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, 332 insertions, 0 deletions

diff --git a/drivers/input/joystick/adc-joystick.c b/drivers/input/joystick/adc-joystick.c
new file mode 100644
index 000000000..4fa42f88b
--- /dev/null
+++ b/drivers/input/joystick/adc-joystick.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Input driver for joysticks connected over ADC.
+ * Copyright (c) 2019-2020 Artur Rojek <contact@artur-rojek.eu>
+ */
+#include <linux/ctype.h>
+#include <linux/input.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/consumer.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+
+#include <linux/unaligned.h>
+
+struct adc_joystick_axis {
+	u32 code;
+	bool inverted;
+};
+
+struct adc_joystick {
+	struct input_dev *input;
+	struct iio_cb_buffer *buffer;
+	struct iio_channel *chans;
+	unsigned int num_chans;
+	struct adc_joystick_axis axes[] __counted_by(num_chans);
+};
+
+static int adc_joystick_invert(struct input_dev *dev,
+			       unsigned int axis, int val)
+{
+	int min = input_abs_get_min(dev, axis);
+	int max = input_abs_get_max(dev, axis);
+
+	return (max + min) - val;
+}
+
+static void adc_joystick_poll(struct input_dev *input)
+{
+	struct adc_joystick *joy = input_get_drvdata(input);
+	int i, val, ret;
+
+	for (i = 0; i < joy->num_chans; i++) {
+		ret = iio_read_channel_raw(&joy->chans[i], &val);
+		if (ret < 0)
+			return;
+		if (joy->axes[i].inverted)
+			val = adc_joystick_invert(input, i, val);
+		input_report_abs(input, joy->axes[i].code, val);
+	}
+	input_sync(input);
+}
+
+static int adc_joystick_handle(const void *data, void *private)
+{
+	struct adc_joystick *joy = private;
+	enum iio_endian endianness;
+	int bytes, msb, val, idx, i;
+	const u16 *data_u16;
+	bool sign;
+
+	bytes = joy->chans[0].channel->scan_type.storagebits >> 3;
+
+	for (i = 0; i < joy->num_chans; ++i) {
+		idx = joy->chans[i].channel->scan_index;
+		endianness = joy->chans[i].channel->scan_type.endianness;
+		msb = joy->chans[i].channel->scan_type.realbits - 1;
+		sign = tolower(joy->chans[i].channel->scan_type.sign) == 's';
+
+		switch (bytes) {
+		case 1:
+			val = ((const u8 *)data)[idx];
+			break;
+		case 2:
+			data_u16 = (const u16 *)data + idx;
+
+			/*
+			 * Data is aligned to the sample size by IIO core.
+			 * Call `get_unaligned_xe16` to hide type casting.
+			 */
+			if (endianness == IIO_BE)
+				val = get_unaligned_be16(data_u16);
+			else if (endianness == IIO_LE)
+				val = get_unaligned_le16(data_u16);
+			else /* IIO_CPU */
+				val = *data_u16;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		val >>= joy->chans[i].channel->scan_type.shift;
+		if (sign)
+			val = sign_extend32(val, msb);
+		else
+			val &= GENMASK(msb, 0);
+		if (joy->axes[i].inverted)
+			val = adc_joystick_invert(joy->input, i, val);
+		input_report_abs(joy->input, joy->axes[i].code, val);
+	}
+
+	input_sync(joy->input);
+
+	return 0;
+}
+
+static int adc_joystick_open(struct input_dev *dev)
+{
+	struct adc_joystick *joy = input_get_drvdata(dev);
+	struct device *devp = &dev->dev;
+	int ret;
+
+	ret = iio_channel_start_all_cb(joy->buffer);
+	if (ret)
+		dev_err(devp, "Unable to start callback buffer: %d\n", ret);
+
+	return ret;
+}
+
+static void adc_joystick_close(struct input_dev *dev)
+{
+	struct adc_joystick *joy = input_get_drvdata(dev);
+
+	iio_channel_stop_all_cb(joy->buffer);
+}
+
+static void adc_joystick_cleanup(void *data)
+{
+	iio_channel_release_all_cb(data);
+}
+
+static int adc_joystick_set_axes(struct device *dev, struct adc_joystick *joy)
+{
+	struct adc_joystick_axis *axes = joy->axes;
+	s32 range[2], fuzz, flat;
+	unsigned int num_axes;
+	int error, i;
+
+	num_axes = device_get_child_node_count(dev);
+	if (!num_axes) {
+		dev_err(dev, "Unable to find child nodes\n");
+		return -EINVAL;
+	}
+
+	if (num_axes != joy->num_chans) {
+		dev_err(dev, "Got %d child nodes for %d channels\n",
+			num_axes, joy->num_chans);
+		return -EINVAL;
+	}
+
+	device_for_each_child_node_scoped(dev, child) {
+		error = fwnode_property_read_u32(child, "reg", &i);
+		if (error) {
+			dev_err(dev, "reg invalid or missing\n");
+			return error;
+		}
+
+		if (i >= num_axes) {
+			dev_err(dev, "No matching axis for reg %d\n", i);
+			return -EINVAL;
+		}
+
+		error = fwnode_property_read_u32(child, "linux,code",
+						 &axes[i].code);
+		if (error) {
+			dev_err(dev, "linux,code invalid or missing\n");
+			return error;
+		}
+
+		error = fwnode_property_read_u32_array(child, "abs-range",
+						       range, 2);
+		if (error) {
+			dev_err(dev, "abs-range invalid or missing\n");
+			return error;
+		}
+
+		if (range[0] > range[1]) {
+			dev_dbg(dev, "abs-axis %d inverted\n", i);
+			axes[i].inverted = true;
+			swap(range[0], range[1]);
+		}
+
+		if (fwnode_property_read_u32(child, "abs-fuzz", &fuzz))
+			fuzz = 0;
+
+		if (fwnode_property_read_u32(child, "abs-flat", &flat))
+			flat = 0;
+
+		input_set_abs_params(joy->input, axes[i].code,
+				     range[0], range[1], fuzz, flat);
+	}
+
+	return 0;
+}
+
+
+static int adc_joystick_count_channels(struct device *dev,
+				       const struct iio_channel *chans,
+				       bool polled,
+				       unsigned int *num_chans)
+{
+	int bits;
+	int i;
+
+	/*
+	 * Count how many channels we got. NULL terminated.
+	 * Do not check the storage size if using polling.
+	 */
+	for (i = 0; chans[i].indio_dev; i++) {
+		if (polled)
+			continue;
+		bits = chans[i].channel->scan_type.storagebits;
+		if (!bits || bits > 16) {
+			dev_err(dev, "Unsupported channel storage size\n");
+			return -EINVAL;
+		}
+		if (bits != chans[0].channel->scan_type.storagebits) {
+			dev_err(dev, "Channels must have equal storage size\n");
+			return -EINVAL;
+		}
+	}
+
+	*num_chans = i;
+	return 0;
+}
+
+static int adc_joystick_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct iio_channel *chans;
+	struct adc_joystick *joy;
+	struct input_dev *input;
+	unsigned int poll_interval = 0;
+	unsigned int num_chans;
+	int error;
+
+	chans = devm_iio_channel_get_all(dev);
+	error = PTR_ERR_OR_ZERO(chans);
+	if (error) {
+		if (error != -EPROBE_DEFER)
+			dev_err(dev, "Unable to get IIO channels");
+		return error;
+	}
+
+	error = device_property_read_u32(dev, "poll-interval", &poll_interval);
+	if (error) {
+		/* -EINVAL means the property is absent. */
+		if (error != -EINVAL)
+			return error;
+	} else if (poll_interval == 0) {
+		dev_err(dev, "Unable to get poll-interval\n");
+		return -EINVAL;
+	}
+
+	error = adc_joystick_count_channels(dev, chans, poll_interval != 0,
+					    &num_chans);
+	if (error)
+		return error;
+
+	joy = devm_kzalloc(dev, struct_size(joy, axes, num_chans), GFP_KERNEL);
+	if (!joy)
+		return -ENOMEM;
+
+	joy->chans = chans;
+	joy->num_chans = num_chans;
+
+	input = devm_input_allocate_device(dev);
+	if (!input) {
+		dev_err(dev, "Unable to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	joy->input = input;
+	input->name = pdev->name;
+	input->id.bustype = BUS_HOST;
+
+	error = adc_joystick_set_axes(dev, joy);
+	if (error)
+		return error;
+
+	if (poll_interval != 0) {
+		input_setup_polling(input, adc_joystick_poll);
+		input_set_poll_interval(input, poll_interval);
+	} else {
+		input->open = adc_joystick_open;
+		input->close = adc_joystick_close;
+
+		joy->buffer = iio_channel_get_all_cb(dev, adc_joystick_handle,
+						     joy);
+		if (IS_ERR(joy->buffer)) {
+			dev_err(dev, "Unable to allocate callback buffer\n");
+			return PTR_ERR(joy->buffer);
+		}
+
+		error = devm_add_action_or_reset(dev, adc_joystick_cleanup,
+						 joy->buffer);
+		if (error)  {
+			dev_err(dev, "Unable to add action\n");
+			return error;
+		}
+	}
+
+	input_set_drvdata(input, joy);
+
+	error = input_register_device(input);
+	if (error) {
+		dev_err(dev, "Unable to register input device\n");
+		return error;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id adc_joystick_of_match[] = {
+	{ .compatible = "adc-joystick", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, adc_joystick_of_match);
+
+static struct platform_driver adc_joystick_driver = {
+	.driver = {
+		.name = "adc-joystick",
+		.of_match_table = adc_joystick_of_match,
+	},
+	.probe = adc_joystick_probe,
+};
+module_platform_driver(adc_joystick_driver);
+
+MODULE_DESCRIPTION("Input driver for joysticks connected over ADC");
+MODULE_AUTHOR("Artur Rojek <contact@artur-rojek.eu>");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("IIO_CONSUMER");