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, 56 insertions, 0 deletions

diff --git a/arch/powerpc/sysdev/ipic.h b/arch/powerpc/sysdev/ipic.h
new file mode 100644
index 000000000..45ab61406
--- /dev/null
+++ b/arch/powerpc/sysdev/ipic.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * IPIC private definitions and structure.
+ *
+ * Maintainer: Kumar Gala <galak@kernel.crashing.org>
+ *
+ * Copyright 2005 Freescale Semiconductor, Inc
+ */
+#ifndef __IPIC_H__
+#define __IPIC_H__
+
+#include <asm/ipic.h>
+
+#define NR_IPIC_INTS 128
+
+/* External IRQS */
+#define IPIC_IRQ_EXT0 48
+#define IPIC_IRQ_EXT1 17
+#define IPIC_IRQ_EXT7 23
+
+/* Default Priority Registers */
+#define IPIC_PRIORITY_DEFAULT 0x05309770
+
+/* System Global Interrupt Configuration Register */
+#define	SICFR_IPSA	0x00010000
+#define	SICFR_IPSB	0x00020000
+#define	SICFR_IPSC	0x00040000
+#define	SICFR_IPSD	0x00080000
+#define	SICFR_MPSA	0x00200000
+#define	SICFR_MPSB	0x00400000
+
+/* System External Interrupt Mask Register */
+#define	SEMSR_SIRQ0	0x00008000
+
+/* System Error Control Register */
+#define SERCR_MCPR	0x00000001
+
+struct ipic {
+	volatile u32 __iomem	*regs;
+
+	/* The remapper for this IPIC */
+	struct irq_domain		*irqhost;
+};
+
+struct ipic_info {
+	u8	ack;		/* pending register offset from base if the irq
+				   supports ack operation */
+	u8	mask;		/* mask register offset from base */
+	u8	prio;		/* priority register offset from base */
+	u8	force;		/* force register offset from base */
+	u8	bit;		/* register bit position (as per doc)
+				   bit mask = 1 << (31 - bit) */
+	u8	prio_mask;	/* priority mask value */
+};
+
+#endif /* __IPIC_H__ */