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, 69 insertions, 0 deletions

diff --git a/fs/bfs/bfs.h b/fs/bfs/bfs.h
new file mode 100644
index 000000000..b08afe733
--- /dev/null
+++ b/fs/bfs/bfs.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *	fs/bfs/bfs.h
+ *	Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com>
+ */
+#ifndef _FS_BFS_BFS_H
+#define _FS_BFS_BFS_H
+
+#include <linux/bfs_fs.h>
+
+/* In theory BFS supports up to 512 inodes, numbered from 2 (for /) up to 513 inclusive.
+   In actual fact, attempting to create the 512th inode (i.e. inode No. 513 or file No. 511)
+   will fail with ENOSPC in bfs_add_entry(): the root directory cannot contain so many entries, counting '..'.
+   So, mkfs.bfs(8) should really limit its -N option to 511 and not 512. For now, we just print a warning
+   if a filesystem is mounted with such "impossible to fill up" number of inodes */
+#define BFS_MAX_LASTI	513
+
+/*
+ * BFS file system in-core superblock info
+ */
+struct bfs_sb_info {
+	unsigned long si_blocks;
+	unsigned long si_freeb;
+	unsigned long si_freei;
+	unsigned long si_lf_eblk;
+	unsigned long si_lasti;
+	DECLARE_BITMAP(si_imap, BFS_MAX_LASTI+1);
+	struct mutex bfs_lock;
+};
+
+/*
+ * BFS file system in-core inode info
+ */
+struct bfs_inode_info {
+	unsigned long i_dsk_ino; /* inode number from the disk, can be 0 */
+	unsigned long i_sblock;
+	unsigned long i_eblock;
+	struct mapping_metadata_bhs i_metadata_bhs;
+	struct inode vfs_inode;
+};
+
+static inline struct bfs_sb_info *BFS_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+static inline struct bfs_inode_info *BFS_I(struct inode *inode)
+{
+	return container_of(inode, struct bfs_inode_info, vfs_inode);
+}
+
+
+#define printf(format, args...) \
+	printk(KERN_ERR "BFS-fs: %s(): " format, __func__, ## args)
+
+/* inode.c */
+extern struct inode *bfs_iget(struct super_block *sb, unsigned long ino);
+extern void bfs_dump_imap(const char *, struct super_block *);
+
+/* file.c */
+extern const struct inode_operations bfs_file_inops;
+extern const struct file_operations bfs_file_operations;
+extern const struct address_space_operations bfs_aops;
+
+/* dir.c */
+extern const struct inode_operations bfs_dir_inops;
+extern const struct file_operations bfs_dir_operations;
+
+#endif /* _FS_BFS_BFS_H */