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, 172 insertions, 0 deletions

diff --git a/include/media/media-devnode.h b/include/media/media-devnode.h
new file mode 100644
index 000000000..dbcabeffc
--- /dev/null
+++ b/include/media/media-devnode.h
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Media device node
+ *
+ * Copyright (C) 2010 Nokia Corporation
+ *
+ * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ *	     Sakari Ailus <sakari.ailus@iki.fi>
+ *
+ * --
+ *
+ * Common functions for media-related drivers to register and unregister media
+ * device nodes.
+ */
+
+#ifndef _MEDIA_DEVNODE_H
+#define _MEDIA_DEVNODE_H
+
+#include <linux/poll.h>
+#include <linux/fs.h>
+#include <linux/device.h>
+#include <linux/cdev.h>
+#include <linux/debugfs.h>
+
+struct media_device;
+
+/* debugfs top-level media directory */
+extern struct dentry *media_debugfs_root;
+
+/*
+ * Flag to mark the media_devnode struct as registered. Drivers must not touch
+ * this flag directly, it will be set and cleared by media_devnode_register and
+ * media_devnode_unregister.
+ */
+#define MEDIA_FLAG_REGISTERED	0
+
+/**
+ * struct media_file_operations - Media device file operations
+ *
+ * @owner: should be filled with %THIS_MODULE
+ * @read: pointer to the function that implements read() syscall
+ * @write: pointer to the function that implements write() syscall
+ * @poll: pointer to the function that implements poll() syscall
+ * @ioctl: pointer to the function that implements ioctl() syscall
+ * @compat_ioctl: pointer to the function that will handle 32 bits userspace
+ *	calls to the ioctl() syscall on a Kernel compiled with 64 bits.
+ * @open: pointer to the function that implements open() syscall
+ * @release: pointer to the function that will release the resources allocated
+ *	by the @open function.
+ */
+struct media_file_operations {
+	struct module *owner;
+	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
+	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
+	__poll_t (*poll) (struct file *, struct poll_table_struct *);
+	long (*ioctl) (struct file *, unsigned int, unsigned long);
+	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
+	int (*open) (struct file *);
+	int (*release) (struct file *);
+};
+
+/**
+ * struct media_devnode - Media device node
+ * @media_dev:	pointer to struct &media_device
+ * @fops:	pointer to struct &media_file_operations with media device ops
+ * @dev:	pointer to struct &device containing the media controller device
+ * @cdev:	struct cdev pointer character device
+ * @parent:	parent device
+ * @minor:	device node minor number
+ * @flags:	flags, combination of the ``MEDIA_FLAG_*`` constants
+ * @release:	release callback called at the end of ``media_devnode_release()``
+ *		routine at media-device.c.
+ *
+ * This structure represents a media-related device node.
+ *
+ * The @parent is a physical device. It must be set by core or device drivers
+ * before registering the node.
+ */
+struct media_devnode {
+	struct media_device *media_dev;
+
+	/* device ops */
+	const struct media_file_operations *fops;
+
+	/* sysfs */
+	struct device dev;		/* media device */
+	struct cdev cdev;		/* character device */
+	struct device *parent;		/* device parent */
+
+	/* device info */
+	int minor;
+	unsigned long flags;		/* Use bitops to access flags */
+
+	/* callbacks */
+	void (*release)(struct media_devnode *devnode);
+};
+
+/* dev to media_devnode */
+#define to_media_devnode(cd) container_of(cd, struct media_devnode, dev)
+
+/**
+ * media_devnode_register - register a media device node
+ *
+ * @mdev: struct media_device we want to register a device node
+ * @devnode: media device node structure we want to register
+ * @owner: should be filled with %THIS_MODULE
+ *
+ * The registration code assigns minor numbers and registers the new device node
+ * with the kernel. An error is returned if no free minor number can be found,
+ * or if the registration of the device node fails.
+ *
+ * Zero is returned on success.
+ *
+ * Note that if the media_devnode_register call fails, the release() callback of
+ * the media_devnode structure is *not* called, so the caller is responsible for
+ * freeing any data.
+ */
+int __must_check media_devnode_register(struct media_device *mdev,
+					struct media_devnode *devnode,
+					struct module *owner);
+
+/**
+ * media_devnode_unregister_prepare - clear the media device node register bit
+ * @devnode: the device node to prepare for unregister
+ *
+ * This clears the passed device register bit. Future open calls will be met
+ * with errors. Should be called before media_devnode_unregister() to avoid
+ * races with unregister and device file open calls.
+ *
+ * This function can safely be called if the device node has never been
+ * registered or has already been unregistered.
+ */
+void media_devnode_unregister_prepare(struct media_devnode *devnode);
+
+/**
+ * media_devnode_unregister - unregister a media device node
+ * @devnode: the device node to unregister
+ *
+ * This unregisters the passed device. Future open calls will be met with
+ * errors.
+ *
+ * Should be called after media_devnode_unregister_prepare()
+ */
+void media_devnode_unregister(struct media_devnode *devnode);
+
+/**
+ * media_devnode_data - returns a pointer to the &media_devnode
+ *
+ * @filp: pointer to struct &file
+ */
+static inline struct media_devnode *media_devnode_data(struct file *filp)
+{
+	return filp->private_data;
+}
+
+/**
+ * media_devnode_is_registered - returns true if &media_devnode is registered;
+ *	false otherwise.
+ *
+ * @devnode: pointer to struct &media_devnode.
+ *
+ * Note: If mdev is NULL, it also returns false.
+ */
+static inline int media_devnode_is_registered(struct media_devnode *devnode)
+{
+	if (!devnode)
+		return false;
+
+	return test_bit(MEDIA_FLAG_REGISTERED, &devnode->flags);
+}
+
+#endif /* _MEDIA_DEVNODE_H */