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, 74 insertions, 0 deletions

diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
new file mode 100644
index 000000000..41e65e45a
--- /dev/null
+++ b/fs/ocfs2/file.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * file.h
+ *
+ * Function prototypes
+ *
+ * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
+ */
+
+#ifndef OCFS2_FILE_H
+#define OCFS2_FILE_H
+
+extern const struct file_operations ocfs2_fops;
+extern const struct file_operations ocfs2_dops;
+extern const struct file_operations ocfs2_fops_no_plocks;
+extern const struct file_operations ocfs2_dops_no_plocks;
+extern const struct inode_operations ocfs2_file_iops;
+extern const struct inode_operations ocfs2_special_file_iops;
+struct ocfs2_alloc_context;
+enum ocfs2_alloc_restarted;
+
+struct ocfs2_file_private {
+	u64			cookie;
+	struct file		*fp_file;
+	struct mutex		fp_mutex;
+	struct ocfs2_lock_res	fp_flock;
+};
+
+int ocfs2_add_inode_data(struct ocfs2_super *osb,
+			 struct inode *inode,
+			 u32 *logical_offset,
+			 u32 clusters_to_add,
+			 int mark_unwritten,
+			 struct buffer_head *fe_bh,
+			 handle_t *handle,
+			 struct ocfs2_alloc_context *data_ac,
+			 struct ocfs2_alloc_context *meta_ac,
+			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
+int ocfs2_simple_size_update(struct inode *inode,
+			     struct buffer_head *di_bh,
+			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
+int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
+			  u64 new_i_size, u64 zero_to);
+int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
+		      loff_t zero_to);
+int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		  struct iattr *attr);
+int ocfs2_getattr(struct mnt_idmap *idmap, const struct path *path,
+		  struct kstat *stat, u32 request_mask, unsigned int flags);
+int ocfs2_permission(struct mnt_idmap *idmap,
+		     struct inode *inode,
+		     int mask);
+
+int ocfs2_should_update_atime(struct inode *inode,
+			      struct vfsmount *vfsmnt);
+int ocfs2_update_inode_atime(struct inode *inode,
+			     struct buffer_head *bh);
+
+int ocfs2_change_file_space(struct file *file, unsigned int cmd,
+			    struct ocfs2_space_resv *sr);
+
+int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos,
+				   size_t count);
+int ocfs2_remove_inode_range(struct inode *inode,
+			     struct buffer_head *di_bh, u64 byte_start,
+			     u64 byte_len);
+#endif /* OCFS2_FILE_H */