bpf: add simple bpf tests in the tx path for so_timestamping feature

Only check if we pass those three key points after we enable the
bpf extension for so_timestamping. During each point, we can choose
whether to print the current timestamp.

Signed-off-by: Jason Xing <[email protected]>

tools/testing/selftests/bpf/prog_tests/so_timestamping.c

@@ -0,0 +1,86 @@
+#define _GNU_SOURCE
+#include <sched.h>
+#include <linux/socket.h>
+#include <linux/tls.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+#include "so_timestamping.skel.h"
+
+#define CG_NAME "/so-timestamping-test"
+
+static const char addr4_str[] = "127.0.0.1";
+static const char addr6_str[] = "::1";
+static struct so_timestamping *skel;
+static int cg_fd;
+
+static void test_tcp(int family)
+{
+	struct so_timestamping__bss *bss = skel->bss;
+	char buf[] = "testing testing";
+	int sfd = -1, cfd = -1;
+	int n;
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_OK_FD(sfd, "start_server"))
+		goto out;
+
+	cfd = connect_to_fd(sfd, 0);
+	if (!ASSERT_OK_FD(cfd, "connect_to_fd_server"))
+		goto out;
+
+	n = write(cfd, buf, sizeof(buf));
+	if (!ASSERT_EQ(n, sizeof(buf), "send to server"))
+		goto out;
+
+	ASSERT_EQ(bss->nr_active, 1, "nr_active");
+	ASSERT_EQ(bss->nr_snd, 2, "nr_snd");
+	ASSERT_EQ(bss->nr_sched, 1, "nr_sched");
+	ASSERT_EQ(bss->nr_txsw, 1, "nr_txsw");
+	ASSERT_EQ(bss->nr_ack, 1, "nr_ack");
+
+out:
+	if (sfd >= 0)
+		close(sfd);
+	if (cfd >= 0)
+		close(cfd);
+}
+
+void test_so_timestamping(void)
+{
+	struct netns_obj *ns;
+
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (cg_fd < 0)
+		return;
+
+	ns = netns_new("so_timestamping_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create ns"))
+		return;
+
+	skel = so_timestamping__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skel"))
+		goto done;
+
+	if (!ASSERT_OK(so_timestamping__attach(skel), "attach skel"))
+		goto done;
+
+	skel->links.skops_sockopt =
+		bpf_program__attach_cgroup(skel->progs.skops_sockopt, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.skops_sockopt, "attach cgroup"))
+		goto done;
+
+	test_tcp(AF_INET6);
+	test_tcp(AF_INET);
+
+done:
+	so_timestamping__destroy(skel);
+	netns_free(ns);
+	close(cg_fd);
+}

tools/testing/selftests/bpf/progs/so_timestamping.c

@@ -0,0 +1,299 @@
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#define BPF_PROG_TEST_TCP_HDR_OPTIONS
+#include "test_tcp_hdr_options.h"
+#include <errno.h>
+
+#define SK_BPF_CB_FLAGS 1009
+#define SK_BPF_CB_TX_TIMESTAMPING 1
+
+int nr_active;
+int nr_snd;
+int nr_passive;
+int nr_sched;
+int nr_txsw;
+int nr_ack;
+
+struct sockopt_test {
+	int opt;
+	int new;
+};
+
+static const struct sockopt_test sol_socket_tests[] = {
+	{ .opt = SK_BPF_CB_FLAGS, .new = SK_BPF_CB_TX_TIMESTAMPING, },
+	{ .opt = 0, },
+};
+
+struct loop_ctx {
+	void *ctx;
+	const struct sock *sk;
+};
+
+struct sk_stg {
+	__u64 sendmsg_ns;	/* record ts when sendmsg is called */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct sk_stg);
+} sk_stg_map SEC(".maps");
+
+
+struct delay_info {
+	u64 sendmsg_ns;		/* record ts when sendmsg is called */
+	u32 sched_delay;	/* SCHED_OPT_CB - sendmsg_ns */
+	u32 sw_snd_delay;	/* SW_OPT_CB - SCHED_OPT_CB */
+	u32 ack_delay;		/* ACK_OPT_CB - SW_OPT_CB */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, struct delay_info);
+	__uint(max_entries, 1024);
+} time_map SEC(".maps");
+
+static u64 delay_tolerance_nsec = 10000000000; /* 10 second as an example */
+
+static int bpf_test_sockopt_int(void *ctx, const struct sock *sk,
+				const struct sockopt_test *t,
+				int level)
+{
+	int new, opt, tmp;
+
+	opt = t->opt;
+	new = t->new;
+
+	if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new)))
+		return 1;
+
+	if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) ||
+	    tmp != new)
+		return 1;
+
+	return 0;
+}
+
+static int bpf_test_socket_sockopt(__u32 i, struct loop_ctx *lc)
+{
+	const struct sockopt_test *t;
+
+	if (i >= ARRAY_SIZE(sol_socket_tests))
+		return 1;
+
+	t = &sol_socket_tests[i];
+	if (!t->opt)
+		return 1;
+
+	return bpf_test_sockopt_int(lc->ctx, lc->sk, t, SOL_SOCKET);
+}
+
+static int bpf_test_sockopt(void *ctx, const struct sock *sk)
+{
+	struct loop_ctx lc = { .ctx = ctx, .sk = sk, };
+	int n;
+
+	n = bpf_loop(ARRAY_SIZE(sol_socket_tests), bpf_test_socket_sockopt, &lc, 0);
+	if (n != ARRAY_SIZE(sol_socket_tests))
+		return -1;
+
+	return 0;
+}
+
+static bool bpf_test_access_sockopt(void *ctx)
+{
+	const struct sockopt_test *t;
+	int tmp, ret, i = 0;
+	int level = SOL_SOCKET;
+
+	t = &sol_socket_tests[i];
+
+	for (; t->opt;) {
+		ret = bpf_setsockopt(ctx, level, t->opt, (void *)&t->new, sizeof(t->new));
+		if (ret != -EOPNOTSUPP)
+			return true;
+
+		ret = bpf_getsockopt(ctx, level, t->opt, &tmp, sizeof(tmp));
+		if (ret != -EOPNOTSUPP)
+			return true;
+
+		if (++i >= ARRAY_SIZE(sol_socket_tests))
+			break;
+	}
+
+	return false;
+}
+
+/* Adding a simple test to see if we can get an expected value */
+static bool bpf_test_access_load_hdr_opt(struct bpf_sock_ops *skops)
+{
+	struct tcp_opt reg_opt;
+	int load_flags = 0;
+	int ret;
+
+	reg_opt.kind = TCPOPT_EXP;
+	reg_opt.len = 0;
+	reg_opt.data32 = 0;
+	ret = bpf_load_hdr_opt(skops, &reg_opt, sizeof(reg_opt), load_flags);
+	if (ret != -EOPNOTSUPP)
+		return true;
+
+	return false;
+}
+
+/* Adding a simple test to see if we can get an expected value */
+static bool bpf_test_access_cb_flags_set(struct bpf_sock_ops *skops)
+{
+	int ret;
+
+	ret = bpf_sock_ops_cb_flags_set(skops, 0);
+	if (ret != -EOPNOTSUPP)
+		return true;
+
+	return false;
+}
+
+/* In the timestamping callbacks, we're not allowed to call the following
+ * BPF CALLs for the safety concern. Return false if expected.
+ */
+static int bpf_test_access_bpf_calls(struct bpf_sock_ops *skops,
+				     const struct sock *sk)
+{
+	if (bpf_test_access_sockopt(skops))
+		return true;
+
+	if (bpf_test_access_load_hdr_opt(skops))
+		return true;
+
+	if (bpf_test_access_cb_flags_set(skops))
+		return true;
+
+	return false;
+}
+
+static bool bpf_test_delay(struct bpf_sock_ops *skops, const struct sock *sk)
+{
+	struct bpf_sock_ops_kern *skops_kern;
+	u64 timestamp = bpf_ktime_get_ns();
+	struct skb_shared_info *shinfo;
+	struct delay_info dinfo = {0};
+	struct delay_info *val;
+	struct sk_buff *skb;
+	struct sk_stg *stg;
+	u64 prior_ts, delay;
+	u32 tskey;
+
+	if (bpf_test_access_bpf_calls(skops, sk))
+		return false;
+
+	skops_kern = bpf_cast_to_kern_ctx(skops);
+	skb = skops_kern->skb;
+	shinfo = bpf_core_cast(skb->head + skb->end, struct skb_shared_info);
+	tskey = shinfo->tskey;
+	if (!tskey)
+		return false;
+
+	if (skops->op == BPF_SOCK_OPS_TS_SND_CB) {
+		stg = bpf_sk_storage_get(&sk_stg_map, (void *)sk, 0, 0);
+		if (!stg)
+			return false;
+		dinfo.sendmsg_ns = stg->sendmsg_ns;
+		bpf_map_update_elem(&time_map, &tskey, &dinfo, BPF_ANY);
+		goto out;
+	}
+
+	val = bpf_map_lookup_elem(&time_map, &tskey);
+	if (!val)
+		return false;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_TS_SCHED_OPT_CB:
+		delay = val->sched_delay = timestamp - val->sendmsg_ns;
+		break;
+	case BPF_SOCK_OPS_TS_SW_OPT_CB:
+		prior_ts = val->sched_delay + val->sendmsg_ns;
+		delay = val->sw_snd_delay = timestamp - prior_ts;
+		break;
+	case BPF_SOCK_OPS_TS_ACK_OPT_CB:
+		prior_ts = val->sw_snd_delay + val->sched_delay + val->sendmsg_ns;
+		delay = val->ack_delay = timestamp - prior_ts;
+		break;
+	}
+
+	if (delay >= delay_tolerance_nsec)
+		return false;
+
+	/* Since it's the last one, remove from the map after latency check */
+	if (skops->op == BPF_SOCK_OPS_TS_ACK_OPT_CB)
+		bpf_map_delete_elem(&time_map, &tskey);
+
+out:
+	return true;
+}
+
+SEC("fentry/tcp_sendmsg_locked")
+int BPF_PROG(trace_tcp_sendmsg_locked, struct sock *sk, struct msghdr *msg, size_t size)
+{
+	u64 timestamp = bpf_ktime_get_ns();
+	u32 flag = sk->sk_bpf_cb_flags;
+	struct sk_stg *stg;
+
+	if (!flag)
+		return 0;
+
+	stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+				 BPF_SK_STORAGE_GET_F_CREATE);
+	if (!stg)
+		return 0;
+
+	stg->sendmsg_ns = timestamp;
+	nr_snd += 1;
+	return 0;
+}
+
+SEC("sockops")
+int skops_sockopt(struct bpf_sock_ops *skops)
+{
+	struct bpf_sock *bpf_sk = skops->sk;
+	const struct sock *sk;
+
+	if (!bpf_sk)
+		return 1;
+
+	sk = (struct sock *)bpf_skc_to_tcp_sock(bpf_sk);
+	if (!sk)
+		return 1;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		nr_active += !bpf_test_sockopt(skops, sk);
+		break;
+	case BPF_SOCK_OPS_TS_SND_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_snd += 1;
+		break;
+	case BPF_SOCK_OPS_TS_SCHED_OPT_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_sched += 1;
+		break;
+	case BPF_SOCK_OPS_TS_SW_OPT_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_txsw += 1;
+		break;
+	case BPF_SOCK_OPS_TS_ACK_OPT_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_ack += 1;
+		break;
+	}
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";