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, 259 insertions, 0 deletions

diff --git a/drivers/gpio/gpio-raspberrypi-exp.c b/drivers/gpio/gpio-raspberrypi-exp.c
new file mode 100644
index 000000000..40413e06b
--- /dev/null
+++ b/drivers/gpio/gpio-raspberrypi-exp.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *  Raspberry Pi 3 expander GPIO driver
+ *
+ *  Uses the firmware mailbox service to communicate with the
+ *  GPIO expander on the VPU.
+ *
+ *  Copyright (C) 2017 Raspberry Pi Trading Ltd.
+ */
+
+#include <linux/err.h>
+#include <linux/gpio/driver.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <soc/bcm2835/raspberrypi-firmware.h>
+
+#define MODULE_NAME "raspberrypi-exp-gpio"
+#define NUM_GPIO 8
+
+#define RPI_EXP_GPIO_BASE	128
+
+#define RPI_EXP_GPIO_DIR_IN	0
+#define RPI_EXP_GPIO_DIR_OUT	1
+
+struct rpi_exp_gpio {
+	struct gpio_chip gc;
+	struct rpi_firmware *fw;
+};
+
+/* VC4 firmware mailbox interface data structures */
+
+struct gpio_set_config {
+	u32 gpio;
+	u32 direction;
+	u32 polarity;
+	u32 term_en;
+	u32 term_pull_up;
+	u32 state;
+};
+
+struct gpio_get_config {
+	u32 gpio;
+	u32 direction;
+	u32 polarity;
+	u32 term_en;
+	u32 term_pull_up;
+};
+
+struct gpio_get_set_state {
+	u32 gpio;
+	u32 state;
+};
+
+static int rpi_exp_gpio_get_polarity(struct gpio_chip *gc, unsigned int off)
+{
+	struct rpi_exp_gpio *gpio;
+	struct gpio_get_config get;
+	int ret;
+
+	gpio = gpiochip_get_data(gc);
+
+	get.gpio = off + RPI_EXP_GPIO_BASE;	/* GPIO to update */
+
+	ret = rpi_firmware_property(gpio->fw, RPI_FIRMWARE_GET_GPIO_CONFIG,
+				    &get, sizeof(get));
+	if (ret || get.gpio != 0) {
+		dev_err(gc->parent, "Failed to get GPIO %u config (%d %x)\n",
+			off, ret, get.gpio);
+		return ret ? ret : -EIO;
+	}
+	return get.polarity;
+}
+
+static int rpi_exp_gpio_dir_in(struct gpio_chip *gc, unsigned int off)
+{
+	struct rpi_exp_gpio *gpio;
+	struct gpio_set_config set_in;
+	int ret;
+
+	gpio = gpiochip_get_data(gc);
+
+	set_in.gpio = off + RPI_EXP_GPIO_BASE;	/* GPIO to update */
+	set_in.direction = RPI_EXP_GPIO_DIR_IN;
+	set_in.term_en = 0;		/* termination disabled */
+	set_in.term_pull_up = 0;	/* n/a as termination disabled */
+	set_in.state = 0;		/* n/a as configured as an input */
+
+	ret = rpi_exp_gpio_get_polarity(gc, off);
+	if (ret < 0)
+		return ret;
+	set_in.polarity = ret;		/* Retain existing setting */
+
+	ret = rpi_firmware_property(gpio->fw, RPI_FIRMWARE_SET_GPIO_CONFIG,
+				    &set_in, sizeof(set_in));
+	if (ret || set_in.gpio != 0) {
+		dev_err(gc->parent, "Failed to set GPIO %u to input (%d %x)\n",
+			off, ret, set_in.gpio);
+		return ret ? ret : -EIO;
+	}
+	return 0;
+}
+
+static int rpi_exp_gpio_dir_out(struct gpio_chip *gc, unsigned int off, int val)
+{
+	struct rpi_exp_gpio *gpio;
+	struct gpio_set_config set_out;
+	int ret;
+
+	gpio = gpiochip_get_data(gc);
+
+	set_out.gpio = off + RPI_EXP_GPIO_BASE;	/* GPIO to update */
+	set_out.direction = RPI_EXP_GPIO_DIR_OUT;
+	set_out.term_en = 0;		/* n/a as an output */
+	set_out.term_pull_up = 0;	/* n/a as termination disabled */
+	set_out.state = val;		/* Output state */
+
+	ret = rpi_exp_gpio_get_polarity(gc, off);
+	if (ret < 0)
+		return ret;
+	set_out.polarity = ret;		/* Retain existing setting */
+
+	ret = rpi_firmware_property(gpio->fw, RPI_FIRMWARE_SET_GPIO_CONFIG,
+				    &set_out, sizeof(set_out));
+	if (ret || set_out.gpio != 0) {
+		dev_err(gc->parent, "Failed to set GPIO %u to output (%d %x)\n",
+			off, ret, set_out.gpio);
+		return ret ? ret : -EIO;
+	}
+	return 0;
+}
+
+static int rpi_exp_gpio_get_direction(struct gpio_chip *gc, unsigned int off)
+{
+	struct rpi_exp_gpio *gpio;
+	struct gpio_get_config get;
+	int ret;
+
+	gpio = gpiochip_get_data(gc);
+
+	get.gpio = off + RPI_EXP_GPIO_BASE;	/* GPIO to update */
+
+	ret = rpi_firmware_property(gpio->fw, RPI_FIRMWARE_GET_GPIO_CONFIG,
+				    &get, sizeof(get));
+	if (ret || get.gpio != 0) {
+		dev_err(gc->parent,
+			"Failed to get GPIO %u config (%d %x)\n", off, ret,
+			get.gpio);
+		return ret ? ret : -EIO;
+	}
+	if (get.direction)
+		return GPIO_LINE_DIRECTION_OUT;
+
+	return GPIO_LINE_DIRECTION_IN;
+}
+
+static int rpi_exp_gpio_get(struct gpio_chip *gc, unsigned int off)
+{
+	struct rpi_exp_gpio *gpio;
+	struct gpio_get_set_state get;
+	int ret;
+
+	gpio = gpiochip_get_data(gc);
+
+	get.gpio = off + RPI_EXP_GPIO_BASE;	/* GPIO to update */
+	get.state = 0;		/* storage for returned value */
+
+	ret = rpi_firmware_property(gpio->fw, RPI_FIRMWARE_GET_GPIO_STATE,
+					 &get, sizeof(get));
+	if (ret || get.gpio != 0) {
+		dev_err(gc->parent,
+			"Failed to get GPIO %u state (%d %x)\n", off, ret,
+			get.gpio);
+		return ret ? ret : -EIO;
+	}
+	return !!get.state;
+}
+
+static int rpi_exp_gpio_set(struct gpio_chip *gc, unsigned int off, int val)
+{
+	struct rpi_exp_gpio *gpio;
+	struct gpio_get_set_state set;
+	int ret;
+
+	gpio = gpiochip_get_data(gc);
+
+	set.gpio = off + RPI_EXP_GPIO_BASE;	/* GPIO to update */
+	set.state = val;	/* Output state */
+
+	ret = rpi_firmware_property(gpio->fw, RPI_FIRMWARE_SET_GPIO_STATE,
+					 &set, sizeof(set));
+	if (ret || set.gpio != 0) {
+		dev_err(gc->parent,
+			"Failed to set GPIO %u state (%d %x)\n", off, ret,
+			set.gpio);
+		return ret ? ret : -EIO;
+	}
+
+	return 0;
+}
+
+static int rpi_exp_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device_node *fw_node;
+	struct rpi_firmware *fw;
+	struct rpi_exp_gpio *rpi_gpio;
+
+	fw_node = of_get_parent(np);
+	if (!fw_node) {
+		dev_err(dev, "Missing firmware node\n");
+		return -ENOENT;
+	}
+
+	fw = devm_rpi_firmware_get(&pdev->dev, fw_node);
+	of_node_put(fw_node);
+	if (!fw)
+		return -EPROBE_DEFER;
+
+	rpi_gpio = devm_kzalloc(dev, sizeof(*rpi_gpio), GFP_KERNEL);
+	if (!rpi_gpio)
+		return -ENOMEM;
+
+	rpi_gpio->fw = fw;
+	rpi_gpio->gc.parent = dev;
+	rpi_gpio->gc.label = MODULE_NAME;
+	rpi_gpio->gc.owner = THIS_MODULE;
+	rpi_gpio->gc.base = -1;
+	rpi_gpio->gc.ngpio = NUM_GPIO;
+
+	rpi_gpio->gc.direction_input = rpi_exp_gpio_dir_in;
+	rpi_gpio->gc.direction_output = rpi_exp_gpio_dir_out;
+	rpi_gpio->gc.get_direction = rpi_exp_gpio_get_direction;
+	rpi_gpio->gc.get = rpi_exp_gpio_get;
+	rpi_gpio->gc.set = rpi_exp_gpio_set;
+	rpi_gpio->gc.can_sleep = true;
+
+	return devm_gpiochip_add_data(dev, &rpi_gpio->gc, rpi_gpio);
+}
+
+static const struct of_device_id rpi_exp_gpio_ids[] = {
+	{ .compatible = "raspberrypi,firmware-gpio" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, rpi_exp_gpio_ids);
+
+static struct platform_driver rpi_exp_gpio_driver = {
+	.driver	= {
+		.name		= MODULE_NAME,
+		.of_match_table	= rpi_exp_gpio_ids,
+	},
+	.probe	= rpi_exp_gpio_probe,
+};
+module_platform_driver(rpi_exp_gpio_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dave Stevenson <dave.stevenson@raspberrypi.org>");
+MODULE_DESCRIPTION("Raspberry Pi 3 expander GPIO driver");
+MODULE_ALIAS("platform:rpi-exp-gpio");