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, 213 insertions, 0 deletions

diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
new file mode 100644
index 000000000..f8f2f621d
--- /dev/null
+++ b/drivers/hwmon/ads7828.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * ads7828.c - driver for TI ADS7828 8-channel A/D converter and compatibles
+ * (C) 2007 EADS Astrium
+ *
+ * This driver is based on the lm75 and other lm_sensors/hwmon drivers
+ *
+ * Written by Steve Hardy <shardy@redhat.com>
+ *
+ * ADS7830 support, by Guillaume Roguez <guillaume.roguez@savoirfairelinux.com>
+ *
+ * For further information, see the Documentation/hwmon/ads7828.rst file.
+ */
+
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_data/ads7828.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/regulator/consumer.h>
+
+/* The ADS7828 registers */
+#define ADS7828_CMD_SD_SE	0x80	/* Single ended inputs */
+#define ADS7828_CMD_PD1		0x04	/* Internal vref OFF && A/D ON */
+#define ADS7828_CMD_PD3		0x0C	/* Internal vref ON && A/D ON */
+#define ADS7828_INT_VREF_MV	2500	/* Internal vref is 2.5V, 2500mV */
+#define ADS7828_EXT_VREF_MV_MIN	50	/* External vref min value 0.05V */
+#define ADS7828_EXT_VREF_MV_MAX	5250	/* External vref max value 5.25V */
+
+/* List of supported devices */
+enum ads7828_chips { ads7828, ads7830 };
+
+/* Client specific data */
+struct ads7828_data {
+	struct regmap *regmap;
+	u8 cmd_byte;			/* Command byte without channel bits */
+	unsigned int lsb_resol;		/* Resolution of the ADC sample LSB */
+};
+
+/* Command byte C2,C1,C0 - see datasheet */
+static inline u8 ads7828_cmd_byte(u8 cmd, int ch)
+{
+	return cmd | (((ch >> 1) | (ch & 0x01) << 2) << 4);
+}
+
+/* sysfs callback function */
+static ssize_t ads7828_in_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	struct ads7828_data *data = dev_get_drvdata(dev);
+	u8 cmd = ads7828_cmd_byte(data->cmd_byte, attr->index);
+	unsigned int regval;
+	int err;
+
+	err = regmap_read(data->regmap, cmd, &regval);
+	if (err < 0)
+		return err;
+
+	return sysfs_emit(buf, "%d\n",
+			  DIV_ROUND_CLOSEST(regval * data->lsb_resol, 1000));
+}
+
+static SENSOR_DEVICE_ATTR_RO(in0_input, ads7828_in, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, ads7828_in, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, ads7828_in, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, ads7828_in, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, ads7828_in, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, ads7828_in, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, ads7828_in, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_input, ads7828_in, 7);
+
+static struct attribute *ads7828_attrs[] = {
+	&sensor_dev_attr_in0_input.dev_attr.attr,
+	&sensor_dev_attr_in1_input.dev_attr.attr,
+	&sensor_dev_attr_in2_input.dev_attr.attr,
+	&sensor_dev_attr_in3_input.dev_attr.attr,
+	&sensor_dev_attr_in4_input.dev_attr.attr,
+	&sensor_dev_attr_in5_input.dev_attr.attr,
+	&sensor_dev_attr_in6_input.dev_attr.attr,
+	&sensor_dev_attr_in7_input.dev_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(ads7828);
+
+static const struct regmap_config ads2828_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+};
+
+static const struct regmap_config ads2830_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
+static int ads7828_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct ads7828_platform_data *pdata = dev_get_platdata(dev);
+	struct ads7828_data *data;
+	struct device *hwmon_dev;
+	unsigned int vref_mv = ADS7828_INT_VREF_MV;
+	int vref_uv;
+	bool diff_input = false;
+	bool ext_vref = false;
+	unsigned int regval;
+	enum ads7828_chips chip;
+
+	data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	if (pdata) {
+		diff_input = pdata->diff_input;
+		ext_vref = pdata->ext_vref;
+		if (ext_vref && pdata->vref_mv)
+			vref_mv = pdata->vref_mv;
+	} else if (dev->of_node) {
+		diff_input = of_property_read_bool(dev->of_node,
+						   "ti,differential-input");
+		vref_uv = devm_regulator_get_enable_read_voltage(dev, "vref");
+		if (vref_uv < 0) {
+			if (vref_uv != -ENODEV)
+				return vref_uv;
+		} else {
+			vref_mv = DIV_ROUND_CLOSEST(vref_uv, 1000);
+			if (vref_mv < ADS7828_EXT_VREF_MV_MIN ||
+			    vref_mv > ADS7828_EXT_VREF_MV_MAX)
+				return -EINVAL;
+			ext_vref = true;
+		}
+	}
+
+	chip = (uintptr_t)i2c_get_match_data(client);
+
+	/* Bound Vref with min/max values */
+	vref_mv = clamp_val(vref_mv, ADS7828_EXT_VREF_MV_MIN,
+			    ADS7828_EXT_VREF_MV_MAX);
+
+	/* ADS7828 uses 12-bit samples, while ADS7830 is 8-bit */
+	if (chip == ads7828) {
+		data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 4096);
+		data->regmap = devm_regmap_init_i2c(client,
+						    &ads2828_regmap_config);
+	} else {
+		data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 256);
+		data->regmap = devm_regmap_init_i2c(client,
+						    &ads2830_regmap_config);
+	}
+
+	if (IS_ERR(data->regmap))
+		return PTR_ERR(data->regmap);
+
+	data->cmd_byte = ext_vref ? ADS7828_CMD_PD1 : ADS7828_CMD_PD3;
+	if (!diff_input)
+		data->cmd_byte |= ADS7828_CMD_SD_SE;
+
+	/*
+	 * Datasheet specifies internal reference voltage is disabled by
+	 * default. The internal reference voltage needs to be enabled and
+	 * voltage needs to settle before getting valid ADC data. So perform a
+	 * dummy read to enable the internal reference voltage.
+	 */
+	if (!ext_vref)
+		regmap_read(data->regmap, data->cmd_byte, &regval);
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
+							   data,
+							   ads7828_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id ads7828_device_ids[] = {
+	{ .name = "ads7828", .driver_data = ads7828 },
+	{ .name = "ads7830", .driver_data = ads7830 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, ads7828_device_ids);
+
+static const struct of_device_id __maybe_unused ads7828_of_match[] = {
+	{
+		.compatible = "ti,ads7828",
+		.data = (void *)ads7828
+	},
+	{
+		.compatible = "ti,ads7830",
+		.data = (void *)ads7830
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ads7828_of_match);
+
+static struct i2c_driver ads7828_driver = {
+	.driver = {
+		.name = "ads7828",
+		.of_match_table = of_match_ptr(ads7828_of_match),
+	},
+
+	.id_table = ads7828_device_ids,
+	.probe = ads7828_probe,
+};
+
+module_i2c_driver(ads7828_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Steve Hardy <shardy@redhat.com>");
+MODULE_DESCRIPTION("Driver for TI ADS7828 A/D converter and compatibles");