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, 345 insertions, 0 deletions

diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
new file mode 100644
index 000000000..dbb84949c
--- /dev/null
+++ b/drivers/leds/leds-gpio.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * LEDs driver for GPIOs
+ *
+ * Copyright (C) 2007 8D Technologies inc.
+ * Raphael Assenat <raph@8d.com>
+ * Copyright (C) 2008 Freescale Semiconductor, Inc.
+ */
+#include <linux/container_of.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/legacy.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/overflow.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+struct gpio_led_data {
+	struct led_classdev cdev;
+	struct gpio_desc *gpiod;
+	u8 can_sleep;
+	u8 blinking;
+	gpio_blink_set_t platform_gpio_blink_set;
+};
+
+static inline struct gpio_led_data *
+			cdev_to_gpio_led_data(struct led_classdev *led_cdev)
+{
+	return container_of(led_cdev, struct gpio_led_data, cdev);
+}
+
+static void gpio_led_set(struct led_classdev *led_cdev,
+	enum led_brightness value)
+{
+	struct gpio_led_data *led_dat = cdev_to_gpio_led_data(led_cdev);
+	int level;
+
+	if (value == LED_OFF)
+		level = 0;
+	else
+		level = 1;
+
+	if (led_dat->blinking) {
+		led_dat->platform_gpio_blink_set(led_dat->gpiod, level,
+						 NULL, NULL);
+		led_dat->blinking = 0;
+	} else {
+		if (led_dat->can_sleep)
+			gpiod_set_value_cansleep(led_dat->gpiod, level);
+		else
+			gpiod_set_value(led_dat->gpiod, level);
+	}
+}
+
+static int gpio_led_set_blocking(struct led_classdev *led_cdev,
+	enum led_brightness value)
+{
+	gpio_led_set(led_cdev, value);
+	return 0;
+}
+
+static int gpio_blink_set(struct led_classdev *led_cdev,
+	unsigned long *delay_on, unsigned long *delay_off)
+{
+	struct gpio_led_data *led_dat = cdev_to_gpio_led_data(led_cdev);
+
+	led_dat->blinking = 1;
+	return led_dat->platform_gpio_blink_set(led_dat->gpiod, GPIO_LED_BLINK,
+						delay_on, delay_off);
+}
+
+static int create_gpio_led(const struct gpio_led *template,
+	struct gpio_led_data *led_dat, struct device *parent,
+	struct fwnode_handle *fwnode, gpio_blink_set_t blink_set)
+{
+	struct led_init_data init_data = {};
+	struct pinctrl *pinctrl;
+	int ret, state;
+
+	led_dat->cdev.default_trigger = template->default_trigger;
+	led_dat->can_sleep = gpiod_cansleep(led_dat->gpiod);
+	if (!led_dat->can_sleep)
+		led_dat->cdev.brightness_set = gpio_led_set;
+	else
+		led_dat->cdev.brightness_set_blocking = gpio_led_set_blocking;
+	led_dat->blinking = 0;
+	if (blink_set) {
+		led_dat->platform_gpio_blink_set = blink_set;
+		led_dat->cdev.blink_set = gpio_blink_set;
+	}
+	if (template->default_state == LEDS_GPIO_DEFSTATE_KEEP) {
+		state = gpiod_get_value_cansleep(led_dat->gpiod);
+		if (state < 0)
+			return state;
+	} else {
+		state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
+	}
+	led_dat->cdev.brightness = state;
+	led_dat->cdev.max_brightness = 1;
+	if (!template->retain_state_suspended)
+		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
+	if (template->panic_indicator)
+		led_dat->cdev.flags |= LED_PANIC_INDICATOR;
+	if (template->retain_state_shutdown)
+		led_dat->cdev.flags |= LED_RETAIN_AT_SHUTDOWN;
+
+	ret = gpiod_direction_output(led_dat->gpiod, state);
+	if (ret < 0)
+		return ret;
+
+	if (template->name) {
+		led_dat->cdev.name = template->name;
+		ret = devm_led_classdev_register(parent, &led_dat->cdev);
+	} else {
+		init_data.fwnode = fwnode;
+		ret = devm_led_classdev_register_ext(parent, &led_dat->cdev,
+						     &init_data);
+	}
+
+	if (ret)
+		return ret;
+
+	pinctrl = devm_pinctrl_get_select_default(led_dat->cdev.dev);
+	ret = PTR_ERR_OR_ZERO(pinctrl);
+	/* pinctrl-%d not present, not an error */
+	if (ret == -ENODEV)
+		ret = 0;
+	if (ret) {
+		dev_warn(led_dat->cdev.dev, "Failed to select %pfw pinctrl: %d\n",
+			 fwnode, ret);
+	}
+
+	return ret;
+}
+
+struct gpio_leds_priv {
+	int num_leds;
+	struct gpio_led_data leds[] __counted_by(num_leds);
+};
+
+static struct gpio_leds_priv *gpio_leds_create(struct device *dev)
+{
+	struct gpio_leds_priv *priv;
+	int count, used, ret;
+
+	count = device_get_child_node_count(dev);
+	if (!count)
+		return ERR_PTR(-ENODEV);
+
+	priv = devm_kzalloc(dev, struct_size(priv, leds, count), GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+	priv->num_leds = count;
+	used = 0;
+
+	device_for_each_child_node_scoped(dev, child) {
+		struct gpio_led_data *led_dat = &priv->leds[used];
+		struct gpio_led led = {};
+
+		/*
+		 * Acquire gpiod from DT with uninitialized label, which
+		 * will be updated after LED class device is registered,
+		 * Only then the final LED name is known.
+		 */
+		led.gpiod = devm_fwnode_gpiod_get(dev, child, NULL, GPIOD_ASIS,
+						  NULL);
+		if (IS_ERR(led.gpiod)) {
+			dev_err_probe(dev, PTR_ERR(led.gpiod), "Failed to get GPIO '%pfw'\n",
+				      child);
+			return ERR_CAST(led.gpiod);
+		}
+
+		led_dat->gpiod = led.gpiod;
+
+		led.default_state = led_init_default_state_get(child);
+
+		if (fwnode_property_present(child, "retain-state-suspended"))
+			led.retain_state_suspended = 1;
+		if (fwnode_property_present(child, "retain-state-shutdown"))
+			led.retain_state_shutdown = 1;
+		if (fwnode_property_present(child, "panic-indicator"))
+			led.panic_indicator = 1;
+
+		ret = create_gpio_led(&led, led_dat, dev, child, NULL);
+		if (ret < 0)
+			return ERR_PTR(ret);
+
+		/* Set gpiod label to match the corresponding LED name. */
+		gpiod_set_consumer_name(led_dat->gpiod,
+					led_dat->cdev.dev->kobj.name);
+		used++;
+	}
+	priv->num_leds = used;
+
+	return priv;
+}
+
+static const struct of_device_id of_gpio_leds_match[] = {
+	{ .compatible = "gpio-leds", },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, of_gpio_leds_match);
+
+static struct gpio_desc *gpio_led_get_gpiod(struct device *dev, int idx,
+					    const struct gpio_led *template)
+{
+	struct gpio_desc *gpiod;
+
+	/*
+	 * This means the LED does not come from the device tree
+	 * or ACPI, so let's try just getting it by index from the
+	 * device, this will hit the board file, if any and get
+	 * the GPIO from there.
+	 */
+	gpiod = devm_gpiod_get_index_optional(dev, NULL, idx, GPIOD_OUT_LOW);
+	if (IS_ERR(gpiod))
+		return gpiod;
+
+	gpiod_set_consumer_name(gpiod, template->name);
+	return gpiod;
+}
+
+#ifdef CONFIG_GPIOLIB_LEGACY
+/*
+ * This is the legacy code path for platform code that still uses
+ * GPIO numbers, mainly MIPS and SuperH board files.
+ * Ultimately we would like to get rid of this block completely.
+ *
+ * ppc44x-warp sets the template->gpiod directly instead of
+ * adding a lookup table or device properties. This is not
+ * much better.
+ */
+static struct gpio_desc *gpio_led_get_legacy_gpiod(struct device *dev, int idx,
+						   const struct gpio_led *template)
+{
+	struct gpio_desc *gpiod;
+	int ret;
+
+	if (template->gpiod)
+		return template->gpiod;
+
+	/* skip leds that aren't available */
+	if (!gpio_is_valid(template->gpio))
+		return ERR_PTR(-ENOENT);
+
+	ret = devm_gpio_request_one(dev, template->gpio, GPIOF_OUT_INIT_LOW,
+				    template->name);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	gpiod = gpio_to_desc(template->gpio);
+	if (!gpiod)
+		return ERR_PTR(-EINVAL);
+
+	if (template->active_low ^ gpiod_is_active_low(gpiod))
+		gpiod_toggle_active_low(gpiod);
+
+	return gpiod;
+}
+#else
+static struct gpio_desc *gpio_led_get_legacy_gpiod(struct device *dev, int idx,
+						   const struct gpio_led *template)
+{
+	return template->gpiod ?: ERR_PTR(-ENOENT);
+}
+#endif
+
+static int gpio_led_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct gpio_led_platform_data *pdata = dev_get_platdata(dev);
+	struct gpio_leds_priv *priv;
+	int i, ret;
+
+	if (pdata && pdata->num_leds) {
+		priv = devm_kzalloc(dev, struct_size(priv, leds, pdata->num_leds), GFP_KERNEL);
+		if (!priv)
+			return -ENOMEM;
+
+		priv->num_leds = pdata->num_leds;
+		for (i = 0; i < priv->num_leds; i++) {
+			const struct gpio_led *template = &pdata->leds[i];
+			struct gpio_led_data *led_dat = &priv->leds[i];
+
+			led_dat->gpiod = gpio_led_get_gpiod(dev, i, template);
+			if (!led_dat->gpiod)
+				led_dat->gpiod =
+					 gpio_led_get_legacy_gpiod(dev, i, template);
+			if (IS_ERR(led_dat->gpiod)) {
+				dev_info(dev, "Skipping unavailable LED gpio %s\n",
+					 template->name);
+				led_dat->gpiod = NULL;
+				continue;
+			}
+
+			ret = create_gpio_led(template, led_dat, dev, NULL,
+					      pdata->gpio_blink_set);
+			if (ret < 0)
+				return ret;
+		}
+	} else {
+		priv = gpio_leds_create(dev);
+		if (IS_ERR(priv))
+			return PTR_ERR(priv);
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+}
+
+static void gpio_led_shutdown(struct platform_device *pdev)
+{
+	struct gpio_leds_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < priv->num_leds; i++) {
+		struct gpio_led_data *led = &priv->leds[i];
+
+		if (!(led->cdev.flags & LED_RETAIN_AT_SHUTDOWN))
+			gpio_led_set(&led->cdev, LED_OFF);
+	}
+}
+
+static struct platform_driver gpio_led_driver = {
+	.probe		= gpio_led_probe,
+	.shutdown	= gpio_led_shutdown,
+	.driver		= {
+		.name	= "leds-gpio",
+		.of_match_table = of_gpio_leds_match,
+	},
+};
+
+module_platform_driver(gpio_led_driver);
+
+MODULE_AUTHOR("Raphael Assenat <raph@8d.com>, Trent Piepho <tpiepho@freescale.com>");
+MODULE_DESCRIPTION("GPIO LED driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:leds-gpio");