Merge tag 'arc-4.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC architecture updates from Vineet Gupta:

 - support for HS38 cores based on ARCv2 ISA

     ARCv2 is the next generation ISA from Synopsys and basis for the
     HS3{4,6,8} families of processors which retain the traditional ARC mantra of
     low power and configurability and are now more performant and feature rich.

     HS38x is a 10 stage pipeline core which supports MMU (with huge pages) and
     SMP (upto 4 cores) among other features.

     + www.synopsys.com/dw/ipdir.php?ds=arc-hs38-processor
     + http://news.synopsys.com/2014-10-14-New-DesignWare-ARC-HS38-Processor-Doubles-Performance-for-Embedded-Linux-Applications
     + http://www.embedded.com/electronics-news/4435975/Synopsys-ARC-HS38-core-gives-2X-boost-to-Linux-based-apps

 - support for ARC SDP (Software Development platform): Main Board + CPU Cards
    = AXS101: CPU Card with ARC700 in silicon @ 700 MHz
    = AXS103: CPU Card with HS38x in FPGA

 - refactoring of ARCompact port to accomodate new ARCv2 ISA

 - misc updates/cleanups

* tag 'arc-4.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (72 commits)
  ARC: Fix build failures for ARCompact in linux-next after ARCv2 support
  ARCv2: Allow older gcc to cope with new regime of ARCv2/ARCompact support
  ARCv2: [vdk] dts files and defconfig for HS38 VDK
  ARCv2: [axs103] Support ARC SDP FPGA platform for HS38x cores
  ARC: [axs101] Prepare for AXS103
  ARCv2: [nsim*hs*] Support simulation platforms for HS38x cores
  ARCv2: All bits in place, allow ARCv2 builds
  ARCv2: SLC: Handle explcit flush for DMA ops (w/o IO-coherency)
  ARCv2: STAR 9000837815 workaround hardware exclusive transactions livelock
  ARC: Reduce bitops lines of code using macros
  ARCv2: barriers
  arch: conditionally define smp_{mb,rmb,wmb}
  ARC: add smp barriers around atomics per Documentation/atomic_ops.txt
  ARC: add compiler barrier to LLSC based cmpxchg
  ARCv2: SMP: intc: IDU 2nd level intc for dynamic IRQ distribution
  ARCv2: SMP: clocksource: Enable Global Real Time counter
  ARCv2: SMP: ARConnect debug/robustness
  ARCv2: SMP: Support ARConnect (MCIP) for Inter-Core-Interrupts et al
  ARC: make plat_smp_ops weak to allow over-rides
  ARCv2: clocksource: Introduce 64bit local RTC counter
  ...

1 files changed, 33 insertions, 2 deletions

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 9917a45fc430..03484cb4d16d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -23,13 +23,21 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
+#ifdef CONFIG_ISA_ARCV2
+#define PREFETCHW	"	prefetchw   [%1]	\n"
+#else
+#define PREFETCHW
+#endif
+
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	unsigned int temp;						\
 									\
 	__asm__ __volatile__(						\
-	"1:	llock   %0, [%1]	\n"				\
+	"1:				\n"				\
+	PREFETCHW							\
+	"	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\
 	"	scond   %0, [%1]	\n"				\
 	"	bnz     1b		\n"				\
@@ -43,8 +51,16 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	unsigned int temp;						\
 									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	__asm__ __volatile__(						\
-	"1:	llock   %0, [%1]	\n"				\
+	"1:				\n"				\
+	PREFETCHW							\
+	"	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\
 	"	scond   %0, [%1]	\n"				\
 	"	bnz     1b		\n"				\
@@ -52,6 +68,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	: "r"(&v->counter), "ir"(i)					\
 	: "cc");							\
 									\
+	smp_mb();							\
+									\
 	return temp;							\
 }
 
@@ -105,6 +123,9 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	unsigned long flags;						\
 	unsigned long temp;						\
 									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
 	atomic_ops_lock(flags);						\
 	temp = v->counter;						\
 	temp c_op i;							\
@@ -142,9 +163,19 @@ ATOMIC_OP(and, &=, and)
 #define __atomic_add_unless(v, a, u)					\
 ({									\
 	int c, old;							\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	c = atomic_read(v);						\
 	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
 		c = old;						\
+									\
+	smp_mb();							\
+									\
 	c;								\
 })