ARC: atomics: Add compiler barrier to atomic operations...

... to avoid unwanted gcc optimizations

SMP kernels fail to boot with commit 596ff4a09b
("cpumask: re-introduce constant-sized cpumask optimizations").

|
| percpu: BUG: failure at mm/percpu.c:2981/pcpu_build_alloc_info()!
|

The write operation performed by the SCOND instruction in the atomic
inline asm code is not properly passed to the compiler. The compiler
cannot correctly optimize a nested loop that runs through the cpumask
in the pcpu_build_alloc_info() function.

Fix this by add a compiler barrier (memory clobber in inline asm).

Apparently atomic ops used to have memory clobber implicitly via
surrounding smp_mb(). However commit b64be68369
("ARC: atomics: implement relaxed variants") removed the smp_mb() for
the relaxed variants, but failed to add the explicit compiler barrier.

Link: https://github.com/foss-for-synopsys-dwc-arc-processors/linux/issues/135
Cc: <stable@vger.kernel.org> # v6.3+
Fixes: b64be68369 ("ARC: atomics: implement relaxed variants")
Signed-off-by: Pavel Kozlov <pavel.kozlov@synopsys.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>
[vgupta: tweaked the changelog and added Fixes tag]

arch/arc/include/asm/atomic-llsc.h

@@ -18,7 +18,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v)			\
 	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
 	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
 	  [i]	"ir"	(i)						\
-	: "cc");							\
+	: "cc", "memory");						\
 }									\
 
 #define ATOMIC_OP_RETURN(op, asm_op)				\
@@ -34,7 +34,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	: [val]	"=&r"	(val)						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
-	: "cc");							\
+	: "cc", "memory");						\
 									\
 	return val;							\
 }
@@ -56,7 +56,7 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 	  [orig] "=&r" (orig)						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
-	: "cc");							\
+	: "cc", "memory");						\
 									\
 	return orig;							\
 }

arch/arc/include/asm/atomic64-arcv2.h

@@ -60,7 +60,7 @@ static inline void arch_atomic64_##op(s64 a, atomic64_t *v)		\
 	"	bnz     1b		\n"				\
 	: "=&r"(val)							\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");							\
+	: "cc", "memory");						\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, op1, op2)		        	\
@@ -77,7 +77,7 @@ static inline s64 arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)	\
 	"	bnz     1b		\n"				\
 	: [val] "=&r"(val)						\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");	/* memory clobber comes from smp_mb() */	\
+	: "cc", "memory");						\
 									\
 	return val;							\
 }
@@ -99,7 +99,7 @@ static inline s64 arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)	\
 	"	bnz     1b		\n"				\
 	: "=&r"(orig), "=&r"(val)					\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");	/* memory clobber comes from smp_mb() */	\
+	: "cc", "memory");						\
 									\
 	return orig;							\
 }