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, 205 insertions, 0 deletions

diff --git a/drivers/input/keyboard/adc-keys.c b/drivers/input/keyboard/adc-keys.c
new file mode 100644
index 000000000..d687459a0
--- /dev/null
+++ b/drivers/input/keyboard/adc-keys.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Input driver for resistor ladder connected on ADC
+ *
+ * Copyright (c) 2016 Alexandre Belloni
+ */
+
+#include <linux/err.h>
+#include <linux/iio/consumer.h>
+#include <linux/iio/types.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/slab.h>
+
+struct adc_keys_button {
+	u32 voltage;
+	u32 keycode;
+};
+
+struct adc_keys_state {
+	struct iio_channel *channel;
+	u32 num_keys;
+	u32 last_key;
+	u32 keyup_voltage;
+	const struct adc_keys_button *map;
+};
+
+static void adc_keys_poll(struct input_dev *input)
+{
+	struct adc_keys_state *st = input_get_drvdata(input);
+	int i, value, ret;
+	u32 diff, closest = 0xffffffff;
+	int keycode = 0;
+
+	ret = iio_read_channel_processed(st->channel, &value);
+	if (unlikely(ret < 0)) {
+		/* Forcibly release key if any was pressed */
+		value = st->keyup_voltage;
+	} else {
+		for (i = 0; i < st->num_keys; i++) {
+			diff = abs(st->map[i].voltage - value);
+			if (diff < closest) {
+				closest = diff;
+				keycode = st->map[i].keycode;
+			}
+		}
+	}
+
+	if (abs(st->keyup_voltage - value) < closest)
+		keycode = 0;
+
+	if (st->last_key && st->last_key != keycode)
+		input_report_key(input, st->last_key, 0);
+
+	if (keycode)
+		input_report_key(input, keycode, 1);
+
+	input_sync(input);
+	st->last_key = keycode;
+}
+
+static int adc_keys_load_keymap(struct device *dev, struct adc_keys_state *st)
+{
+	struct adc_keys_button *map;
+	int i;
+
+	st->num_keys = device_get_child_node_count(dev);
+	if (st->num_keys == 0) {
+		dev_err(dev, "keymap is missing\n");
+		return -EINVAL;
+	}
+
+	map = devm_kmalloc_array(dev, st->num_keys, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	i = 0;
+	device_for_each_child_node_scoped(dev, child) {
+		if (fwnode_property_read_u32(child, "press-threshold-microvolt",
+					     &map[i].voltage)) {
+			dev_err(dev, "Key with invalid or missing voltage\n");
+			return -EINVAL;
+		}
+		map[i].voltage /= 1000;
+
+		if (fwnode_property_read_u32(child, "linux,code",
+					     &map[i].keycode)) {
+			dev_err(dev, "Key with invalid or missing linux,code\n");
+			return -EINVAL;
+		}
+
+		i++;
+	}
+
+	st->map = map;
+	return 0;
+}
+
+static int adc_keys_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct adc_keys_state *st;
+	struct input_dev *input;
+	enum iio_chan_type type;
+	int i, value;
+	int error;
+
+	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return -ENOMEM;
+
+	st->channel = devm_iio_channel_get(dev, "buttons");
+	if (IS_ERR(st->channel))
+		return PTR_ERR(st->channel);
+
+	if (!st->channel->indio_dev)
+		return -ENXIO;
+
+	error = iio_get_channel_type(st->channel, &type);
+	if (error < 0)
+		return error;
+
+	if (type != IIO_VOLTAGE) {
+		dev_err(dev, "Incompatible channel type %d\n", type);
+		return -EINVAL;
+	}
+
+	if (device_property_read_u32(dev, "keyup-threshold-microvolt",
+				     &st->keyup_voltage)) {
+		dev_err(dev, "Invalid or missing keyup voltage\n");
+		return -EINVAL;
+	}
+	st->keyup_voltage /= 1000;
+
+	error = adc_keys_load_keymap(dev, st);
+	if (error)
+		return error;
+
+	input = devm_input_allocate_device(dev);
+	if (!input) {
+		dev_err(dev, "failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	input_set_drvdata(input, st);
+
+	input->name = pdev->name;
+	input->phys = "adc-keys/input0";
+
+	input->id.bustype = BUS_HOST;
+	input->id.vendor = 0x0001;
+	input->id.product = 0x0001;
+	input->id.version = 0x0100;
+
+	__set_bit(EV_KEY, input->evbit);
+	for (i = 0; i < st->num_keys; i++)
+		__set_bit(st->map[i].keycode, input->keybit);
+
+	if (device_property_read_bool(dev, "autorepeat"))
+		__set_bit(EV_REP, input->evbit);
+
+
+	error = input_setup_polling(input, adc_keys_poll);
+	if (error) {
+		dev_err(dev, "Unable to set up polling: %d\n", error);
+		return error;
+	}
+
+	if (!device_property_read_u32(dev, "poll-interval", &value))
+		input_set_poll_interval(input, value);
+
+	error = input_register_device(input);
+	if (error) {
+		dev_err(dev, "Unable to register input device: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id adc_keys_of_match[] = {
+	{ .compatible = "adc-keys", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, adc_keys_of_match);
+#endif
+
+static struct platform_driver adc_keys_driver = {
+	.driver = {
+		.name = "adc_keys",
+		.of_match_table = of_match_ptr(adc_keys_of_match),
+	},
+	.probe = adc_keys_probe,
+};
+module_platform_driver(adc_keys_driver);
+
+MODULE_AUTHOR("Alexandre Belloni <alexandre.belloni@free-electrons.com>");
+MODULE_DESCRIPTION("Input driver for resistor ladder connected on ADC");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("IIO_CONSUMER");