Merge branch 'for-next/atomics' into for-next/core

* for-next/atomics: (10 commits)
  Rework LSE instruction selection to use static keys instead of alternatives

arch/arm64/Kconfig

@@ -1290,6 +1290,7 @@ config ARM64_PAN
 
 config ARM64_LSE_ATOMICS
 	bool "Atomic instructions"
+	depends on JUMP_LABEL
 	default y
 	help
 	  As part of the Large System Extensions, ARMv8.1 introduces new

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)

arch/arm64/include/asm/atomic.h

@@ -13,19 +13,91 @@
 #include <linux/types.h>
 
 #include <asm/barrier.h>
+#include <asm/cmpxchg.h>
 #include <asm/lse.h>
 
-#define __ARM64_IN_ATOMIC_IMPL
-
-#if defined(CONFIG_ARM64_LSE_ATOMICS) && defined(CONFIG_AS_LSE)
-#include <asm/atomic_lse.h>
-#else
-#include <asm/atomic_ll_sc.h>
-#endif
-
-#undef __ARM64_IN_ATOMIC_IMPL
-
-#include <asm/cmpxchg.h>
+#define ATOMIC_OP(op)							\
+static inline void arch_##op(int i, atomic_t *v)			\
+{									\
+	__lse_ll_sc_body(op, i, v);					\
+}
+
+ATOMIC_OP(atomic_andnot)
+ATOMIC_OP(atomic_or)
+ATOMIC_OP(atomic_xor)
+ATOMIC_OP(atomic_add)
+ATOMIC_OP(atomic_and)
+ATOMIC_OP(atomic_sub)
+
+#undef ATOMIC_OP
+
+#define ATOMIC_FETCH_OP(name, op)					\
+static inline int arch_##op##name(int i, atomic_t *v)			\
+{									\
+	return __lse_ll_sc_body(op##name, i, v);			\
+}
+
+#define ATOMIC_FETCH_OPS(op)						\
+	ATOMIC_FETCH_OP(_relaxed, op)					\
+	ATOMIC_FETCH_OP(_acquire, op)					\
+	ATOMIC_FETCH_OP(_release, op)					\
+	ATOMIC_FETCH_OP(        , op)
+
+ATOMIC_FETCH_OPS(atomic_fetch_andnot)
+ATOMIC_FETCH_OPS(atomic_fetch_or)
+ATOMIC_FETCH_OPS(atomic_fetch_xor)
+ATOMIC_FETCH_OPS(atomic_fetch_add)
+ATOMIC_FETCH_OPS(atomic_fetch_and)
+ATOMIC_FETCH_OPS(atomic_fetch_sub)
+ATOMIC_FETCH_OPS(atomic_add_return)
+ATOMIC_FETCH_OPS(atomic_sub_return)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_FETCH_OPS
+
+#define ATOMIC64_OP(op)							\
+static inline void arch_##op(long i, atomic64_t *v)			\
+{									\
+	__lse_ll_sc_body(op, i, v);					\
+}
+
+ATOMIC64_OP(atomic64_andnot)
+ATOMIC64_OP(atomic64_or)
+ATOMIC64_OP(atomic64_xor)
+ATOMIC64_OP(atomic64_add)
+ATOMIC64_OP(atomic64_and)
+ATOMIC64_OP(atomic64_sub)
+
+#undef ATOMIC64_OP
+
+#define ATOMIC64_FETCH_OP(name, op)					\
+static inline long arch_##op##name(long i, atomic64_t *v)		\
+{									\
+	return __lse_ll_sc_body(op##name, i, v);			\
+}
+
+#define ATOMIC64_FETCH_OPS(op)						\
+	ATOMIC64_FETCH_OP(_relaxed, op)					\
+	ATOMIC64_FETCH_OP(_acquire, op)					\
+	ATOMIC64_FETCH_OP(_release, op)					\
+	ATOMIC64_FETCH_OP(        , op)
+
+ATOMIC64_FETCH_OPS(atomic64_fetch_andnot)
+ATOMIC64_FETCH_OPS(atomic64_fetch_or)
+ATOMIC64_FETCH_OPS(atomic64_fetch_xor)
+ATOMIC64_FETCH_OPS(atomic64_fetch_add)
+ATOMIC64_FETCH_OPS(atomic64_fetch_and)
+ATOMIC64_FETCH_OPS(atomic64_fetch_sub)
+ATOMIC64_FETCH_OPS(atomic64_add_return)
+ATOMIC64_FETCH_OPS(atomic64_sub_return)
+
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_FETCH_OPS
+
+static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+{
+	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
+}
 
 #define ATOMIC_INIT(i)	{ (i) }
 

arch/arm64/include/asm/cmpxchg.h

@@ -10,7 +10,6 @@
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
 
-#include <asm/atomic.h>
 #include <asm/barrier.h>
 #include <asm/lse.h>
 
@@ -104,6 +103,50 @@ __XCHG_GEN(_mb)
 #define arch_xchg_release(...)	__xchg_wrapper(_rel, __VA_ARGS__)
 #define arch_xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
 
+#define __CMPXCHG_CASE(name, sz)			\
+static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr,	\
+					      u##sz old,		\
+					      u##sz new)		\
+{									\
+	return __lse_ll_sc_body(_cmpxchg_case_##name##sz,		\
+				ptr, old, new);				\
+}
+
+__CMPXCHG_CASE(    ,  8)
+__CMPXCHG_CASE(    , 16)
+__CMPXCHG_CASE(    , 32)
+__CMPXCHG_CASE(    , 64)
+__CMPXCHG_CASE(acq_,  8)
+__CMPXCHG_CASE(acq_, 16)
+__CMPXCHG_CASE(acq_, 32)
+__CMPXCHG_CASE(acq_, 64)
+__CMPXCHG_CASE(rel_,  8)
+__CMPXCHG_CASE(rel_, 16)
+__CMPXCHG_CASE(rel_, 32)
+__CMPXCHG_CASE(rel_, 64)
+__CMPXCHG_CASE(mb_,  8)
+__CMPXCHG_CASE(mb_, 16)
+__CMPXCHG_CASE(mb_, 32)
+__CMPXCHG_CASE(mb_, 64)
+
+#undef __CMPXCHG_CASE
+
+#define __CMPXCHG_DBL(name)						\
+static inline long __cmpxchg_double##name(unsigned long old1,		\
+					 unsigned long old2,		\
+					 unsigned long new1,		\
+					 unsigned long new2,		\
+					 volatile void *ptr)		\
+{									\
+	return __lse_ll_sc_body(_cmpxchg_double##name, 			\
+				old1, old2, new1, new2, ptr);		\
+}
+
+__CMPXCHG_DBL(   )
+__CMPXCHG_DBL(_mb)
+
+#undef __CMPXCHG_DBL
+
 #define __CMPXCHG_GEN(sfx)						\
 static inline unsigned long __cmpxchg##sfx(volatile void *ptr,		\
 					   unsigned long old,		\

arch/arm64/include/asm/lse.h

@@ -2,56 +2,47 @@
 #ifndef __ASM_LSE_H
 #define __ASM_LSE_H
 
+#include <asm/atomic_ll_sc.h>
+
 #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
 
 #include <linux/compiler_types.h>
 #include <linux/export.h>
+#include <linux/jump_label.h>
 #include <linux/stringify.h>
 #include <asm/alternative.h>
+#include <asm/atomic_lse.h>
 #include <asm/cpucaps.h>
 
-#ifdef __ASSEMBLER__
-
-.arch_extension	lse
-
-.macro alt_lse, llsc, lse
-	alternative_insn "\llsc", "\lse", ARM64_HAS_LSE_ATOMICS
-.endm
-
-#else	/* __ASSEMBLER__ */
-
 __asm__(".arch_extension	lse");
 
-/* Move the ll/sc atomics out-of-line */
-#define __LL_SC_INLINE		notrace
-#define __LL_SC_PREFIX(x)	__ll_sc_##x
-#define __LL_SC_EXPORT(x)	EXPORT_SYMBOL(__LL_SC_PREFIX(x))
+extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
+extern struct static_key_false arm64_const_caps_ready;
+
+static inline bool system_uses_lse_atomics(void)
+{
+	return (static_branch_likely(&arm64_const_caps_ready)) &&
+		static_branch_likely(&cpu_hwcap_keys[ARM64_HAS_LSE_ATOMICS]);
+}
 
-/* Macro for constructing calls to out-of-line ll/sc atomics */
-#define __LL_SC_CALL(op)	"bl\t" __stringify(__LL_SC_PREFIX(op)) "\n"
-#define __LL_SC_CLOBBERS	"x16", "x17", "x30"
+#define __lse_ll_sc_body(op, ...)					\
+({									\
+	system_uses_lse_atomics() ?					\
+		__lse_##op(__VA_ARGS__) :				\
+		__ll_sc_##op(__VA_ARGS__);				\
+})
 
 /* In-line patching at runtime */
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
 	ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS)
 
-#endif	/* __ASSEMBLER__ */
 #else	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
 
-#ifdef __ASSEMBLER__
-
-.macro alt_lse, llsc, lse
-	\llsc
-.endm
-
-#else	/* __ASSEMBLER__ */
+static inline bool system_uses_lse_atomics(void) { return false; }
 
-#define __LL_SC_INLINE		static inline
-#define __LL_SC_PREFIX(x)	x
-#define __LL_SC_EXPORT(x)
+#define __lse_ll_sc_body(op, ...)		__ll_sc_##op(__VA_ARGS__)
 
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc
 
-#endif	/* __ASSEMBLER__ */
 #endif	/* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
 #endif	/* __ASM_LSE_H */

arch/arm64/lib/Makefile

@@ -11,25 +11,6 @@ CFLAGS_REMOVE_xor-neon.o	+= -mgeneral-regs-only
 CFLAGS_xor-neon.o		+= -ffreestanding
 endif
 
-# Tell the compiler to treat all general purpose registers (with the
-# exception of the IP registers, which are already handled by the caller
-# in case of a PLT) as callee-saved, which allows for efficient runtime
-# patching of the bl instruction in the caller with an atomic instruction
-# when supported by the CPU. Result and argument registers are handled
-# correctly, based on the function prototype.
-lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
-CFLAGS_atomic_ll_sc.o	:= -ffixed-x1 -ffixed-x2        		\
-		   -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6		\
-		   -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9		\
-		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\
-		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
-		   -fcall-saved-x18 -fomit-frame-pointer
-CFLAGS_REMOVE_atomic_ll_sc.o := $(CC_FLAGS_FTRACE)
-GCOV_PROFILE_atomic_ll_sc.o	:= n
-KASAN_SANITIZE_atomic_ll_sc.o	:= n
-KCOV_INSTRUMENT_atomic_ll_sc.o	:= n
-UBSAN_SANITIZE_atomic_ll_sc.o	:= n
-
 lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
 
 obj-$(CONFIG_CRC32) += crc32.o

arch/arm64/lib/atomic_ll_sc.c

-#include <asm/atomic.h>
-#define __ARM64_IN_ATOMIC_IMPL
-#include <asm/atomic_ll_sc.h>

kernel/jump_label.c

@@ -407,7 +407,9 @@ static bool jump_label_can_update(struct jump_entry *entry, bool init)
 		return false;
 
 	if (!kernel_text_address(jump_entry_code(entry))) {
-		WARN_ONCE(1, "can't patch jump_label at %pS", (void *)jump_entry_code(entry));
+		WARN_ONCE(!jump_entry_is_init(entry),
+			  "can't patch jump_label at %pS",
+			  (void *)jump_entry_code(entry));
 		return false;
 	}