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, 226 insertions, 0 deletions

diff --git a/drivers/misc/isl29020.c b/drivers/misc/isl29020.c
new file mode 100644
index 000000000..dd966db28
--- /dev/null
+++ b/drivers/misc/isl29020.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * isl29020.c - Intersil  ALS Driver
+ *
+ * Copyright (C) 2008 Intel Corp
+ *
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * Data sheet at: http://www.intersil.com/data/fn/fn6505.pdf
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/sysfs.h>
+#include <linux/pm_runtime.h>
+
+static DEFINE_MUTEX(mutex);
+
+static ssize_t als_sensing_range_show(struct device *dev,
+			struct device_attribute *attr,  char *buf)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int  val;
+
+	val = i2c_smbus_read_byte_data(client, 0x00);
+
+	if (val < 0)
+		return val;
+	return sprintf(buf, "%d000\n", 1 << (2 * (val & 3)));
+
+}
+
+static ssize_t als_lux_input_data_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret_val, val;
+	unsigned long int lux;
+	int temp;
+
+	pm_runtime_get_sync(dev);
+	msleep(100);
+
+	mutex_lock(&mutex);
+	temp = i2c_smbus_read_byte_data(client, 0x02); /* MSB data */
+	if (temp < 0) {
+		pm_runtime_put_sync(dev);
+		mutex_unlock(&mutex);
+		return temp;
+	}
+
+	ret_val = i2c_smbus_read_byte_data(client, 0x01); /* LSB data */
+	mutex_unlock(&mutex);
+
+	if (ret_val < 0) {
+		pm_runtime_put_sync(dev);
+		return ret_val;
+	}
+
+	ret_val |= temp << 8;
+	val = i2c_smbus_read_byte_data(client, 0x00);
+	pm_runtime_put_sync(dev);
+	if (val < 0)
+		return val;
+	lux = ((((1 << (2 * (val & 3))))*1000) * ret_val) / 65536;
+	return sprintf(buf, "%lu\n", lux);
+}
+
+static ssize_t als_sensing_range_store(struct device *dev,
+		struct device_attribute *attr, const  char *buf, size_t count)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret_val;
+	unsigned long val;
+
+	ret_val = kstrtoul(buf, 10, &val);
+	if (ret_val)
+		return ret_val;
+
+	if (val < 1 || val > 64000)
+		return -EINVAL;
+
+	/* Pick the smallest sensor range that will meet our requirements */
+	if (val <= 1000)
+		val = 1;
+	else if (val <= 4000)
+		val = 2;
+	else if (val <= 16000)
+		val = 3;
+	else
+		val = 4;
+
+	ret_val = i2c_smbus_read_byte_data(client, 0x00);
+	if (ret_val < 0)
+		return ret_val;
+
+	ret_val &= 0xFC; /*reset the bit before setting them */
+	ret_val |= val - 1;
+	ret_val = i2c_smbus_write_byte_data(client, 0x00, ret_val);
+
+	if (ret_val < 0)
+		return ret_val;
+	return count;
+}
+
+static void als_set_power_state(struct i2c_client *client, int enable)
+{
+	int ret_val;
+
+	ret_val = i2c_smbus_read_byte_data(client, 0x00);
+	if (ret_val < 0)
+		return;
+
+	if (enable)
+		ret_val |= 0x80;
+	else
+		ret_val &= 0x7F;
+
+	i2c_smbus_write_byte_data(client, 0x00, ret_val);
+}
+
+static DEVICE_ATTR(lux0_sensor_range, S_IRUGO | S_IWUSR,
+	als_sensing_range_show, als_sensing_range_store);
+static DEVICE_ATTR(lux0_input, S_IRUGO, als_lux_input_data_show, NULL);
+
+static struct attribute *mid_att_als[] = {
+	&dev_attr_lux0_sensor_range.attr,
+	&dev_attr_lux0_input.attr,
+	NULL
+};
+
+static const struct attribute_group m_als_gr = {
+	.name = "isl29020",
+	.attrs = mid_att_als
+};
+
+static int als_set_default_config(struct i2c_client *client)
+{
+	int retval;
+
+	retval = i2c_smbus_write_byte_data(client, 0x00, 0xc0);
+	if (retval < 0) {
+		dev_err(&client->dev, "default write failed.");
+		return retval;
+	}
+	return 0;
+}
+
+static int  isl29020_probe(struct i2c_client *client)
+{
+	int res;
+
+	res = als_set_default_config(client);
+	if (res <  0)
+		return res;
+
+	res = sysfs_create_group(&client->dev.kobj, &m_als_gr);
+	if (res) {
+		dev_err(&client->dev, "isl29020: device create file failed\n");
+		return res;
+	}
+	dev_info(&client->dev, "%s isl29020: ALS chip found\n", client->name);
+	als_set_power_state(client, 0);
+	pm_runtime_enable(&client->dev);
+	return res;
+}
+
+static void isl29020_remove(struct i2c_client *client)
+{
+	pm_runtime_disable(&client->dev);
+	sysfs_remove_group(&client->dev.kobj, &m_als_gr);
+}
+
+static const struct i2c_device_id isl29020_id[] = {
+	{ .name = "isl29020" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(i2c, isl29020_id);
+
+#ifdef CONFIG_PM
+
+static int isl29020_runtime_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	als_set_power_state(client, 0);
+	return 0;
+}
+
+static int isl29020_runtime_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	als_set_power_state(client, 1);
+	return 0;
+}
+
+static const struct dev_pm_ops isl29020_pm_ops = {
+	.runtime_suspend = isl29020_runtime_suspend,
+	.runtime_resume = isl29020_runtime_resume,
+};
+
+#define ISL29020_PM_OPS (&isl29020_pm_ops)
+#else	/* CONFIG_PM */
+#define ISL29020_PM_OPS NULL
+#endif	/* CONFIG_PM */
+
+static struct i2c_driver isl29020_driver = {
+	.driver = {
+		.name = "isl29020",
+		.pm = ISL29020_PM_OPS,
+	},
+	.probe = isl29020_probe,
+	.remove = isl29020_remove,
+	.id_table = isl29020_id,
+};
+
+module_i2c_driver(isl29020_driver);
+
+MODULE_AUTHOR("Kalhan Trisal <kalhan.trisal@intel.com>");
+MODULE_DESCRIPTION("Intersil isl29020 ALS Driver");
+MODULE_LICENSE("GPL v2");