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/omfs/omfs.h b/fs/omfs/omfs.h
new file mode 100644
index 000000000..4008be73d
--- /dev/null
+++ b/fs/omfs/omfs.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _OMFS_H
+#define _OMFS_H
+
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "omfs_fs.h"
+
+/* In-memory structures */
+struct omfs_sb_info {
+	u64 s_num_blocks;
+	u64 s_bitmap_ino;
+	u64 s_root_ino;
+	u32 s_blocksize;
+	u32 s_mirrors;
+	u32 s_sys_blocksize;
+	u32 s_clustersize;
+	int s_block_shift;
+	unsigned long **s_imap;
+	int s_imap_size;
+	struct mutex s_bitmap_lock;
+	kuid_t s_uid;
+	kgid_t s_gid;
+	int s_dmask;
+	int s_fmask;
+};
+
+/* convert a cluster number to a scaled block number */
+static inline sector_t clus_to_blk(struct omfs_sb_info *sbi, sector_t block)
+{
+	return block << sbi->s_block_shift;
+}
+
+static inline struct omfs_sb_info *OMFS_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/* bitmap.c */
+extern unsigned long omfs_count_free(struct super_block *sb);
+extern int omfs_allocate_block(struct super_block *sb, u64 block);
+extern int omfs_allocate_range(struct super_block *sb, int min_request,
+			int max_request, u64 *return_block, int *return_size);
+extern int omfs_clear_range(struct super_block *sb, u64 block, int count);
+
+/* dir.c */
+extern const struct file_operations omfs_dir_operations;
+extern const struct inode_operations omfs_dir_inops;
+extern int omfs_make_empty(struct inode *inode, struct super_block *sb);
+extern int omfs_is_bad(struct omfs_sb_info *sbi, struct omfs_header *header,
+			u64 fsblock);
+
+/* file.c */
+extern const struct file_operations omfs_file_operations;
+extern const struct inode_operations omfs_file_inops;
+extern const struct address_space_operations omfs_aops;
+extern void omfs_make_empty_table(struct buffer_head *bh, int offset);
+extern int omfs_shrink_inode(struct inode *inode);
+
+/* inode.c */
+extern struct buffer_head *omfs_bread(struct super_block *sb, sector_t block);
+extern struct inode *omfs_iget(struct super_block *sb, ino_t inode);
+extern struct inode *omfs_new_inode(struct inode *dir, umode_t mode);
+extern int omfs_reserve_block(struct super_block *sb, sector_t block);
+extern int omfs_find_empty_block(struct super_block *sb, int mode, ino_t *ino);
+extern int omfs_sync_inode(struct inode *inode);
+
+#endif