[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>
diff --git a/include/asm-i386/atomic.h b/include/asm-i386/atomic.h
index 78b0032..22d80ec 100644
--- a/include/asm-i386/atomic.h
+++ b/include/asm-i386/atomic.h
@@ -225,8 +225,14 @@
({ \
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 d3e0dfa..569ec75 100644
--- a/include/asm-ia64/atomic.h
+++ b/include/asm-ia64/atomic.h
@@ -95,8 +95,14 @@
({ \
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 862e497..732d696 100644
--- a/include/asm-m68k/atomic.h
+++ b/include/asm-m68k/atomic.h
@@ -175,8 +175,14 @@
({ \
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 be6fefe..de1d992 100644
--- a/include/asm-s390/atomic.h
+++ b/include/asm-s390/atomic.h
@@ -89,10 +89,15 @@
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 @@
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 25256bd..468eb48 100644
--- a/include/asm-sparc64/atomic.h
+++ b/include/asm-sparc64/atomic.h
@@ -78,9 +78,15 @@
({ \
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 4b5cd55..cecbf7b 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -405,8 +405,14 @@
({ \
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)