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, 322 insertions, 0 deletions

diff --git a/drivers/gpio/gpio-shared-proxy.c b/drivers/gpio/gpio-shared-proxy.c
new file mode 100644
index 000000000..bc69b8729
--- /dev/null
+++ b/drivers/gpio/gpio-shared-proxy.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Linaro Ltd.
+ */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/cleanup.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/driver.h>
+#include <linux/lockdep.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/string_choices.h>
+#include <linux/types.h>
+
+#include "gpiolib-shared.h"
+
+struct gpio_shared_proxy_data {
+	struct gpio_chip gc;
+	struct gpio_shared_desc *shared_desc;
+	struct device *dev;
+	bool voted_change;
+};
+
+static int
+gpio_shared_proxy_set_unlocked(struct gpio_shared_proxy_data *proxy, int value)
+{
+	struct gpio_shared_desc *shared_desc = proxy->shared_desc;
+	struct gpio_desc *desc = shared_desc->desc;
+	int ret = 0;
+
+	lockdep_assert_held(&shared_desc->mutex);
+
+	if (value != shared_desc->def_val) {
+	       /* User wants to vote for a value change. */
+		if (proxy->voted_change)
+			/* Already voted for a change, nothing to do. */
+			goto out;
+
+		/* Haven't voted for a value change yet. */
+		if (!shared_desc->votecnt) {
+			/*
+			 * Current value is default, need to actually set value
+			 * to the opposite.
+			 */
+			ret = gpiod_set_value_cansleep(desc, value);
+			if (ret)
+				goto out;
+		}
+
+		shared_desc->votecnt++;
+		proxy->voted_change = true;
+
+		goto out;
+	}
+
+	/* Desired value is the default. */
+	if (!proxy->voted_change)
+		/* We didn't vote for change previously, nothing to do. */
+		goto out;
+
+	/* We previously voted for change. */
+	if (shared_desc->votecnt == 1) {
+		/* This is the last remaining vote for change, set value to default. */
+		ret = gpiod_set_value_cansleep(desc, shared_desc->def_val);
+		if (ret)
+			goto out;
+	}
+
+	shared_desc->votecnt--;
+	proxy->voted_change = false;
+
+out:
+	if (shared_desc->votecnt)
+		dev_dbg(proxy->dev,
+			"Voted for value '%s', effective value is '%s', number of votes: %u\n",
+			str_high_low(value), str_high_low(!shared_desc->def_val),
+			shared_desc->votecnt);
+	else
+		dev_dbg(proxy->dev, "Voted for value '%s', effective value is '%s'\n",
+			str_high_low(value), str_high_low(shared_desc->def_val));
+
+	return ret;
+}
+
+static int gpio_shared_proxy_request(struct gpio_chip *gc, unsigned int offset)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+	struct gpio_shared_desc *shared_desc = proxy->shared_desc;
+
+	guard(mutex)(&shared_desc->mutex);
+
+	proxy->shared_desc->usecnt++;
+
+	dev_dbg(proxy->dev, "Shared GPIO requested, number of users: %u\n",
+		proxy->shared_desc->usecnt);
+
+	return 0;
+}
+
+static void gpio_shared_proxy_free(struct gpio_chip *gc, unsigned int offset)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+	struct gpio_shared_desc *shared_desc = proxy->shared_desc;
+	int ret;
+
+	guard(mutex)(&shared_desc->mutex);
+
+	if (proxy->voted_change) {
+		ret = gpio_shared_proxy_set_unlocked(proxy, shared_desc->def_val);
+		if (ret)
+			dev_err(proxy->dev,
+				"Failed to unset the shared GPIO value on release: %d\n", ret);
+	}
+
+	proxy->shared_desc->usecnt--;
+
+	dev_dbg(proxy->dev, "Shared GPIO freed, number of users: %u\n",
+		proxy->shared_desc->usecnt);
+}
+
+static int gpio_shared_proxy_set_config(struct gpio_chip *gc,
+					unsigned int offset, unsigned long cfg)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+	struct gpio_shared_desc *shared_desc = proxy->shared_desc;
+	struct gpio_desc *desc = shared_desc->desc;
+	int ret;
+
+	guard(mutex)(&shared_desc->mutex);
+
+	if (shared_desc->usecnt > 1) {
+		if (shared_desc->cfg != cfg) {
+			dev_dbg(proxy->dev,
+				"Shared GPIO's configuration already set, accepting changes but users may conflict!!\n");
+		} else {
+			dev_dbg(proxy->dev, "Equal config requested, nothing to do\n");
+			return 0;
+		}
+	}
+
+	ret = gpiod_set_config(desc, cfg);
+	if (ret && ret != -ENOTSUPP)
+		return ret;
+
+	shared_desc->cfg = cfg;
+	return 0;
+}
+
+static int gpio_shared_proxy_direction_input(struct gpio_chip *gc,
+					     unsigned int offset)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+	struct gpio_shared_desc *shared_desc = proxy->shared_desc;
+	struct gpio_desc *desc = shared_desc->desc;
+	int dir;
+
+	guard(mutex)(&shared_desc->mutex);
+
+	if (shared_desc->usecnt == 1) {
+		dev_dbg(proxy->dev,
+			"Only one user of this shared GPIO, allowing to set direction to input\n");
+
+		return gpiod_direction_input(desc);
+	}
+
+	dir = gpiod_get_direction(desc);
+	if (dir < 0)
+		return dir;
+
+	if (dir == GPIO_LINE_DIRECTION_OUT) {
+		dev_dbg(proxy->dev,
+			"Shared GPIO's direction already set to output, refusing to change\n");
+		return -EPERM;
+	}
+
+	return 0;
+}
+
+static int gpio_shared_proxy_direction_output(struct gpio_chip *gc,
+					      unsigned int offset, int value)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+	struct gpio_shared_desc *shared_desc = proxy->shared_desc;
+	struct gpio_desc *desc = shared_desc->desc;
+	int ret, dir;
+
+	guard(mutex)(&shared_desc->mutex);
+
+	if (shared_desc->usecnt == 1) {
+		dev_dbg(proxy->dev,
+			"Only one user of this shared GPIO, allowing to set direction to output with value '%s'\n",
+			str_high_low(value));
+
+		ret = gpiod_direction_output(desc, value);
+		if (ret)
+			return ret;
+
+		shared_desc->def_val = value;
+		shared_desc->votecnt = 0;
+		proxy->voted_change = false;
+
+		return 0;
+	}
+
+	dir = gpiod_get_direction(desc);
+	if (dir < 0)
+		return dir;
+
+	if (dir == GPIO_LINE_DIRECTION_IN) {
+		dev_dbg(proxy->dev,
+			"Shared GPIO's direction already set to input, refusing to change\n");
+		return -EPERM;
+	}
+
+	return gpio_shared_proxy_set_unlocked(proxy, value);
+}
+
+static int gpio_shared_proxy_get_cansleep(struct gpio_chip *gc,
+					  unsigned int offset)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+
+	return gpiod_get_value_cansleep(proxy->shared_desc->desc);
+}
+
+static int gpio_shared_proxy_set_cansleep(struct gpio_chip *gc,
+					  unsigned int offset, int value)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+
+	guard(mutex)(&proxy->shared_desc->mutex);
+
+	return gpio_shared_proxy_set_unlocked(proxy, value);
+}
+
+static int gpio_shared_proxy_get_direction(struct gpio_chip *gc,
+					   unsigned int offset)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+
+	return gpiod_get_direction(proxy->shared_desc->desc);
+}
+
+static int gpio_shared_proxy_to_irq(struct gpio_chip *gc, unsigned int offset)
+{
+	struct gpio_shared_proxy_data *proxy = gpiochip_get_data(gc);
+
+	return gpiod_to_irq(proxy->shared_desc->desc);
+}
+
+static int gpio_shared_proxy_probe(struct auxiliary_device *adev,
+				   const struct auxiliary_device_id *id)
+{
+	struct gpio_shared_proxy_data *proxy;
+	struct gpio_shared_desc *shared_desc;
+	struct device *dev = &adev->dev;
+	struct gpio_chip *gc;
+
+	shared_desc = devm_gpiod_shared_get(dev);
+	if (IS_ERR(shared_desc))
+		return PTR_ERR(shared_desc);
+
+	proxy = devm_kzalloc(dev, sizeof(*proxy), GFP_KERNEL);
+	if (!proxy)
+		return -ENOMEM;
+
+	proxy->shared_desc = shared_desc;
+	proxy->dev = dev;
+
+	gc = &proxy->gc;
+	gc->base = -1;
+	gc->ngpio = 1;
+	gc->label = dev_name(dev);
+	gc->parent = dev;
+	gc->owner = THIS_MODULE;
+	/*
+	 * Under the descriptor mutex the proxy may call
+	 * gpiod_set_config()/gpiod_direction_*(), which can reach pinctrl
+	 * paths that take a mutex (e.g. gpiod_set_config() ->
+	 * gpiochip_generic_config() -> pinctrl_gpio_set_config()), independent
+	 * of the underlying chip's can_sleep. So the descriptor lock must be a
+	 * mutex and the proxy gpiochip is therefore always sleeping; drive the
+	 * underlying GPIO through the cansleep value accessors, which are valid
+	 * for both sleeping and non-sleeping chips.
+	 */
+	gc->can_sleep = true;
+
+	gc->request = gpio_shared_proxy_request;
+	gc->free = gpio_shared_proxy_free;
+	gc->set_config = gpio_shared_proxy_set_config;
+	gc->direction_input = gpio_shared_proxy_direction_input;
+	gc->direction_output = gpio_shared_proxy_direction_output;
+	gc->set = gpio_shared_proxy_set_cansleep;
+	gc->get = gpio_shared_proxy_get_cansleep;
+	gc->get_direction = gpio_shared_proxy_get_direction;
+	gc->to_irq = gpio_shared_proxy_to_irq;
+
+	return devm_gpiochip_add_data(dev, &proxy->gc, proxy);
+}
+
+static const struct auxiliary_device_id gpio_shared_proxy_id_table[] = {
+	{ .name = "gpiolib_shared.proxy" },
+	{},
+};
+MODULE_DEVICE_TABLE(auxiliary, gpio_shared_proxy_id_table);
+
+static struct auxiliary_driver gpio_shared_proxy_driver = {
+	.driver = {
+		.name = "gpio-shared-proxy",
+		.suppress_bind_attrs = true,
+	},
+	.probe = gpio_shared_proxy_probe,
+	.id_table = gpio_shared_proxy_id_table,
+};
+module_auxiliary_driver(gpio_shared_proxy_driver);
+
+MODULE_AUTHOR("Bartosz Golaszewski <bartosz.golaszewski@linaro.org>");
+MODULE_DESCRIPTION("Shared GPIO mux driver.");
+MODULE_LICENSE("GPL");