Without branch hints, the very unlikely chance of the loop repeating due to
cmpxchg failure is unrolled with gcc-4 that I have tested.

Improve this for architectures with a native cas/cmpxchg.  llsc archs
should try to implement this natively.

Signed-off-by: Nick Piggin <npiggin@suse.de>

Index: linux-2.6/include/asm-i386/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-i386/atomic.h
+++ linux-2.6/include/asm-i386/atomic.h
@@ -231,8 +231,14 @@ static __inline__ int atomic_sub_return(
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
+	}							\
 	c != (u);						\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
Index: linux-2.6/include/asm-ia64/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-ia64/atomic.h
+++ linux-2.6/include/asm-ia64/atomic.h
@@ -95,8 +95,14 @@ ia64_atomic64_sub (__s64 i, atomic64_t *
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
+	}							\
 	c != (u);						\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
Index: linux-2.6/include/asm-m68k/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-m68k/atomic.h
+++ linux-2.6/include/asm-m68k/atomic.h
@@ -175,8 +175,14 @@ static inline void atomic_set_mask(unsig
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
+	}							\
 	c != (u);						\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
Index: linux-2.6/include/asm-s390/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-s390/atomic.h
+++ linux-2.6/include/asm-s390/atomic.h
@@ -89,10 +89,15 @@ static __inline__ int atomic_cmpxchg(ato
 static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
-
 	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
+	for (;;) {
+		if (unlikely(c == u))
+			break;
+		old = atomic_cmpxchg(v, c, c + a);
+		if (likely(old == c))
+			break;
 		c = old;
+	}
 	return c != u;
 }
 
@@ -167,10 +172,15 @@ static __inline__ int atomic64_add_unles
 					  long long a, long long u)
 {
 	long long c, old;
-
 	c = atomic64_read(v);
-	while (c != u && (old = atomic64_cmpxchg(v, c, c + a)) != c)
+	for (;;) {
+		if (unlikely(c == u))
+			break;
+		old = atomic64_cmpxchg(v, c, c + a);
+		if (likely(old == c))
+			break;
 		c = old;
+	}
 	return c != u;
 }
 
Index: linux-2.6/include/asm-sparc64/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-sparc64/atomic.h
+++ linux-2.6/include/asm-sparc64/atomic.h
@@ -78,9 +78,15 @@ extern int atomic64_sub_ret(int, atomic6
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
-	c != (u);						\
+	}							\
+	likely(c != (u));					\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
Index: linux-2.6/include/asm-x86_64/atomic.h
===================================================================
--- linux-2.6.orig/include/asm-x86_64/atomic.h
+++ linux-2.6/include/asm-x86_64/atomic.h
@@ -405,8 +405,14 @@ static __inline__ long atomic64_sub_retu
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
+	}							\
 	c != (u);						\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)