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, 75 insertions, 0 deletions

diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h
new file mode 100644
index 000000000..52701d958
--- /dev/null
+++ b/drivers/cpuidle/cpuidle.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * cpuidle.h - The internal header file
+ */
+
+#ifndef __DRIVER_CPUIDLE_H
+#define __DRIVER_CPUIDLE_H
+
+/* For internal use only */
+extern char param_governor[];
+extern struct cpuidle_governor *cpuidle_curr_governor;
+extern struct cpuidle_governor *cpuidle_prev_governor;
+extern struct list_head cpuidle_governors;
+extern struct list_head cpuidle_detected_devices;
+extern struct mutex cpuidle_lock;
+extern spinlock_t cpuidle_driver_lock;
+extern int cpuidle_disabled(void);
+extern int cpuidle_enter_state(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int next_state);
+
+/* idle loop */
+extern void cpuidle_install_idle_handler(void);
+extern void cpuidle_uninstall_idle_handler(void);
+
+/* governors */
+extern struct cpuidle_governor *cpuidle_find_governor(const char *str);
+extern int cpuidle_switch_governor(struct cpuidle_governor *gov);
+
+/* sysfs */
+
+struct device;
+
+extern int cpuidle_add_interface(void);
+extern void cpuidle_remove_interface(struct device *dev);
+extern int cpuidle_add_device_sysfs(struct cpuidle_device *device);
+extern void cpuidle_remove_device_sysfs(struct cpuidle_device *device);
+extern int cpuidle_add_sysfs(struct cpuidle_device *dev);
+extern void cpuidle_remove_sysfs(struct cpuidle_device *dev);
+
+#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
+bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state);
+int cpuidle_coupled_state_verify(struct cpuidle_driver *drv);
+int cpuidle_enter_state_coupled(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int next_state);
+int cpuidle_coupled_register_device(struct cpuidle_device *dev);
+void cpuidle_coupled_unregister_device(struct cpuidle_device *dev);
+#else
+static inline
+bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state)
+{
+	return false;
+}
+
+static inline int cpuidle_coupled_state_verify(struct cpuidle_driver *drv)
+{
+	return 0;
+}
+
+static inline int cpuidle_enter_state_coupled(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int next_state)
+{
+	return -1;
+}
+
+static inline int cpuidle_coupled_register_device(struct cpuidle_device *dev)
+{
+	return 0;
+}
+
+static inline void cpuidle_coupled_unregister_device(struct cpuidle_device *dev)
+{
+}
+#endif
+
+#endif /* __DRIVER_CPUIDLE_H */