Define curthread as an inline function that loads the thread pointer

directly from g7, the pcpu pointer. This guarantees correct behavior
when the thread migrates to a different CPU.
Commit message stolen from r205431. Additional testing by Peter Jeremy.

MFC after:	3 days

sys/sparc64/include/pcpu.h

@@ -74,6 +74,16 @@ register struct pcpu *pcpup __asm__(__XSTRING(PCPU_REG));
 
 #define	PCPU_GET(member)	(pcpup->pc_ ## member)
 
+static __inline __pure2 struct thread *
+__curthread(void)
+{
+	struct thread *td;
+
+	__asm("ldx [%" __XSTRING(PCPU_REG) "], %0" : "=r" (td));
+	return (td);
+}
+#define	curthread	(__curthread())
+
 /*
  * XXX The implementation of this operation should be made atomic
  * with respect to preemption.