x86/qspinlock-paravirt: Fix missing-prototype warning

__pv_queued_spin_unlock_slowpath() is defined in a header file as
a global function, and designed to be called from inline asm, but
there is no prototype visible in the definition:

  kernel/locking/qspinlock_paravirt.h:493:1: error: no previous \
    prototype for '__pv_queued_spin_unlock_slowpath' [-Werror=missing-prototypes]

Add this to the x86 header that contains the inline asm calling it,
and ensure this gets included before the definition, rather than
after it.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20230803082619.1369127-8-arnd@kernel.org

Author: arndb

arch/x86/include/asm/qspinlock_paravirt.h

@@ -4,6 +4,8 @@
 
 #include <asm/ibt.h>
 
+void __lockfunc __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked);
+
 /*
  * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit
  * registers. For i386, however, only 1 32-bit register needs to be saved

kernel/locking/qspinlock_paravirt.h

@@ -485,6 +485,16 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	return (u32)(atomic_read(&lock->val) | _Q_LOCKED_VAL);
 }
 
+/*
+ * Include the architecture specific callee-save thunk of the
+ * __pv_queued_spin_unlock(). This thunk is put together with
+ * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
+ * function close to each other sharing consecutive instruction cachelines.
+ * Alternatively, architecture specific version of __pv_queued_spin_unlock()
+ * can be defined.
+ */
+#include <asm/qspinlock_paravirt.h>
+
 /*
  * PV versions of the unlock fastpath and slowpath functions to be used
  * instead of queued_spin_unlock().
@@ -533,16 +543,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	pv_kick(node->cpu);
 }
 
-/*
- * Include the architecture specific callee-save thunk of the
- * __pv_queued_spin_unlock(). This thunk is put together with
- * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
- * function close to each other sharing consecutive instruction cachelines.
- * Alternatively, architecture specific version of __pv_queued_spin_unlock()
- * can be defined.
- */
-#include <asm/qspinlock_paravirt.h>
-
 #ifndef __pv_queued_spin_unlock
 __visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
 {