selftests/bpf: Add a test to stress bpf_timer_start and map_delete race

Add a test to stress bpf_timer_start and map_delete race

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20260201025403.66625-10-alexei.starovoitov@gmail.com

Author: Alexei Starovoitov

tools/testing/selftests/bpf/prog_tests/timer_start_delete_race.c

@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <pthread.h>
+#include <test_progs.h>
+#include "timer_start_delete_race.skel.h"
+
+/*
+ * Test for race between bpf_timer_start() and map element deletion.
+ *
+ * The race scenario:
+ * - CPU 1: bpf_timer_start() proceeds to bpf_async_process() and is about
+ *          to call hrtimer_start() but hasn't yet
+ * - CPU 2: map_delete_elem() calls __bpf_async_cancel_and_free(), since
+ *          timer is not scheduled yet hrtimer_try_to_cancel() is a nop,
+ *          then calls bpf_async_refcount_put() dropping refcnt to zero
+ *          and scheduling call_rcu_tasks_trace()
+ * - CPU 1: continues and calls hrtimer_start()
+ * - After RCU tasks trace grace period: memory is freed
+ * - Timer callback fires on freed memory: UAF!
+ *
+ * This test stresses this race by having two threads:
+ * - Thread 1: repeatedly starts timers
+ * - Thread 2: repeatedly deletes map elements
+ *
+ * KASAN should detect use-after-free.
+ */
+
+#define ITERATIONS 1000
+
+struct ctx {
+	struct timer_start_delete_race *skel;
+	volatile bool start;
+	volatile bool stop;
+	int errors;
+};
+
+static void *start_timer_thread(void *arg)
+{
+	struct ctx *ctx = arg;
+	cpu_set_t cpuset;
+	int fd, i;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	while (!ctx->start && !ctx->stop)
+		usleep(1);
+	if (ctx->stop)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->skel->progs.start_timer);
+
+	for (i = 0; i < ITERATIONS && !ctx->stop; i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+		int err;
+
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err || opts.retval) {
+			ctx->errors++;
+			break;
+		}
+	}
+
+	return NULL;
+}
+
+static void *delete_elem_thread(void *arg)
+{
+	struct ctx *ctx = arg;
+	cpu_set_t cpuset;
+	int fd, i;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(1, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	while (!ctx->start && !ctx->stop)
+		usleep(1);
+	if (ctx->stop)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->skel->progs.delete_elem);
+
+	for (i = 0; i < ITERATIONS && !ctx->stop; i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+		int err;
+
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err || opts.retval) {
+			ctx->errors++;
+			break;
+		}
+	}
+
+	return NULL;
+}
+
+void test_timer_start_delete_race(void)
+{
+	struct timer_start_delete_race *skel;
+	pthread_t threads[2];
+	struct ctx ctx = {};
+	int err;
+
+	skel = timer_start_delete_race__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	ctx.skel = skel;
+
+	err = pthread_create(&threads[0], NULL, start_timer_thread, &ctx);
+	if (!ASSERT_OK(err, "create start_timer_thread")) {
+		ctx.stop = true;
+		goto cleanup;
+	}
+
+	err = pthread_create(&threads[1], NULL, delete_elem_thread, &ctx);
+	if (!ASSERT_OK(err, "create delete_elem_thread")) {
+		ctx.stop = true;
+		pthread_join(threads[0], NULL);
+		goto cleanup;
+	}
+
+	ctx.start = true;
+
+	pthread_join(threads[0], NULL);
+	pthread_join(threads[1], NULL);
+
+	ASSERT_EQ(ctx.errors, 0, "thread_errors");
+
+	/* Either KASAN will catch UAF or kernel will crash or nothing happens */
+cleanup:
+	timer_start_delete_race__destroy(skel);
+}

tools/testing/selftests/bpf/progs/timer_start_delete_race.c

@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#define ITER_CNT 2000
+
+struct map_value {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} timer_map SEC(".maps");
+
+long cb_cnt;
+
+/*
+ * Timer callback that accesses the map value.
+ * If the race bug exists and this runs on freed memory,
+ * KASAN should detect it.
+ */
+static int timer_cb(void *map, int *key, struct map_value *value)
+{
+	__sync_fetch_and_add(&cb_cnt, 1);
+	return 0;
+}
+
+SEC("syscall")
+int start_timer(void *ctx)
+{
+	struct map_value *value;
+	int i;
+
+	for (i = 0; i < ITER_CNT; i++) {
+		int key = 0;
+
+		value = bpf_map_lookup_elem(&timer_map, &key);
+		/* hey claude, no if (!value) here. The verifier got smarter */
+
+		bpf_timer_init(&value->timer, &timer_map, CLOCK_MONOTONIC);
+		bpf_timer_set_callback(&value->timer, timer_cb);
+		bpf_timer_start(&value->timer, 100000000, 0);
+	}
+	return 0;
+}
+
+SEC("syscall")
+int delete_elem(void *ctx)
+{
+	int i;
+
+	for (i = 0; i < ITER_CNT; i++) {
+		int key = 0;
+
+		bpf_map_delete_elem(&timer_map, &key);
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";