ARM: atomic ops: add memory constraints to inline asm

add memory constraints to the rmw parameters in barrier-less
atomic operations (atomic_add, atomic_sub, etc.), so that
optimizing compilers do not constant-fold expressions surrounding
these operations.

based on a patch submitted to lakml by Will
Deacon (will.deacon@arm.com)

Change-Id: Idfc10bbda9b4a26ee8af6b3281075c4387e8c11f
Reviewed-on: http://git-master/r/3649
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
Tested-by: Bharat Nihalani <bnihalani@nvidia.com>
Reviewed-by: Gary King <gking@nvidia.com>

1 files changed, 24 insertions, 24 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index d0daeab2234e..88b0d3e22e05 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -40,12 +40,12 @@ static inline void atomic_add(int i, atomic_t *v)
 	int result;
 
 	__asm__ __volatile__("@ atomic_add\n"
-"1:	ldrex	%0, [%2]\n"
-"	add	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+        : "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }
@@ -58,12 +58,12 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic_add_return\n"
-"1:	ldrex	%0, [%2]\n"
-"	add	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
@@ -78,12 +78,12 @@ static inline void atomic_sub(int i, atomic_t *v)
 	int result;
 
 	__asm__ __volatile__("@ atomic_sub\n"
-"1:	ldrex	%0, [%2]\n"
-"	sub	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }
@@ -96,12 +96,12 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic_sub_return\n"
-"1:	ldrex	%0, [%2]\n"
-"	sub	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
@@ -118,11 +118,11 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
-		"ldrex	%1, [%2]\n"
+		"ldrex	%1, [%3]\n"
 		"mov	%0, #0\n"
-		"teq	%1, %3\n"
-		"strexeq %0, %4, [%2]\n"
-		    : "=&r" (res), "=&r" (oldval)
+		"teq	%1, %4\n"
+		"strexeq %0, %5, [%3]\n"
+		    : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
 		    : "r" (&ptr->counter), "Ir" (old), "r" (new)
 		    : "cc");
 	} while (res);
@@ -137,12 +137,12 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 	unsigned long tmp, tmp2;
 
 	__asm__ __volatile__("@ atomic_clear_mask\n"
-"1:	ldrex	%0, [%2]\n"
-"	bic	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	bic	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (tmp), "=&r" (tmp2)
+	: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
 	: "r" (addr), "Ir" (mask)
 	: "cc");
 }