xtensa: fix __delay for small loop count

Avoid __delay counter underflow for loop counts < 2.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Chris Zankel <chris@zankel.net>
diff --git a/arch/xtensa/include/asm/delay.h b/arch/xtensa/include/asm/delay.h
index 3899610c..742b89f 100644
--- a/arch/xtensa/include/asm/delay.h
+++ b/arch/xtensa/include/asm/delay.h
@@ -19,9 +19,12 @@
 
 static inline void __delay(unsigned long loops)
 {
-	/* 2 cycles per loop. */
-	__asm__ __volatile__ ("1: addi %0, %0, -2; bgeui %0, 2, 1b"
-			      : "=r" (loops) : "0" (loops));
+	if (__builtin_constant_p(loops) && loops < 2)
+		__asm__ __volatile__ ("nop");
+	else if (loops >= 2)
+		/* 2 cycles per loop. */
+		__asm__ __volatile__ ("1: addi %0, %0, -2; bgeui %0, 2, 1b"
+				: "+r" (loops));
 }
 
 /* For SMP/NUMA systems, change boot_cpu_data to something like