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, 253 insertions, 0 deletions

diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
new file mode 100644
index 000000000..0e19e97d9
--- /dev/null
+++ b/drivers/input/misc/pwm-beeper.c
@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (C) 2010, Lars-Peter Clausen <lars@metafoo.de>
+ *  PWM beeper driver
+ */
+
+#include <linux/input.h>
+#include <linux/regulator/consumer.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/pwm.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+struct pwm_beeper {
+	struct input_dev *input;
+	struct pwm_device *pwm;
+	struct regulator *amplifier;
+	struct work_struct work;
+	unsigned long period;
+	unsigned int bell_frequency;
+	bool suspended;
+	bool amplifier_on;
+};
+
+#define HZ_TO_NANOSECONDS(x) (1000000000UL/(x))
+
+static int pwm_beeper_on(struct pwm_beeper *beeper, unsigned long period)
+{
+	struct pwm_state state;
+	int error;
+
+	pwm_get_state(beeper->pwm, &state);
+
+	state.enabled = true;
+	state.period = period;
+	pwm_set_relative_duty_cycle(&state, 50, 100);
+
+	error = pwm_apply_might_sleep(beeper->pwm, &state);
+	if (error)
+		return error;
+
+	if (!beeper->amplifier_on) {
+		error = regulator_enable(beeper->amplifier);
+		if (error) {
+			pwm_disable(beeper->pwm);
+			return error;
+		}
+
+		beeper->amplifier_on = true;
+	}
+
+	return 0;
+}
+
+static void pwm_beeper_off(struct pwm_beeper *beeper)
+{
+	if (beeper->amplifier_on) {
+		regulator_disable(beeper->amplifier);
+		beeper->amplifier_on = false;
+	}
+
+	pwm_disable(beeper->pwm);
+}
+
+static void pwm_beeper_work(struct work_struct *work)
+{
+	struct pwm_beeper *beeper = container_of(work, struct pwm_beeper, work);
+	unsigned long period = READ_ONCE(beeper->period);
+
+	if (period)
+		pwm_beeper_on(beeper, period);
+	else
+		pwm_beeper_off(beeper);
+}
+
+static int pwm_beeper_event(struct input_dev *input,
+			    unsigned int type, unsigned int code, int value)
+{
+	struct pwm_beeper *beeper = input_get_drvdata(input);
+
+	if (type != EV_SND || value < 0)
+		return -EINVAL;
+
+	switch (code) {
+	case SND_BELL:
+		value = value ? beeper->bell_frequency : 0;
+		break;
+	case SND_TONE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (value == 0)
+		beeper->period = 0;
+	else
+		beeper->period = HZ_TO_NANOSECONDS(value);
+
+	if (!beeper->suspended)
+		schedule_work(&beeper->work);
+
+	return 0;
+}
+
+static void pwm_beeper_stop(struct pwm_beeper *beeper)
+{
+	cancel_work_sync(&beeper->work);
+	pwm_beeper_off(beeper);
+}
+
+static void pwm_beeper_close(struct input_dev *input)
+{
+	struct pwm_beeper *beeper = input_get_drvdata(input);
+
+	pwm_beeper_stop(beeper);
+}
+
+static int pwm_beeper_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct pwm_beeper *beeper;
+	struct pwm_state state;
+	u32 bell_frequency;
+	int error;
+
+	beeper = devm_kzalloc(dev, sizeof(*beeper), GFP_KERNEL);
+	if (!beeper)
+		return -ENOMEM;
+
+	beeper->pwm = devm_pwm_get(dev, NULL);
+	if (IS_ERR(beeper->pwm))
+		return dev_err_probe(dev, PTR_ERR(beeper->pwm), "Failed to request PWM device\n");
+
+	/* Sync up PWM state and ensure it is off. */
+	pwm_init_state(beeper->pwm, &state);
+	state.enabled = false;
+	error = pwm_apply_might_sleep(beeper->pwm, &state);
+	if (error) {
+		dev_err(dev, "failed to apply initial PWM state: %d\n",
+			error);
+		return error;
+	}
+
+	beeper->amplifier = devm_regulator_get(dev, "amp");
+	if (IS_ERR(beeper->amplifier))
+		return dev_err_probe(dev, PTR_ERR(beeper->amplifier),
+				     "Failed to get 'amp' regulator\n");
+
+	INIT_WORK(&beeper->work, pwm_beeper_work);
+
+	error = device_property_read_u32(dev, "beeper-hz", &bell_frequency);
+	if (error) {
+		bell_frequency = 1000;
+		dev_dbg(dev,
+			"failed to parse 'beeper-hz' property, using default: %uHz\n",
+			bell_frequency);
+	}
+
+	beeper->bell_frequency = bell_frequency;
+
+	beeper->input = devm_input_allocate_device(dev);
+	if (!beeper->input) {
+		dev_err(dev, "Failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	beeper->input->name = "pwm-beeper";
+	beeper->input->phys = "pwm/input0";
+	beeper->input->id.bustype = BUS_HOST;
+	beeper->input->id.vendor = 0x001f;
+	beeper->input->id.product = 0x0001;
+	beeper->input->id.version = 0x0100;
+
+	input_set_capability(beeper->input, EV_SND, SND_TONE);
+	input_set_capability(beeper->input, EV_SND, SND_BELL);
+
+	beeper->input->event = pwm_beeper_event;
+	beeper->input->close = pwm_beeper_close;
+
+	input_set_drvdata(beeper->input, beeper);
+
+	error = input_register_device(beeper->input);
+	if (error) {
+		dev_err(dev, "Failed to register input device: %d\n", error);
+		return error;
+	}
+
+	platform_set_drvdata(pdev, beeper);
+
+	return 0;
+}
+
+static int pwm_beeper_suspend(struct device *dev)
+{
+	struct pwm_beeper *beeper = dev_get_drvdata(dev);
+
+	/*
+	 * Spinlock is taken here is not to protect write to
+	 * beeper->suspended, but to ensure that pwm_beeper_event
+	 * does not re-submit work once flag is set.
+	 */
+	scoped_guard(spinlock_irq, &beeper->input->event_lock) {
+		beeper->suspended = true;
+	}
+
+	pwm_beeper_stop(beeper);
+
+	return 0;
+}
+
+static int pwm_beeper_resume(struct device *dev)
+{
+	struct pwm_beeper *beeper = dev_get_drvdata(dev);
+
+	scoped_guard(spinlock_irq, &beeper->input->event_lock) {
+		beeper->suspended = false;
+	}
+
+	/* Let worker figure out if we should resume beeping */
+	schedule_work(&beeper->work);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(pwm_beeper_pm_ops,
+				pwm_beeper_suspend, pwm_beeper_resume);
+
+#ifdef CONFIG_OF
+static const struct of_device_id pwm_beeper_match[] = {
+	{ .compatible = "pwm-beeper", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, pwm_beeper_match);
+#endif
+
+static struct platform_driver pwm_beeper_driver = {
+	.probe	= pwm_beeper_probe,
+	.driver = {
+		.name	= "pwm-beeper",
+		.pm	= pm_sleep_ptr(&pwm_beeper_pm_ops),
+		.of_match_table = of_match_ptr(pwm_beeper_match),
+	},
+};
+module_platform_driver(pwm_beeper_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("PWM beeper driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:pwm-beeper");