local_t: architecture independent extension

This series extena and standardises local_t operations on each architecture,
allowing a rich set of atomic operations to be done on per-cpu data with
minimal performance impact.  On architectures where there seems to be no
difference between the SMP and UP operation (same memory barriers, same
LOCKing), local.h simply includes asm-generic/local.h, which removes
duplicated code from the current kernel tree.

This patch:

local_t: architecture independent extension
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/asm-generic/local.h

@@ -33,6 +33,19 @@ typedef struct
 #define local_add(i,l)	atomic_long_add((i),(&(l)->a))
 #define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
 
+#define local_sub_and_test(i, l) atomic_long_sub_and_test((i), (&(l)->a))
+#define local_dec_and_test(l) atomic_long_dec_and_test(&(l)->a)
+#define local_inc_and_test(l) atomic_long_inc_and_test(&(l)->a)
+#define local_add_negative(i, l) atomic_long_add_negative((i), (&(l)->a))
+#define local_add_return(i, l) atomic_long_add_return((i), (&(l)->a))
+#define local_sub_return(i, l) atomic_long_sub_return((i), (&(l)->a))
+#define local_inc_return(l) atomic_long_inc_return(&(l)->a)
+
+#define local_cmpxchg(l, o, n) atomic_long_cmpxchg((&(l)->a), (o), (n))
+#define local_xchg(l, n) atomic_long_xchg((&(l)->a), (n))
+#define local_add_unless(l, a, u) atomic_long_add_unless((&(l)->a), (a), (u))
+#define local_inc_not_zero(l) atomic_long_inc_not_zero(&(l)->a)
+
 /* Non-atomic variants, ie. preemption disabled and won't be touched
  * in interrupt, etc.  Some archs can optimize this case well. */
 #define __local_inc(l)		local_set((l), local_read(l) + 1)
@@ -44,19 +57,19 @@ typedef struct
  * much more efficient than these naive implementations.  Note they take
  * a variable (eg. mystruct.foo), not an address.
  */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
+#define cpu_local_read(l)	local_read(&__get_cpu_var(l))
+#define cpu_local_set(l, i)	local_set(&__get_cpu_var(l), (i))
+#define cpu_local_inc(l)	local_inc(&__get_cpu_var(l))
+#define cpu_local_dec(l)	local_dec(&__get_cpu_var(l))
+#define cpu_local_add(i, l)	local_add((i), &__get_cpu_var(l))
+#define cpu_local_sub(i, l)	local_sub((i), &__get_cpu_var(l))
 
 /* Non-atomic increments, ie. preemption disabled and won't be touched
  * in interrupt, etc.  Some archs can optimize this case well.
  */
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
+#define __cpu_local_inc(l)	__local_inc(&__get_cpu_var(l))
+#define __cpu_local_dec(l)	__local_dec(&__get_cpu_var(l))
+#define __cpu_local_add(i, l)	__local_add((i), &__get_cpu_var(l))
+#define __cpu_local_sub(i, l)	__local_sub((i), &__get_cpu_var(l))
 
 #endif /* _ASM_GENERIC_LOCAL_H */