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, 219 insertions, 0 deletions

diff --git a/drivers/leds/uleds.c b/drivers/leds/uleds.c
new file mode 100644
index 000000000..6affa581b
--- /dev/null
+++ b/drivers/leds/uleds.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Userspace driver for the LED subsystem
+ *
+ * Copyright (C) 2016 David Lechner <david@lechnology.com>
+ *
+ * Based on uinput.c: Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
+ */
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <uapi/linux/uleds.h>
+
+#define ULEDS_NAME	"uleds"
+
+enum uleds_state {
+	ULEDS_STATE_UNKNOWN,
+	ULEDS_STATE_REGISTERED,
+};
+
+struct uleds_device {
+	struct uleds_user_dev	user_dev;
+	struct led_classdev	led_cdev;
+	struct mutex		mutex;
+	enum uleds_state	state;
+	wait_queue_head_t	waitq;
+	int			brightness;
+	bool			new_data;
+};
+
+static struct miscdevice uleds_misc;
+
+static void uleds_brightness_set(struct led_classdev *led_cdev,
+				 enum led_brightness brightness)
+{
+	struct uleds_device *udev = container_of(led_cdev, struct uleds_device,
+						 led_cdev);
+
+	if (udev->brightness != brightness) {
+		udev->brightness = brightness;
+		udev->new_data = true;
+		wake_up_interruptible(&udev->waitq);
+	}
+}
+
+static int uleds_open(struct inode *inode, struct file *file)
+{
+	struct uleds_device *udev;
+
+	udev = kzalloc_obj(*udev);
+	if (!udev)
+		return -ENOMEM;
+
+	udev->led_cdev.name = udev->user_dev.name;
+	udev->led_cdev.brightness_set = uleds_brightness_set;
+
+	mutex_init(&udev->mutex);
+	init_waitqueue_head(&udev->waitq);
+	udev->state = ULEDS_STATE_UNKNOWN;
+
+	file->private_data = udev;
+	stream_open(inode, file);
+
+	return 0;
+}
+
+static ssize_t uleds_write(struct file *file, const char __user *buffer,
+			   size_t count, loff_t *ppos)
+{
+	struct uleds_device *udev = file->private_data;
+	const char *name;
+	int ret;
+
+	if (count == 0)
+		return 0;
+
+	ret = mutex_lock_interruptible(&udev->mutex);
+	if (ret)
+		return ret;
+
+	if (udev->state == ULEDS_STATE_REGISTERED) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (count != sizeof(struct uleds_user_dev)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (copy_from_user(&udev->user_dev, buffer,
+			   sizeof(struct uleds_user_dev))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	name = udev->user_dev.name;
+	if (!name[0] || !strcmp(name, ".") || !strcmp(name, "..") ||
+	    strnchr(name, sizeof(udev->user_dev.name), '/') ||
+	    !strnchr(name, sizeof(udev->user_dev.name), '\0')) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (udev->user_dev.max_brightness <= 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+	udev->led_cdev.max_brightness = udev->user_dev.max_brightness;
+
+	ret = devm_led_classdev_register(uleds_misc.this_device,
+					 &udev->led_cdev);
+	if (ret < 0)
+		goto out;
+
+	udev->new_data = true;
+	udev->state = ULEDS_STATE_REGISTERED;
+	ret = count;
+
+out:
+	mutex_unlock(&udev->mutex);
+
+	return ret;
+}
+
+static ssize_t uleds_read(struct file *file, char __user *buffer, size_t count,
+			  loff_t *ppos)
+{
+	struct uleds_device *udev = file->private_data;
+	ssize_t retval;
+
+	if (count < sizeof(udev->brightness))
+		return 0;
+
+	do {
+		retval = mutex_lock_interruptible(&udev->mutex);
+		if (retval)
+			return retval;
+
+		if (udev->state != ULEDS_STATE_REGISTERED) {
+			retval = -ENODEV;
+		} else if (!udev->new_data && (file->f_flags & O_NONBLOCK)) {
+			retval = -EAGAIN;
+		} else if (udev->new_data) {
+			if (copy_to_user(buffer, &udev->brightness,
+					 sizeof(udev->brightness))) {
+				retval = -EFAULT;
+			} else {
+				udev->new_data = false;
+				retval = sizeof(udev->brightness);
+			}
+		}
+
+		mutex_unlock(&udev->mutex);
+
+		if (retval)
+			break;
+
+		if (!(file->f_flags & O_NONBLOCK))
+			retval = wait_event_interruptible(udev->waitq,
+					udev->new_data ||
+					udev->state != ULEDS_STATE_REGISTERED);
+	} while (retval == 0);
+
+	return retval;
+}
+
+static __poll_t uleds_poll(struct file *file, poll_table *wait)
+{
+	struct uleds_device *udev = file->private_data;
+
+	poll_wait(file, &udev->waitq, wait);
+
+	if (udev->new_data)
+		return EPOLLIN | EPOLLRDNORM;
+
+	return 0;
+}
+
+static int uleds_release(struct inode *inode, struct file *file)
+{
+	struct uleds_device *udev = file->private_data;
+
+	if (udev->state == ULEDS_STATE_REGISTERED) {
+		udev->state = ULEDS_STATE_UNKNOWN;
+		devm_led_classdev_unregister(uleds_misc.this_device,
+					     &udev->led_cdev);
+	}
+	kfree(udev);
+
+	return 0;
+}
+
+static const struct file_operations uleds_fops = {
+	.owner		= THIS_MODULE,
+	.open		= uleds_open,
+	.release	= uleds_release,
+	.read		= uleds_read,
+	.write		= uleds_write,
+	.poll		= uleds_poll,
+};
+
+static struct miscdevice uleds_misc = {
+	.fops		= &uleds_fops,
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= ULEDS_NAME,
+};
+
+module_misc_device(uleds_misc);
+
+MODULE_AUTHOR("David Lechner <david@lechnology.com>");
+MODULE_DESCRIPTION("Userspace driver for the LED subsystem");
+MODULE_LICENSE("GPL");