ARCv2: spinlock/rwlock/atomics: reduce 1 instruction in exponential backoff

The increment of delay counter was 2 instructions:
Arithmatic Shfit Left (ASL) + set to 1 on overflow

This can be done in 1 using ROtate Left (ROL)
Suggested-by: Nigel Topham <ntopham@synopsys.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

arch/arc/include/asm/atomic.h

@@ -34,8 +34,7 @@
 	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
 	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
 	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	asl.f	%[delay], %[delay], 1	\n"	/* delay *= 2 */	\
-	"	mov.z	%[delay], 1		\n"	/* handle overflow */	\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
 	"	b	1b			\n"	/* start over */	\
 	"4: ; --- success ---			\n"				\
 

arch/arc/include/asm/spinlock.h

@@ -260,8 +260,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
 	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
 	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	asl.f	%[delay], %[delay], 1	\n"	/* delay *= 2 */	\
-	"	mov.z	%[delay], 1		\n"	/* handle overflow */	\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
 	"	b	1b			\n"	/* start over */	\
 	"					\n"				\
 	"4: ; --- done ---			\n"				\