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, 134 insertions, 0 deletions

diff --git a/drivers/input/misc/pcspkr.c b/drivers/input/misc/pcspkr.c
new file mode 100644
index 000000000..046780840
--- /dev/null
+++ b/drivers/input/misc/pcspkr.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  PC Speaker beeper driver for Linux
+ *
+ *  Copyright (c) 2002 Vojtech Pavlik
+ *  Copyright (c) 1992 Orest Zborowski
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/i8253.h>
+#include <linux/input.h>
+#include <linux/platform_device.h>
+#include <linux/timex.h>
+#include <linux/io.h>
+
+MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
+MODULE_DESCRIPTION("PC Speaker beeper driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:pcspkr");
+
+static int pcspkr_event(struct input_dev *dev, unsigned int type,
+			unsigned int code, int value)
+{
+	unsigned int count = 0;
+	unsigned long flags;
+
+	if (type != EV_SND)
+		return -EINVAL;
+
+	switch (code) {
+	case SND_BELL:
+		if (value)
+			value = 1000;
+		break;
+	case SND_TONE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (value > 20 && value < 32767)
+		count = PIT_TICK_RATE / value;
+
+	raw_spin_lock_irqsave(&i8253_lock, flags);
+
+	if (count) {
+		/* set command for counter 2, 2 byte write */
+		outb_p(0xB6, 0x43);
+		/* select desired HZ */
+		outb_p(count & 0xff, 0x42);
+		outb((count >> 8) & 0xff, 0x42);
+		/* enable counter 2 */
+		outb_p(inb_p(0x61) | 3, 0x61);
+	} else {
+		/* disable counter 2 */
+		outb(inb_p(0x61) & 0xFC, 0x61);
+	}
+
+	raw_spin_unlock_irqrestore(&i8253_lock, flags);
+
+	return 0;
+}
+
+static int pcspkr_probe(struct platform_device *dev)
+{
+	struct input_dev *pcspkr_dev;
+	int err;
+
+	pcspkr_dev = input_allocate_device();
+	if (!pcspkr_dev)
+		return -ENOMEM;
+
+	pcspkr_dev->name = "PC Speaker";
+	pcspkr_dev->phys = "isa0061/input0";
+	pcspkr_dev->id.bustype = BUS_ISA;
+	pcspkr_dev->id.vendor = 0x001f;
+	pcspkr_dev->id.product = 0x0001;
+	pcspkr_dev->id.version = 0x0100;
+	pcspkr_dev->dev.parent = &dev->dev;
+
+	pcspkr_dev->evbit[0] = BIT_MASK(EV_SND);
+	pcspkr_dev->sndbit[0] = BIT_MASK(SND_BELL) | BIT_MASK(SND_TONE);
+	pcspkr_dev->event = pcspkr_event;
+
+	err = input_register_device(pcspkr_dev);
+	if (err) {
+		input_free_device(pcspkr_dev);
+		return err;
+	}
+
+	platform_set_drvdata(dev, pcspkr_dev);
+
+	return 0;
+}
+
+static void pcspkr_remove(struct platform_device *dev)
+{
+	struct input_dev *pcspkr_dev = platform_get_drvdata(dev);
+
+	input_unregister_device(pcspkr_dev);
+	/* turn off the speaker */
+	pcspkr_event(NULL, EV_SND, SND_BELL, 0);
+}
+
+static int pcspkr_suspend(struct device *dev)
+{
+	pcspkr_event(NULL, EV_SND, SND_BELL, 0);
+
+	return 0;
+}
+
+static void pcspkr_shutdown(struct platform_device *dev)
+{
+	/* turn off the speaker */
+	pcspkr_event(NULL, EV_SND, SND_BELL, 0);
+}
+
+static const struct dev_pm_ops pcspkr_pm_ops = {
+	.suspend = pcspkr_suspend,
+};
+
+static struct platform_driver pcspkr_platform_driver = {
+	.driver		= {
+		.name	= "pcspkr",
+		.pm	= &pcspkr_pm_ops,
+	},
+	.probe		= pcspkr_probe,
+	.remove		= pcspkr_remove,
+	.shutdown	= pcspkr_shutdown,
+};
+module_platform_driver(pcspkr_platform_driver);
+