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, 114 insertions, 0 deletions

diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
new file mode 100644
index 000000000..c8683c046
--- /dev/null
+++ b/include/asm-generic/preempt.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <linux/thread_info.h>
+
+#define PREEMPT_ENABLED	(0)
+
+static __always_inline int preempt_count(void)
+{
+	return READ_ONCE(current_thread_info()->preempt_count);
+}
+
+static __always_inline volatile int *preempt_count_ptr(void)
+{
+	return &current_thread_info()->preempt_count;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+	*preempt_count_ptr() = pc;
+}
+
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+static __always_inline void set_preempt_need_resched(void)
+{
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return false;
+}
+
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+	*preempt_count_ptr() += val;
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+	*preempt_count_ptr() -= val;
+}
+
+static __always_inline int __preempt_count_add_return(int val)
+{
+	*preempt_count_ptr() += val;
+
+	return *preempt_count_ptr();
+}
+
+static __always_inline int __preempt_count_sub_return(int val)
+{
+	*preempt_count_ptr() -= val;
+
+	return *preempt_count_ptr();
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	/*
+	 * Because of load-store architectures cannot do per-cpu atomic
+	 * operations; we cannot use PREEMPT_NEED_RESCHED because it might get
+	 * lost.
+	 */
+	return !--*preempt_count_ptr() && tif_need_resched();
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(int preempt_offset)
+{
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
+}
+
+#ifdef CONFIG_PREEMPTION
+extern asmlinkage void preempt_schedule(void);
+extern asmlinkage void preempt_schedule_notrace(void);
+
+#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+
+void dynamic_preempt_schedule(void);
+void dynamic_preempt_schedule_notrace(void);
+#define __preempt_schedule()		dynamic_preempt_schedule()
+#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
+
+#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
+
+#define __preempt_schedule() preempt_schedule()
+#define __preempt_schedule_notrace() preempt_schedule_notrace()
+
+#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
+#endif /* CONFIG_PREEMPTION */
+
+#endif /* __ASM_PREEMPT_H */