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, 100 insertions, 0 deletions

diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h
new file mode 100644
index 000000000..4b9f5a12c
--- /dev/null
+++ b/fs/ocfs2/dir.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * dir.h
+ *
+ * Function prototypes
+ *
+ * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
+ */
+
+#ifndef OCFS2_DIR_H
+#define OCFS2_DIR_H
+
+struct ocfs2_dx_hinfo {
+	u32	major_hash;
+	u32	minor_hash;
+};
+
+struct ocfs2_dir_lookup_result {
+	struct buffer_head		*dl_leaf_bh;	/* Unindexed leaf
+							 * block */
+	struct ocfs2_dir_entry		*dl_entry;	/* Target dirent in
+							 * unindexed leaf */
+
+	struct buffer_head		*dl_dx_root_bh;	/* Root of indexed
+							 * tree */
+
+	struct buffer_head		*dl_dx_leaf_bh;	/* Indexed leaf block */
+	struct ocfs2_dx_entry		*dl_dx_entry;	/* Target dx_entry in
+							 * indexed leaf */
+	struct ocfs2_dx_hinfo		dl_hinfo;	/* Name hash results */
+
+	struct buffer_head		*dl_prev_leaf_bh;/* Previous entry in
+							  * dir free space
+							  * list. NULL if
+							  * previous entry is
+							  * dx root block. */
+};
+
+void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res);
+
+int ocfs2_find_entry(const char *name, int namelen,
+		     struct inode *dir,
+		     struct ocfs2_dir_lookup_result *lookup);
+int ocfs2_delete_entry(handle_t *handle,
+		       struct inode *dir,
+		       struct ocfs2_dir_lookup_result *res);
+int __ocfs2_add_entry(handle_t *handle,
+		      struct inode *dir,
+		      const char *name, int namelen,
+		      struct inode *inode, u64 blkno,
+		      struct buffer_head *parent_fe_bh,
+		      struct ocfs2_dir_lookup_result *lookup);
+static inline int ocfs2_add_entry(handle_t *handle,
+				  struct dentry *dentry,
+				  struct inode *inode, u64 blkno,
+				  struct buffer_head *parent_fe_bh,
+				  struct ocfs2_dir_lookup_result *lookup)
+{
+	return __ocfs2_add_entry(handle, d_inode(dentry->d_parent),
+				 dentry->d_name.name, dentry->d_name.len,
+				 inode, blkno, parent_fe_bh, lookup);
+}
+int ocfs2_update_entry(struct inode *dir, handle_t *handle,
+		       struct ocfs2_dir_lookup_result *res,
+		       struct inode *new_entry_inode);
+
+int ocfs2_check_dir_for_entry(struct inode *dir,
+			      const char *name,
+			      int namelen);
+int ocfs2_empty_dir(struct inode *inode);
+
+int ocfs2_find_files_on_disk(const char *name,
+			     int namelen,
+			     u64 *blkno,
+			     struct inode *inode,
+			     struct ocfs2_dir_lookup_result *res);
+int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
+			       int namelen, u64 *blkno);
+int ocfs2_readdir(struct file *file, struct dir_context *ctx);
+int ocfs2_dir_foreach(struct inode *inode, struct dir_context *ctx);
+int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
+				 struct inode *dir,
+				 struct buffer_head *parent_fe_bh,
+				 const char *name,
+				 int namelen,
+				 struct ocfs2_dir_lookup_result *lookup);
+struct ocfs2_alloc_context;
+int ocfs2_fill_new_dir(struct ocfs2_super *osb,
+		       handle_t *handle,
+		       struct inode *parent,
+		       struct inode *inode,
+		       struct buffer_head *fe_bh,
+		       struct ocfs2_alloc_context *data_ac,
+		       struct ocfs2_alloc_context *meta_ac);
+
+int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh);
+
+struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize,
+							    void *data);
+#endif /* OCFS2_DIR_H */