
+		return -ENOENT;
+
+	if (unlikely(i >= array->map.max_entries))
+		return -E2BIG;
+
+	cgrp = READ_ONCE(array->ptrs[i]);
+	if (unlikely(!cgrp))
+		return -EAGAIN;
+
+	return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp);
+}
+
+static const struct bpf_func_proto bpf_skb_in_cgroup_proto = {
+	.func		= bpf_skb_in_cgroup,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+#endif
+
 static const struct bpf_func_proto *
 sk_filter_func_proto(enum bpf_func_id func_id)
 {
@@ -2307,6 +2341,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return bpf_get_event_output_proto();
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	case BPF_FUNC_skb_in_cgroup:
+		return &bpf_skb_in_cgroup_proto;
+#endif
 	default:
 		return sk_filter_func_proto(func_id);
 	}