Perf-based event notification for sock_ops

This patchset uses eBPF perf-event based notification mechanism to solve the problem described in
https://marc.info/?l=linux-netdev&m=154022219423571&w=2.
Thanks to Daniel Borkmann for feedback/input.

V2: inlined the call to sys_perf_event_open() following the style
of existing code in kselftests/bpf

The problem statement is
We would like to monitor some subset of TCP sockets in user-space, (the monitoring application would define 4-tuples it wants to monitor) using TCP_INFO stats to analyze reported problems. The idea is to use those stats to see where the bottlenecks are likely to be ("is it application-limited?" or "is there evidence of BufferBloat in the path?" etc)

Today we can do this by periodically polling for tcp_info, but this could be made more efficient if the kernel would asynchronously notify the application via tcp_info when some "interesting" thresholds (e.g., "RTT variance > X", or "total_retrans > Y" etc) are reached. And to make this effective, it is better if we could apply the threshold check *before* constructing the tcp_info netlink notification, so that we don't waste resources constructing notifications that will be discarded by the filter.

This patchset solves the problem by adding perf-event based notification support for sock_ops (Patch1). The eBPF kernel module can thus be designed to apply any desired filters to the bpf_sock_ops and trigger a perf-event notification based on the verdict from the filter. The uspace component can use these perf-event notifications to either read any state managed by the eBPF kernel module, or issue a TCP_INFO netlink call if desired.

Patch 2 provides a simple example that shows how to use this infra (and also provides a test case for it)

Sowmini Varadhan (2):
bpf: add perf-event notificaton support for sock_ops selftests/bpf: add a test case for sock_ops perf-event notification

 net/core/filter.c                                 |   19 ++
 tools/testing/selftests/bpf/Makefile              |    4 +-
 tools/testing/selftests/bpf/test_tcpnotify.h      |   19 ++
 tools/testing/selftests/bpf/test_tcpnotify_kern.c |   95 +++++++++++
 tools/testing/selftests/bpf/test_tcpnotify_user.c |  186 +++++++++++++++++++++
 5 files changed, 322 insertions(+), 1 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify.h
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_kern.c
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_user.c

This patch allows eBPF programs that use sock_ops to send perf-based event notifications using bpf_perf_event_output()

---
 net/core/filter.c |   19 +++++++++++++++++++
 1 files changed, 19 insertions(+), 0 deletions(-)

index e521c5e..23464a3 100644
@@ -4048,6 +4048,23 @@ static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
 	return ret;
 }
 
+BPF_CALL_5(bpf_sock_opts_event_output, struct bpf_sock_ops *, skops,
+	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
+}
+
+static const struct bpf_func_proto bpf_sock_ops_event_output_proto =  {
+	.func		= bpf_sock_opts_event_output,
+	.gpl_only       = true,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+};
+
 static const struct bpf_func_proto bpf_setsockopt_proto = {
 	.func		= bpf_setsockopt,
 	.gpl_only	= false,

@@ -5226,6 +5243,8 @@ bool bpf_helper_changes_pkt_data(void *func)
 sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_sock_ops_event_output_proto;
 	case BPF_FUNC_setsockopt:
 		return &bpf_setsockopt_proto;
 	case BPF_FUNC_getsockopt:

1.7.1

This patch provides a tcp_bpf based eBPF sample. The test
- ncat(1) as the TCP client program to connect() to a port with the intention of triggerring SYN retransmissions: we first install an iptables DROP rule to make sure ncat SYNs are resent (instead of aborting instantly after a TCP RST)
- has a bpf kernel module that sends a perf-event notification for each TCP retransmit, and also tracks the number of such notifications sent in the global_map
The test passes when the number of event notifications intercepted in user-space matches the value in the global_map.

---
V2: inline call to sys_perf_event_open() following the style of existing code in kselftests/bpf

 tools/testing/selftests/bpf/Makefile              |    4 +-
 tools/testing/selftests/bpf/test_tcpnotify.h      |   19 ++
 tools/testing/selftests/bpf/test_tcpnotify_kern.c |   95 +++++++++++
 tools/testing/selftests/bpf/test_tcpnotify_user.c |  186 +++++++++++++++++++++
 4 files changed, 303 insertions(+), 1 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify.h
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_kern.c
 create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_user.c

index e39dfb4..6c94048 100644
@@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
 	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
-	test_netcnt
+	test_netcnt test_tcpnotify_user
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
 	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
 	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+	test_tcpnotify_kern.o \
 	sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
 	sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \

@@ -74,6 +75,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
+$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c

new file mode 100644
index 0000000..8b6cea0
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpnotify_globals {
+	__u32 total_retrans;
+	__u32 ncalls;
+};
+
+struct tcp_notifier {
+	__u8    type;
+	__u8    subtype;
+	__u8    source;
+	__u8    hash;
+};
+
+#define	TESTPORT	12877
+#endif

1.7.1