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, 166 insertions, 0 deletions

diff --git a/fs/failfs.c b/fs/failfs.c
new file mode 100644
index 000000000..66a36da3d
--- /dev/null
+++ b/fs/failfs.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2026 Christian Brauner <brauner@kernel.org> */
+#include <linux/fs.h>
+#include <linux/fs/super_types.h>
+#include <linux/fs_context.h>
+#include <linux/fs_struct.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+
+#include "internal.h"
+
+static struct path failfs_root_path = {};
+
+void failfs_get_root(struct path *path)
+{
+	*path = failfs_root_path;
+	path_get(path);
+}
+
+bool failfs_mnt(const struct vfsmount *mnt)
+{
+	return mnt->mnt_sb == failfs_root_path.mnt->mnt_sb;
+}
+
+static int failfs_permission(struct mnt_idmap *idmap, struct inode *inode,
+			     int mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct dentry *failfs_lookup(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	/* Unreachable: ->permission() already failed the walk. */
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static int failfs_getattr(struct mnt_idmap *idmap, const struct path *path,
+			  struct kstat *stat, u32 request_mask,
+			  unsigned int query_flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct inode_operations failfs_dir_inode_operations = {
+	.permission	= failfs_permission,
+	.lookup		= failfs_lookup,
+	.getattr	= failfs_getattr,
+};
+
+static const struct file_operations failfs_dir_operations = {};
+
+static int failfs_d_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	/*
+	 * The root is only ever reached as a path-walk terminal by jumping
+	 * to it: as "/" when it is the caller's root, or through a
+	 * /proc/<pid>/{root,cwd} magic link. ->permission() already fails
+	 * every walk of a component, but a jump lands on the root without
+	 * one. Refuse here too so the root cannot be pinned by an O_PATH
+	 * open or encoded into a file handle.
+	 */
+	return -EOPNOTSUPP;
+}
+
+static char *failfs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	return dynamic_dname(buffer, buflen, "failfs:/");
+}
+
+static const struct dentry_operations failfs_dentry_operations = {
+	.d_dname		= failfs_dname,
+	.d_weak_revalidate	= failfs_d_weak_revalidate,
+};
+
+static int failfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct super_operations failfs_super_operations = {
+	.statfs	= failfs_statfs,
+};
+
+static int failfs_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct inode *inode;
+
+	s->s_maxbytes		= MAX_LFS_FILESIZE;
+	s->s_blocksize		= PAGE_SIZE;
+	s->s_blocksize_bits	= PAGE_SHIFT;
+	s->s_magic		= FAIL_FS_MAGIC;
+	s->s_op			= &failfs_super_operations;
+	s->s_export_op		= NULL;
+	s->s_xattr		= NULL;
+	s->s_time_gran		= 1;
+	s->s_d_flags		= 0;
+
+	inode = new_inode(s);
+	if (!inode)
+		return -ENOMEM;
+
+	/* failfs supports no operations... */
+	inode->i_mode	= S_IFDIR;
+	set_nlink(inode, 2);
+	inode->i_op	= &failfs_dir_inode_operations;
+	inode->i_fop	= &failfs_dir_operations;
+	simple_inode_init_ts(inode);
+	inode->i_ino	= 1;
+	/* ... and is immutable. */
+	inode->i_flags |= S_IMMUTABLE;
+
+	set_default_d_op(s, &failfs_dentry_operations);
+	s->s_root = d_make_root(inode);
+	if (!s->s_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int failfs_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, failfs_fill_super);
+}
+
+static const struct fs_context_operations failfs_context_ops = {
+	.get_tree	= failfs_get_tree,
+};
+
+static int failfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops		= &failfs_context_ops;
+	fc->global	= true;
+	fc->sb_flags	|= SB_NOUSER;
+	fc->s_iflags	|= SB_I_NOEXEC | SB_I_NODEV;
+	return 0;
+}
+
+int failfs_current_chdir(void)
+{
+	struct path path;
+
+	failfs_get_root(&path);
+	set_fs_pwd(current->fs, &path);
+	path_put(&path);
+	return 0;
+}
+
+static struct file_system_type failfs_fs_type = {
+	.name			= "failfs",
+	.init_fs_context	= failfs_init_fs_context,
+	.kill_sb		= kill_anon_super,
+};
+
+void __init failfs_init(void)
+{
+	struct vfsmount *mnt;
+
+	/* A single instance that is member of no mount namespace. */
+	mnt = kern_mount(&failfs_fs_type);
+	if (IS_ERR(mnt))
+		panic("VFS: Failed to create failfs");
+
+	failfs_root_path.mnt	= mnt;
+	failfs_root_path.dentry	= mnt->mnt_root;
+}