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, 64 insertions, 0 deletions

diff --git a/arch/powerpc/sysdev/dart.h b/arch/powerpc/sysdev/dart.h
new file mode 100644
index 000000000..7f5df03d3
--- /dev/null
+++ b/arch/powerpc/sysdev/dart.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
+ */
+
+#ifndef _POWERPC_SYSDEV_DART_H
+#define _POWERPC_SYSDEV_DART_H
+
+
+/* Offset from base to control register */
+#define DART_CNTL	0
+
+/* Offset from base to exception register */
+#define DART_EXCP_U3	0x10
+/* Offset from base to TLB tag registers */
+#define DART_TAGS_U3	0x1000
+
+/* U4 registers */
+#define DART_BASE_U4	0x10
+#define DART_SIZE_U4	0x20
+#define DART_EXCP_U4	0x30
+#define DART_TAGS_U4	0x1000
+
+/* Control Register fields */
+
+/* U3 registers */
+#define DART_CNTL_U3_BASE_MASK	0xfffff
+#define DART_CNTL_U3_BASE_SHIFT	12
+#define DART_CNTL_U3_FLUSHTLB	0x400
+#define DART_CNTL_U3_ENABLE	0x200
+#define DART_CNTL_U3_SIZE_MASK	0x1ff
+#define DART_CNTL_U3_SIZE_SHIFT	0
+
+/* U4 registers */
+#define DART_BASE_U4_BASE_MASK	0xffffff
+#define DART_BASE_U4_BASE_SHIFT	0
+#define DART_CNTL_U4_ENABLE	0x80000000
+#define DART_CNTL_U4_IONE	0x40000000
+#define DART_CNTL_U4_FLUSHTLB	0x20000000
+#define DART_CNTL_U4_IDLE	0x10000000
+#define DART_CNTL_U4_PAR_EN	0x08000000
+#define DART_CNTL_U4_IONE_MASK	0x07ffffff
+#define DART_SIZE_U4_SIZE_MASK	0x1fff
+#define DART_SIZE_U4_SIZE_SHIFT	0
+
+#define DART_REG(r)	(dart + ((r) >> 2))
+#define DART_IN(r)	(in_be32(DART_REG(r)))
+#define DART_OUT(r,v)	(out_be32(DART_REG(r), (v)))
+
+
+/* size of table in pages */
+
+
+/* DART table fields */
+
+#define DARTMAP_VALID   0x80000000
+#define DARTMAP_RPNMASK 0x00ffffff
+
+
+#define DART_PAGE_SHIFT		12
+#define DART_PAGE_SIZE		(1 << DART_PAGE_SHIFT)
+
+
+#endif /* _POWERPC_SYSDEV_DART_H */