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, 243 insertions, 0 deletions

diff --git a/drivers/iio/temperature/tmp117.c b/drivers/iio/temperature/tmp117.c
new file mode 100644
index 000000000..74cb8d62b
--- /dev/null
+++ b/drivers/iio/temperature/tmp117.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Digital temperature sensor with integrated Non-volatile memory
+ * Copyright (c) 2021 Puranjay Mohan <puranjay12@gmail.com>
+ *
+ * Driver for the Texas Instruments TMP117 Temperature Sensor
+ * (7-bit I2C slave address (0x48 - 0x4B), changeable via ADD pins)
+ *
+ * Note: This driver assumes that the sensor has been calibrated beforehand.
+ */
+
+#include <linux/array_size.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/property.h>
+#include <linux/regulator/consumer.h>
+
+#include <linux/iio/iio.h>
+
+#define TMP117_REG_TEMP			0x0
+#define TMP117_REG_CFGR			0x1
+#define TMP117_REG_HIGH_LIM		0x2
+#define TMP117_REG_LOW_LIM		0x3
+#define TMP117_REG_EEPROM_UL		0x4
+#define TMP117_REG_EEPROM1		0x5
+#define TMP117_REG_EEPROM2		0x6
+#define TMP117_REG_TEMP_OFFSET		0x7
+#define TMP117_REG_EEPROM3		0x8
+#define TMP117_REG_DEVICE_ID		0xF
+
+#define TMP117_RESOLUTION_10UC		78125
+#define MICRODEGREE_PER_10MILLIDEGREE	10000
+
+#define TMP116_DEVICE_ID		0x1116
+#define TMP117_DEVICE_ID		0x0117
+#define TMP119_DEVICE_ID		0x2117
+
+struct tmp117_data {
+	struct i2c_client *client;
+	s16 calibbias;
+};
+
+struct tmp11x_info {
+	const char *name;
+	struct iio_chan_spec const *channels;
+	int num_channels;
+};
+
+static int tmp117_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *channel, int *val,
+			   int *val2, long mask)
+{
+	struct tmp117_data *data = iio_priv(indio_dev);
+	s32 ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = i2c_smbus_read_word_swapped(data->client,
+						  TMP117_REG_TEMP);
+		if (ret < 0)
+			return ret;
+		*val = sign_extend32(ret, 15);
+		return IIO_VAL_INT;
+
+	case IIO_CHAN_INFO_CALIBBIAS:
+		ret = i2c_smbus_read_word_swapped(data->client,
+						  TMP117_REG_TEMP_OFFSET);
+		if (ret < 0)
+			return ret;
+		*val = sign_extend32(ret, 15);
+		return IIO_VAL_INT;
+
+	case IIO_CHAN_INFO_SCALE:
+		/*
+		 * Conversion from 10s of uC to mC
+		 * as IIO reports temperature in mC
+		 */
+		*val = TMP117_RESOLUTION_10UC / MICRODEGREE_PER_10MILLIDEGREE;
+		*val2 = (TMP117_RESOLUTION_10UC %
+					MICRODEGREE_PER_10MILLIDEGREE) * 100;
+
+		return IIO_VAL_INT_PLUS_MICRO;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tmp117_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec
+			    const *channel, int val, int val2, long mask)
+{
+	struct tmp117_data *data = iio_priv(indio_dev);
+	s16 off;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_CALIBBIAS:
+		off = clamp_t(int, val, S16_MIN, S16_MAX);
+		if (off == data->calibbias)
+			return 0;
+		data->calibbias = off;
+		return i2c_smbus_write_word_swapped(data->client,
+						TMP117_REG_TEMP_OFFSET, off);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_chan_spec tmp117_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_CALIBBIAS) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+	},
+};
+
+static const struct iio_chan_spec tmp116_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				      BIT(IIO_CHAN_INFO_SCALE),
+	},
+};
+
+static const struct tmp11x_info tmp116_channels_info = {
+	.name = "tmp116",
+	.channels = tmp116_channels,
+	.num_channels = ARRAY_SIZE(tmp116_channels)
+};
+
+static const struct tmp11x_info tmp117_channels_info = {
+	.name = "tmp117",
+	.channels = tmp117_channels,
+	.num_channels = ARRAY_SIZE(tmp117_channels)
+};
+
+static const struct tmp11x_info tmp119_channels_info = {
+	.name = "tmp119",
+	.channels = tmp117_channels,
+	.num_channels = ARRAY_SIZE(tmp117_channels)
+};
+
+static const struct iio_info tmp117_info = {
+	.read_raw = tmp117_read_raw,
+	.write_raw = tmp117_write_raw,
+};
+
+static int tmp117_probe(struct i2c_client *client)
+{
+	const struct tmp11x_info *match_data;
+	struct tmp117_data *data;
+	struct iio_dev *indio_dev;
+	int dev_id;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_WORD_DATA))
+		return -EOPNOTSUPP;
+
+	ret = devm_regulator_get_enable(&client->dev, "vcc");
+	if (ret)
+		return ret;
+
+	fsleep(1500);
+
+	dev_id = i2c_smbus_read_word_swapped(client, TMP117_REG_DEVICE_ID);
+	if (dev_id < 0)
+		return dev_id;
+
+	switch (dev_id) {
+	case TMP116_DEVICE_ID:
+		match_data = &tmp116_channels_info;
+		break;
+	case TMP117_DEVICE_ID:
+		match_data = &tmp117_channels_info;
+		break;
+	case TMP119_DEVICE_ID:
+		match_data = &tmp119_channels_info;
+		break;
+	default:
+		dev_info(&client->dev,
+			 "Unknown device id (0x%x), use fallback compatible\n",
+			 dev_id);
+		match_data = i2c_get_match_data(client);
+	}
+
+	if (!match_data)
+		return dev_err_probe(&client->dev, -ENODEV,
+				     "Failed to identify unsupported device\n");
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+	data->calibbias = 0;
+
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &tmp117_info;
+	indio_dev->channels = match_data->channels;
+	indio_dev->num_channels = match_data->num_channels;
+	indio_dev->name = match_data->name;
+
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static const struct of_device_id tmp117_of_match[] = {
+	{ .compatible = "ti,tmp116", .data = &tmp116_channels_info },
+	{ .compatible = "ti,tmp117", .data = &tmp117_channels_info },
+	{ .compatible = "ti,tmp119", .data = &tmp119_channels_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tmp117_of_match);
+
+static const struct i2c_device_id tmp117_id[] = {
+	{ .name = "tmp116", .driver_data = (kernel_ulong_t)&tmp116_channels_info },
+	{ .name = "tmp117", .driver_data = (kernel_ulong_t)&tmp117_channels_info },
+	{ .name = "tmp119", .driver_data = (kernel_ulong_t)&tmp119_channels_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, tmp117_id);
+
+static struct i2c_driver tmp117_driver = {
+	.driver = {
+		.name	= "tmp117",
+		.of_match_table = tmp117_of_match,
+	},
+	.probe		= tmp117_probe,
+	.id_table	= tmp117_id,
+};
+module_i2c_driver(tmp117_driver);
+
+MODULE_AUTHOR("Puranjay Mohan <puranjay12@gmail.com>");
+MODULE_DESCRIPTION("TI TMP117 Temperature sensor driver");
+MODULE_LICENSE("GPL");