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, 217 insertions, 0 deletions

diff --git a/drivers/hwmon/g760a.c b/drivers/hwmon/g760a.c
new file mode 100644
index 000000000..e2166ee76
--- /dev/null
+++ b/drivers/hwmon/g760a.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * g760a - Driver for the Global Mixed-mode Technology Inc. G760A
+ *	   fan speed PWM controller chip
+ *
+ * Copyright (C) 2007  Herbert Valerio Riedel <hvr@gnu.org>
+ *
+ * Complete datasheet is available at GMT's website:
+ * http://www.gmt.com.tw/product/datasheet/EDS-760A.pdf
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/i2c.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/sysfs.h>
+
+enum g760a_regs {
+	G760A_REG_SET_CNT = 0x00,
+	G760A_REG_ACT_CNT = 0x01,
+	G760A_REG_FAN_STA = 0x02
+};
+
+#define G760A_REG_FAN_STA_RPM_OFF 0x1 /* +/-20% off */
+#define G760A_REG_FAN_STA_RPM_LOW 0x2 /* below 1920rpm */
+
+/* register data is read (and cached) at most once per second */
+#define G760A_UPDATE_INTERVAL (HZ)
+
+struct g760a_data {
+	struct i2c_client *client;
+	struct mutex update_lock;
+
+	/* board specific parameters */
+	u32 clk; /* default 32kHz */
+	u16 fan_div; /* default P=2 */
+
+	/* g760a register cache */
+	unsigned int valid:1;
+	unsigned long last_updated; /* In jiffies */
+
+	u8 set_cnt; /* PWM (period) count number; 0xff stops fan */
+	u8 act_cnt; /*   formula: cnt = (CLK * 30)/(rpm * P) */
+	u8 fan_sta; /* bit 0: set when actual fan speed more than 20%
+		     *   outside requested fan speed
+		     * bit 1: set when fan speed below 1920 rpm
+		     */
+};
+
+#define G760A_DEFAULT_CLK 32768
+#define G760A_DEFAULT_FAN_DIV 2
+
+#define PWM_FROM_CNT(cnt)	(0xff-(cnt))
+#define PWM_TO_CNT(pwm)		(0xff-(pwm))
+
+static inline unsigned int rpm_from_cnt(u8 val, u32 clk, u16 div)
+{
+	return ((val == 0x00) ? 0 : ((clk*30)/(val*div)));
+}
+
+/* read/write wrappers */
+static int g760a_read_value(struct i2c_client *client, enum g760a_regs reg)
+{
+	return i2c_smbus_read_byte_data(client, reg);
+}
+
+static int g760a_write_value(struct i2c_client *client, enum g760a_regs reg,
+			     u16 value)
+{
+	return i2c_smbus_write_byte_data(client, reg, value);
+}
+
+/*
+ * sysfs attributes
+ */
+
+static struct g760a_data *g760a_update_client(struct device *dev)
+{
+	struct g760a_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+
+	mutex_lock(&data->update_lock);
+
+	if (time_after(jiffies, data->last_updated + G760A_UPDATE_INTERVAL)
+	    || !data->valid) {
+		dev_dbg(&client->dev, "Starting g760a update\n");
+
+		data->set_cnt = g760a_read_value(client, G760A_REG_SET_CNT);
+		data->act_cnt = g760a_read_value(client, G760A_REG_ACT_CNT);
+		data->fan_sta = g760a_read_value(client, G760A_REG_FAN_STA);
+
+		data->last_updated = jiffies;
+		data->valid = true;
+	}
+
+	mutex_unlock(&data->update_lock);
+
+	return data;
+}
+
+static ssize_t fan1_input_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
+{
+	struct g760a_data *data = g760a_update_client(dev);
+	unsigned int rpm = 0;
+
+	mutex_lock(&data->update_lock);
+	if (!(data->fan_sta & G760A_REG_FAN_STA_RPM_LOW))
+		rpm = rpm_from_cnt(data->act_cnt, data->clk, data->fan_div);
+	mutex_unlock(&data->update_lock);
+
+	return sprintf(buf, "%d\n", rpm);
+}
+
+static ssize_t fan1_alarm_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
+{
+	struct g760a_data *data = g760a_update_client(dev);
+
+	int fan_alarm = (data->fan_sta & G760A_REG_FAN_STA_RPM_OFF) ? 1 : 0;
+
+	return sprintf(buf, "%d\n", fan_alarm);
+}
+
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *da,
+			 char *buf)
+{
+	struct g760a_data *data = g760a_update_client(dev);
+
+	return sprintf(buf, "%d\n", PWM_FROM_CNT(data->set_cnt));
+}
+
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *da,
+			  const char *buf, size_t count)
+{
+	struct g760a_data *data = g760a_update_client(dev);
+	struct i2c_client *client = data->client;
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	mutex_lock(&data->update_lock);
+	data->set_cnt = PWM_TO_CNT(clamp_val(val, 0, 255));
+	g760a_write_value(client, G760A_REG_SET_CNT, data->set_cnt);
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RO(fan1_alarm);
+
+static struct attribute *g760a_attrs[] = {
+	&dev_attr_pwm1.attr,
+	&dev_attr_fan1_input.attr,
+	&dev_attr_fan1_alarm.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(g760a);
+
+/*
+ * new-style driver model code
+ */
+
+static int g760a_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct g760a_data *data;
+	struct device *hwmon_dev;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+		return -EIO;
+
+	data = devm_kzalloc(dev, sizeof(struct g760a_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	mutex_init(&data->update_lock);
+
+	/* setup default configuration for now */
+	data->fan_div = G760A_DEFAULT_FAN_DIV;
+	data->clk = G760A_DEFAULT_CLK;
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
+							   data,
+							   g760a_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id g760a_id[] = {
+	{ .name = "g760a" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, g760a_id);
+
+static struct i2c_driver g760a_driver = {
+	.driver = {
+		.name	= "g760a",
+	},
+	.probe = g760a_probe,
+	.id_table = g760a_id,
+};
+
+module_i2c_driver(g760a_driver);
+
+MODULE_AUTHOR("Herbert Valerio Riedel <hvr@gnu.org>");
+MODULE_DESCRIPTION("GMT G760A driver");
+MODULE_LICENSE("GPL");