arm64: lse: fix LSE atomics with LLVM's integrated assembler

Unlike gcc, clang considers each inline assembly block to be independent
and therefore, when using the integrated assembler for inline assembly,
any preambles that enable features must be repeated in each block.

This change defines __LSE_PREAMBLE and adds it to each inline assembly
block that has LSE instructions, which allows them to be compiled also
with clang's assembler.

Link: https://github.com/ClangBuiltLinux/linux/issues/671
Signed-off-by: Sami Tolvanen <[e-mail]>
Tested-by: Andrew Murray <[e-mail]>
Tested-by: Kees Cook <[e-mail]>
Reviewed-by: Andrew Murray <[e-mail]>
Reviewed-by: Kees Cook <[e-mail]>
Reviewed-by: Nick Desaulniers <[e-mail]>
Signed-off-by: Will Deacon <[e-mail]>

arch/arm64/include/asm/atomic_lse.h

···
 static inline void __lse_atomic_##op(int i, atomic_t *v)			\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op "	%w[i], %[v]\n"					\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v));							\
···
 static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op #mb "	%w[i], %w[i], %[v]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v)							\
···
 	u32 tmp;							\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	ldadd" #mb "	%w[i], %w[tmp], %[v]\n"			\
 	"	add	%w[i], %w[i], %w[tmp]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
···
 static inline void __lse_atomic_and(int i, atomic_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	mvn	%w[i], %w[i]\n"
 	"	stclr	%w[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
···
 static inline int __lse_atomic_fetch_and##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mvn	%w[i], %w[i]\n"					\
 	"	ldclr" #mb "	%w[i], %w[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
···
 static inline void __lse_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	neg	%w[i], %w[i]\n"
 	"	stadd	%w[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
···
 	u32 tmp;							\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[tmp], %[v]\n"			\
 	"	add	%w[i], %w[i], %w[tmp]"				\
···
 static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
···
 static inline void __lse_atomic64_##op(s64 i, atomic64_t *v)		\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op "	%[i], %[v]\n"					\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v));							\
···
 static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 "	" #asm_op #mb "	%[i], %[i], %[v]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter)				\
 	: "r" (v)							\
···
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
 	"	add	%[i], %[i], %x[tmp]"				\
 	: [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)	\
···
 static inline void __lse_atomic64_and(s64 i, atomic64_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	mvn	%[i], %[i]\n"
 	"	stclr	%[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
···
 static inline long __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mvn	%[i], %[i]\n"					\
 	"	ldclr" #mb "	%[i], %[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
···
 static inline void __lse_atomic64_sub(s64 i, atomic64_t *v)
 {
 	asm volatile(
+	__LSE_PREAMBLE
 	"	neg	%[i], %[i]\n"
 	"	stadd	%[i], %[v]"
 	: [i] "+&r" (i), [v] "+Q" (v->counter)
···
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %x[tmp], %[v]\n"			\
 	"	add	%[i], %[i], %x[tmp]"				\
···
 static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v)	\
 {									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %[i], %[v]"			\
 	: [i] "+&r" (i), [v] "+Q" (v->counter)				\
···
 	unsigned long tmp;
 
 	asm volatile(
+	__LSE_PREAMBLE
 	"1:	ldr	%x[tmp], %[v]\n"
 	"	subs	%[ret], %x[tmp], #1\n"
 	"	b.lt	2f\n"
···
 	unsigned long tmp;						\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	mov	%" #w "[tmp], %" #w "[old]\n"			\
 	"	cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n"	\
 	"	mov	%" #w "[ret], %" #w "[tmp]"			\
···
 	register unsigned long x4 asm ("x4") = (unsigned long)ptr;	\
 									\
 	asm volatile(							\
+	__LSE_PREAMBLE							\
 	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
 	"	eor	%[old1], %[old1], %[oldval1]\n"			\
 	"	eor	%[old2], %[old2], %[oldval2]\n"			\

arch/arm64/include/asm/lse.h

···
 
 #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
 
+#define __LSE_PREAMBLE	".arch armv8-a+lse\n"
+
 #include <linux/compiler_types.h>
 #include <linux/export.h>
 #include <linux/jump_label.h>
···
 #include <asm/alternative.h>
 #include <asm/atomic_lse.h>
 #include <asm/cpucaps.h>
-
-__asm__(".arch_extension	lse");
 
 extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
 extern struct static_key_false arm64_const_caps_ready;
···
 
 /* In-line patching at runtime */
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
-	ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
+	ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS)
 
 #else	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */