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 c38c4597e4bf ("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 <kafai@xxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Acked-by: Alexei Starovoitov <ast@xxxxxxxxxx>
---
include/uapi/linux/bpf.h | 12 ++++++++++++
kernel/bpf/verifier.c | 8 ++++++++
net/core/filter.c | 40 ++++++++++++++++++++++++++++++++++++++++
3 files changed, 60 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ef4e386..bad309f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -314,6 +314,18 @@ enum bpf_func_id {
*/
BPF_FUNC_skb_get_tunnel_opt,
BPF_FUNC_skb_set_tunnel_opt,
+
+ /**
+ * 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 --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 668e079..68753e0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1062,6 +1062,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
if (func_id != BPF_FUNC_get_stackid)
goto error;
break;
+ case BPF_MAP_TYPE_CGROUP_ARRAY:
+ if (func_id != BPF_FUNC_skb_in_cgroup)
+ goto error;
+ break;
default:
break;
}
@@ -1081,6 +1085,10 @@ 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 --git a/net/core/filter.c b/net/core/filter.c
index df6860c..a16f7d2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2024,6 +2024,42 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
}
}
+#ifdef CONFIG_CGROUPS
+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;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ 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 -ENOENT;
+
+ 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)
{
@@ -2086,6 +2122,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return &bpf_get_route_realm_proto;
case BPF_FUNC_perf_event_output:
return bpf_get_event_output_proto();
+#ifdef CONFIG_CGROUPS
+ case BPF_FUNC_skb_in_cgroup:
+ return &bpf_skb_in_cgroup_proto;
+#endif
default:
return sk_filter_func_proto(func_id);
}
--
2.5.1
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
