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, 75 insertions, 0 deletions

diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
new file mode 100644
index 000000000..114efc911
--- /dev/null
+++ b/fs/ocfs2/aops.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2002, 2004, 2005 Oracle.  All rights reserved.
+ */
+
+#ifndef OCFS2_AOPS_H
+#define OCFS2_AOPS_H
+
+#include <linux/fs.h>
+
+int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno,
+			  struct inode *inode, unsigned int from,
+			  unsigned int to, int new);
+
+void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios);
+
+int walk_page_buffers(	handle_t *handle,
+			struct buffer_head *head,
+			unsigned from,
+			unsigned to,
+			int *partial,
+			int (*fn)(	handle_t *handle,
+					struct buffer_head *bh));
+
+int ocfs2_write_end_nolock(struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied, void *fsdata);
+
+typedef enum {
+	OCFS2_WRITE_BUFFER = 0,
+	OCFS2_WRITE_DIRECT,
+	OCFS2_WRITE_MMAP,
+} ocfs2_write_type_t;
+
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+		loff_t pos, unsigned len, ocfs2_write_type_t type,
+		struct folio **foliop, void **fsdata,
+		struct buffer_head *di_bh, struct folio *mmap_folio);
+
+int ocfs2_read_inline_data(struct inode *inode, struct folio *folio,
+			   struct buffer_head *di_bh);
+int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size);
+
+int ocfs2_get_block(struct inode *inode, sector_t iblock,
+		    struct buffer_head *bh_result, int create);
+/* all ocfs2_dio_end_io()'s fault */
+#define ocfs2_iocb_is_rw_locked(iocb) \
+	test_bit(0, (unsigned long *)&iocb->private)
+static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
+{
+	set_bit(0, (unsigned long *)&iocb->private);
+	if (level)
+		set_bit(1, (unsigned long *)&iocb->private);
+	else
+		clear_bit(1, (unsigned long *)&iocb->private);
+}
+
+/*
+ * Using a named enum representing lock types in terms of #N bit stored in
+ * iocb->private, which is going to be used for communication between
+ * ocfs2_dio_end_io() and ocfs2_file_write/read_iter().
+ */
+enum ocfs2_iocb_lock_bits {
+	OCFS2_IOCB_RW_LOCK = 0,
+	OCFS2_IOCB_RW_LOCK_LEVEL,
+	OCFS2_IOCB_NUM_LOCKS
+};
+
+#define ocfs2_iocb_init_rw_locked(iocb) \
+	(iocb->private = NULL)
+#define ocfs2_iocb_clear_rw_locked(iocb) \
+	clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_rw_locked_level(iocb) \
+	test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
+
+#endif /* OCFS2_FILE_H */