x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

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");