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, 313 insertions, 0 deletions

diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c
new file mode 100644
index 000000000..8c19975c8
--- /dev/null
+++ b/drivers/input/serio/userio.c
@@ -0,0 +1,313 @@
+/*
+ * userio kernel serio device emulation module
+ * Copyright (C) 2015 Red Hat
+ * Copyright (C) 2015 Lyude Paul <thatslyude@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser
+ * General Public License for more details.
+ */
+
+#include <linux/circ_buf.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/serio.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/sched.h>
+#include <linux/poll.h>
+#include <uapi/linux/userio.h>
+
+#define USERIO_NAME		"userio"
+#define USERIO_BUFSIZE		16
+
+static struct miscdevice userio_misc;
+
+struct userio_device {
+	struct serio *serio;
+	struct mutex mutex;
+
+	bool running;
+
+	u8 head;
+	u8 tail;
+
+	spinlock_t buf_lock;
+	unsigned char buf[USERIO_BUFSIZE];
+
+	wait_queue_head_t waitq;
+};
+
+/**
+ * userio_device_write - Write data from serio to a userio device in userspace
+ * @id: The serio port for the userio device
+ * @val: The data to write to the device
+ */
+static int userio_device_write(struct serio *id, unsigned char val)
+{
+	struct userio_device *userio = id->port_data;
+
+	scoped_guard(spinlock_irqsave, &userio->buf_lock) {
+		userio->buf[userio->head] = val;
+		userio->head = (userio->head + 1) % USERIO_BUFSIZE;
+
+		if (userio->head == userio->tail)
+			dev_warn(userio_misc.this_device,
+				 "Buffer overflowed, userio client isn't keeping up");
+	}
+
+	wake_up_interruptible(&userio->waitq);
+
+	return 0;
+}
+
+static int userio_char_open(struct inode *inode, struct file *file)
+{
+	struct userio_device *userio __free(kfree) =
+			kzalloc_obj(*userio);
+	if (!userio)
+		return -ENOMEM;
+
+	mutex_init(&userio->mutex);
+	spin_lock_init(&userio->buf_lock);
+	init_waitqueue_head(&userio->waitq);
+
+	userio->serio = kzalloc_obj(*userio->serio);
+	if (!userio->serio)
+		return -ENOMEM;
+
+	userio->serio->write = userio_device_write;
+	userio->serio->port_data = userio;
+
+	file->private_data = no_free_ptr(userio);
+
+	return 0;
+}
+
+static int userio_char_release(struct inode *inode, struct file *file)
+{
+	struct userio_device *userio = file->private_data;
+
+	if (userio->running) {
+		/*
+		 * Don't free the serio port here, serio_unregister_port()
+		 * does it for us.
+		 */
+		serio_unregister_port(userio->serio);
+	} else {
+		kfree(userio->serio);
+	}
+
+	kfree(userio);
+
+	return 0;
+}
+
+static size_t userio_fetch_data(struct userio_device *userio, u8 *buf,
+				size_t count, size_t *copylen)
+{
+	size_t available, len;
+
+	guard(spinlock_irqsave)(&userio->buf_lock);
+
+	available = CIRC_CNT_TO_END(userio->head, userio->tail,
+				    USERIO_BUFSIZE);
+	len = min(available, count);
+	if (len) {
+		memcpy(buf, &userio->buf[userio->tail], len);
+		userio->tail = (userio->tail + len) % USERIO_BUFSIZE;
+	}
+
+	*copylen = len;
+	return available;
+}
+
+static ssize_t userio_char_read(struct file *file, char __user *user_buffer,
+				size_t count, loff_t *ppos)
+{
+	struct userio_device *userio = file->private_data;
+	int error;
+	size_t available, copylen;
+	u8 buf[USERIO_BUFSIZE];
+
+	/*
+	 * By the time we get here, the data that was waiting might have
+	 * been taken by another thread. Grab the buffer lock and check if
+	 * there's still any data waiting, otherwise repeat this process
+	 * until we have data (unless the file descriptor is non-blocking
+	 * of course).
+	 */
+	for (;;) {
+		available = userio_fetch_data(userio, buf, count, &copylen);
+		if (available)
+			break;
+
+		/* buffer was/is empty */
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		/*
+		 * count == 0 is special - no IO is done but we check
+		 * for error conditions (see above).
+		 */
+		if (count == 0)
+			return 0;
+
+		error = wait_event_interruptible(userio->waitq,
+						 userio->head != userio->tail);
+		if (error)
+			return error;
+	}
+
+	if (copylen)
+		if (copy_to_user(user_buffer, buf, copylen))
+			return -EFAULT;
+
+	return copylen;
+}
+
+static int userio_execute_cmd(struct userio_device *userio,
+			      const struct userio_cmd *cmd)
+{
+	switch (cmd->type) {
+	case USERIO_CMD_REGISTER:
+		if (!userio->serio->id.type) {
+			dev_warn(userio_misc.this_device,
+				 "No port type given on /dev/userio\n");
+			return -EINVAL;
+		}
+
+		if (userio->running) {
+			dev_warn(userio_misc.this_device,
+				 "Begin command sent, but we're already running\n");
+			return -EBUSY;
+		}
+
+		userio->running = true;
+		serio_register_port(userio->serio);
+		break;
+
+	case USERIO_CMD_SET_PORT_TYPE:
+		if (userio->running) {
+			dev_warn(userio_misc.this_device,
+				 "Can't change port type on an already running userio instance\n");
+			return -EBUSY;
+		}
+
+		userio->serio->id.type = cmd->data;
+		break;
+
+	case USERIO_CMD_SET_PORT_EXTRA:
+		if (userio->running) {
+			dev_warn(userio_misc.this_device,
+				 "Can't change port extra on an already running userio instance\n");
+			return -EBUSY;
+		}
+
+		userio->serio->id.extra = cmd->data;
+		break;
+
+	case USERIO_CMD_SET_PORT_ID:
+		if (userio->running) {
+			dev_warn(userio_misc.this_device,
+				 "Can't change port id on an already running userio instance\n");
+			return -EBUSY;
+		}
+
+		userio->serio->id.id = cmd->data;
+		break;
+
+	case USERIO_CMD_SET_PORT_PROTO:
+		if (userio->running) {
+			dev_warn(userio_misc.this_device,
+				 "Can't change port proto on an already running userio instance\n");
+			return -EBUSY;
+		}
+
+		userio->serio->id.proto = cmd->data;
+		break;
+
+	case USERIO_CMD_SEND_INTERRUPT:
+		if (!userio->running) {
+			dev_warn(userio_misc.this_device,
+				 "The device must be registered before sending interrupts\n");
+			return -ENODEV;
+		}
+
+		serio_interrupt(userio->serio, cmd->data, 0);
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static ssize_t userio_char_write(struct file *file, const char __user *buffer,
+				 size_t count, loff_t *ppos)
+{
+	struct userio_device *userio = file->private_data;
+	struct userio_cmd cmd;
+	int error;
+
+	if (count != sizeof(cmd)) {
+		dev_warn(userio_misc.this_device, "Invalid payload size\n");
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&cmd, buffer, sizeof(cmd)))
+		return -EFAULT;
+
+	scoped_cond_guard(mutex_intr, return -EINTR, &userio->mutex) {
+		error = userio_execute_cmd(userio, &cmd);
+		if (error)
+			return error;
+	}
+
+	return count;
+}
+
+static __poll_t userio_char_poll(struct file *file, poll_table *wait)
+{
+	struct userio_device *userio = file->private_data;
+
+	poll_wait(file, &userio->waitq, wait);
+
+	if (userio->head != userio->tail)
+		return EPOLLIN | EPOLLRDNORM;
+
+	return 0;
+}
+
+static const struct file_operations userio_fops = {
+	.owner		= THIS_MODULE,
+	.open		= userio_char_open,
+	.release	= userio_char_release,
+	.read		= userio_char_read,
+	.write		= userio_char_write,
+	.poll		= userio_char_poll,
+};
+
+static struct miscdevice userio_misc = {
+	.fops	= &userio_fops,
+	.minor	= USERIO_MINOR,
+	.name	= USERIO_NAME,
+};
+module_driver(userio_misc, misc_register, misc_deregister);
+
+MODULE_ALIAS_MISCDEV(USERIO_MINOR);
+MODULE_ALIAS("devname:" USERIO_NAME);
+
+MODULE_AUTHOR("Lyude Paul <thatslyude@gmail.com>");
+MODULE_DESCRIPTION("Virtual Serio Device Support");
+MODULE_LICENSE("GPL");