[PATCH -v2 22/33] locking,sparc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()

From: Peter Zijlstra
Date: Tue May 31 2016 - 06:34:26 EST


Implement FETCH-OP atomic primitives, these are very similar to the
existing OP-RETURN primitives we already have, except they return the
value of the atomic variable _before_ modification.

This is especially useful for irreversible operations -- such as
bitops (because it becomes impossible to reconstruct the state prior
to modification).

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
arch/sparc/include/asm/atomic.h | 1
arch/sparc/include/asm/atomic_32.h | 15 +++++++--
arch/sparc/include/asm/atomic_64.h | 16 +++++++--
arch/sparc/lib/atomic32.c | 29 ++++++++++-------
arch/sparc/lib/atomic_64.S | 61 ++++++++++++++++++++++++++++++-------
arch/sparc/lib/ksyms.c | 17 +++++++---
6 files changed, 105 insertions(+), 34 deletions(-)

--- a/arch/sparc/include/asm/atomic.h
+++ b/arch/sparc/include/asm/atomic.h
@@ -5,4 +5,5 @@
#else
#include <asm/atomic_32.h>
#endif
+#define atomic_fetch_or atomic_fetch_or
#endif
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,9 +20,10 @@
#define ATOMIC_INIT(i) { (i) }

int atomic_add_return(int, atomic_t *);
-void atomic_and(int, atomic_t *);
-void atomic_or(int, atomic_t *);
-void atomic_xor(int, atomic_t *);
+int atomic_fetch_add(int, atomic_t *);
+int atomic_fetch_and(int, atomic_t *);
+int atomic_fetch_or(int, atomic_t *);
+int atomic_fetch_xor(int, atomic_t *);
int atomic_cmpxchg(atomic_t *, int, int);
int atomic_xchg(atomic_t *, int);
int __atomic_add_unless(atomic_t *, int, int);
@@ -35,7 +36,15 @@ void atomic_set(atomic_t *, int);
#define atomic_inc(v) ((void)atomic_add_return( 1, (v)))
#define atomic_dec(v) ((void)atomic_add_return( -1, (v)))

+#define atomic_fetch_or atomic_fetch_or
+
+#define atomic_and(i, v) ((void)atomic_fetch_and((i), (v)))
+#define atomic_or(i, v) ((void)atomic_fetch_or((i), (v)))
+#define atomic_xor(i, v) ((void)atomic_fetch_xor((i), (v)))
+
#define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v)))
+#define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v)))
+
#define atomic_inc_return(v) (atomic_add_return( 1, (v)))
#define atomic_dec_return(v) (atomic_add_return( -1, (v)))

--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -28,16 +28,24 @@ void atomic64_##op(long, atomic64_t *);
int atomic_##op##_return(int, atomic_t *); \
long atomic64_##op##_return(long, atomic64_t *);

-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op) \
+int atomic_fetch_##op(int, atomic_t *); \
+long atomic64_fetch_##op(long, atomic64_t *);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)

ATOMIC_OPS(add)
ATOMIC_OPS(sub)

-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)

#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP

--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,39 +27,44 @@ static DEFINE_SPINLOCK(dummy);

#endif /* SMP */

-#define ATOMIC_OP_RETURN(op, c_op) \
-int atomic_##op##_return(int i, atomic_t *v) \
+#define ATOMIC_FETCH_OP(op, c_op) \
+int atomic_fetch_##op(int i, atomic_t *v) \
{ \
int ret; \
unsigned long flags; \
spin_lock_irqsave(ATOMIC_HASH(v), flags); \
\
- ret = (v->counter c_op i); \
+ ret = v->counter; \
+ v->counter c_op i; \
\
spin_unlock_irqrestore(ATOMIC_HASH(v), flags); \
return ret; \
} \
-EXPORT_SYMBOL(atomic_##op##_return);
+EXPORT_SYMBOL(atomic_fetch_##op);

-#define ATOMIC_OP(op, c_op) \
-void atomic_##op(int i, atomic_t *v) \
+#define ATOMIC_OP_RETURN(op, c_op) \
+int atomic_##op##_return(int i, atomic_t *v) \
{ \
+ int ret; \
unsigned long flags; \
spin_lock_irqsave(ATOMIC_HASH(v), flags); \
\
- v->counter c_op i; \
+ ret = (v->counter c_op i); \
\
spin_unlock_irqrestore(ATOMIC_HASH(v), flags); \
+ return ret; \
} \
-EXPORT_SYMBOL(atomic_##op);
+EXPORT_SYMBOL(atomic_##op##_return);

ATOMIC_OP_RETURN(add, +=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)

+ATOMIC_FETCH_OP(add, +=)
+ATOMIC_FETCH_OP(and, &=)
+ATOMIC_FETCH_OP(or, |=)
+ATOMIC_FETCH_OP(xor, ^=)
+
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP

int atomic_xchg(atomic_t *v, int new)
{
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -9,10 +9,11 @@

.text

- /* Two versions of the atomic routines, one that
+ /* Three versions of the atomic routines, one that
* does not return a value and does not perform
- * memory barriers, and a second which returns
- * a value and does the barriers.
+ * memory barriers, and a two which return
+ * a value, the new and old value resp. and does the
+ * barriers.
*/

#define ATOMIC_OP(op) \
@@ -43,15 +44,34 @@ ENTRY(atomic_##op##_return) /* %o0 = inc
2: BACKOFF_SPIN(%o2, %o3, 1b); \
ENDPROC(atomic_##op##_return);

-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op) \
+ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \
+ BACKOFF_SETUP(%o2); \
+1: lduw [%o1], %g1; \
+ op %g1, %o0, %g7; \
+ cas [%o1], %g1, %g7; \
+ cmp %g1, %g7; \
+ bne,pn %icc, BACKOFF_LABEL(2f, 1b); \
+ nop; \
+ retl; \
+ sra %g1, 0, %o0; \
+2: BACKOFF_SPIN(%o2, %o3, 1b); \
+ENDPROC(atomic_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)

ATOMIC_OPS(add)
ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)

#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP

@@ -83,15 +103,34 @@ ENTRY(atomic64_##op##_return) /* %o0 = i
2: BACKOFF_SPIN(%o2, %o3, 1b); \
ENDPROC(atomic64_##op##_return);

-#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op) \
+ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \
+ BACKOFF_SETUP(%o2); \
+1: ldx [%o1], %g1; \
+ op %g1, %o0, %g7; \
+ casx [%o1], %g1, %g7; \
+ cmp %g1, %g7; \
+ bne,pn %xcc, BACKOFF_LABEL(2f, 1b); \
+ nop; \
+ retl; \
+ mov %g1, %o0; \
+2: BACKOFF_SPIN(%o2, %o3, 1b); \
+ENDPROC(atomic64_fetch_##op);
+
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)

ATOMIC64_OPS(add)
ATOMIC64_OPS(sub)
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)

#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP

--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -107,15 +107,24 @@ EXPORT_SYMBOL(atomic64_##op);
EXPORT_SYMBOL(atomic_##op##_return); \
EXPORT_SYMBOL(atomic64_##op##_return);

-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op) \
+EXPORT_SYMBOL(atomic_fetch_##op); \
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)

ATOMIC_OPS(add)
ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)

#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP