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, 173 insertions, 0 deletions

diff --git a/drivers/mfd/88pm886.c b/drivers/mfd/88pm886.c
new file mode 100644
index 000000000..f8401d5e6
--- /dev/null
+++ b/drivers/mfd/88pm886.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/regmap.h>
+
+#include <linux/mfd/88pm886.h>
+
+static const struct regmap_config pm886_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = PM886_REG_RTC_SPARE6,
+};
+
+static const struct regmap_config pm886_regmap_battery_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = PM886_REG_CLS_CONFIG1,
+};
+
+static const struct regmap_irq pm886_regmap_irqs[] = {
+	REGMAP_IRQ_REG(PM886_IRQ_ONKEY, 0, PM886_INT_ENA1_ONKEY),
+};
+
+static const struct regmap_irq_chip pm886_regmap_irq_chip = {
+	.name = "88pm886",
+	.irqs = pm886_regmap_irqs,
+	.num_irqs = ARRAY_SIZE(pm886_regmap_irqs),
+	.num_regs = 4,
+	.status_base = PM886_REG_INT_STATUS1,
+	.ack_base = PM886_REG_INT_STATUS1,
+	.unmask_base = PM886_REG_INT_ENA_1,
+};
+
+static const struct resource pm886_onkey_resources[] = {
+	DEFINE_RES_IRQ_NAMED(PM886_IRQ_ONKEY, "88pm886-onkey"),
+};
+
+static const struct mfd_cell pm886_devs[] = {
+	MFD_CELL_NAME("88pm886-gpadc"),
+	MFD_CELL_RES("88pm886-onkey", pm886_onkey_resources),
+	MFD_CELL_NAME("88pm886-regulator"),
+	MFD_CELL_NAME("88pm886-rtc"),
+};
+
+static int pm886_power_off_handler(struct sys_off_data *sys_off_data)
+{
+	struct pm886_chip *chip = sys_off_data->cb_data;
+	struct regmap *regmap = chip->regmap;
+	struct device *dev = &chip->client->dev;
+	int err;
+
+	err = regmap_update_bits(regmap, PM886_REG_MISC_CONFIG1, PM886_SW_PDOWN, PM886_SW_PDOWN);
+	if (err) {
+		dev_err(dev, "Failed to power off the device: %d\n", err);
+		return NOTIFY_BAD;
+	}
+	return NOTIFY_DONE;
+}
+
+static int pm886_setup_irq(struct pm886_chip *chip,
+		struct regmap_irq_chip_data **irq_data)
+{
+	struct regmap *regmap = chip->regmap;
+	struct device *dev = &chip->client->dev;
+	int err;
+
+	/* Set interrupt clearing mode to clear on write. */
+	err = regmap_update_bits(regmap, PM886_REG_MISC_CONFIG2,
+			PM886_INT_INV | PM886_INT_CLEAR | PM886_INT_MASK_MODE,
+			PM886_INT_WC);
+	if (err) {
+		dev_err(dev, "Failed to set interrupt clearing mode: %d\n", err);
+		return err;
+	}
+
+	err = devm_regmap_add_irq_chip(dev, regmap, chip->client->irq,
+					IRQF_ONESHOT, 0, &pm886_regmap_irq_chip,
+					irq_data);
+	if (err) {
+		dev_err(dev, "Failed to request IRQ: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int pm886_probe(struct i2c_client *client)
+{
+	struct regmap *regmap, *regmap_battery;
+	struct regmap_irq_chip_data *irq_data;
+	struct device *dev = &client->dev;
+	struct i2c_client *battery_page;
+	struct pm886_chip *chip;
+	unsigned int chip_id;
+	int err;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->client = client;
+	chip->chip_id = (uintptr_t)device_get_match_data(dev);
+	i2c_set_clientdata(client, chip);
+
+	regmap = devm_regmap_init_i2c(client, &pm886_regmap_config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap), "Failed to initialize regmap\n");
+	chip->regmap = regmap;
+
+	err = regmap_read(regmap, PM886_REG_ID, &chip_id);
+	if (err)
+		return dev_err_probe(dev, err, "Failed to read chip ID\n");
+
+	if (chip->chip_id != chip_id)
+		return dev_err_probe(dev, -EINVAL, "Unsupported chip: 0x%x\n", chip_id);
+
+	battery_page = devm_i2c_new_dummy_device(dev, client->adapter,
+						 client->addr + PM886_PAGE_OFFSET_BATTERY);
+	if (IS_ERR(battery_page))
+		return dev_err_probe(dev, PTR_ERR(battery_page),
+				     "Failed to initialize battery page\n");
+
+	regmap_battery = devm_regmap_init_i2c(battery_page, &pm886_regmap_battery_config);
+	if (IS_ERR(regmap_battery))
+		return dev_err_probe(dev, PTR_ERR(regmap_battery),
+				     "Failed to initialize battery regmap\n");
+	chip->regmap_battery = regmap_battery;
+
+	err = pm886_setup_irq(chip, &irq_data);
+	if (err)
+		return err;
+
+	err = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE, pm886_devs, ARRAY_SIZE(pm886_devs),
+				NULL, 0, regmap_irq_get_domain(irq_data));
+	if (err)
+		return dev_err_probe(dev, err, "Failed to add devices\n");
+
+	err = devm_register_power_off_handler(dev, pm886_power_off_handler, chip);
+	if (err)
+		return dev_err_probe(dev, err, "Failed to register power off handler\n");
+
+	if (device_property_read_bool(dev, "wakeup-source")) {
+		err = devm_device_init_wakeup(dev);
+		if (err)
+			return dev_err_probe(dev, err, "Failed to init wakeup\n");
+	}
+
+	return 0;
+}
+
+static const struct of_device_id pm886_of_match[] = {
+	{ .compatible = "marvell,88pm886-a1", .data = (void *)PM886_A1_CHIP_ID },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pm886_of_match);
+
+static struct i2c_driver pm886_i2c_driver = {
+	.driver = {
+		.name = "88pm886",
+		.of_match_table = pm886_of_match,
+	},
+	.probe = pm886_probe,
+};
+module_i2c_driver(pm886_i2c_driver);
+
+MODULE_DESCRIPTION("Marvell 88PM886 PMIC driver");
+MODULE_AUTHOR("Karel Balej <balejk@matfyz.cz>");
+MODULE_LICENSE("GPL");