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, 170 insertions, 0 deletions

diff --git a/drivers/mfd/max7360.c b/drivers/mfd/max7360.c
new file mode 100644
index 000000000..52fffed0c
--- /dev/null
+++ b/drivers/mfd/max7360.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Maxim MAX7360 Core Driver
+ *
+ * Copyright 2025 Bootlin
+ *
+ * Authors:
+ *    Kamel Bouhara <kamel.bouhara@bootlin.com>
+ *    Mathieu Dubois-Briand <mathieu.dubois-briand@bootlin.com>
+ */
+
+#include <linux/array_size.h>
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/device/devres.h>
+#include <linux/dev_printk.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/max7360.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/types.h>
+
+static const struct mfd_cell max7360_cells[] = {
+	{ .name           = "max7360-pinctrl" },
+	{ .name           = "max7360-pwm" },
+	{ .name           = "max7360-keypad" },
+	{ .name           = "max7360-rotary" },
+	{
+		.name           = "max7360-gpo",
+		.of_compatible	= "maxim,max7360-gpo",
+	},
+	{
+		.name           = "max7360-gpio",
+		.of_compatible	= "maxim,max7360-gpio",
+	},
+};
+
+static const struct regmap_range max7360_volatile_ranges[] = {
+	regmap_reg_range(MAX7360_REG_KEYFIFO, MAX7360_REG_KEYFIFO),
+	regmap_reg_range(MAX7360_REG_I2C_TIMEOUT, MAX7360_REG_RTR_CNT),
+};
+
+static const struct regmap_access_table max7360_volatile_table = {
+	.yes_ranges = max7360_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(max7360_volatile_ranges),
+};
+
+static const struct regmap_config max7360_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = MAX7360_REG_PWMCFG(MAX7360_PORT_PWM_COUNT - 1),
+	.volatile_table = &max7360_volatile_table,
+	.cache_type = REGCACHE_MAPLE,
+};
+
+static int max7360_mask_irqs(struct regmap *regmap)
+{
+	struct device *dev = regmap_get_device(regmap);
+	unsigned int val;
+	int ret;
+
+	/*
+	 * GPIO/PWM interrupts are not masked on reset: as the MAX7360 "INTI"
+	 * interrupt line is shared between GPIOs and rotary encoder, this could
+	 * result in repeated spurious interrupts on the rotary encoder driver
+	 * if the GPIO driver is not loaded. Mask them now to avoid this
+	 * situation.
+	 */
+	for (unsigned int i = 0; i < MAX7360_PORT_PWM_COUNT; i++) {
+		ret = regmap_write_bits(regmap, MAX7360_REG_PWMCFG(i),
+					MAX7360_PORT_CFG_INTERRUPT_MASK,
+					MAX7360_PORT_CFG_INTERRUPT_MASK);
+		if (ret)
+			return dev_err_probe(dev, ret,
+					     "Failed to write MAX7360 port configuration\n");
+	}
+
+	/* Read GPIO in register, to ACK any pending IRQ. */
+	ret = regmap_read(regmap, MAX7360_REG_GPIOIN, &val);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to read GPIO values\n");
+
+	return 0;
+}
+
+static int max7360_reset(struct regmap *regmap)
+{
+	struct device *dev = regmap_get_device(regmap);
+	int ret;
+
+	ret = regmap_write(regmap, MAX7360_REG_GPIOCFG, MAX7360_GPIO_CFG_GPIO_RST);
+	if (ret) {
+		dev_err(dev, "Failed to reset GPIO configuration: %x\n", ret);
+		return ret;
+	}
+
+	ret = regcache_drop_region(regmap, MAX7360_REG_GPIOCFG, MAX7360_REG_GPIO_LAST);
+	if (ret) {
+		dev_err(dev, "Failed to drop regmap cache: %x\n", ret);
+		return ret;
+	}
+
+	ret = regmap_write(regmap, MAX7360_REG_SLEEP, 0);
+	if (ret) {
+		dev_err(dev, "Failed to reset autosleep configuration: %x\n", ret);
+		return ret;
+	}
+
+	ret = regmap_write(regmap, MAX7360_REG_DEBOUNCE, 0);
+	if (ret)
+		dev_err(dev, "Failed to reset GPO port count: %x\n", ret);
+
+	return ret;
+}
+
+static int max7360_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct regmap *regmap;
+	int ret;
+
+	regmap = devm_regmap_init_i2c(client, &max7360_regmap_config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap), "Failed to initialise regmap\n");
+
+	ret = max7360_reset(regmap);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to reset device\n");
+
+	/* Get the device out of shutdown mode. */
+	ret = regmap_write_bits(regmap, MAX7360_REG_GPIOCFG,
+				MAX7360_GPIO_CFG_GPIO_EN,
+				MAX7360_GPIO_CFG_GPIO_EN);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable GPIO and PWM module\n");
+
+	ret = max7360_mask_irqs(regmap);
+	if (ret)
+		return dev_err_probe(dev, ret, "Could not mask interrupts\n");
+
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE,
+				   max7360_cells, ARRAY_SIZE(max7360_cells),
+				   NULL, 0, NULL);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to register child devices\n");
+
+	return 0;
+}
+
+static const struct of_device_id max7360_dt_match[] = {
+	{ .compatible = "maxim,max7360" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, max7360_dt_match);
+
+static struct i2c_driver max7360_driver = {
+	.driver = {
+		.name = "max7360",
+		.of_match_table = max7360_dt_match,
+	},
+	.probe = max7360_probe,
+};
+module_i2c_driver(max7360_driver);
+
+MODULE_DESCRIPTION("Maxim MAX7360 I2C IO Expander core driver");
+MODULE_AUTHOR("Kamel Bouhara <kamel.bouhara@bootlin.com>");
+MODULE_LICENSE("GPL");