selftests/bpf: Test concurrent updates on bpf_task_storage_busy

Under full preemptible kernel, task local storage lookup operations on
the same CPU may update per-cpu bpf_task_storage_busy concurrently. If
the update of bpf_task_storage_busy is not preemption safe, the final
value of bpf_task_storage_busy may become not-zero forever and
bpf_task_storage_trylock() will always fail. So add a test case to
ensure the update of bpf_task_storage_busy is preemption safe.

Will skip the test case when CONFIG_PREEMPT is disabled, and it can only
reproduce the problem probabilistically. By increasing
TASK_STORAGE_MAP_NR_LOOP and running it under ARM64 VM with 4-cpus, it
takes about four rounds to reproduce:

> test_maps is modified to only run test_task_storage_map_stress_lookup()
$ export TASK_STORAGE_MAP_NR_THREAD=256
$ export TASK_STORAGE_MAP_NR_LOOP=81920
$ export TASK_STORAGE_MAP_PIN_CPU=1
$ time ./test_maps
test_task_storage_map_stress_lookup(135):FAIL:bad bpf_task_storage_busy got -2

real    0m24.743s
user    0m6.772s
sys     0m17.966s

Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/r/20220901061938.3789460-5-houtao@huaweicloud.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

2 files changed, 161 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/map_tests/task_storage_map.c b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
new file mode 100644
index 000000000000..1adc9c292eb2
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <string.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "test_maps.h"
+#include "task_local_storage_helpers.h"
+#include "read_bpf_task_storage_busy.skel.h"
+
+struct lookup_ctx {
+	bool start;
+	bool stop;
+	int pid_fd;
+	int map_fd;
+	int loop;
+};
+
+static void *lookup_fn(void *arg)
+{
+	struct lookup_ctx *ctx = arg;
+	long value;
+	int i = 0;
+
+	while (!ctx->start)
+		usleep(1);
+
+	while (!ctx->stop && i++ < ctx->loop)
+		bpf_map_lookup_elem(ctx->map_fd, &ctx->pid_fd, &value);
+	return NULL;
+}
+
+static void abort_lookup(struct lookup_ctx *ctx, pthread_t *tids, unsigned int nr)
+{
+	unsigned int i;
+
+	ctx->stop = true;
+	ctx->start = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+}
+
+void test_task_storage_map_stress_lookup(void)
+{
+#define MAX_NR_THREAD 4096
+	unsigned int i, nr = 256, loop = 8192, cpu = 0;
+	struct read_bpf_task_storage_busy *skel;
+	pthread_t tids[MAX_NR_THREAD];
+	struct lookup_ctx ctx;
+	cpu_set_t old, new;
+	const char *cfg;
+	int err;
+
+	cfg = getenv("TASK_STORAGE_MAP_NR_THREAD");
+	if (cfg) {
+		nr = atoi(cfg);
+		if (nr > MAX_NR_THREAD)
+			nr = MAX_NR_THREAD;
+	}
+	cfg = getenv("TASK_STORAGE_MAP_NR_LOOP");
+	if (cfg)
+		loop = atoi(cfg);
+	cfg = getenv("TASK_STORAGE_MAP_PIN_CPU");
+	if (cfg)
+		cpu = atoi(cfg);
+
+	skel = read_bpf_task_storage_busy__open_and_load();
+	err = libbpf_get_error(skel);
+	CHECK(err, "open_and_load", "error %d\n", err);
+
+	/* Only for a fully preemptible kernel */
+	if (!skel->kconfig->CONFIG_PREEMPT)
+		return;
+
+	/* Save the old affinity setting */
+	sched_getaffinity(getpid(), sizeof(old), &old);
+
+	/* Pinned on a specific CPU */
+	CPU_ZERO(&new);
+	CPU_SET(cpu, &new);
+	sched_setaffinity(getpid(), sizeof(new), &new);
+
+	ctx.start = false;
+	ctx.stop = false;
+	ctx.pid_fd = sys_pidfd_open(getpid(), 0);
+	ctx.map_fd = bpf_map__fd(skel->maps.task);
+	ctx.loop = loop;
+	for (i = 0; i < nr; i++) {
+		err = pthread_create(&tids[i], NULL, lookup_fn, &ctx);
+		if (err) {
+			abort_lookup(&ctx, tids, i);
+			CHECK(err, "pthread_create", "error %d\n", err);
+			goto out;
+		}
+	}
+
+	ctx.start = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+
+	skel->bss->pid = getpid();
+	err = read_bpf_task_storage_busy__attach(skel);
+	CHECK(err, "attach", "error %d\n", err);
+
+	/* Trigger program */
+	syscall(SYS_gettid);
+	skel->bss->pid = 0;
+
+	CHECK(skel->bss->busy != 0, "bad bpf_task_storage_busy", "got %d\n", skel->bss->busy);
+out:
+	read_bpf_task_storage_busy__destroy(skel);
+	/* Restore affinity setting */
+	sched_setaffinity(getpid(), sizeof(old), &old);
+}
diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
new file mode 100644
index 000000000000..a47bb0120719
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022. Huawei Technologies Co., Ltd */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern bool CONFIG_PREEMPT __kconfig __weak;
+extern const int bpf_task_storage_busy __ksym;
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+int busy = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, long);
+} task SEC(".maps");
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(read_bpf_task_storage_busy)
+{
+	int *value;
+	int key;
+
+	if (!CONFIG_PREEMPT)
+		return 0;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	value = bpf_this_cpu_ptr(&bpf_task_storage_busy);
+	if (value)
+		busy = *value;
+
+	return 0;
+}