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, 285 insertions, 0 deletions

diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c
new file mode 100644
index 000000000..0123ca815
--- /dev/null
+++ b/drivers/regulator/ad5398.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Voltage and current regulation for AD5398 and AD5821
+ *
+ * Copyright 2010 Analog Devices Inc.
+ *
+ * Enter bugs at http://blackfin.uclinux.org/
+ */
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+
+#define AD5398_SW_POWER_DOWN	BIT(15)
+
+struct ad5398_chip_info {
+	struct i2c_client *client;
+	int min_uA;
+	int max_uA;
+	unsigned int current_level;
+	unsigned int current_mask;
+	unsigned int current_offset;
+	struct regulator_dev *rdev;
+};
+
+static int ad5398_calc_current(struct ad5398_chip_info *chip,
+	unsigned selector)
+{
+	unsigned range_uA = chip->max_uA - chip->min_uA;
+
+	return chip->min_uA + (selector * range_uA / chip->current_level);
+}
+
+static int ad5398_read_reg(struct i2c_client *client, unsigned short *data)
+{
+	unsigned short val;
+	int ret;
+
+	ret = i2c_master_recv(client, (char *)&val, 2);
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C read error\n");
+		return ret;
+	}
+	*data = be16_to_cpu(val);
+
+	return ret;
+}
+
+static int ad5398_write_reg(struct i2c_client *client, const unsigned short data)
+{
+	unsigned short val;
+	int ret;
+
+	val = cpu_to_be16(data);
+	ret = i2c_master_send(client, (char *)&val, 2);
+	if (ret != 2) {
+		dev_err(&client->dev, "I2C write error\n");
+		return ret < 0 ? ret : -EIO;
+	}
+
+	return 0;
+}
+
+static int ad5398_get_current_limit(struct regulator_dev *rdev)
+{
+	struct ad5398_chip_info *chip = rdev_get_drvdata(rdev);
+	struct i2c_client *client = chip->client;
+	unsigned short data;
+	int ret;
+
+	ret = ad5398_read_reg(client, &data);
+	if (ret < 0)
+		return ret;
+
+	ret = (data & chip->current_mask) >> chip->current_offset;
+
+	return ad5398_calc_current(chip, ret);
+}
+
+static int ad5398_set_current_limit(struct regulator_dev *rdev, int min_uA, int max_uA)
+{
+	struct ad5398_chip_info *chip = rdev_get_drvdata(rdev);
+	struct i2c_client *client = chip->client;
+	unsigned range_uA = chip->max_uA - chip->min_uA;
+	unsigned selector;
+	unsigned short data;
+	int ret;
+
+	if (min_uA < chip->min_uA)
+		min_uA = chip->min_uA;
+	if (max_uA > chip->max_uA)
+		max_uA = chip->max_uA;
+
+	if (min_uA > chip->max_uA || max_uA < chip->min_uA)
+		return -EINVAL;
+
+	selector = DIV_ROUND_UP((min_uA - chip->min_uA) * chip->current_level,
+				range_uA);
+	if (ad5398_calc_current(chip, selector) > max_uA)
+		return -EINVAL;
+
+	dev_dbg(&client->dev, "changing current %duA\n",
+		ad5398_calc_current(chip, selector));
+
+	/* read chip enable bit */
+	ret = ad5398_read_reg(client, &data);
+	if (ret < 0)
+		return ret;
+
+	/* prepare register data */
+	selector = (selector << chip->current_offset) & chip->current_mask;
+	data = (unsigned short)selector | (data & AD5398_SW_POWER_DOWN);
+
+	/* write the new current value back as well as enable bit */
+	ret = ad5398_write_reg(client, data);
+
+	return ret;
+}
+
+static int ad5398_is_enabled(struct regulator_dev *rdev)
+{
+	struct ad5398_chip_info *chip = rdev_get_drvdata(rdev);
+	struct i2c_client *client = chip->client;
+	unsigned short data;
+	int ret;
+
+	ret = ad5398_read_reg(client, &data);
+	if (ret < 0)
+		return ret;
+
+	if (data & AD5398_SW_POWER_DOWN)
+		return 0;
+	else
+		return 1;
+}
+
+static int ad5398_enable(struct regulator_dev *rdev)
+{
+	struct ad5398_chip_info *chip = rdev_get_drvdata(rdev);
+	struct i2c_client *client = chip->client;
+	unsigned short data;
+	int ret;
+
+	ret = ad5398_read_reg(client, &data);
+	if (ret < 0)
+		return ret;
+
+	if (!(data & AD5398_SW_POWER_DOWN))
+		return 0;
+
+	data &= ~AD5398_SW_POWER_DOWN;
+
+	ret = ad5398_write_reg(client, data);
+
+	return ret;
+}
+
+static int ad5398_disable(struct regulator_dev *rdev)
+{
+	struct ad5398_chip_info *chip = rdev_get_drvdata(rdev);
+	struct i2c_client *client = chip->client;
+	unsigned short data;
+	int ret;
+
+	ret = ad5398_read_reg(client, &data);
+	if (ret < 0)
+		return ret;
+
+	if (data & AD5398_SW_POWER_DOWN)
+		return 0;
+
+	data |= AD5398_SW_POWER_DOWN;
+
+	ret = ad5398_write_reg(client, data);
+
+	return ret;
+}
+
+static const struct regulator_ops ad5398_ops = {
+	.get_current_limit = ad5398_get_current_limit,
+	.set_current_limit = ad5398_set_current_limit,
+	.enable = ad5398_enable,
+	.disable = ad5398_disable,
+	.is_enabled = ad5398_is_enabled,
+};
+
+static const struct regulator_desc ad5398_reg = {
+	.name = "isink",
+	.id = 0,
+	.ops = &ad5398_ops,
+	.type = REGULATOR_CURRENT,
+	.owner = THIS_MODULE,
+};
+
+struct ad5398_current_data_format {
+	int current_bits;
+	int current_offset;
+	int min_uA;
+	int max_uA;
+};
+
+static const struct ad5398_current_data_format df_10_4_120 = {10, 4, 0, 120000};
+
+static const struct i2c_device_id ad5398_id[] = {
+	{ .name = "ad5398", .driver_data = (kernel_ulong_t)&df_10_4_120 },
+	{ .name = "ad5821", .driver_data = (kernel_ulong_t)&df_10_4_120 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, ad5398_id);
+
+static int ad5398_probe(struct i2c_client *client)
+{
+	const struct i2c_device_id *id = i2c_client_get_device_id(client);
+	struct regulator_init_data *init_data = dev_get_platdata(&client->dev);
+	struct regulator_config config = { };
+	struct ad5398_chip_info *chip;
+	const struct ad5398_current_data_format *df =
+			(struct ad5398_current_data_format *)id->driver_data;
+
+	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	config.dev = &client->dev;
+	if (client->dev.of_node)
+		init_data = of_get_regulator_init_data(&client->dev,
+						       client->dev.of_node,
+						       &ad5398_reg);
+	if (!init_data)
+		return -EINVAL;
+
+	config.init_data = init_data;
+	config.of_node = client->dev.of_node;
+	config.driver_data = chip;
+
+	chip->client = client;
+
+	chip->min_uA = df->min_uA;
+	chip->max_uA = df->max_uA;
+	chip->current_level = 1 << df->current_bits;
+	chip->current_offset = df->current_offset;
+	chip->current_mask = (chip->current_level - 1) << chip->current_offset;
+
+	chip->rdev = devm_regulator_register(&client->dev, &ad5398_reg,
+					     &config);
+	if (IS_ERR(chip->rdev)) {
+		dev_err(&client->dev, "failed to register %s %s\n",
+			id->name, ad5398_reg.name);
+		return PTR_ERR(chip->rdev);
+	}
+
+	i2c_set_clientdata(client, chip);
+	dev_dbg(&client->dev, "%s regulator driver is registered.\n", id->name);
+	return 0;
+}
+
+static struct i2c_driver ad5398_driver = {
+	.probe = ad5398_probe,
+	.driver		= {
+		.name	= "ad5398",
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+	},
+	.id_table	= ad5398_id,
+};
+
+static int __init ad5398_init(void)
+{
+	return i2c_add_driver(&ad5398_driver);
+}
+subsys_initcall(ad5398_init);
+
+static void __exit ad5398_exit(void)
+{
+	i2c_del_driver(&ad5398_driver);
+}
+module_exit(ad5398_exit);
+
+MODULE_DESCRIPTION("AD5398 and AD5821 current regulator driver");
+MODULE_AUTHOR("Sonic Zhang");
+MODULE_LICENSE("GPL");