Merge branch 'bpf-cgroup2'

Martin KaFai Lau says:

====================
cgroup: bpf: cgroup2 membership test on skb

This series is to implement a bpf-way to
check the cgroup2 membership of a skb (sk_buff).

It is similar to the feature added in netfilter:
c38c4597e4bf ("netfilter: implement xt_cgroup cgroup2 path match")

The current target is the tc-like usage.

v3:
- Remove WARN_ON_ONCE(!rcu_read_lock_held())
- Stop BPF_MAP_TYPE_CGROUP_ARRAY usage in patch 2/4
- Avoid mounting bpf fs manually in patch 4/4

- Thanks for Daniel's review and the above suggestions

- Check CONFIG_SOCK_CGROUP_DATA instead of CONFIG_CGROUPS.  Thanks to
  the kbuild bot's report.
  Patch 2/4 only needs CONFIG_CGROUPS while patch 3/4 needs
  CONFIG_SOCK_CGROUP_DATA.  Since a single bpf cgrp2 array alone is
  not useful for now, CONFIG_SOCK_CGROUP_DATA is also used in
  patch 2/4.  We can fine tune it later if we find other use cases
  for the cgrp2 array.
- Return EAGAIN instead of ENOENT if the cgrp2 array entry is
  NULL.  It is to distinguish these two cases: 1) the userland has
  not populated this array entry yet. or 2) not finding cgrp2 from the skb.

- Be-lated thanks to Alexei and Tejun on reviewing v1 and giving advice on
  this work.

v2:
- Fix two return cases in cgroup_get_from_fd()
- Fix compilation errors when CONFIG_CGROUPS is not used:
  - arraymap.c: avoid registering BPF_MAP_TYPE_CGROUP_ARRAY
  - filter.c: tc_cls_act_func_proto() returns NULL on BPF_FUNC_skb_in_cgroup
- Add comments to BPF_FUNC_skb_in_cgroup and cgroup_get_from_fd()
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 38 insertions, 0 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 76fee35da244..54071cf70fb5 100644
--- a/net/core/filter.c
+++ b/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);
 	}