diff mbox series

[v2,2/5] arm64: Use correct ll/sc atomic constraints

Message ID 20190731161256.22210-3-andrew.murray@arm.com (mailing list archive)
State New, archived
Headers show
Series arm64: avoid out-of-line ll/sc atomics | expand

Commit Message

Andrew Murray July 31, 2019, 4:12 p.m. UTC
For many of the ll/sc atomic operations we use the 'I' machine constraint
regardless to the instruction used - this may not be optimal.

Let's add an additional parameter to the ATOMIC_xx macros that allows the
caller to specify an appropriate machine constraint.

Let's also improve __CMPXCHG_CASE by replacing the 'K' constraint with a
caller provided constraint. Please note that whilst we would like to use
the 'K' constraint on 32 bit operations, we choose not to provide any
constraint to avoid a GCC bug which results in a build error.

Earlier versions of GCC (no later than 8.1.0) appear to incorrectly handle
the 'K' constraint for the value 4294967295.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
---
 arch/arm64/include/asm/atomic_ll_sc.h | 89 ++++++++++++++-------------
 1 file changed, 47 insertions(+), 42 deletions(-)
diff mbox series

Patch

diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index c8c850bc3dfb..4ebff769f3ed 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -26,7 +26,7 @@ 
  * (the optimize attribute silently ignores these options).
  */
 
-#define ATOMIC_OP(op, asm_op)						\
+#define ATOMIC_OP(op, asm_op, constraint)				\
 __LL_SC_INLINE void							\
 __LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v))			\
 {									\
@@ -40,11 +40,11 @@  __LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v))			\
 "	stxr	%w1, %w0, %2\n"						\
 "	cbnz	%w1, 1b"						\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
+	: #constraint "r" (i));						\
 }									\
 __LL_SC_EXPORT(arch_atomic_##op);
 
-#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
 __LL_SC_INLINE int							\
 __LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v))	\
 {									\
@@ -59,14 +59,14 @@  __LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v))	\
 "	cbnz	%w1, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
 }									\
 __LL_SC_EXPORT(arch_atomic_##op##_return##name);
 
-#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)	\
 __LL_SC_INLINE int							\
 __LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v))	\
 {									\
@@ -81,7 +81,7 @@  __LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v))	\
 "	cbnz	%w2, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
@@ -99,8 +99,8 @@  __LL_SC_EXPORT(arch_atomic_fetch_##op##name);
 	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
 	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS(add, add)
-ATOMIC_OPS(sub, sub)
+ATOMIC_OPS(add, add, I)
+ATOMIC_OPS(sub, sub, J)
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(...)							\
@@ -110,17 +110,17 @@  ATOMIC_OPS(sub, sub)
 	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
 	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS(and, and)
-ATOMIC_OPS(andnot, bic)
-ATOMIC_OPS(or, orr)
-ATOMIC_OPS(xor, eor)
+ATOMIC_OPS(and, and, K)
+ATOMIC_OPS(andnot, bic, )
+ATOMIC_OPS(or, orr, K)
+ATOMIC_OPS(xor, eor, K)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define ATOMIC64_OP(op, asm_op)						\
+#define ATOMIC64_OP(op, asm_op, constraint)				\
 __LL_SC_INLINE void							\
 __LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v))		\
 {									\
@@ -134,11 +134,11 @@  __LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v))		\
 "	stxr	%w1, %0, %2\n"						\
 "	cbnz	%w1, 1b"						\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i));							\
+	: #constraint "r" (i));						\
 }									\
 __LL_SC_EXPORT(arch_atomic64_##op);
 
-#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
 __LL_SC_INLINE s64							\
 __LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
 {									\
@@ -153,14 +153,14 @@  __LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
 "	cbnz	%w1, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
 }									\
 __LL_SC_EXPORT(arch_atomic64_##op##_return##name);
 
-#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\
 __LL_SC_INLINE s64							\
 __LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v))	\
 {									\
@@ -175,7 +175,7 @@  __LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v))	\
 "	cbnz	%w2, 1b\n"						\
 "	" #mb								\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
-	: "Ir" (i)							\
+	: #constraint "r" (i)						\
 	: cl);								\
 									\
 	return result;							\
@@ -193,8 +193,8 @@  __LL_SC_EXPORT(arch_atomic64_fetch_##op##name);
 	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
 	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS(add, add)
-ATOMIC64_OPS(sub, sub)
+ATOMIC64_OPS(add, add, I)
+ATOMIC64_OPS(sub, sub, J)
 
 #undef ATOMIC64_OPS
 #define ATOMIC64_OPS(...)						\
@@ -204,10 +204,10 @@  ATOMIC64_OPS(sub, sub)
 	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
 	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS(and, and)
-ATOMIC64_OPS(andnot, bic)
-ATOMIC64_OPS(or, orr)
-ATOMIC64_OPS(xor, eor)
+ATOMIC64_OPS(and, and, K)
+ATOMIC64_OPS(andnot, bic, )
+ATOMIC64_OPS(or, orr, K)
+ATOMIC64_OPS(xor, eor, K)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_FETCH_OP
@@ -237,7 +237,7 @@  __LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v))
 }
 __LL_SC_EXPORT(arch_atomic64_dec_if_positive);
 
-#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl)		\
+#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint)	\
 __LL_SC_INLINE u##sz							\
 __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr,		\
 					 unsigned long old,		\
@@ -265,29 +265,34 @@  __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr,		\
 	"2:"								\
 	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
 	  [v] "+Q" (*(u##sz *)ptr)					\
-	: [old] "Kr" (old), [new] "r" (new)				\
+	: [old] #constraint "r" (old), [new] "r" (new)			\
 	: cl);								\
 									\
 	return oldval;							\
 }									\
 __LL_SC_EXPORT(__cmpxchg_case_##name##sz);
 
-__CMPXCHG_CASE(w, b,     ,  8,        ,  ,  ,         )
-__CMPXCHG_CASE(w, h,     , 16,        ,  ,  ,         )
-__CMPXCHG_CASE(w,  ,     , 32,        ,  ,  ,         )
-__CMPXCHG_CASE( ,  ,     , 64,        ,  ,  ,         )
-__CMPXCHG_CASE(w, b, acq_,  8,        , a,  , "memory")
-__CMPXCHG_CASE(w, h, acq_, 16,        , a,  , "memory")
-__CMPXCHG_CASE(w,  , acq_, 32,        , a,  , "memory")
-__CMPXCHG_CASE( ,  , acq_, 64,        , a,  , "memory")
-__CMPXCHG_CASE(w, b, rel_,  8,        ,  , l, "memory")
-__CMPXCHG_CASE(w, h, rel_, 16,        ,  , l, "memory")
-__CMPXCHG_CASE(w,  , rel_, 32,        ,  , l, "memory")
-__CMPXCHG_CASE( ,  , rel_, 64,        ,  , l, "memory")
-__CMPXCHG_CASE(w, b,  mb_,  8, dmb ish,  , l, "memory")
-__CMPXCHG_CASE(w, h,  mb_, 16, dmb ish,  , l, "memory")
-__CMPXCHG_CASE(w,  ,  mb_, 32, dmb ish,  , l, "memory")
-__CMPXCHG_CASE( ,  ,  mb_, 64, dmb ish,  , l, "memory")
+/*
+ * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly
+ * handle the 'K' constraint for the value 4294967295 - thus we use no
+ * constraint for 32 bit operations.
+ */
+__CMPXCHG_CASE(w, b,     ,  8,        ,  ,  ,         , )
+__CMPXCHG_CASE(w, h,     , 16,        ,  ,  ,         , )
+__CMPXCHG_CASE(w,  ,     , 32,        ,  ,  ,         , )
+__CMPXCHG_CASE( ,  ,     , 64,        ,  ,  ,         , L)
+__CMPXCHG_CASE(w, b, acq_,  8,        , a,  , "memory", )
+__CMPXCHG_CASE(w, h, acq_, 16,        , a,  , "memory", )
+__CMPXCHG_CASE(w,  , acq_, 32,        , a,  , "memory", )
+__CMPXCHG_CASE( ,  , acq_, 64,        , a,  , "memory", L)
+__CMPXCHG_CASE(w, b, rel_,  8,        ,  , l, "memory", )
+__CMPXCHG_CASE(w, h, rel_, 16,        ,  , l, "memory", )
+__CMPXCHG_CASE(w,  , rel_, 32,        ,  , l, "memory", )
+__CMPXCHG_CASE( ,  , rel_, 64,        ,  , l, "memory", L)
+__CMPXCHG_CASE(w, b,  mb_,  8, dmb ish,  , l, "memory", )
+__CMPXCHG_CASE(w, h,  mb_, 16, dmb ish,  , l, "memory", )
+__CMPXCHG_CASE(w,  ,  mb_, 32, dmb ish,  , l, "memory", )
+__CMPXCHG_CASE( ,  ,  mb_, 64, dmb ish,  , l, "memory", L)
 
 #undef __CMPXCHG_CASE