Blackfin: SMP: make all barriers handle cache issues

When suspending/resuming, the common task freezing code will run in
parallel and freeze processes on each core. This is because the code
uses the non-smp version of memory barriers (as well it should).

The Blackfin smp barrier logic at the moment contains the cache sync
logic, but the non-smp barriers do not. This is incorrect as Rafel
summarized:
> ...
> The existing memory barriers are SMP barriers too, but they are more
> than _just_ SMP barriers. At least that's how it is _supposed_ to be
> (eg. rmb() is supposed to be stronger than smp_rmb()).
> ...
> However, looking at the blackfin's definitions of SMP barriers I see
> that it uses extra stuff that should _also_ be used in the definitions
> of the mandatory barriers.
> ...

URL: http://lkml.org/lkml/2011/4/13/11
LKML-Reference: <BANLkTi=[e-mail]>
Signed-off-by: Graf Yang <[e-mail]>
Signed-off-by: Mike Frysinger <[e-mail]>

arch/blackfin/include/asm/system.h

···
  * Force strict CPU ordering.
  */
 #define nop()  __asm__ __volatile__ ("nop;\n\t" : : )
-#define mb()   __asm__ __volatile__ (""   : : : "memory")
-#define rmb()  __asm__ __volatile__ (""   : : : "memory")
-#define wmb()  __asm__ __volatile__ (""   : : : "memory")
-#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
-#define read_barrier_depends() 		do { } while(0)
+#define smp_mb()  mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_read_barrier_depends()	read_barrier_depends()
 
 #ifdef CONFIG_SMP
 asmlinkage unsigned long __raw_xchg_1_asm(volatile void *ptr, unsigned long value);
···
 					unsigned long new, unsigned long old);
 
 #ifdef __ARCH_SYNC_CORE_DCACHE
-# define smp_mb()	do { barrier(); smp_check_barrier(); smp_mark_barrier(); } while (0)
-# define smp_rmb()	do { barrier(); smp_check_barrier(); } while (0)
-# define smp_wmb()	do { barrier(); smp_mark_barrier(); } while (0)
-#define smp_read_barrier_depends()	do { barrier(); smp_check_barrier(); } while (0)
-
+/* Force Core data cache coherence */
+# define mb()	do { barrier(); smp_check_barrier(); smp_mark_barrier(); } while (0)
+# define rmb()	do { barrier(); smp_check_barrier(); } while (0)
+# define wmb()	do { barrier(); smp_mark_barrier(); } while (0)
+# define read_barrier_depends()	do { barrier(); smp_check_barrier(); } while (0)
 #else
-# define smp_mb()	barrier()
-# define smp_rmb()	barrier()
-# define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	barrier()
+# define mb()	barrier()
+# define rmb()	barrier()
+# define wmb()	barrier()
+# define read_barrier_depends()	do { } while (0)
 #endif
 
 static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
···
 
 #else /* !CONFIG_SMP */
 
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
+#define mb()	barrier()
+#define rmb()	barrier()
+#define wmb()	barrier()
+#define read_barrier_depends()	do { } while (0)
 
 struct __xchg_dummy {
 	unsigned long a[100];