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, 153 insertions, 0 deletions

diff --git a/drivers/input/misc/qnap-mcu-input.c b/drivers/input/misc/qnap-mcu-input.c
new file mode 100644
index 000000000..3be899bfc
--- /dev/null
+++ b/drivers/input/misc/qnap-mcu-input.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Driver for input events on QNAP-MCUs
+ *
+ * Copyright (C) 2024 Heiko Stuebner <heiko@sntech.de>
+ */
+
+#include <linux/input.h>
+#include <linux/mfd/qnap-mcu.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <uapi/linux/input-event-codes.h>
+
+/*
+ * The power-key needs to be pressed for a while to create an event,
+ * so there is no use for overly frequent polling.
+ */
+#define POLL_INTERVAL		500
+
+struct qnap_mcu_input_dev {
+	struct input_dev *input;
+	struct qnap_mcu *mcu;
+	struct device *dev;
+
+	struct work_struct beep_work;
+	int beep_type;
+};
+
+static void qnap_mcu_input_poll(struct input_dev *input)
+{
+	struct qnap_mcu_input_dev *idev = input_get_drvdata(input);
+	static const u8 cmd[] = { '@', 'C', 'V' };
+	u8 reply[4];
+	int state, ret;
+
+	/* poll the power button */
+	ret = qnap_mcu_exec(idev->mcu, cmd, sizeof(cmd), reply, sizeof(reply));
+	if (ret)
+		return;
+
+	/* First bytes must mirror the sent command */
+	if (memcmp(cmd, reply, sizeof(cmd))) {
+		dev_err(idev->dev, "malformed data received\n");
+		return;
+	}
+
+	state = reply[3] - 0x30;
+	input_event(input, EV_KEY, KEY_POWER, state);
+	input_sync(input);
+}
+
+static void qnap_mcu_input_beeper_work(struct work_struct *work)
+{
+	struct qnap_mcu_input_dev *idev =
+		container_of(work, struct qnap_mcu_input_dev, beep_work);
+	const u8 cmd[] = { '@', 'C', (idev->beep_type == SND_TONE) ? '3' : '2' };
+
+	qnap_mcu_exec_with_ack(idev->mcu, cmd, sizeof(cmd));
+}
+
+static int qnap_mcu_input_event(struct input_dev *input, unsigned int type,
+				unsigned int code, int value)
+{
+	struct qnap_mcu_input_dev *idev = input_get_drvdata(input);
+
+	if (type != EV_SND || (code != SND_BELL && code != SND_TONE))
+		return -EOPNOTSUPP;
+
+	if (value < 0)
+		return -EINVAL;
+
+	/* beep runtime is determined by the MCU */
+	if (value == 0)
+		return 0;
+
+	/* Schedule work to actually turn the beeper on */
+	idev->beep_type = code;
+	schedule_work(&idev->beep_work);
+
+	return 0;
+}
+
+static void qnap_mcu_input_close(struct input_dev *input)
+{
+	struct qnap_mcu_input_dev *idev = input_get_drvdata(input);
+
+	cancel_work_sync(&idev->beep_work);
+}
+
+static int qnap_mcu_input_probe(struct platform_device *pdev)
+{
+	struct qnap_mcu *mcu = dev_get_drvdata(pdev->dev.parent);
+	struct qnap_mcu_input_dev *idev;
+	struct device *dev = &pdev->dev;
+	struct input_dev *input;
+	int ret;
+
+	idev = devm_kzalloc(dev, sizeof(*idev), GFP_KERNEL);
+	if (!idev)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(dev);
+	if (!input)
+		return -ENOMEM;
+
+	idev->input = input;
+	idev->dev = dev;
+	idev->mcu = mcu;
+
+	input_set_drvdata(input, idev);
+
+	input->name		= "qnap-mcu";
+	input->phys		= "qnap-mcu-input/input0";
+	input->id.bustype	= BUS_HOST;
+	input->id.vendor	= 0x0001;
+	input->id.product	= 0x0001;
+	input->id.version	= 0x0100;
+	input->event		= qnap_mcu_input_event;
+	input->close		= qnap_mcu_input_close;
+
+	input_set_capability(input, EV_KEY, KEY_POWER);
+	input_set_capability(input, EV_SND, SND_BELL);
+	input_set_capability(input, EV_SND, SND_TONE);
+
+	INIT_WORK(&idev->beep_work, qnap_mcu_input_beeper_work);
+
+	ret = input_setup_polling(input, qnap_mcu_input_poll);
+	if (ret)
+		return dev_err_probe(dev, ret, "unable to set up polling\n");
+
+	input_set_poll_interval(input, POLL_INTERVAL);
+
+	ret = input_register_device(input);
+	if (ret)
+		return dev_err_probe(dev, ret, "unable to register input device\n");
+
+	return 0;
+}
+
+static struct platform_driver qnap_mcu_input_driver = {
+	.probe = qnap_mcu_input_probe,
+	.driver = {
+		.name = "qnap-mcu-input",
+	},
+};
+module_platform_driver(qnap_mcu_input_driver);
+
+MODULE_ALIAS("platform:qnap-mcu-input");
+MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
+MODULE_DESCRIPTION("QNAP MCU input driver");
+MODULE_LICENSE("GPL");