selftests/bpf: Add bpf_stale scheduler & test

This patch implements the setting a subflow as stale/unstale in BPF MPTCP
scheduler, named bpf_stale. The staled subflow id will be added into a
map in sk_storage.

Two helper mptcp_subflow_set_stale() and mptcp_subflow_clear_stale() are
added.

In this test, subflow 1 is set as stale in bpf_stale_data_init(). Each
subflow is checked whether it's a stale one in bpf_stale_get_subflow() to
select a unstale subflow to send data.

This patch adds the bpf_stale scheduler test: test_stale(). Use sysctl to
set net.mptcp.scheduler to use this sched. Add two veth net devices to
simulate the multiple addresses case. Use 'ip mptcp endpoint' command to
add the new endpoint ADDR_2 to PM netlink. Send data and check bytes_sent
of 'ss' output after it to make sure the data has been only sent on ADDR_1
since ADDR_2 is set as stale.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>

3 files changed, 161 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 2200e2cb1fd692..6658533728aa40 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -240,6 +240,7 @@ struct mptcp_subflow_context {
 	unsigned long avg_pacing_rate;
 	__u32	backup : 1;
 	__u8	stale_count;
+	__u32	subflow_id;
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 } __attribute__((preserve_access_index));
 
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index c94418b4cda6a2..1a43e9ed1fa27a 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -15,6 +15,7 @@
 #include "mptcp_bpf_rr.skel.h"
 #include "mptcp_bpf_red.skel.h"
 #include "mptcp_bpf_burst.skel.h"
+#include "mptcp_bpf_stale.skel.h"
 
 #define NS_TEST "mptcp_ns"
 #define ADDR_1	"10.0.1.1"
@@ -602,6 +603,7 @@ MPTCP_SCHED_TEST(bkup, WITH_DATA, WITHOUT_DATA);
 MPTCP_SCHED_TEST(rr, WITH_DATA, WITH_DATA);
 MPTCP_SCHED_TEST(red, WITH_DATA, WITH_DATA);
 MPTCP_SCHED_TEST(burst, WITH_DATA, WITH_DATA);
+MPTCP_SCHED_TEST(stale, WITH_DATA, WITHOUT_DATA);
 
 #define RUN_MPTCP_TEST(suffix)					\
 do {								\
@@ -620,4 +622,5 @@ void test_mptcp(void)
 	RUN_MPTCP_TEST(rr);
 	RUN_MPTCP_TEST(red);
 	RUN_MPTCP_TEST(burst);
+	RUN_MPTCP_TEST(stale);
 }
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c
new file mode 100644
index 00000000000000..89533d5577a137
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_stale.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023, SUSE. */
+/* Copyright (c) 2024, Kylin Software */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct mptcp_stale_storage {
+	__u8 nr;
+	__u32 ids[MPTCP_SUBFLOWS_MAX];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct mptcp_stale_storage);
+} mptcp_stale_map SEC(".maps");
+
+static void mptcp_subflow_set_stale(struct mptcp_stale_storage *storage,
+				    __u32 subflow_id)
+{
+	if (!subflow_id)
+		return;
+
+	for (int i = 0; i < storage->nr && i < MPTCP_SUBFLOWS_MAX; i++) {
+		if (storage->ids[i] == subflow_id)
+			return;
+	}
+
+	if (storage->nr < MPTCP_SUBFLOWS_MAX - 1)
+		storage->ids[storage->nr++] = subflow_id;
+}
+
+static void mptcp_subflow_clear_stale(struct mptcp_stale_storage *storage,
+				      __u32 subflow_id)
+{
+	if (!subflow_id)
+		return;
+
+	for (int i = 0; i < storage->nr && i < MPTCP_SUBFLOWS_MAX; i++) {
+		if (storage->ids[i] == subflow_id) {
+			for (int j = i; j < MPTCP_SUBFLOWS_MAX - 1; j++) {
+				if (!storage->ids[j + 1])
+					break;
+				storage->ids[j] = storage->ids[j + 1];
+				storage->ids[j + 1] = 0;
+			}
+			storage->nr--;
+			return;
+		}
+	}
+}
+
+static bool mptcp_subflow_is_stale(struct mptcp_stale_storage *storage,
+				   __u32 subflow_id)
+{
+	for (int i = 0; i < storage->nr && i < MPTCP_SUBFLOWS_MAX; i++) {
+		if (storage->ids[i] == subflow_id)
+			return true;
+	}
+
+	return false;
+}
+
+static bool mptcp_subflow_is_active(struct mptcp_sched_data *data,
+				    __u32 subflow_id)
+{
+	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
+		struct mptcp_subflow_context *subflow;
+
+		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
+		if (!subflow)
+			break;
+		if (subflow->subflow_id == subflow_id)
+			return true;
+	}
+
+	return false;
+}
+
+SEC("struct_ops/mptcp_sched_stale_init")
+void BPF_PROG(mptcp_sched_stale_init, struct mptcp_sock *msk)
+{
+	struct mptcp_stale_storage *storage;
+
+	storage = bpf_sk_storage_get(&mptcp_stale_map, msk, 0,
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!storage)
+		return;
+
+	for (int i = 0; i < MPTCP_SUBFLOWS_MAX; i++)
+		storage->ids[i] = 0;
+	storage->nr = 0;
+
+	mptcp_subflow_set_stale(storage, 2);
+	mptcp_subflow_set_stale(storage, 3);
+}
+
+SEC("struct_ops/mptcp_sched_stale_release")
+void BPF_PROG(mptcp_sched_stale_release, struct mptcp_sock *msk)
+{
+	bpf_sk_storage_delete(&mptcp_stale_map, msk);
+}
+
+int BPF_STRUCT_OPS(bpf_stale_get_subflow, struct mptcp_sock *msk,
+		   struct mptcp_sched_data *data)
+{
+	struct mptcp_stale_storage *storage;
+	int nr = -1, i;
+
+	if (data->subflows == 1) {
+		mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, 0), true);
+		return 0;
+	}
+
+	storage = bpf_sk_storage_get(&mptcp_stale_map, msk, 0, 0);
+	if (!storage)
+		return -1;
+
+	/* Handle invalid subflow ids for subflows that have been closed */
+	if (data->subflows < storage->nr + 1) {
+		for (i = 0; i < storage->nr && i < MPTCP_SUBFLOWS_MAX; i++) {
+			if (!mptcp_subflow_is_active(data, storage->ids[i]))
+				mptcp_subflow_clear_stale(storage, storage->ids[i]);
+		}
+	}
+
+	for (i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
+		struct mptcp_subflow_context *subflow;
+
+		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
+		if (!subflow)
+			break;
+
+		if (mptcp_subflow_is_stale(storage, subflow->subflow_id))
+			continue;
+
+		nr = i;
+	}
+
+	if (nr != -1) {
+		mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, nr), true);
+		return -1;
+	}
+	return 0;
+}
+
+SEC(".struct_ops")
+struct mptcp_sched_ops stale = {
+	.init		= (void *)mptcp_sched_stale_init,
+	.release	= (void *)mptcp_sched_stale_release,
+	.get_subflow	= (void *)bpf_stale_get_subflow,
+	.name		= "bpf_stale",
+};