ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 153 insertions, 0 deletions

diff --git a/lib/tests/test_ratelimit.c b/lib/tests/test_ratelimit.c
new file mode 100644
index 000000000..e244f8cd4
--- /dev/null
+++ b/lib/tests/test_ratelimit.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <kunit/test.h>
+
+#include <linux/ratelimit.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/cpumask.h>
+
+/* a simple boot-time regression test */
+
+#define TESTRL_INTERVAL (5 * HZ)
+static DEFINE_RATELIMIT_STATE(testrl, TESTRL_INTERVAL, 3);
+
+#define test_ratelimited(test, expected) \
+	KUNIT_ASSERT_EQ(test, ___ratelimit(&testrl, "test_ratelimit_smoke"), (expected))
+
+static void test_ratelimit_smoke(struct kunit *test)
+{
+	// Check settings.
+	KUNIT_ASSERT_GE(test, TESTRL_INTERVAL, 100);
+
+	// Test normal operation.
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, false);
+
+	schedule_timeout_idle(TESTRL_INTERVAL / 2);
+	test_ratelimited(test, false);
+
+	schedule_timeout_idle(TESTRL_INTERVAL * 3 / 4);
+	test_ratelimited(test, true);
+
+	schedule_timeout_idle(2 * TESTRL_INTERVAL);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+
+	schedule_timeout_idle(TESTRL_INTERVAL / 2 );
+	test_ratelimited(test, true);
+	schedule_timeout_idle(TESTRL_INTERVAL * 3 / 4);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, false);
+
+	// Test disabling.
+	testrl.burst = 0;
+	test_ratelimited(test, false);
+	testrl.burst = 2;
+	testrl.interval = 0;
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+
+	// Testing re-enabling.
+	testrl.interval = TESTRL_INTERVAL;
+	test_ratelimited(test, true);
+	test_ratelimited(test, true);
+	test_ratelimited(test, false);
+	test_ratelimited(test, false);
+}
+
+static struct ratelimit_state stressrl = RATELIMIT_STATE_INIT_FLAGS("stressrl", HZ / 10, 3,
+								    RATELIMIT_MSG_ON_RELEASE);
+
+static const int stress_duration = 2 * HZ;
+
+struct stress_kthread {
+	unsigned long nattempts;
+	unsigned long nunlimited;
+	unsigned long nlimited;
+	unsigned long nmissed;
+	struct task_struct *tp;
+};
+
+static int test_ratelimit_stress_child(void *arg)
+{
+	struct stress_kthread *sktp = arg;
+
+	set_user_nice(current, MAX_NICE);
+
+	while (!kthread_should_stop()) {
+		sktp->nattempts++;
+		if (___ratelimit(&stressrl, __func__))
+			sktp->nunlimited++;
+		else
+			sktp->nlimited++;
+		cond_resched();
+	}
+
+	sktp->nmissed = ratelimit_state_reset_miss(&stressrl);
+	return 0;
+}
+
+static void test_ratelimit_stress(struct kunit *test)
+{
+	int i;
+	const int n_stress_kthread = cpumask_weight(cpu_online_mask);
+	struct stress_kthread skt = { 0 };
+	struct stress_kthread *sktp = kzalloc_objs(*sktp, n_stress_kthread);
+	int n_started = 0;
+
+	KUNIT_ASSERT_NOT_NULL_MSG(test, sktp, "Memory allocation failure");
+	for (i = 0; i < n_stress_kthread; i++) {
+		sktp[i].tp = kthread_run(test_ratelimit_stress_child, &sktp[i], "%s/%i",
+					 "test_ratelimit_stress_child", i);
+		if (IS_ERR(sktp[i].tp)) {
+			KUNIT_FAIL(test, "kthread_run failed: %ld", PTR_ERR(sktp[i].tp));
+			goto out_stop;
+		}
+		n_started++;
+		pr_alert("Spawned test_ratelimit_stress_child %d\n", i);
+	}
+	schedule_timeout_idle(stress_duration);
+
+out_stop:
+	for (i = 0; i < n_started; i++) {
+		kthread_stop(sktp[i].tp);
+		skt.nattempts += sktp[i].nattempts;
+		skt.nunlimited += sktp[i].nunlimited;
+		skt.nlimited += sktp[i].nlimited;
+		skt.nmissed += sktp[i].nmissed;
+	}
+	if (n_started == n_stress_kthread) {
+		KUNIT_ASSERT_EQ_MSG(test, skt.nunlimited + skt.nlimited, skt.nattempts,
+				    "Outcomes not equal to attempts");
+		KUNIT_ASSERT_EQ_MSG(test, skt.nlimited, skt.nmissed,
+				    "Misses not equal to limits");
+	}
+
+	kfree(sktp);
+}
+
+static struct kunit_case ratelimit_test_cases[] = {
+	KUNIT_CASE_SLOW(test_ratelimit_smoke),
+	KUNIT_CASE_SLOW(test_ratelimit_stress),
+	{}
+};
+
+static struct kunit_suite ratelimit_test_suite = {
+	.name = "lib_ratelimit",
+	.test_cases = ratelimit_test_cases,
+};
+
+kunit_test_suites(&ratelimit_test_suite);
+
+MODULE_DESCRIPTION("___ratelimit() KUnit test suite");
+MODULE_LICENSE("GPL");