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, 184 insertions, 0 deletions

diff --git a/drivers/pinctrl/pinctrl-generic-mux.c b/drivers/pinctrl/pinctrl-generic-mux.c
new file mode 100644
index 000000000..202b72351
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-generic-mux.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Generic Pin Control Driver for Board-Level Mux Chips
+ * Copyright 2026 NXP
+ */
+
+#include <linux/cleanup.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/mutex.h>
+#include <linux/mux/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/slab.h>
+
+#include "core.h"
+#include "pinconf.h"
+#include "pinmux.h"
+#include "pinctrl-utils.h"
+
+struct mux_pin_function {
+	struct mux_state *mux_state;
+};
+
+struct mux_pinctrl {
+	struct device *dev;
+	struct pinctrl_dev *pctl;
+
+	/* mutex protect [pinctrl|pinmux]_generic functions */
+	struct mutex lock;
+};
+
+static int
+mux_pinmux_dt_node_to_map(struct pinctrl_dev *pctldev,
+			  struct device_node *np_config,
+			  struct pinctrl_map **maps, unsigned int *num_maps)
+{
+	unsigned int num_reserved_maps = 0;
+	struct mux_pin_function *function;
+	const char **group_names;
+	int ret;
+
+	function = devm_kzalloc(pctldev->dev, sizeof(*function), GFP_KERNEL);
+	if (!function)
+		return -ENOMEM;
+
+	group_names = devm_kcalloc(pctldev->dev, 1, sizeof(*group_names), GFP_KERNEL);
+	if (!group_names)
+		return -ENOMEM;
+
+	function->mux_state = devm_mux_state_get_from_np(pctldev->dev, NULL, np_config);
+	if (IS_ERR(function->mux_state))
+		return PTR_ERR(function->mux_state);
+
+	ret = pinctrl_generic_to_map(pctldev, np_config, np_config, maps,
+				     num_maps, &num_reserved_maps, group_names,
+				     0, &np_config->name, NULL, 0);
+
+	if (ret)
+		return ret;
+
+	ret = pinmux_generic_add_function(pctldev, np_config->name, group_names,
+					  1, function);
+	if (ret < 0) {
+		pinctrl_utils_free_map(pctldev, *maps, *num_maps);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct pinctrl_ops mux_pinctrl_ops = {
+	.get_groups_count = pinctrl_generic_get_group_count,
+	.get_group_name = pinctrl_generic_get_group_name,
+	.get_group_pins = pinctrl_generic_get_group_pins,
+	.dt_node_to_map = mux_pinmux_dt_node_to_map,
+	.dt_free_map = pinctrl_utils_free_map,
+};
+
+static int mux_pinmux_set_mux(struct pinctrl_dev *pctldev,
+			      unsigned int func_selector,
+			      unsigned int group_selector)
+{
+	struct mux_pinctrl *mpctl = pinctrl_dev_get_drvdata(pctldev);
+	const struct function_desc *function;
+	struct mux_pin_function *func;
+	int ret;
+
+	guard(mutex)(&mpctl->lock);
+
+	function = pinmux_generic_get_function(pctldev, func_selector);
+	func = function->data;
+
+	ret = mux_state_try_select(func->mux_state);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void mux_pinmux_release_mux(struct pinctrl_dev *pctldev,
+				   unsigned int func_selector,
+				   unsigned int group_selector)
+{
+	struct mux_pinctrl *mpctl = pinctrl_dev_get_drvdata(pctldev);
+	const struct function_desc *function;
+	struct mux_pin_function *func;
+
+	guard(mutex)(&mpctl->lock);
+
+	function = pinmux_generic_get_function(pctldev, func_selector);
+	func = function->data;
+
+	mux_state_deselect(func->mux_state);
+}
+
+static const struct pinmux_ops mux_pinmux_ops = {
+	.get_functions_count = pinmux_generic_get_function_count,
+	.get_function_name = pinmux_generic_get_function_name,
+	.get_function_groups = pinmux_generic_get_function_groups,
+	.set_mux = mux_pinmux_set_mux,
+	.release_mux = mux_pinmux_release_mux,
+};
+
+static int mux_pinctrl_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mux_pinctrl *mpctl;
+	struct pinctrl_desc *pctl_desc;
+	int ret;
+
+	mpctl = devm_kzalloc(dev, sizeof(*mpctl), GFP_KERNEL);
+	if (!mpctl)
+		return -ENOMEM;
+
+	mpctl->dev = dev;
+
+	platform_set_drvdata(pdev, mpctl);
+
+	pctl_desc = devm_kzalloc(dev, sizeof(*pctl_desc), GFP_KERNEL);
+	if (!pctl_desc)
+		return -ENOMEM;
+
+	ret = devm_mutex_init(dev, &mpctl->lock);
+	if (ret)
+		return ret;
+
+	pctl_desc->name = dev_name(dev);
+	pctl_desc->owner = THIS_MODULE;
+	pctl_desc->pctlops = &mux_pinctrl_ops;
+	pctl_desc->pmxops = &mux_pinmux_ops;
+
+	ret = devm_pinctrl_register_and_init(dev, pctl_desc, mpctl,
+					     &mpctl->pctl);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to register pinctrl.\n");
+
+	ret = pinctrl_enable(mpctl->pctl);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable pinctrl.\n");
+
+	return 0;
+}
+
+static const struct of_device_id mux_pinctrl_of_match[] = {
+	{ .compatible = "pinctrl-multiplexer" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mux_pinctrl_of_match);
+
+static struct platform_driver mux_pinctrl_driver = {
+	.driver = {
+		.name = "generic-pinctrl-mux",
+		.of_match_table = mux_pinctrl_of_match,
+	},
+	.probe = mux_pinctrl_probe,
+};
+module_platform_driver(mux_pinctrl_driver);
+
+MODULE_AUTHOR("Frank Li <Frank.Li@nxp.com>");
+MODULE_DESCRIPTION("Generic Pin Control Driver for Board-Level Mux Chips");
+MODULE_LICENSE("GPL");