Merge branch 'bpf-tcp-rtt-hook'

Stanislav Fomichev says:

====================
Congestion control team would like to have a periodic callback to
track some TCP statistics. Let's add a sock_ops callback that can be
selectively enabled on a socket by socket basis and is executed for
every RTT. BPF program frequency can be further controlled by calling
bpf_ktime_get_ns and bailing out early.

I run neper tcp_stream and tcp_rr tests with the sample program
from the last patch and didn't observe any noticeable performance
difference.

v2:
* add a comment about second accept() in selftest (Yonghong Song)
* refer to tcp_bpf.readme in sample program (Yonghong Song)
====================

Suggested-by: Eric Dumazet <edumazet@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Priyaranjan Jha <priyarjha@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

3 files changed, 70 insertions, 1 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 35640414ebb3..f90daadfbc89 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -154,6 +154,7 @@ always += tcp_iw_kern.o
 always += tcp_clamp_kern.o
 always += tcp_basertt_kern.o
 always += tcp_tos_reflect_kern.o
+always += tcp_dumpstats_kern.o
 always += xdp_redirect_kern.o
 always += xdp_redirect_map_kern.o
 always += xdp_redirect_cpu_kern.o
diff --git a/samples/bpf/tcp_bpf.readme b/samples/bpf/tcp_bpf.readme
index fee746621aec..78e247f62108 100644
--- a/samples/bpf/tcp_bpf.readme
+++ b/samples/bpf/tcp_bpf.readme
@@ -25,4 +25,4 @@ attached to the cgroupv2).
 
 To remove (unattach) a socket_ops BPF program from a cgroupv2:
 
-  bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog
+  bpftool cgroup detach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog
diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c
new file mode 100644
index 000000000000..8557913106a0
--- /dev/null
+++ b/samples/bpf/tcp_dumpstats_kern.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Refer to samples/bpf/tcp_bpf.readme for the instructions on
+ * how to run this sample program.
+ */
+#include <linux/bpf.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define INTERVAL			1000000000ULL
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__u32 type;
+	__u32 map_flags;
+	int *key;
+	__u64 *value;
+} bpf_next_dump SEC(".maps") = {
+	.type = BPF_MAP_TYPE_SK_STORAGE,
+	.map_flags = BPF_F_NO_PREALLOC,
+};
+
+SEC("sockops")
+int _sockops(struct bpf_sock_ops *ctx)
+{
+	struct bpf_tcp_sock *tcp_sk;
+	struct bpf_sock *sk;
+	__u64 *next_dump;
+	__u64 now;
+
+	switch (ctx->op) {
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG);
+		return 1;
+	case BPF_SOCK_OPS_RTT_CB:
+		break;
+	default:
+		return 1;
+	}
+
+	sk = ctx->sk;
+	if (!sk)
+		return 1;
+
+	next_dump = bpf_sk_storage_get(&bpf_next_dump, sk, 0,
+				       BPF_SK_STORAGE_GET_F_CREATE);
+	if (!next_dump)
+		return 1;
+
+	now = bpf_ktime_get_ns();
+	if (now < *next_dump)
+		return 1;
+
+	tcp_sk = bpf_tcp_sock(sk);
+	if (!tcp_sk)
+		return 1;
+
+	*next_dump = now + INTERVAL;
+
+	bpf_printk("dsack_dups=%u delivered=%u\n",
+		   tcp_sk->dsack_dups, tcp_sk->delivered);
+	bpf_printk("delivered_ce=%u icsk_retransmits=%u\n",
+		   tcp_sk->delivered_ce, tcp_sk->icsk_retransmits);
+
+	return 1;
+}