Merge branch 'expand-cg_skb-helpers'

Andrey Ignatov says:

====================
v2->v3:
- better documentation for bpf_sk_cgroup_id in uapi (Yonghong Song)
- save/restore errno in network helpers (Yonghong Song)
- cleanup leftover after switching selftest to skeleton (Yonghong Song)
- switch from map to skel->bss in selftest (Yonghong Song)

v1->v2:
- switch selftests to skeleton.

This patch set allows a bunch of existing sk lookup and skb cgroup id
helpers, and adds two new bpf_sk_{,ancestor_}cgroup_id helpers to be used
in cgroup skb programs.

It fills the gap to cover a use-case to apply intra-host cgroup-bpf network
policy based on a source cgroup a packet comes from.

For example, there can be multiple containers A, B, C running on a host.
Every such container runs in its own cgroup that can have multiple
sub-cgroups. But all these containers can share some IP addresses.

At the same time container A wants to have a policy for a server S running
in it so that only clients from this same container can connect to S, but
not from other containers (such as B, C). Source IP address can't be used
to decide whether to allow or deny a packet, but it looks reasonable to
filter by cgroup id.

The patch set allows to implement the following policy:
* when an ingress packet comes to container's cgroup, lookup peer (client)
  socket this packet comes from;
* having peer socket, get its cgroup id;
* compare peer cgroup id with self cgroup id and allow packet only if they
  match, i.e. it comes from same cgroup;
* the "sub-cgroup" part of the story can be addressed by getting not direct
  cgroup id of the peer socket, but ancestor cgroup id on specified level,
  similar to existing "ancestor" flavors of cgroup id helpers.

A newly introduced selftest implements such a policy in its basic form to
provide a better idea on the use-case.

Patch 1 allows existing sk lookup helpers in cgroup skb.
Patch 2 allows skb_ancestor_cgroup_id in cgrou skb.
Patch 3 introduces two new helpers to get cgroup id of socket.
Patch 4 extends network helpers to use them in the next patch.
Patch 5 adds selftest / example of use-case.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 97 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
new file mode 100644
index 000000000000..3f757e30d7a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+__u16 g_serv_port = 0;
+
+static inline void set_ip(__u32 *dst, const struct in6_addr *src)
+{
+	dst[0] = src->in6_u.u6_addr32[0];
+	dst[1] = src->in6_u.u6_addr32[1];
+	dst[2] = src->in6_u.u6_addr32[2];
+	dst[3] = src->in6_u.u6_addr32[3];
+}
+
+static inline void set_tuple(struct bpf_sock_tuple *tuple,
+			     const struct ipv6hdr *ip6h,
+			     const struct tcphdr *tcph)
+{
+	set_ip(tuple->ipv6.saddr, &ip6h->daddr);
+	set_ip(tuple->ipv6.daddr, &ip6h->saddr);
+	tuple->ipv6.sport = tcph->dest;
+	tuple->ipv6.dport = tcph->source;
+}
+
+static inline int is_allowed_peer_cg(struct __sk_buff *skb,
+				     const struct ipv6hdr *ip6h,
+				     const struct tcphdr *tcph)
+{
+	__u64 cgid, acgid, peer_cgid, peer_acgid;
+	struct bpf_sock_tuple tuple;
+	size_t tuple_len = sizeof(tuple.ipv6);
+	struct bpf_sock *peer_sk;
+
+	set_tuple(&tuple, ip6h, tcph);
+
+	peer_sk = bpf_sk_lookup_tcp(skb, &tuple, tuple_len,
+				    BPF_F_CURRENT_NETNS, 0);
+	if (!peer_sk)
+		return 0;
+
+	cgid = bpf_skb_cgroup_id(skb);
+	peer_cgid = bpf_sk_cgroup_id(peer_sk);
+
+	acgid = bpf_skb_ancestor_cgroup_id(skb, 2);
+	peer_acgid = bpf_sk_ancestor_cgroup_id(peer_sk, 2);
+
+	bpf_sk_release(peer_sk);
+
+	return cgid && cgid == peer_cgid && acgid && acgid == peer_acgid;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress_lookup(struct __sk_buff *skb)
+{
+	__u32 serv_port_key = 0;
+	struct ipv6hdr ip6h;
+	struct tcphdr tcph;
+
+	if (skb->protocol != bpf_htons(ETH_P_IPV6))
+		return 1;
+
+	/* For SYN packets coming to listening socket skb->remote_port will be
+	 * zero, so IPv6/TCP headers are loaded to identify remote peer
+	 * instead.
+	 */
+	if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h)))
+		return 1;
+
+	if (ip6h.nexthdr != IPPROTO_TCP)
+		return 1;
+
+	if (bpf_skb_load_bytes(skb, sizeof(ip6h), &tcph, sizeof(tcph)))
+		return 1;
+
+	if (!g_serv_port)
+		return 0;
+
+	if (tcph.dest != g_serv_port)
+		return 1;
+
+	return is_allowed_peer_cg(skb, &ip6h, &tcph);
+}