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, 186 insertions, 0 deletions

diff --git a/drivers/iio/accel/da280.c b/drivers/iio/accel/da280.c
new file mode 100644
index 000000000..15acbe1c2
--- /dev/null
+++ b/drivers/iio/accel/da280.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IIO driver for the MiraMEMS DA217 and DA280 3-axis accelerometer and
+ * IIO driver for the MiraMEMS DA226 2-axis accelerometer
+ *
+ * Copyright (c) 2016 Hans de Goede <hdegoede@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/acpi.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/byteorder/generic.h>
+
+#define DA280_REG_CHIP_ID		0x01
+#define DA280_REG_ACC_X_LSB		0x02
+#define DA280_REG_ACC_Y_LSB		0x04
+#define DA280_REG_ACC_Z_LSB		0x06
+#define DA280_REG_MODE_BW		0x11
+
+#define DA280_CHIP_ID			0x13
+#define DA280_MODE_ENABLE		0x1e
+#define DA280_MODE_DISABLE		0x9e
+
+/*
+ * a value of + or -4096 corresponds to + or - 1G
+ * scale = 9.81 / 4096 = 0.002395019
+ */
+
+static const int da280_nscale = 2395019;
+
+#define DA280_CHANNEL(reg, axis) {	\
+	.type = IIO_ACCEL,	\
+	.address = reg,	\
+	.modified = 1,	\
+	.channel2 = IIO_MOD_##axis,	\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),	\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),	\
+}
+
+static const struct iio_chan_spec da280_channels[] = {
+	DA280_CHANNEL(DA280_REG_ACC_X_LSB, X),
+	DA280_CHANNEL(DA280_REG_ACC_Y_LSB, Y),
+	DA280_CHANNEL(DA280_REG_ACC_Z_LSB, Z),
+};
+
+struct da280_match_data {
+	const char *name;
+	int num_channels;
+};
+
+struct da280_data {
+	struct i2c_client *client;
+};
+
+static int da280_enable(struct i2c_client *client, bool enable)
+{
+	u8 data = enable ? DA280_MODE_ENABLE : DA280_MODE_DISABLE;
+
+	return i2c_smbus_write_byte_data(client, DA280_REG_MODE_BW, data);
+}
+
+static int da280_read_raw(struct iio_dev *indio_dev,
+				struct iio_chan_spec const *chan,
+				int *val, int *val2, long mask)
+{
+	struct da280_data *data = iio_priv(indio_dev);
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = i2c_smbus_read_word_data(data->client, chan->address);
+		if (ret < 0)
+			return ret;
+		/*
+		 * Values are 14 bits, stored as 16 bits with the 2
+		 * least significant bits always 0.
+		 */
+		*val = (short)ret >> 2;
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		*val = 0;
+		*val2 = da280_nscale;
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct iio_info da280_info = {
+	.read_raw	= da280_read_raw,
+};
+
+static void da280_disable(void *client)
+{
+	da280_enable(client, false);
+}
+
+static int da280_probe(struct i2c_client *client)
+{
+	const struct da280_match_data *match_data;
+	struct iio_dev *indio_dev;
+	struct da280_data *data;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(client, DA280_REG_CHIP_ID);
+	if (ret != DA280_CHIP_ID)
+		return (ret < 0) ? ret : -ENODEV;
+
+	match_data = i2c_get_match_data(client);
+	if (!match_data) {
+		dev_err(&client->dev, "Error match-data not set\n");
+		return -EINVAL;
+	}
+
+	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	data = iio_priv(indio_dev);
+	data->client = client;
+
+	indio_dev->info = &da280_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = da280_channels;
+	indio_dev->num_channels = match_data->num_channels;
+	indio_dev->name = match_data->name;
+
+	ret = da280_enable(client, true);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_add_action_or_reset(&client->dev, da280_disable, client);
+	if (ret)
+		return ret;
+
+	return devm_iio_device_register(&client->dev, indio_dev);
+}
+
+static int da280_suspend(struct device *dev)
+{
+	return da280_enable(to_i2c_client(dev), false);
+}
+
+static int da280_resume(struct device *dev)
+{
+	return da280_enable(to_i2c_client(dev), true);
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(da280_pm_ops, da280_suspend, da280_resume);
+
+static const struct da280_match_data da217_match_data = { "da217", 3 };
+static const struct da280_match_data da226_match_data = { "da226", 2 };
+static const struct da280_match_data da280_match_data = { "da280", 3 };
+
+static const struct acpi_device_id da280_acpi_match[] = {
+	{ "NSA2513", (kernel_ulong_t)&da217_match_data },
+	{ "MIRAACC", (kernel_ulong_t)&da280_match_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, da280_acpi_match);
+
+static const struct i2c_device_id da280_i2c_id[] = {
+	{ .name = "da217", .driver_data = (kernel_ulong_t)&da217_match_data },
+	{ .name = "da226", .driver_data = (kernel_ulong_t)&da226_match_data },
+	{ .name = "da280", .driver_data = (kernel_ulong_t)&da280_match_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, da280_i2c_id);
+
+static struct i2c_driver da280_driver = {
+	.driver = {
+		.name = "da280",
+		.acpi_match_table = da280_acpi_match,
+		.pm = pm_sleep_ptr(&da280_pm_ops),
+	},
+	.probe		= da280_probe,
+	.id_table	= da280_i2c_id,
+};
+
+module_i2c_driver(da280_driver);
+
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_DESCRIPTION("MiraMEMS DA280 3-Axis Accelerometer driver");
+MODULE_LICENSE("GPL v2");