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, 84 insertions, 0 deletions

diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
new file mode 100644
index 000000000..cc9fb72cb
--- /dev/null
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Copyright (C) IBM Corporation, 2011
+ *
+ * Authors: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
+ *          Anton Blanchard <anton@au.ibm.com>
+ */
+#include <linux/uaccess.h>
+#include <linux/hardirq.h>
+#include <asm/switch_to.h>
+
+int enter_vmx_usercopy(void)
+{
+	if (in_interrupt())
+		return 0;
+
+	preempt_disable();
+	/*
+	 * We need to disable page faults as they can call schedule and
+	 * thus make us lose the VMX context. So on page faults, we just
+	 * fail which will cause a fallback to the normal non-vmx copy.
+	 */
+	pagefault_disable();
+
+	enable_kernel_altivec();
+
+	return 1;
+}
+EXPORT_SYMBOL(enter_vmx_usercopy);
+
+/*
+ * This function must return 0 because we tail call optimise when calling
+ * from __copy_tofrom_user_power7 which returns 0 on success.
+ */
+int exit_vmx_usercopy(void)
+{
+	disable_kernel_altivec();
+	pagefault_enable();
+	preempt_enable_no_resched();
+	/*
+	 * Must never explicitly call schedule (including preempt_enable())
+	 * while in a kuap-unlocked user copy, because the AMR register will
+	 * not be saved and restored across context switch. However preempt
+	 * kernels need to be preempted as soon as possible if need_resched is
+	 * set and we are preemptible. The hack here is to schedule a
+	 * decrementer to fire here and reschedule for us if necessary.
+	 */
+	if (need_resched())
+		set_dec(1);
+	return 0;
+}
+EXPORT_SYMBOL(exit_vmx_usercopy);
+
+/*
+ * Can be called from kexec copy_page() path with MMU off. The kexec
+ * code sets preempt_count to HARDIRQ_OFFSET so we return early here.
+ * Since in_interrupt() is always inline, __no_sanitize_address on this
+ * function is sufficient to avoid KASAN shadow memory accesses in real
+ * mode.
+ */
+int __no_sanitize_address enter_vmx_ops(void)
+{
+	if (in_interrupt())
+		return 0;
+
+	preempt_disable();
+
+	enable_kernel_altivec();
+
+	return 1;
+}
+
+/*
+ * All calls to this function will be optimised into tail calls. We are
+ * passed a pointer to the destination which we return as required by a
+ * memcpy implementation.
+ */
+void *exit_vmx_ops(void *dest)
+{
+	disable_kernel_altivec();
+	preempt_enable();
+	return dest;
+}