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, 274 insertions, 0 deletions

diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c
new file mode 100644
index 000000000..3e5ed685e
--- /dev/null
+++ b/drivers/input/misc/pwm-vibra.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  PWM vibrator driver
+ *
+ *  Copyright (C) 2017 Collabora Ltd.
+ *
+ *  Based on previous work from:
+ *  Copyright (C) 2012 Dmitry Torokhov <dmitry.torokhov@gmail.com>
+ *
+ *  Based on PWM beeper driver:
+ *  Copyright (C) 2010, Lars-Peter Clausen <lars@metafoo.de>
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/input.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/pwm.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+struct pwm_vibrator {
+	struct input_dev *input;
+	struct gpio_desc *enable_gpio;
+	struct pwm_device *pwm;
+	struct pwm_device *pwm_dir;
+	struct regulator *vcc;
+
+	struct work_struct play_work;
+	u16 level;
+	u32 direction_duty_cycle;
+	bool vcc_on;
+};
+
+static int pwm_vibrator_start(struct pwm_vibrator *vibrator)
+{
+	struct device *pdev = vibrator->input->dev.parent;
+	struct pwm_state state;
+	int err;
+
+	if (!vibrator->vcc_on) {
+		err = regulator_enable(vibrator->vcc);
+		if (err) {
+			dev_err(pdev, "failed to enable regulator: %d\n", err);
+			return err;
+		}
+		vibrator->vcc_on = true;
+	}
+
+	gpiod_set_value_cansleep(vibrator->enable_gpio, 1);
+
+	pwm_get_state(vibrator->pwm, &state);
+	pwm_set_relative_duty_cycle(&state, vibrator->level, 0xffff);
+	state.enabled = true;
+
+	err = pwm_apply_might_sleep(vibrator->pwm, &state);
+	if (err) {
+		dev_err(pdev, "failed to apply pwm state: %d\n", err);
+		return err;
+	}
+
+	if (vibrator->pwm_dir) {
+		pwm_get_state(vibrator->pwm_dir, &state);
+		state.duty_cycle = vibrator->direction_duty_cycle;
+		state.enabled = true;
+
+		err = pwm_apply_might_sleep(vibrator->pwm_dir, &state);
+		if (err) {
+			dev_err(pdev, "failed to apply dir-pwm state: %d\n", err);
+			pwm_disable(vibrator->pwm);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void pwm_vibrator_stop(struct pwm_vibrator *vibrator)
+{
+	if (vibrator->pwm_dir)
+		pwm_disable(vibrator->pwm_dir);
+	pwm_disable(vibrator->pwm);
+
+	gpiod_set_value_cansleep(vibrator->enable_gpio, 0);
+
+	if (vibrator->vcc_on) {
+		regulator_disable(vibrator->vcc);
+		vibrator->vcc_on = false;
+	}
+}
+
+static void pwm_vibrator_play_work(struct work_struct *work)
+{
+	struct pwm_vibrator *vibrator = container_of(work,
+					struct pwm_vibrator, play_work);
+
+	if (vibrator->level)
+		pwm_vibrator_start(vibrator);
+	else
+		pwm_vibrator_stop(vibrator);
+}
+
+static int pwm_vibrator_play_effect(struct input_dev *dev, void *data,
+				    struct ff_effect *effect)
+{
+	struct pwm_vibrator *vibrator = input_get_drvdata(dev);
+
+	vibrator->level = effect->u.rumble.strong_magnitude;
+	if (!vibrator->level)
+		vibrator->level = effect->u.rumble.weak_magnitude;
+
+	schedule_work(&vibrator->play_work);
+
+	return 0;
+}
+
+static void pwm_vibrator_close(struct input_dev *input)
+{
+	struct pwm_vibrator *vibrator = input_get_drvdata(input);
+
+	cancel_work_sync(&vibrator->play_work);
+	pwm_vibrator_stop(vibrator);
+}
+
+static int pwm_vibrator_probe(struct platform_device *pdev)
+{
+	struct pwm_vibrator *vibrator;
+	struct pwm_state state;
+	int err;
+
+	vibrator = devm_kzalloc(&pdev->dev, sizeof(*vibrator), GFP_KERNEL);
+	if (!vibrator)
+		return -ENOMEM;
+
+	vibrator->input = devm_input_allocate_device(&pdev->dev);
+	if (!vibrator->input)
+		return -ENOMEM;
+
+	vibrator->vcc = devm_regulator_get(&pdev->dev, "vcc");
+	if (IS_ERR(vibrator->vcc))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->vcc),
+				     "Failed to request regulator\n");
+
+	vibrator->enable_gpio = devm_gpiod_get_optional(&pdev->dev, "enable",
+							GPIOD_OUT_LOW);
+	if (IS_ERR(vibrator->enable_gpio))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->enable_gpio),
+				     "Failed to request enable gpio\n");
+
+	vibrator->pwm = devm_pwm_get(&pdev->dev, "enable");
+	if (IS_ERR(vibrator->pwm))
+		return dev_err_probe(&pdev->dev, PTR_ERR(vibrator->pwm),
+				     "Failed to request main pwm\n");
+
+	INIT_WORK(&vibrator->play_work, pwm_vibrator_play_work);
+
+	/* Sync up PWM state and ensure it is off. */
+	pwm_init_state(vibrator->pwm, &state);
+	state.enabled = false;
+	err = pwm_apply_might_sleep(vibrator->pwm, &state);
+	if (err) {
+		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
+			err);
+		return err;
+	}
+
+	vibrator->pwm_dir = devm_pwm_get(&pdev->dev, "direction");
+	err = PTR_ERR_OR_ZERO(vibrator->pwm_dir);
+	switch (err) {
+	case 0:
+		/* Sync up PWM state and ensure it is off. */
+		pwm_init_state(vibrator->pwm_dir, &state);
+		state.enabled = false;
+		err = pwm_apply_might_sleep(vibrator->pwm_dir, &state);
+		if (err) {
+			dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
+				err);
+			return err;
+		}
+
+		vibrator->direction_duty_cycle =
+			pwm_get_period(vibrator->pwm_dir) / 2;
+		device_property_read_u32(&pdev->dev, "direction-duty-cycle-ns",
+					 &vibrator->direction_duty_cycle);
+		break;
+
+	case -ENODATA:
+		/* Direction PWM is optional */
+		vibrator->pwm_dir = NULL;
+		break;
+
+	default:
+		dev_err(&pdev->dev, "Failed to request direction pwm: %d\n", err);
+		fallthrough;
+
+	case -EPROBE_DEFER:
+		return err;
+	}
+
+	vibrator->input->name = "pwm-vibrator";
+	vibrator->input->id.bustype = BUS_HOST;
+	vibrator->input->dev.parent = &pdev->dev;
+	vibrator->input->close = pwm_vibrator_close;
+
+	input_set_drvdata(vibrator->input, vibrator);
+	input_set_capability(vibrator->input, EV_FF, FF_RUMBLE);
+
+	err = input_ff_create_memless(vibrator->input, NULL,
+				      pwm_vibrator_play_effect);
+	if (err) {
+		dev_err(&pdev->dev, "Couldn't create FF dev: %d\n", err);
+		return err;
+	}
+
+	err = input_register_device(vibrator->input);
+	if (err) {
+		dev_err(&pdev->dev, "Couldn't register input dev: %d\n", err);
+		return err;
+	}
+
+	platform_set_drvdata(pdev, vibrator);
+
+	return 0;
+}
+
+static int pwm_vibrator_suspend(struct device *dev)
+{
+	struct pwm_vibrator *vibrator = dev_get_drvdata(dev);
+
+	cancel_work_sync(&vibrator->play_work);
+	if (vibrator->level)
+		pwm_vibrator_stop(vibrator);
+
+	return 0;
+}
+
+static int pwm_vibrator_resume(struct device *dev)
+{
+	struct pwm_vibrator *vibrator = dev_get_drvdata(dev);
+
+	if (vibrator->level)
+		pwm_vibrator_start(vibrator);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(pwm_vibrator_pm_ops,
+				pwm_vibrator_suspend, pwm_vibrator_resume);
+
+#ifdef CONFIG_OF
+static const struct of_device_id pwm_vibra_dt_match_table[] = {
+	{ .compatible = "pwm-vibrator" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, pwm_vibra_dt_match_table);
+#endif
+
+static struct platform_driver pwm_vibrator_driver = {
+	.probe	= pwm_vibrator_probe,
+	.driver	= {
+		.name	= "pwm-vibrator",
+		.pm	= pm_sleep_ptr(&pwm_vibrator_pm_ops),
+		.of_match_table = of_match_ptr(pwm_vibra_dt_match_table),
+	},
+};
+module_platform_driver(pwm_vibrator_driver);
+
+MODULE_AUTHOR("Sebastian Reichel <sre@kernel.org>");
+MODULE_DESCRIPTION("PWM vibrator driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:pwm-vibrator");