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, 137 insertions, 0 deletions

diff --git a/drivers/leds/leds-syscon.c b/drivers/leds/leds-syscon.c
new file mode 100644
index 000000000..d633ad519
--- /dev/null
+++ b/drivers/leds/leds-syscon.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic Syscon LEDs Driver
+ *
+ * Copyright (c) 2014, Linaro Limited
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ */
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/leds.h>
+
+/**
+ * struct syscon_led - state container for syscon based LEDs
+ * @cdev: LED class device for this LED
+ * @map: regmap to access the syscon device backing this LED
+ * @offset: the offset into the syscon regmap for the LED register
+ * @mask: the bit in the register corresponding to the LED
+ * @state: current state of the LED
+ */
+struct syscon_led {
+	struct led_classdev cdev;
+	struct regmap *map;
+	u32 offset;
+	u32 mask;
+	bool state;
+};
+
+static void syscon_led_set(struct led_classdev *led_cdev,
+	enum led_brightness value)
+{
+	struct syscon_led *sled =
+		container_of(led_cdev, struct syscon_led, cdev);
+	u32 val;
+	int ret;
+
+	if (value == LED_OFF) {
+		val = 0;
+		sled->state = false;
+	} else {
+		val = sled->mask;
+		sled->state = true;
+	}
+
+	ret = regmap_update_bits(sled->map, sled->offset, sled->mask, val);
+	if (ret < 0)
+		dev_err(sled->cdev.dev, "error updating LED status\n");
+}
+
+static int syscon_led_probe(struct platform_device *pdev)
+{
+	struct led_init_data init_data = {};
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct device *parent;
+	struct regmap *map;
+	struct syscon_led *sled;
+	enum led_default_state state;
+	u32 value;
+	int ret;
+
+	parent = dev->parent;
+	if (!parent) {
+		dev_err(dev, "no parent for syscon LED\n");
+		return -ENODEV;
+	}
+	map = syscon_node_to_regmap(dev_of_node(parent));
+	if (IS_ERR(map)) {
+		dev_err(dev, "no regmap for syscon LED parent\n");
+		return PTR_ERR(map);
+	}
+
+	sled = devm_kzalloc(dev, sizeof(*sled), GFP_KERNEL);
+	if (!sled)
+		return -ENOMEM;
+
+	sled->map = map;
+
+	if (of_property_read_u32(np, "reg", &sled->offset) &&
+	    of_property_read_u32(np, "offset", &sled->offset))
+		return -EINVAL;
+	if (of_property_read_u32(np, "mask", &sled->mask))
+		return -EINVAL;
+
+	init_data.fwnode = of_fwnode_handle(np);
+
+	state = led_init_default_state_get(init_data.fwnode);
+	switch (state) {
+	case LEDS_DEFSTATE_ON:
+		ret = regmap_update_bits(map, sled->offset, sled->mask, sled->mask);
+		if (ret < 0)
+			return ret;
+		sled->state = true;
+		break;
+	case LEDS_DEFSTATE_KEEP:
+		ret = regmap_read(map, sled->offset, &value);
+		if (ret < 0)
+			return ret;
+		sled->state = !!(value & sled->mask);
+		break;
+	default:
+		ret = regmap_update_bits(map, sled->offset, sled->mask, 0);
+		if (ret < 0)
+			return ret;
+		sled->state = false;
+	}
+	sled->cdev.brightness_set = syscon_led_set;
+
+	ret = devm_led_classdev_register_ext(dev, &sled->cdev, &init_data);
+	if (ret < 0)
+		return ret;
+
+	platform_set_drvdata(pdev, sled);
+	dev_info(dev, "registered LED %s\n", sled->cdev.name);
+
+	return 0;
+}
+
+static const struct of_device_id of_syscon_leds_match[] = {
+	{ .compatible = "register-bit-led", },
+	{},
+};
+
+static struct platform_driver syscon_led_driver = {
+	.probe		= syscon_led_probe,
+	.driver		= {
+		.name	= "leds-syscon",
+		.of_match_table = of_syscon_leds_match,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver(syscon_led_driver);