selftests/bpf: cgroup local storage-based network counters

This commit adds a bpf kselftest, which demonstrates how percpu
and shared cgroup local storage can be used for efficient lookup-free
network accounting.

Cgroup local storage provides generic memory area with a very efficient
lookup free access. To avoid expensive atomic operations for each
packet, per-cpu cgroup local storage is used. Each packet is initially
charged to a per-cpu counter, and only if the counter reaches certain
value (32 in this case), the charge is moved into the global atomic
counter. This allows to amortize atomic operations, keeping reasonable
accuracy.

The test also implements a naive network traffic throttling, mostly to
demonstrate the possibility of bpf cgroup--based network bandwidth
control.

Expected output:
  ./test_netcnt
  test_netcnt:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 71 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
new file mode 100644
index 000000000000..1198abca1360
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_prog.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/version.h>
+
+#include "bpf_helpers.h"
+#include "netcnt_common.h"
+
+#define MAX_BPS	(3 * 1024 * 1024)
+
+#define REFRESH_TIME_NS	100000000
+#define NS_PER_SEC	1000000000
+
+struct bpf_map_def SEC("maps") percpu_netcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct percpu_net_cnt),
+};
+
+struct bpf_map_def SEC("maps") netcnt = {
+	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct net_cnt),
+};
+
+SEC("cgroup/skb")
+int bpf_nextcnt(struct __sk_buff *skb)
+{
+	struct percpu_net_cnt *percpu_cnt;
+	char fmt[] = "%d %llu %llu\n";
+	struct net_cnt *cnt;
+	__u64 ts, dt;
+	int ret;
+
+	cnt = bpf_get_local_storage(&netcnt, 0);
+	percpu_cnt = bpf_get_local_storage(&percpu_netcnt, 0);
+
+	percpu_cnt->packets++;
+	percpu_cnt->bytes += skb->len;
+
+	if (percpu_cnt->packets > MAX_PERCPU_PACKETS) {
+		__sync_fetch_and_add(&cnt->packets,
+				     percpu_cnt->packets);
+		percpu_cnt->packets = 0;
+
+		__sync_fetch_and_add(&cnt->bytes,
+				     percpu_cnt->bytes);
+		percpu_cnt->bytes = 0;
+	}
+
+	ts = bpf_ktime_get_ns();
+	dt = ts - percpu_cnt->prev_ts;
+
+	dt *= MAX_BPS;
+	dt /= NS_PER_SEC;
+
+	if (cnt->bytes + percpu_cnt->bytes - percpu_cnt->prev_bytes < dt)
+		ret = 1;
+	else
+		ret = 0;
+
+	if (dt > REFRESH_TIME_NS) {
+		percpu_cnt->prev_ts = ts;
+		percpu_cnt->prev_packets = cnt->packets;
+		percpu_cnt->prev_bytes = cnt->bytes;
+	}
+
+	return !!ret;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = LINUX_VERSION_CODE;