[Mesa-dev] [PATCH v3 4/9] gallium/auxiliary: add inc and dec alternative with return (v2)

[David Heidelberg]

At this moment we use only zero or positive values.

v2: Implement it for also for Solaris, MSVC assembly
     and enable for other combinations.

Signed-off-by: David Heidelberg <david at ixit.cz>
---
  src/gallium/auxiliary/util/u_atomic.h | 78 
+++++++++++++++++++++++++++++++++++
  1 file changed, 78 insertions(+)

diff --git a/src/gallium/auxiliary/util/u_atomic.h 
b/src/gallium/auxiliary/util/u_atomic.h
index 2f2b42b..f177b60 100644
--- a/src/gallium/auxiliary/util/u_atomic.h
+++ b/src/gallium/auxiliary/util/u_atomic.h
@@ -69,6 +69,18 @@ p_atomic_dec(int32_t *v)
  }
   static INLINE int32_t
+p_atomic_inc_return(int32_t *v)
+{
+   return __sync_add_and_fetch(v, 1);
+}
+
+static INLINE int32_t
+p_atomic_dec_return(int32_t *v)
+{
+   return __sync_sub_and_fetch(v, 1);
+}
+
+static INLINE int32_t
  p_atomic_cmpxchg(int32_t *v, int32_t old, int32_t _new)
  {
     return __sync_val_compare_and_swap(v, old, _new);
@@ -116,6 +128,18 @@ p_atomic_dec(int32_t *v)
  }
   static INLINE int32_t
+p_atomic_inc_return(int32_t *v)
+{
+   return __sync_add_and_fetch(v, 1);
+}
+
+static INLINE int32_t
+p_atomic_dec_return(int32_t *v)
+{
+   return __sync_sub_and_fetch(v, 1);
+}
+
+static INLINE int32_t
  p_atomic_cmpxchg(int32_t *v, int32_t old, int32_t _new)
  {
     return __sync_val_compare_and_swap(v, old, _new);
@@ -161,6 +185,18 @@ p_atomic_dec(int32_t *v)
  }
   static INLINE int32_t
+p_atomic_inc_return(int32_t *v)
+{
+   return __sync_add_and_fetch(v, 1);
+}
+
+static INLINE int32_t
+p_atomic_dec_return(int32_t *v)
+{
+   return __sync_sub_and_fetch(v, 1);
+}
+
+static INLINE int32_t
  p_atomic_cmpxchg(int32_t *v, int32_t old, int32_t _new)
  {
     return __sync_val_compare_and_swap(v, old, _new);
@@ -186,6 +222,8 @@ p_atomic_cmpxchg(int32_t *v, int32_t old, int32_t _new)
  #define p_atomic_dec_zero(_v) ((boolean) --(*(_v)))
  #define p_atomic_inc(_v) ((void) (*(_v))++)
  #define p_atomic_dec(_v) ((void) (*(_v))--)
+#define p_atomic_inc_return(_v) ((*(_v))++)
+#define p_atomic_dec_return(_v) ((*(_v))--)
  #define p_atomic_cmpxchg(_v, old, _new) (*(_v) == old ? *(_v) = (_new) 
: *(_v))
   #endif
@@ -237,6 +275,32 @@ p_atomic_dec(int32_t *v)
  }
   static INLINE int32_t
+p_atomic_inc_return(int32_t *v)
+{
+   int32_t i;
+
+   __asm {
+      mov       eax, [v]
+      lock inc  dword ptr [eax]
+      mov       [i], eax
+   }
+   return i;
+}
+
+static INLINE int32_t
+p_atomic_dec_return(int32_t *v)
+{
+   int32_t i;
+
+   __asm {
+      mov       eax, [v]
+      lock dec  dword ptr [eax]
+      mov       [i], eax
+   }
+   return i;
+}
+
+static INLINE int32_t
  p_atomic_cmpxchg(int32_t *v, int32_t old, int32_t _new)
  {
     int32_t orig;
@@ -288,6 +352,12 @@ p_atomic_inc(int32_t *v)
     _InterlockedIncrement((long *)v);
  }
  +static INLINE int32_t
+p_atomic_inc_return(int32_t *v)
+{
+   return _InterlockedIncrement((long *)v);
+}
+
  static INLINE void
  p_atomic_dec(int32_t *v)
  {
@@ -295,6 +365,12 @@ p_atomic_dec(int32_t *v)
  }
   static INLINE int32_t
+p_atomic_dec_return(int32_t *v)
+{
+   return _InterlockedDecrement((long *)v);
+}
+
+static INLINE int32_t
  p_atomic_cmpxchg(int32_t *v, int32_t old, int32_t _new)
  {
     return _InterlockedCompareExchange((long *)v, _new, old);
@@ -329,6 +405,8 @@ p_atomic_dec_zero(int32_t *v)
   #define p_atomic_inc(_v) atomic_inc_32((uint32_t *) _v)
  #define p_atomic_dec(_v) atomic_dec_32((uint32_t *) _v)
+#define p_atomic_inc_return(_v) atomic_inc_32_nv((uint32_t *) _v)
+#define p_atomic_dec_return(_v) atomic_dec_32_nv((uint32_t *) _v)
   #define p_atomic_cmpxchg(_v, _old, _new) \
  	atomic_cas_32( (uint32_t *) _v, (uint32_t) _old, (uint32_t) _new)
-- 
2.1.3