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, 287 insertions, 0 deletions

diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
new file mode 100644
index 000000000..e7366fcb7
--- /dev/null
+++ b/drivers/acpi/acpi_apd.c
@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD ACPI support for ACPI2platform device.
+ *
+ * Copyright (c) 2014,2015 AMD Corporation.
+ * Authors: Ken Xue <Ken.Xue@amd.com>
+ *	Wu, Jeff <Jeff.Wu@amd.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/platform_data/clk-fch.h>
+#include <linux/platform_device.h>
+#include <linux/units.h>
+
+#include "internal.h"
+
+struct apd_private_data;
+
+/**
+ * struct apd_device_desc - a descriptor for apd device
+ * @fixed_clk_rate: fixed rate input clock source for acpi device;
+ *			0 means no fixed rate input clock source
+ * @properties: build-in properties of the device such as UART
+ * @setup: a hook routine to set device resource during create platform device
+ *
+ * Device description defined as acpi_device_id.driver_data
+ */
+struct apd_device_desc {
+	unsigned int fixed_clk_rate;
+	struct property_entry *properties;
+	int (*setup)(struct apd_private_data *pdata);
+};
+
+struct apd_private_data {
+	struct clk *clk;
+	struct acpi_device *adev;
+	const struct apd_device_desc *dev_desc;
+};
+
+#if defined(CONFIG_X86_AMD_PLATFORM_DEVICE) || defined(CONFIG_ARM64)
+#define APD_ADDR(desc)	((unsigned long)&desc)
+
+static int acpi_apd_setup(struct apd_private_data *pdata)
+{
+	const struct apd_device_desc *dev_desc = pdata->dev_desc;
+	struct clk *clk;
+
+	if (dev_desc->fixed_clk_rate) {
+		clk = clk_register_fixed_rate(&pdata->adev->dev,
+					dev_name(&pdata->adev->dev),
+					NULL, 0, dev_desc->fixed_clk_rate);
+		clk_register_clkdev(clk, NULL, dev_name(&pdata->adev->dev));
+		pdata->clk = clk;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_X86_AMD_PLATFORM_DEVICE
+
+static int fch_misc_setup(struct apd_private_data *pdata)
+{
+	struct acpi_device *adev = pdata->adev;
+	const union acpi_object *obj;
+	struct platform_device *clkdev;
+	struct fch_clk_data *clk_data;
+	struct resource_entry *rentry;
+	struct list_head resource_list;
+	int ret;
+
+	clk_data = devm_kzalloc(&adev->dev, sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_memory_resources(adev, &resource_list);
+	if (ret < 0)
+		return -ENOENT;
+
+	if (!acpi_dev_get_property(adev, "clk-name", ACPI_TYPE_STRING, &obj)) {
+		clk_data->name = devm_kzalloc(&adev->dev, obj->string.length,
+					      GFP_KERNEL);
+		if (!clk_data->name)
+			return -ENOMEM;
+
+		strscpy(clk_data->name, obj->string.pointer, obj->string.length);
+	} else {
+		/* Set default name to mclk if entry missing in firmware */
+		clk_data->name = "mclk";
+	}
+
+	list_for_each_entry(rentry, &resource_list, node) {
+		clk_data->base = devm_ioremap(&adev->dev, rentry->res->start,
+					      resource_size(rentry->res));
+		break;
+	}
+	if (!clk_data->base)
+		return -ENOMEM;
+
+	acpi_dev_free_resource_list(&resource_list);
+
+	clkdev = platform_device_register_data(&adev->dev, "clk-fch",
+					       PLATFORM_DEVID_NONE, clk_data,
+					       sizeof(*clk_data));
+	return PTR_ERR_OR_ZERO(clkdev);
+}
+
+static const struct apd_device_desc cz_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 133 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc wt_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 150 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc wt_i3c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 125 * HZ_PER_MHZ,
+};
+
+static struct property_entry uart_properties[] = {
+	PROPERTY_ENTRY_U32("reg-io-width", 4),
+	PROPERTY_ENTRY_U32("reg-shift", 2),
+	PROPERTY_ENTRY_BOOL("snps,uart-16550-compatible"),
+	{ },
+};
+
+static const struct apd_device_desc cz_uart_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 48 * HZ_PER_MHZ,
+	.properties = uart_properties,
+};
+
+static const struct apd_device_desc fch_misc_desc = {
+	.setup = fch_misc_setup,
+};
+#endif /* CONFIG_X86_AMD_PLATFORM_DEVICE */
+
+#ifdef CONFIG_ARM64
+static const struct apd_device_desc xgene_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 100 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc vulcan_spi_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 133 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc hip07_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 200 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc hip08_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 250 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc hip08_lite_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 125 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc thunderx2_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 125 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc nxp_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 350 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc hip08_spi_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 250 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc leca_spi_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 400 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc leca_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 250 * HZ_PER_MHZ,
+};
+
+static const struct apd_device_desc hjmc_i2c_desc = {
+	.setup = acpi_apd_setup,
+	.fixed_clk_rate = 200 * HZ_PER_MHZ,
+};
+
+#endif /* CONFIG_ARM64 */
+
+#endif
+
+/*
+ * Create platform device during acpi scan attach handle.
+ * Return value > 0 on success of creating device.
+ */
+static int acpi_apd_create_device(struct acpi_device *adev,
+				   const struct acpi_device_id *id)
+{
+	const struct apd_device_desc *dev_desc = (void *)id->driver_data;
+	struct apd_private_data *pdata;
+	struct platform_device *pdev;
+	int ret;
+
+	if (!dev_desc) {
+		pdev = acpi_create_platform_device(adev, NULL);
+		return IS_ERR_OR_NULL(pdev) ? PTR_ERR(pdev) : 1;
+	}
+
+	pdata = kzalloc_obj(*pdata);
+	if (!pdata)
+		return -ENOMEM;
+
+	pdata->adev = adev;
+	pdata->dev_desc = dev_desc;
+
+	if (dev_desc->setup) {
+		ret = dev_desc->setup(pdata);
+		if (ret)
+			goto err_out;
+	}
+
+	adev->driver_data = pdata;
+	pdev = acpi_create_platform_device(adev, dev_desc->properties);
+	if (!IS_ERR_OR_NULL(pdev))
+		return 1;
+
+	ret = PTR_ERR(pdev);
+	adev->driver_data = NULL;
+
+ err_out:
+	kfree(pdata);
+	return ret;
+}
+
+static const struct acpi_device_id acpi_apd_device_ids[] = {
+	/* Generic apd devices */
+#ifdef CONFIG_X86_AMD_PLATFORM_DEVICE
+	{ "AMD0010", APD_ADDR(cz_i2c_desc) },
+	{ "AMD0020", APD_ADDR(cz_uart_desc) },
+	{ "AMD0030", },
+	{ "AMD0040", APD_ADDR(fch_misc_desc)},
+	{ "AMDI0010", APD_ADDR(wt_i2c_desc) },
+	{ "AMDI0015", APD_ADDR(wt_i3c_desc) },
+	{ "AMDI0019", APD_ADDR(wt_i2c_desc) },
+	{ "AMDI0020", APD_ADDR(cz_uart_desc) },
+	{ "AMDI0022", APD_ADDR(cz_uart_desc) },
+	{ "HYGO0010", APD_ADDR(wt_i2c_desc) },
+#endif
+#ifdef CONFIG_ARM64
+	{ "APMC0D0F", APD_ADDR(xgene_i2c_desc) },
+	{ "BRCM900D", APD_ADDR(vulcan_spi_desc) },
+	{ "CAV900D",  APD_ADDR(vulcan_spi_desc) },
+	{ "CAV9007",  APD_ADDR(thunderx2_i2c_desc) },
+	{ "HISI02A1", APD_ADDR(hip07_i2c_desc) },
+	{ "HISI02A2", APD_ADDR(hip08_i2c_desc) },
+	{ "HISI02A3", APD_ADDR(hip08_lite_i2c_desc) },
+	{ "HISI0173", APD_ADDR(hip08_spi_desc) },
+	{ "HJMC3001", APD_ADDR(hjmc_i2c_desc) },
+	{ "LECA0002", APD_ADDR(leca_spi_desc) },
+	{ "LECA0003", APD_ADDR(leca_i2c_desc) },
+	{ "NXP0001", APD_ADDR(nxp_i2c_desc) },
+#endif
+	{ }
+};
+
+static struct acpi_scan_handler apd_handler = {
+	.ids = acpi_apd_device_ids,
+	.attach = acpi_apd_create_device,
+};
+
+void __init acpi_apd_init(void)
+{
+	acpi_scan_add_handler(&apd_handler);
+}