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, 60 insertions, 0 deletions

diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
new file mode 100644
index 000000000..bb460ff57
--- /dev/null
+++ b/arch/powerpc/sysdev/mpic.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _POWERPC_SYSDEV_MPIC_H
+#define _POWERPC_SYSDEV_MPIC_H
+
+/*
+ * Copyright 2006-2007, Michael Ellerman, IBM Corporation.
+ */
+
+#ifdef CONFIG_PCI_MSI
+extern void mpic_msi_reserve_hwirq(struct mpic *mpic, irq_hw_number_t hwirq);
+int __init mpic_msi_init_allocator(struct mpic *mpic);
+int __init mpic_u3msi_init(struct mpic *mpic);
+#else
+static inline void mpic_msi_reserve_hwirq(struct mpic *mpic,
+					  irq_hw_number_t hwirq)
+{
+	return;
+}
+
+static inline int mpic_u3msi_init(struct mpic *mpic)
+{
+	return -1;
+}
+#endif
+
+#if defined(CONFIG_PCI_MSI) && defined(CONFIG_PPC_PASEMI)
+int __init mpic_pasemi_msi_init(struct mpic *mpic);
+#else
+static inline int mpic_pasemi_msi_init(struct mpic *mpic) { return -1; }
+#endif
+
+extern int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type);
+extern void mpic_set_vector(unsigned int virq, unsigned int vector);
+extern int mpic_set_affinity(struct irq_data *d,
+			     const struct cpumask *cpumask, bool force);
+extern void mpic_reset_core(int cpu);
+
+#ifdef CONFIG_FSL_SOC
+extern int mpic_map_error_int(struct mpic *mpic, unsigned int virq, irq_hw_number_t  hw);
+void __init mpic_err_int_init(struct mpic *mpic, irq_hw_number_t irqnum);
+int __init mpic_setup_error_int(struct mpic *mpic, int intvec);
+#else
+static inline int mpic_map_error_int(struct mpic *mpic, unsigned int virq, irq_hw_number_t  hw)
+{
+	return 0;
+}
+
+
+static inline void mpic_err_int_init(struct mpic *mpic, irq_hw_number_t irqnum)
+{
+	return;
+}
+
+static inline int mpic_setup_error_int(struct mpic *mpic, int intvec)
+{
+	return -1;
+}
+#endif
+
+#endif /* _POWERPC_SYSDEV_MPIC_H */