ARC: [plat-eznps] Use dedicated SMP barriers

NPS device got 256 cores and each got 16 HW threads (SMT).
We use EZchip dedicated ISA to trigger HW scheduler of the
core that current HW thread belongs to.
This scheduling makes sure that data beyond barrier is available
to all HW threads in core and by that to all in device (4K).
Signed-off-by: Noam Camus <noamc@ezchip.com>
Cc: Peter Zijlstra <peterz@infradead.org>

arch/arc/include/asm/barrier.h

@@ -30,9 +30,7 @@
 #define rmb()	asm volatile("dmb 1\n" : : : "memory")
 #define wmb()	asm volatile("dmb 2\n" : : : "memory")
 
-#endif
-
-#ifdef CONFIG_ISA_ARCOMPACT
+#elif !defined(CONFIG_ARC_PLAT_EZNPS)  /* CONFIG_ISA_ARCOMPACT */
 
 /*
  * ARCompact based cores (ARC700) only have SYNC instruction which is super
@@ -41,6 +39,14 @@
  */
 
 #define mb()	asm volatile("sync\n" : : : "memory")
+
+#else	/* CONFIG_ARC_PLAT_EZNPS */
+
+#include <plat/ctop.h>
+
+#define mb()	asm volatile (".word %0" : : "i"(CTOP_INST_SCHD_RW) : "memory")
+#define rmb()	asm volatile (".word %0" : : "i"(CTOP_INST_SCHD_RD) : "memory")
+
 #endif
 
 #include <asm-generic/barrier.h>