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, 123 insertions, 0 deletions

diff --git a/arch/m68k/lib/divsi3.S b/arch/m68k/lib/divsi3.S
new file mode 100644
index 000000000..62787b433
--- /dev/null
+++ b/arch/m68k/lib/divsi3.S
@@ -0,0 +1,123 @@
+/* libgcc1 routines for 68000 w/o floating-point hardware.
+   Copyright (C) 1994, 1996, 1997, 1998 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file with other programs, and to distribute
+those programs without any restriction coming from the use of this
+file.  (The General Public License restrictions do apply in other
+respects; for example, they cover modification of the file, and
+distribution when not linked into another program.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details. */
+
+/* As a special exception, if you link this library with files
+   compiled with GCC to produce an executable, this does not cause
+   the resulting executable to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.  */
+
+/* Use this one for any 680x0; assumes no floating point hardware.
+   The trailing " '" appearing on some lines is for ANSI preprocessors.  Yuk.
+   Some of this code comes from MINIX, via the folks at ericsson.
+   D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992
+*/
+
+#include <linux/export.h>
+
+/* These are predefined by new versions of GNU cpp.  */
+
+#ifndef __USER_LABEL_PREFIX__
+#define __USER_LABEL_PREFIX__ _
+#endif
+
+#ifndef __REGISTER_PREFIX__
+#define __REGISTER_PREFIX__
+#endif
+
+#ifndef __IMMEDIATE_PREFIX__
+#define __IMMEDIATE_PREFIX__ #
+#endif
+
+/* ANSI concatenation macros.  */
+
+#define CONCAT1(a, b) CONCAT2(a, b)
+#define CONCAT2(a, b) a ## b
+
+/* Use the right prefix for global labels.  */
+
+#define SYM(x) CONCAT1 (__USER_LABEL_PREFIX__, x)
+
+/* Use the right prefix for registers.  */
+
+#define REG(x) CONCAT1 (__REGISTER_PREFIX__, x)
+
+/* Use the right prefix for immediate values.  */
+
+#define IMM(x) CONCAT1 (__IMMEDIATE_PREFIX__, x)
+
+#define d0 REG (d0)
+#define d1 REG (d1)
+#define d2 REG (d2)
+#define d3 REG (d3)
+#define d4 REG (d4)
+#define d5 REG (d5)
+#define d6 REG (d6)
+#define d7 REG (d7)
+#define a0 REG (a0)
+#define a1 REG (a1)
+#define a2 REG (a2)
+#define a3 REG (a3)
+#define a4 REG (a4)
+#define a5 REG (a5)
+#define a6 REG (a6)
+#define fp REG (fp)
+#define sp REG (sp)
+
+	.text
+	.proc
+	.globl	SYM (__divsi3)
+SYM (__divsi3):
+	movel	d2, sp@-
+
+	moveq	IMM (1), d2	/* sign of result stored in d2 (=1 or =-1) */
+	movel	sp@(12), d1	/* d1 = divisor */
+	jpl	L1
+	negl	d1
+#if !(defined(__mcf5200__) || defined(__mcoldfire__))
+	negb	d2		/* change sign because divisor <0  */
+#else
+	negl	d2		/* change sign because divisor <0  */
+#endif
+L1:	movel	sp@(8), d0	/* d0 = dividend */
+	jpl	L2
+	negl	d0
+#if !(defined(__mcf5200__) || defined(__mcoldfire__))
+	negb	d2
+#else
+	negl	d2
+#endif
+
+L2:	movel	d1, sp@-
+	movel	d0, sp@-
+	jbsr	SYM (__udivsi3)	/* divide abs(dividend) by abs(divisor) */
+	addql	IMM (8), sp
+
+	tstb	d2
+	jpl	L3
+	negl	d0
+
+L3:	movel	sp@+, d2
+	rts
+
+	EXPORT_SYMBOL(__divsi3)