[RFC PATCH bpf-next v4 4/4] selftests/bpf: add tests for the numab kfuncs

[Yafang Shao]

Exercise the bpf_numab_set_mode() and bpf_numab_get_mode() kfuncs
through BPF_PROG_TYPE_SYSCALL programs: the set/get roundtrip, the
mode domain (NUMAB_FOLLOW_SYSTEM and the NUMA_BALANCING_* bitmasks
accepted, anything else rejected with -EINVAL), unknown cgroup ids
rejected with -ENOENT, and the hierarchy combination the memcg walk
produces (inheritance, OR-ing, and an opt-out winning over every
request in the chain). Also verify the memory-controller requirement:
setting on a cgroup without a memcg is rejected with -EOPNOTSUPP,
while bpf_numab_get_mode() resolves it to the nearest ancestor memcg.

Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
---
 tools/testing/selftests/bpf/config            |   2 +
 .../selftests/bpf/prog_tests/bpf_numab.c      | 273 ++++++++++++++++++
 tools/testing/selftests/bpf/progs/bpf_numab.c |  32 ++
 3 files changed, 307 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/bpf_numab.c
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_numab.c

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 49dfe939467c..e56c8872e51a 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -7,6 +7,7 @@ CONFIG_BPF_JIT=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_BPF_LIRC_MODE2=y
 CONFIG_BPF_LSM=y
+CONFIG_BPF_NUMAB=y
 CONFIG_BPF_STREAM_PARSER=y
 CONFIG_BPF_SYSCALL=y
 # CONFIG_BPF_UNPRIV_DEFAULT_OFF is not set
@@ -78,6 +79,7 @@ CONFIG_NET_CLS_FLOWER=y
 CONFIG_NET_CLS_MATCHALL=y
 CONFIG_NET_FOU=y
 CONFIG_NET_FOU_IP_TUNNELS=y
+CONFIG_NUMA_BALANCING=y
 CONFIG_NET_IPGRE=y
 CONFIG_NET_IPGRE_DEMUX=y
 CONFIG_NET_IPIP=y
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_numab.c b/tools/testing/selftests/bpf/prog_tests/bpf_numab.c
new file mode 100644
index 000000000000..6fb6a4d9f291
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_numab.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "bpf_numab.skel.h"
+
+#define CGROUP_PATH	"/bpf_numab"
+#define CHILD_PATH	CGROUP_PATH "/child"
+#define HIER_PATH	"/bpf_numab_hier"
+#define HIER_CHILD_PATH	HIER_PATH "/child"
+#define NOMEM_PATH	"/bpf_numab_nomem"
+#define NOMEM_CHILD_PATH NOMEM_PATH "/child"
+
+/* The per-cgroup request domain, mirroring the kernel constants. */
+#define NUMAB_FOLLOW_SYSTEM	(-1)
+#define NUMAB_DISABLED		0
+#define NUMAB_NORMAL		1
+#define NUMAB_TIERING		2
+#define NUMAB_NORMAL_TIERING	3
+
+static int numab_set(struct bpf_numab *skel, u64 cgid,
+		     long mode)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	int ret;
+
+	skel->bss->set_cgid = cgid;
+	skel->bss->set_mode = mode;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.numab_set),
+				     &opts);
+	if (!ASSERT_OK(ret, "set run"))
+		return -1;
+	return skel->bss->set_ret;
+}
+
+static long numab_get(struct bpf_numab *skel, u64 cgid)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	int ret;
+
+	skel->bss->get_cgid = cgid;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.numab_get),
+				     &opts);
+	if (!ASSERT_OK(ret, "get run"))
+		return -EIO;
+	return skel->bss->get_mode;
+}
+
+static void test_set_get(void)
+{
+	struct bpf_numab *skel;
+	int cgroup_fd;
+	u64 cgid;
+
+	cgroup_fd = test__join_cgroup(CGROUP_PATH);
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		return;
+
+	skel = bpf_numab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	cgid = get_cgroup_id(CGROUP_PATH);
+	if (!ASSERT_GT(cgid, 0, "get_cgroup_id"))
+		goto cleanup;
+
+	ASSERT_EQ(numab_set(skel, cgid, NUMAB_NORMAL), 0, "set normal");
+	ASSERT_EQ(numab_get(skel, cgid), NUMAB_NORMAL, "get normal");
+
+	ASSERT_EQ(numab_set(skel, cgid, NUMAB_TIERING), 0, "set tiering");
+	ASSERT_EQ(numab_get(skel, cgid), NUMAB_TIERING, "get tiering");
+
+	ASSERT_EQ(numab_set(skel, cgid, NUMAB_NORMAL_TIERING), 0, "set both");
+	ASSERT_EQ(numab_get(skel, cgid), NUMAB_NORMAL_TIERING, "get both");
+
+	ASSERT_EQ(numab_set(skel, cgid, NUMAB_DISABLED), 0, "set disabled");
+	ASSERT_EQ(numab_get(skel, cgid), NUMAB_DISABLED, "get disabled");
+
+	/* Back to the system setting. */
+	ASSERT_EQ(numab_set(skel, cgid, NUMAB_FOLLOW_SYSTEM), 0, "unset");
+	ASSERT_EQ(numab_get(skel, cgid), NUMAB_FOLLOW_SYSTEM, "get unset");
+
+cleanup:
+	bpf_numab__destroy(skel);
+	close(cgroup_fd);
+}
+
+static void test_invalid_mode(void)
+{
+	struct bpf_numab *skel;
+	int cgroup_fd;
+	u64 cgid;
+
+	cgroup_fd = test__join_cgroup(CGROUP_PATH);
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		return;
+
+	skel = bpf_numab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	cgid = get_cgroup_id(CGROUP_PATH);
+	if (!ASSERT_GT(cgid, 0, "get_cgroup_id"))
+		goto cleanup;
+
+	ASSERT_EQ(numab_set(skel, cgid, -2), -EINVAL, "set below domain");
+	ASSERT_EQ(numab_set(skel, cgid, 4), -EINVAL, "set above domain");
+	ASSERT_EQ(numab_set(skel, cgid, 0x1000), -EINVAL, "set far above");
+
+	/* The rejected requests must not have stuck. */
+	ASSERT_EQ(numab_get(skel, cgid), NUMAB_FOLLOW_SYSTEM, "get unchanged");
+
+cleanup:
+	bpf_numab__destroy(skel);
+	close(cgroup_fd);
+}
+
+static void test_bad_cgid(void)
+{
+	struct bpf_numab *skel;
+
+	skel = bpf_numab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	ASSERT_EQ(numab_set(skel, 0, NUMAB_NORMAL), -ENOENT, "set cgid 0");
+	ASSERT_EQ(numab_get(skel, 0), -ENOENT, "get cgid 0");
+	ASSERT_EQ(numab_set(skel, 0xdeadbeef, NUMAB_NORMAL), -ENOENT,
+		  "set bad cgid");
+	ASSERT_EQ(numab_get(skel, 0xdeadbeef), -ENOENT, "get bad cgid");
+
+	bpf_numab__destroy(skel);
+}
+
+static void test_hierarchy(void)
+{
+	u64 parent_cgid, child_cgid;
+	int runner_fd, parent_fd, child_fd;
+	struct bpf_numab *skel;
+
+	runner_fd = test__join_cgroup("/bpf_numab_runner");
+	if (!ASSERT_GE(runner_fd, 0, "join_runner_cgroup"))
+		return;
+
+	parent_fd = create_and_get_cgroup(HIER_PATH);
+	if (!ASSERT_GE(parent_fd, 0, "create_parent_cgroup"))
+		goto cleanup_runner;
+
+	if (!ASSERT_OK(enable_controllers(HIER_PATH, "memory"),
+		       "enable_memory_controller"))
+		goto cleanup_parent;
+
+	child_fd = create_and_get_cgroup(HIER_CHILD_PATH);
+	if (!ASSERT_GE(child_fd, 0, "create_child_cgroup"))
+		goto cleanup_parent;
+
+	skel = bpf_numab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	parent_cgid = get_cgroup_id(HIER_PATH);
+	child_cgid = get_cgroup_id(HIER_CHILD_PATH);
+	if (!ASSERT_GT(parent_cgid, 0, "get_parent_cgid") ||
+	    !ASSERT_GT(child_cgid, 0, "get_child_cgid"))
+		goto cleanup;
+
+	/* The child inherits an ancestor's request untouched. */
+	ASSERT_EQ(numab_set(skel, parent_cgid, NUMAB_TIERING), 0,
+		  "set parent tiering");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_TIERING,
+		  "child inherits");
+
+	/* A request ORs with the ancestor's; NORMAL does not undo TIERING. */
+	ASSERT_EQ(numab_set(skel, child_cgid, NUMAB_NORMAL), 0,
+		  "set child normal");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_NORMAL_TIERING,
+		  "or both");
+
+	/* The child's own opt-out wins. */
+	ASSERT_EQ(numab_set(skel, child_cgid, NUMAB_DISABLED), 0,
+		  "set child disabled");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_DISABLED,
+		  "own opt-out wins");
+
+	/* So does an ancestor's: a task is never forced into balancing. */
+	ASSERT_EQ(numab_set(skel, child_cgid, NUMAB_TIERING), 0,
+		  "set child tiering");
+	ASSERT_EQ(numab_set(skel, parent_cgid, NUMAB_DISABLED), 0,
+		  "set parent disabled");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_DISABLED,
+		  "ancestor opt-out wins");
+
+	/* Unsetting the parent re-exposes the child's own request. */
+	ASSERT_EQ(numab_set(skel, parent_cgid, NUMAB_FOLLOW_SYSTEM), 0,
+		  "unset parent");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_TIERING,
+		  "child request again");
+
+	/* Unsetting the child leaves the chain with no request. */
+	ASSERT_EQ(numab_set(skel, child_cgid, NUMAB_FOLLOW_SYSTEM), 0,
+		  "unset child");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_FOLLOW_SYSTEM,
+		  "no request");
+
+cleanup:
+	bpf_numab__destroy(skel);
+	close(child_fd);
+	remove_cgroup(HIER_CHILD_PATH);
+cleanup_parent:
+	close(parent_fd);
+	remove_cgroup(HIER_PATH);
+cleanup_runner:
+	close(runner_fd);
+}
+
+static void test_no_memcg(void)
+{
+	struct bpf_numab *skel;
+	int parent_fd, child_fd;
+	u64 parent_cgid, child_cgid;
+
+	parent_fd = test__join_cgroup(NOMEM_PATH);
+	if (!ASSERT_GE(parent_fd, 0, "join_nomem_parent"))
+		return;
+
+	child_fd = create_and_get_cgroup(NOMEM_CHILD_PATH);
+	if (!ASSERT_GE(child_fd, 0, "create_nomem_child"))
+		goto cleanup_parent;
+
+	skel = bpf_numab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	parent_cgid = get_cgroup_id(NOMEM_PATH);
+	child_cgid = get_cgroup_id(NOMEM_CHILD_PATH);
+	if (!ASSERT_GT(parent_cgid, 0, "get_nomem_parent_cgid") ||
+	    !ASSERT_GT(child_cgid, 0, "get_nomem_child_cgid"))
+		goto cleanup;
+
+	/*
+	 * The parent has a memcg; the child was created without enabling
+	 * the memory controller in the parent's subtree, so it has none.
+	 */
+	ASSERT_EQ(numab_set(skel, parent_cgid, NUMAB_NORMAL), 0,
+		  "set parent normal");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_NORMAL,
+		  "child resolves to parent memcg");
+	ASSERT_EQ(numab_set(skel, child_cgid, NUMAB_TIERING), -EOPNOTSUPP,
+		  "child set rejected");
+	ASSERT_EQ(numab_get(skel, child_cgid), NUMAB_NORMAL,
+		  "child get unchanged");
+
+cleanup:
+	bpf_numab__destroy(skel);
+	close(child_fd);
+	remove_cgroup(NOMEM_CHILD_PATH);
+cleanup_parent:
+	close(parent_fd);
+}
+
+void test_bpf_numab(void)
+{
+	if (test__start_subtest("set_get"))
+		test_set_get();
+	if (test__start_subtest("invalid_mode"))
+		test_invalid_mode();
+	if (test__start_subtest("bad_cgid"))
+		test_bad_cgid();
+	if (test__start_subtest("hierarchy"))
+		test_hierarchy();
+	if (test__start_subtest("no_memcg"))
+		test_no_memcg();
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_numab.c b/tools/testing/selftests/bpf/progs/bpf_numab.c
new file mode 100644
index 000000000000..25da97bce82f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_numab.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+/* Inputs, set from userspace before each run. */
+u64 set_cgid;
+long set_mode;
+u64 get_cgid;
+
+/* Results, read back after each run. */
+long set_ret;
+long get_mode;
+
+extern int bpf_numab_set_mode(u64 cgid, enum numab_mode mode) __ksym;
+extern s64 bpf_numab_get_mode(u64 cgid) __ksym;
+
+SEC("syscall")
+int numab_set(void *ctx)
+{
+	set_ret = bpf_numab_set_mode(set_cgid, (enum numab_mode)set_mode);
+	return 0;
+}
+
+SEC("syscall")
+int numab_get(void *ctx)
+{
+	get_mode = bpf_numab_get_mode(get_cgid);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
2.52.0