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, 73 insertions, 0 deletions

diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
new file mode 100644
index 000000000..aa02599b7
--- /dev/null
+++ b/fs/hostfs/hostfs.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_FS_HOSTFS
+#define __UM_FS_HOSTFS
+
+#include <os.h>
+#include <generated/asm-offsets.h>
+
+struct hostfs_timespec {
+	long long tv_sec;
+	long long tv_nsec;
+};
+
+struct hostfs_iattr {
+	unsigned int		ia_valid;
+	unsigned short		ia_mode;
+	uid_t			ia_uid;
+	gid_t			ia_gid;
+	loff_t			ia_size;
+	struct hostfs_timespec	ia_atime;
+	struct hostfs_timespec	ia_mtime;
+	struct hostfs_timespec	ia_ctime;
+};
+
+struct hostfs_stat {
+	unsigned long long ino;
+	unsigned int mode;
+	unsigned int nlink;
+	unsigned int uid;
+	unsigned int gid;
+	unsigned long long size;
+	struct hostfs_timespec atime, mtime, ctime, btime;
+	unsigned int blksize;
+	unsigned long long blocks;
+	struct {
+		unsigned int maj;
+		unsigned int min;
+	} rdev, dev;
+};
+
+extern int stat_file(const char *path, struct hostfs_stat *p, int fd);
+extern int access_file(char *path, int r, int w, int x);
+extern int open_file(char *path, int r, int w, int append);
+extern void *open_dir(char *path, int *err_out);
+extern void seek_dir(void *stream, unsigned long long pos);
+extern char *read_dir(void *stream, unsigned long long *pos_out,
+		      unsigned long long *ino_out, int *len_out,
+		      unsigned int *type_out);
+extern void close_file(void *stream);
+extern int replace_file(int oldfd, int fd);
+extern void close_dir(void *stream);
+extern int read_file(int fd, unsigned long long *offset, char *buf, int len);
+extern int write_file(int fd, unsigned long long *offset, const char *buf,
+		      int len);
+extern int lseek_file(int fd, long long offset, int whence);
+extern int fsync_file(int fd, int datasync);
+extern int file_create(char *name, int mode);
+extern int set_attr(const char *file, struct hostfs_iattr *attrs, int fd);
+extern int make_symlink(const char *from, const char *to);
+extern int unlink_file(const char *file);
+extern int do_mkdir(const char *file, int mode);
+extern int hostfs_do_rmdir(const char *file);
+extern int do_mknod(const char *file, int mode, unsigned int major,
+		    unsigned int minor);
+extern int link_file(const char *to, const char *from);
+extern int hostfs_do_readlink(char *file, char *buf, int size);
+extern int rename_file(char *from, char *to);
+extern int rename2_file(char *from, char *to, unsigned int flags);
+extern int do_statfs(char *root, long *bsize_out, long long *blocks_out,
+		     long long *bfree_out, long long *bavail_out,
+		     long long *files_out, long long *ffree_out,
+		     void *fsid_out, int fsid_size, long *namelen_out);
+
+#endif