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, 52 insertions, 0 deletions

diff --git a/include/xen/interface/nmi.h b/include/xen/interface/nmi.h
new file mode 100644
index 000000000..b665fdbef
--- /dev/null
+++ b/include/xen/interface/nmi.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: MIT */
+/******************************************************************************
+ * nmi.h
+ *
+ * NMI callback registration and reason codes.
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_NMI_H__
+#define __XEN_PUBLIC_NMI_H__
+
+#include <xen/interface/xen.h>
+
+/*
+ * NMI reason codes:
+ * Currently these are x86-specific, stored in arch_shared_info.nmi_reason.
+ */
+ /* I/O-check error reported via ISA port 0x61, bit 6. */
+#define _XEN_NMIREASON_io_error     0
+#define XEN_NMIREASON_io_error      (1UL << _XEN_NMIREASON_io_error)
+ /* PCI SERR reported via ISA port 0x61, bit 7. */
+#define _XEN_NMIREASON_pci_serr     1
+#define XEN_NMIREASON_pci_serr      (1UL << _XEN_NMIREASON_pci_serr)
+ /* Unknown hardware-generated NMI. */
+#define _XEN_NMIREASON_unknown      2
+#define XEN_NMIREASON_unknown       (1UL << _XEN_NMIREASON_unknown)
+
+/*
+ * long nmi_op(unsigned int cmd, void *arg)
+ * NB. All ops return zero on success, else a negative error code.
+ */
+
+/*
+ * Register NMI callback for this (calling) VCPU. Currently this only makes
+ * sense for domain 0, vcpu 0. All other callers will be returned EINVAL.
+ * arg == pointer to xennmi_callback structure.
+ */
+#define XENNMI_register_callback   0
+struct xennmi_callback {
+    unsigned long handler_address;
+    unsigned long pad;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xennmi_callback);
+
+/*
+ * Deregister NMI callback for this (calling) VCPU.
+ * arg == NULL.
+ */
+#define XENNMI_unregister_callback 1
+
+#endif /* __XEN_PUBLIC_NMI_H__ */