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, 220 insertions, 0 deletions

diff --git a/drivers/mfd/max77541.c b/drivers/mfd/max77541.c
new file mode 100644
index 000000000..f91b4f537
--- /dev/null
+++ b/drivers/mfd/max77541.c
@@ -0,0 +1,220 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022 Analog Devices, Inc.
+ * Driver for the MAX77540 and MAX77541
+ */
+
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/max77541.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+
+static const struct regmap_config max77541_regmap_config = {
+	.reg_bits   = 8,
+	.val_bits   = 8,
+};
+
+static const struct regmap_irq max77541_src_irqs[] = {
+	{ .mask = MAX77541_BIT_INT_SRC_TOPSYS },
+	{ .mask = MAX77541_BIT_INT_SRC_BUCK },
+};
+
+static const struct regmap_irq_chip max77541_src_irq_chip = {
+	.name		= "max77541-src",
+	.status_base	= MAX77541_REG_INT_SRC,
+	.mask_base	= MAX77541_REG_INT_SRC_M,
+	.num_regs	= 1,
+	.irqs		= max77541_src_irqs,
+	.num_irqs       = ARRAY_SIZE(max77541_src_irqs),
+};
+
+static const struct regmap_irq max77541_topsys_irqs[] = {
+	{ .mask = MAX77541_BIT_TOPSYS_INT_TJ_120C },
+	{ .mask = MAX77541_BIT_TOPSYS_INT_TJ_140C },
+	{ .mask = MAX77541_BIT_TOPSYS_INT_TSHDN },
+	{ .mask = MAX77541_BIT_TOPSYS_INT_UVLO },
+	{ .mask = MAX77541_BIT_TOPSYS_INT_ALT_SWO },
+	{ .mask = MAX77541_BIT_TOPSYS_INT_EXT_FREQ_DET },
+};
+
+static const struct regmap_irq_chip max77541_topsys_irq_chip = {
+	.name		= "max77541-topsys",
+	.status_base	= MAX77541_REG_TOPSYS_INT,
+	.mask_base	= MAX77541_REG_TOPSYS_INT_M,
+	.num_regs	= 1,
+	.irqs		= max77541_topsys_irqs,
+	.num_irqs	= ARRAY_SIZE(max77541_topsys_irqs),
+};
+
+static const struct regmap_irq max77541_buck_irqs[] = {
+	{ .mask = MAX77541_BIT_BUCK_INT_M1_POK_FLT },
+	{ .mask = MAX77541_BIT_BUCK_INT_M2_POK_FLT },
+	{ .mask = MAX77541_BIT_BUCK_INT_M1_SCFLT },
+	{ .mask = MAX77541_BIT_BUCK_INT_M2_SCFLT },
+};
+
+static const struct regmap_irq_chip max77541_buck_irq_chip = {
+	.name		= "max77541-buck",
+	.status_base	= MAX77541_REG_BUCK_INT,
+	.mask_base	= MAX77541_REG_BUCK_INT_M,
+	.num_regs	= 1,
+	.irqs		= max77541_buck_irqs,
+	.num_irqs	= ARRAY_SIZE(max77541_buck_irqs),
+};
+
+static const struct regmap_irq max77541_adc_irqs[] = {
+	{ .mask = MAX77541_BIT_ADC_INT_CH1_I },
+	{ .mask = MAX77541_BIT_ADC_INT_CH2_I },
+	{ .mask = MAX77541_BIT_ADC_INT_CH3_I },
+	{ .mask = MAX77541_BIT_ADC_INT_CH6_I },
+};
+
+static const struct regmap_irq_chip max77541_adc_irq_chip = {
+	.name		= "max77541-adc",
+	.status_base	= MAX77541_REG_ADC_INT,
+	.mask_base	= MAX77541_REG_ADC_INT_M,
+	.num_regs	= 1,
+	.irqs		= max77541_adc_irqs,
+	.num_irqs	= ARRAY_SIZE(max77541_adc_irqs),
+};
+
+static const struct mfd_cell max77540_devs[] = {
+	MFD_CELL_OF("max77540-regulator", NULL, NULL, 0, 0, NULL),
+};
+
+static const struct mfd_cell max77541_devs[] = {
+	MFD_CELL_OF("max77541-regulator", NULL, NULL, 0, 0, NULL),
+	MFD_CELL_OF("max77541-adc", NULL, NULL, 0, 0, NULL),
+};
+
+static int max77541_pmic_irq_init(struct device *dev)
+{
+	struct max77541 *max77541 = dev_get_drvdata(dev);
+	int irq = max77541->i2c->irq;
+	int ret;
+
+	ret = devm_regmap_add_irq_chip(dev, max77541->regmap, irq,
+				       IRQF_ONESHOT | IRQF_SHARED, 0,
+				       &max77541_src_irq_chip,
+				       &max77541->irq_data);
+	if (ret)
+		return ret;
+
+	ret = devm_regmap_add_irq_chip(dev, max77541->regmap, irq,
+				       IRQF_ONESHOT | IRQF_SHARED, 0,
+				       &max77541_topsys_irq_chip,
+				       &max77541->irq_topsys);
+	if (ret)
+		return ret;
+
+	ret = devm_regmap_add_irq_chip(dev, max77541->regmap, irq,
+				       IRQF_ONESHOT | IRQF_SHARED, 0,
+				       &max77541_buck_irq_chip,
+				       &max77541->irq_buck);
+	if (ret)
+		return ret;
+
+	if (max77541->id == MAX77541) {
+		ret = devm_regmap_add_irq_chip(dev, max77541->regmap, irq,
+					       IRQF_ONESHOT | IRQF_SHARED, 0,
+					       &max77541_adc_irq_chip,
+					       &max77541->irq_adc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int max77541_pmic_setup(struct device *dev)
+{
+	struct max77541 *max77541 = dev_get_drvdata(dev);
+	const struct mfd_cell *cells;
+	int n_devs;
+	int ret;
+
+	switch (max77541->id) {
+	case MAX77540:
+		cells =  max77540_devs;
+		n_devs = ARRAY_SIZE(max77540_devs);
+		break;
+	case MAX77541:
+		cells =  max77541_devs;
+		n_devs = ARRAY_SIZE(max77541_devs);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = max77541_pmic_irq_init(dev);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to initialize IRQ\n");
+
+	ret = devm_device_init_wakeup(dev);
+	if (ret)
+		return dev_err_probe(dev, ret, "Unable to init wakeup\n");
+
+	return devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE,
+				    cells, n_devs, NULL, 0, NULL);
+}
+
+static int max77541_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct max77541 *max77541;
+
+	max77541 = devm_kzalloc(dev, sizeof(*max77541), GFP_KERNEL);
+	if (!max77541)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, max77541);
+	max77541->i2c = client;
+
+	max77541->id = (uintptr_t)i2c_get_match_data(client);
+	if (!max77541->id)
+		return -EINVAL;
+
+	max77541->regmap = devm_regmap_init_i2c(client,
+						&max77541_regmap_config);
+	if (IS_ERR(max77541->regmap))
+		return dev_err_probe(dev, PTR_ERR(max77541->regmap),
+				     "Failed to allocate register map\n");
+
+	return max77541_pmic_setup(dev);
+}
+
+static const struct of_device_id max77541_of_id[] = {
+	{
+		.compatible = "adi,max77540",
+		.data = (void *)MAX77540,
+	},
+	{
+		.compatible = "adi,max77541",
+		.data = (void *)MAX77541,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max77541_of_id);
+
+static const struct i2c_device_id max77541_id[] = {
+	{ "max77540", MAX77540 },
+	{ "max77541", MAX77541 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, max77541_id);
+
+static struct i2c_driver max77541_driver = {
+	.driver = {
+		.name = "max77541",
+		.of_match_table = max77541_of_id,
+	},
+	.probe = max77541_probe,
+	.id_table = max77541_id,
+};
+module_i2c_driver(max77541_driver);
+
+MODULE_DESCRIPTION("MAX7740/MAX7741 Driver");
+MODULE_AUTHOR("Okan Sahin <okan.sahin@analog.com>");
+MODULE_LICENSE("GPL");