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, 70 insertions, 0 deletions

diff --git a/drivers/scsi/a2091.h b/drivers/scsi/a2091.h
new file mode 100644
index 000000000..8d8a4074a
--- /dev/null
+++ b/drivers/scsi/a2091.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef A2091_H
+#define A2091_H
+
+/* $Id: a2091.h,v 1.4 1997/01/19 23:07:09 davem Exp $
+ *
+ * Header file for the Commodore A2091 Zorro II SCSI controller for Linux
+ *
+ * Written and (C) 1993, Hamish Macdonald, see a2091.c for more info
+ *
+ */
+
+#include <linux/types.h>
+
+#ifndef CMD_PER_LUN
+#define CMD_PER_LUN		2
+#endif
+
+#ifndef CAN_QUEUE
+#define CAN_QUEUE		16
+#endif
+
+/*
+ * if the transfer address ANDed with this results in a non-zero
+ * result, then we can't use DMA.
+ */
+#define A2091_XFER_MASK		(0xff000001)
+
+struct a2091_scsiregs {
+		 unsigned char	pad1[64];
+	volatile unsigned short	ISTR;
+	volatile unsigned short	CNTR;
+		 unsigned char	pad2[60];
+	volatile unsigned int	WTC;
+	volatile unsigned long	ACR;
+		 unsigned char	pad3[6];
+	volatile unsigned short	DAWR;
+		 unsigned char	pad4;
+	volatile unsigned char	SASR;
+		 unsigned char	pad5;
+	volatile unsigned char	SCMD;
+		 unsigned char	pad6[76];
+	volatile unsigned short	ST_DMA;
+	volatile unsigned short	SP_DMA;
+	volatile unsigned short	CINT;
+		 unsigned char	pad7[2];
+	volatile unsigned short	FLUSH;
+};
+
+#define DAWR_A2091		(3)
+
+/* CNTR bits. */
+#define CNTR_TCEN		(1<<7)
+#define CNTR_PREST		(1<<6)
+#define CNTR_PDMD		(1<<5)
+#define CNTR_INTEN		(1<<4)
+#define CNTR_DDIR		(1<<3)
+
+/* ISTR bits. */
+#define ISTR_INTX		(1<<8)
+#define ISTR_INT_F		(1<<7)
+#define ISTR_INTS		(1<<6)
+#define ISTR_E_INT		(1<<5)
+#define ISTR_INT_P		(1<<4)
+#define ISTR_UE_INT		(1<<3)
+#define ISTR_OE_INT		(1<<2)
+#define ISTR_FF_FLG		(1<<1)
+#define ISTR_FE_FLG		(1<<0)
+
+#endif /* A2091_H */