[PATCH] atomic: add_unless cmpxchg optimise

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>
Cc: Andi Kleen <ak@muc.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 50 insertions, 10 deletions

diff --git a/include/asm-i386/atomic.h b/include/asm-i386/atomic.h
index 78b0032d1f29..22d80ece95cb 100644
--- a/include/asm-i386/atomic.h
+++ b/include/asm-i386/atomic.h
@@ -225,8 +225,14 @@ static __inline__ int atomic_sub_return(int i, atomic_t *v)
 ({                                                              \
         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)
diff --git a/include/asm-ia64/atomic.h b/include/asm-ia64/atomic.h
index d3e0dfa99e1f..569ec7574baf 100644
--- a/include/asm-ia64/atomic.h
+++ b/include/asm-ia64/atomic.h
@@ -95,8 +95,14 @@ ia64_atomic64_sub (__s64 i, atomic64_t *v)
 ({                                                              \
         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)
diff --git a/include/asm-m68k/atomic.h b/include/asm-m68k/atomic.h
index 862e497c2645..732d696d31a6 100644
--- a/include/asm-m68k/atomic.h
+++ b/include/asm-m68k/atomic.h
@@ -175,8 +175,14 @@ static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
 ({                                                              \
         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)
diff --git a/include/asm-s390/atomic.h b/include/asm-s390/atomic.h
index be6fefe223d6..de1d9926aa60 100644
--- a/include/asm-s390/atomic.h
+++ b/include/asm-s390/atomic.h
@@ -89,10 +89,15 @@ static __inline__ int atomic_cmpxchg(atomic_t *v, int old, int new)
 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_unless(atomic64_t *v,
                                           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;
 }
 
diff --git a/include/asm-sparc64/atomic.h b/include/asm-sparc64/atomic.h
index 25256bdc8aae..468eb48d8142 100644
--- a/include/asm-sparc64/atomic.h
+++ b/include/asm-sparc64/atomic.h
@@ -78,9 +78,15 @@ extern int atomic64_sub_ret(int, 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);                                               \
+        }                                                       \
+        likely(c != (u));                                       \
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
diff --git a/include/asm-x86_64/atomic.h b/include/asm-x86_64/atomic.h
index 4b5cd553e772..cecbf7baa6aa 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -405,8 +405,14 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t *v)
 ({                                                              \
         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)