arm64: atomics: Use K constraint when toolchain appears to support it

The 'K' constraint is a documented AArch64 machine constraint supported
by GCC for matching integer constants that can be used with a 32-bit
logical instruction. Unfortunately, some released compilers erroneously
accept the immediate '4294967295' for this constraint, which is later
refused by GAS at assembly time. This had led us to avoid the use of
the 'K' constraint altogether.

Instead, detect whether the compiler is up to the job when building the
kernel and pass the 'K' constraint to our 32-bit atomic macros when it
appears to be supported.

Signed-off-by: Will Deacon <will@kernel.org>

2 files changed, 48 insertions, 24 deletions

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 61de992bbea3..0cef056b5fb1 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -39,6 +39,12 @@ $(warning LSE atomics not supported by binutils)
   endif
 endif
 
+cc_has_k_constraint := $(call try-run,echo				\
+	'int main(void) {						\
+		asm volatile("and w0, w0, %w0" :: "K" (4294967295));	\
+		return 0;						\
+	}' | $(CC) -S -x c -o "$$TMP" -,,-DCONFIG_CC_HAS_K_CONSTRAINT=1)
+
 ifeq ($(CONFIG_ARM64), y)
 brokengasinst := $(call as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n,,-DCONFIG_BROKEN_GAS_INST=1)
 
@@ -63,7 +69,8 @@ ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
   endif
 endif
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst) $(compat_vdso)
+KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst)	\
+		   $(compat_vdso) $(cc_has_k_constraint)
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst) $(compat_vdso)
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index 95091f72228b..7b012148bfd6 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -10,6 +10,8 @@
 #ifndef __ASM_ATOMIC_LL_SC_H
 #define __ASM_ATOMIC_LL_SC_H
 
+#include <linux/stringify.h>
+
 #if IS_ENABLED(CONFIG_ARM64_LSE_ATOMICS) && IS_ENABLED(CONFIG_AS_LSE)
 #define __LL_SC_FALLBACK(asm_ops)					\
 "	b	3f\n"							\
@@ -23,6 +25,10 @@ asm_ops "\n"								\
 #define __LL_SC_FALLBACK(asm_ops) asm_ops
 #endif
 
+#ifndef CONFIG_CC_HAS_K_CONSTRAINT
+#define K
+#endif
+
 /*
  * AArch64 UP and SMP safe atomic ops.  We use load exclusive and
  * store exclusive to ensure that these are atomic.  We may loop
@@ -44,7 +50,7 @@ __ll_sc_atomic_##op(int i, atomic_t *v)					\
 "	stxr	%w1, %w0, %2\n"						\
 "	cbnz	%w1, 1b\n")						\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: #constraint "r" (i));						\
+	: __stringify(constraint) "r" (i));				\
 }
 
 #define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
@@ -63,7 +69,7 @@ __ll_sc_atomic_##op##_return##name(int i, atomic_t *v)			\
 "	cbnz	%w1, 1b\n"						\
 "	" #mb )								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: #constraint "r" (i)						\
+	: __stringify(constraint) "r" (i)				\
 	: cl);								\
 									\
 	return result;							\
@@ -85,7 +91,7 @@ __ll_sc_atomic_fetch_##op##name(int i, atomic_t *v)			\
 "	cbnz	%w2, 1b\n"						\
 "	" #mb )								\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
-	: #constraint "r" (i)						\
+	: __stringify(constraint) "r" (i)				\
 	: cl);								\
 									\
 	return result;							\
@@ -113,10 +119,15 @@ ATOMIC_OPS(sub, sub, J)
 	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
 	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS(and, and, )
+ATOMIC_OPS(and, and, K)
+ATOMIC_OPS(or, orr, K)
+ATOMIC_OPS(xor, eor, K)
+/*
+ * GAS converts the mysterious and undocumented BIC (immediate) alias to
+ * an AND (immediate) instruction with the immediate inverted. We don't
+ * have a constraint for this, so fall back to register.
+ */
 ATOMIC_OPS(andnot, bic, )
-ATOMIC_OPS(or, orr, )
-ATOMIC_OPS(xor, eor, )
 
 #undef ATOMIC_OPS
 #undef ATOMIC_FETCH_OP
@@ -138,7 +149,7 @@ __ll_sc_atomic64_##op(s64 i, atomic64_t *v)				\
 "	stxr	%w1, %0, %2\n"						\
 "	cbnz	%w1, 1b")						\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: #constraint "r" (i));						\
+	: __stringify(constraint) "r" (i));				\
 }
 
 #define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
@@ -157,7 +168,7 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v)		\
 "	cbnz	%w1, 1b\n"						\
 "	" #mb )								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
-	: #constraint "r" (i)						\
+	: __stringify(constraint) "r" (i)				\
 	: cl);								\
 									\
 	return result;							\
@@ -179,7 +190,7 @@ __ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v)		\
 "	cbnz	%w2, 1b\n"						\
 "	" #mb )								\
 	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
-	: #constraint "r" (i)						\
+	: __stringify(constraint) "r" (i)				\
 	: cl);								\
 									\
 	return result;							\
@@ -208,9 +219,14 @@ ATOMIC64_OPS(sub, sub, J)
 	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
 ATOMIC64_OPS(and, and, L)
-ATOMIC64_OPS(andnot, bic, )
 ATOMIC64_OPS(or, orr, L)
 ATOMIC64_OPS(xor, eor, L)
+/*
+ * GAS converts the mysterious and undocumented BIC (immediate) alias to
+ * an AND (immediate) instruction with the immediate inverted. We don't
+ * have a constraint for this, so fall back to register.
+ */
+ATOMIC64_OPS(andnot, bic, )
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_FETCH_OP
@@ -269,7 +285,7 @@ __ll_sc__cmpxchg_case_##name##sz(volatile void *ptr,			\
 	"2:")								\
 	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
 	  [v] "+Q" (*(u##sz *)ptr)					\
-	: [old] #constraint "r" (old), [new] "r" (new)			\
+	: [old] __stringify(constraint) "r" (old), [new] "r" (new)	\
 	: cl);								\
 									\
 	return oldval;							\
@@ -280,21 +296,21 @@ __ll_sc__cmpxchg_case_##name##sz(volatile void *ptr,			\
  * 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(w, b,     ,  8,        ,  ,  ,         , K)
+__CMPXCHG_CASE(w, h,     , 16,        ,  ,  ,         , K)
+__CMPXCHG_CASE(w,  ,     , 32,        ,  ,  ,         , K)
 __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(w, b, acq_,  8,        , a,  , "memory", K)
+__CMPXCHG_CASE(w, h, acq_, 16,        , a,  , "memory", K)
+__CMPXCHG_CASE(w,  , acq_, 32,        , a,  , "memory", K)
 __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(w, b, rel_,  8,        ,  , l, "memory", K)
+__CMPXCHG_CASE(w, h, rel_, 16,        ,  , l, "memory", K)
+__CMPXCHG_CASE(w,  , rel_, 32,        ,  , l, "memory", K)
 __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(w, b,  mb_,  8, dmb ish,  , l, "memory", K)
+__CMPXCHG_CASE(w, h,  mb_, 16, dmb ish,  , l, "memory", K)
+__CMPXCHG_CASE(w,  ,  mb_, 32, dmb ish,  , l, "memory", K)
 __CMPXCHG_CASE( ,  ,  mb_, 64, dmb ish,  , l, "memory", L)
 
 #undef __CMPXCHG_CASE
@@ -332,5 +348,6 @@ __CMPXCHG_DBL(   ,        ,  ,         )
 __CMPXCHG_DBL(_mb, dmb ish, l, "memory")
 
 #undef __CMPXCHG_DBL
+#undef K
 
 #endif	/* __ASM_ATOMIC_LL_SC_H */