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, 47 insertions, 0 deletions

diff --git a/arch/powerpc/boot/of.h b/arch/powerpc/boot/of.h
new file mode 100644
index 000000000..31b2f5dfd
--- /dev/null
+++ b/arch/powerpc/boot/of.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PPC_BOOT_OF_H_
+#define _PPC_BOOT_OF_H_
+
+#include "swab.h"
+
+typedef void *phandle;
+typedef u32 ihandle;
+
+void of_init(void *promptr);
+int of_call_prom(const char *service, int nargs, int nret, ...);
+unsigned int of_claim(unsigned long virt, unsigned long size,
+	unsigned long align);
+void *of_vmlinux_alloc(unsigned long size);
+void of_exit(void);
+void *of_finddevice(const char *name);
+int of_getprop(const void *phandle, const char *name, void *buf,
+	       const int buflen);
+int of_setprop(const void *phandle, const char *name, const void *buf,
+	       const int buflen);
+
+/* Console functions */
+void of_console_init(void);
+
+typedef u16			__be16;
+typedef u32			__be32;
+typedef u64			__be64;
+
+#ifdef __LITTLE_ENDIAN__
+#define cpu_to_be16(x) swab16(x)
+#define be16_to_cpu(x) swab16(x)
+#define cpu_to_be32(x) swab32(x)
+#define be32_to_cpu(x) swab32(x)
+#define cpu_to_be64(x) swab64(x)
+#define be64_to_cpu(x) swab64(x)
+#else
+#define cpu_to_be16(x) (x)
+#define be16_to_cpu(x) (x)
+#define cpu_to_be32(x) (x)
+#define be32_to_cpu(x) (x)
+#define cpu_to_be64(x) (x)
+#define be64_to_cpu(x) (x)
+#endif
+
+#define PROM_ERROR (-1u)
+
+#endif /* _PPC_BOOT_OF_H_ */