Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "The locking tree was busier in this cycle than the usual pattern - a
  couple of major projects happened to coincide.

  The main changes are:

   - implement the atomic_fetch_{add,sub,and,or,xor}() API natively
     across all SMP architectures (Peter Zijlstra)

   - add atomic_fetch_{inc/dec}() as well, using the generic primitives
     (Davidlohr Bueso)

   - optimize various aspects of rwsems (Jason Low, Davidlohr Bueso,
     Waiman Long)

   - optimize smp_cond_load_acquire() on arm64 and implement LSE based
     atomic{,64}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}()
     on arm64 (Will Deacon)

   - introduce smp_acquire__after_ctrl_dep() and fix various barrier
     mis-uses and bugs (Peter Zijlstra)

   - after discovering ancient spin_unlock_wait() barrier bugs in its
     implementation and usage, strengthen its semantics and update/fix
     usage sites (Peter Zijlstra)

   - optimize mutex_trylock() fastpath (Peter Zijlstra)

   - ... misc fixes and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (67 commits)
  locking/atomic: Introduce inc/dec variants for the atomic_fetch_$op() API
  locking/barriers, arch/arm64: Implement LDXR+WFE based smp_cond_load_acquire()
  locking/static_keys: Fix non static symbol Sparse warning
  locking/qspinlock: Use __this_cpu_dec() instead of full-blown this_cpu_dec()
  locking/atomic, arch/tile: Fix tilepro build
  locking/atomic, arch/m68k: Remove comment
  locking/atomic, arch/arc: Fix build
  locking/Documentation: Clarify limited control-dependency scope
  locking/atomic, arch/rwsem: Employ atomic_long_fetch_add()
  locking/atomic, arch/qrwlock: Employ atomic_fetch_add_acquire()
  locking/atomic, arch/mips: Convert to _relaxed atomics
  locking/atomic, arch/alpha: Convert to _relaxed atomics
  locking/atomic: Remove the deprecated atomic_{set,clear}_mask() functions
  locking/atomic: Remove linux/atomic.h:atomic_fetch_or()
  locking/atomic: Implement atomic{,64,_long}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}()
  locking/atomic: Fix atomic64_relaxed() bits
  locking/atomic, arch/xtensa: Implement atomic_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/x86: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/tile: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/sparc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  ...

5 files changed, 406 insertions, 106 deletions

diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index f3a3586..c0235e0 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -76,6 +76,36 @@
 #define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
 
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_add_acquire	atomic_fetch_add_acquire
+#define atomic_fetch_add_release	atomic_fetch_add_release
+#define atomic_fetch_add		atomic_fetch_add
+
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+#define atomic_fetch_sub_acquire	atomic_fetch_sub_acquire
+#define atomic_fetch_sub_release	atomic_fetch_sub_release
+#define atomic_fetch_sub		atomic_fetch_sub
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_and_acquire	atomic_fetch_and_acquire
+#define atomic_fetch_and_release	atomic_fetch_and_release
+#define atomic_fetch_and		atomic_fetch_and
+
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
+#define atomic_fetch_andnot_acquire	atomic_fetch_andnot_acquire
+#define atomic_fetch_andnot_release	atomic_fetch_andnot_release
+#define atomic_fetch_andnot		atomic_fetch_andnot
+
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_or_acquire		atomic_fetch_or_acquire
+#define atomic_fetch_or_release		atomic_fetch_or_release
+#define atomic_fetch_or			atomic_fetch_or
+
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
+#define atomic_fetch_xor_acquire	atomic_fetch_xor_acquire
+#define atomic_fetch_xor_release	atomic_fetch_xor_release
+#define atomic_fetch_xor		atomic_fetch_xor
+
 #define atomic_xchg_relaxed(v, new)	xchg_relaxed(&((v)->counter), (new))
 #define atomic_xchg_acquire(v, new)	xchg_acquire(&((v)->counter), (new))
 #define atomic_xchg_release(v, new)	xchg_release(&((v)->counter), (new))
@@ -125,6 +155,36 @@
 #define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
 
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_add_acquire	atomic64_fetch_add_acquire
+#define atomic64_fetch_add_release	atomic64_fetch_add_release
+#define atomic64_fetch_add		atomic64_fetch_add
+
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+#define atomic64_fetch_sub_acquire	atomic64_fetch_sub_acquire
+#define atomic64_fetch_sub_release	atomic64_fetch_sub_release
+#define atomic64_fetch_sub		atomic64_fetch_sub
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_and_acquire	atomic64_fetch_and_acquire
+#define atomic64_fetch_and_release	atomic64_fetch_and_release
+#define atomic64_fetch_and		atomic64_fetch_and
+
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot_acquire
+#define atomic64_fetch_andnot_release	atomic64_fetch_andnot_release
+#define atomic64_fetch_andnot		atomic64_fetch_andnot
+
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_or_acquire	atomic64_fetch_or_acquire
+#define atomic64_fetch_or_release	atomic64_fetch_or_release
+#define atomic64_fetch_or		atomic64_fetch_or
+
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
+#define atomic64_fetch_xor_acquire	atomic64_fetch_xor_acquire
+#define atomic64_fetch_xor_release	atomic64_fetch_xor_release
+#define atomic64_fetch_xor		atomic64_fetch_xor
+
 #define atomic64_xchg_relaxed		atomic_xchg_relaxed
 #define atomic64_xchg_acquire		atomic_xchg_acquire
 #define atomic64_xchg_release		atomic_xchg_release
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index f61c84f6..f819fdc 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -77,26 +77,57 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v))		\
 }									\
 __LL_SC_EXPORT(atomic_##op##_return##name);
 
+#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+__LL_SC_INLINE int							\
+__LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v))		\
+{									\
+	unsigned long tmp;						\
+	int val, result;						\
+									\
+	asm volatile("// atomic_fetch_" #op #name "\n"			\
+"	prfm	pstl1strm, %3\n"					\
+"1:	ld" #acq "xr	%w0, %3\n"					\
+"	" #asm_op "	%w1, %w0, %w4\n"				\
+"	st" #rel "xr	%w2, %w1, %3\n"					\
+"	cbnz	%w2, 1b\n"						\
+"	" #mb								\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
+	: "Ir" (i)							\
+	: cl);								\
+									\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic_fetch_##op##name);
+
 #define ATOMIC_OPS(...)							\
 	ATOMIC_OP(__VA_ARGS__)						\
-	ATOMIC_OP_RETURN(        , dmb ish,  , l, "memory", __VA_ARGS__)
-
-#define ATOMIC_OPS_RLX(...)						\
-	ATOMIC_OPS(__VA_ARGS__)						\
+	ATOMIC_OP_RETURN(        , dmb ish,  , l, "memory", __VA_ARGS__)\
 	ATOMIC_OP_RETURN(_relaxed,        ,  ,  ,         , __VA_ARGS__)\
 	ATOMIC_OP_RETURN(_acquire,        , a,  , "memory", __VA_ARGS__)\
-	ATOMIC_OP_RETURN(_release,        ,  , l, "memory", __VA_ARGS__)
+	ATOMIC_OP_RETURN(_release,        ,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS_RLX(add, add)
-ATOMIC_OPS_RLX(sub, sub)
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(...)							\
+	ATOMIC_OP(__VA_ARGS__)						\
+	ATOMIC_FETCH_OP (        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(andnot, bic)
-ATOMIC_OP(or, orr)
-ATOMIC_OP(xor, eor)
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, orr)
+ATOMIC_OPS(xor, eor)
 
-#undef ATOMIC_OPS_RLX
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -140,26 +171,57 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v))	\
 }									\
 __LL_SC_EXPORT(atomic64_##op##_return##name);
 
+#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+__LL_SC_INLINE long							\
+__LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v))	\
+{									\
+	long result, val;						\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_fetch_" #op #name "\n"		\
+"	prfm	pstl1strm, %3\n"					\
+"1:	ld" #acq "xr	%0, %3\n"					\
+"	" #asm_op "	%1, %0, %4\n"					\
+"	st" #rel "xr	%w2, %1, %3\n"					\
+"	cbnz	%w2, 1b\n"						\
+"	" #mb								\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
+	: "Ir" (i)							\
+	: cl);								\
+									\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic64_fetch_##op##name);
+
 #define ATOMIC64_OPS(...)						\
 	ATOMIC64_OP(__VA_ARGS__)					\
-	ATOMIC64_OP_RETURN(, dmb ish,  , l, "memory", __VA_ARGS__)
-
-#define ATOMIC64_OPS_RLX(...)						\
-	ATOMIC64_OPS(__VA_ARGS__)					\
+	ATOMIC64_OP_RETURN(, dmb ish,  , l, "memory", __VA_ARGS__)	\
 	ATOMIC64_OP_RETURN(_relaxed,,  ,  ,         , __VA_ARGS__)	\
 	ATOMIC64_OP_RETURN(_acquire,, a,  , "memory", __VA_ARGS__)	\
-	ATOMIC64_OP_RETURN(_release,,  , l, "memory", __VA_ARGS__)
+	ATOMIC64_OP_RETURN(_release,,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS_RLX(add, add)
-ATOMIC64_OPS_RLX(sub, sub)
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(...)						\
+	ATOMIC64_OP(__VA_ARGS__)					\
+	ATOMIC64_FETCH_OP (, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, orr)
-ATOMIC64_OP(xor, eor)
+ATOMIC64_OPS(and, and)
+ATOMIC64_OPS(andnot, bic)
+ATOMIC64_OPS(or, orr)
+ATOMIC64_OPS(xor, eor)
 
-#undef ATOMIC64_OPS_RLX
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 39c1d34..b5890be 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -26,54 +26,57 @@
 #endif
 
 #define __LL_SC_ATOMIC(op)	__LL_SC_CALL(atomic_##op)
-
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(andnot),
-	"	stclr	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#define ATOMIC_OP(op, asm_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op),		\
+"	" #asm_op "	%w[i], %[v]\n")					\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS);						\
 }
 
-static inline void atomic_or(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
+ATOMIC_OP(andnot, stclr)
+ATOMIC_OP(or, stset)
+ATOMIC_OP(xor, steor)
+ATOMIC_OP(add, stadd)
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(or),
-	"	stset	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+#undef ATOMIC_OP
 
-static inline void atomic_xor(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(xor),
-	"	steor	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...)			\
+static inline int atomic_fetch_##op##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	__LL_SC_ATOMIC(fetch_##op##name),				\
+	/* LSE atomics */						\
+"	" #asm_op #mb "	%w[i], %w[i], %[v]")				\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return w0;							\
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
+#define ATOMIC_FETCH_OPS(op, asm_op)					\
+	ATOMIC_FETCH_OP(_relaxed,   , op, asm_op)			\
+	ATOMIC_FETCH_OP(_acquire,  a, op, asm_op, "memory")		\
+	ATOMIC_FETCH_OP(_release,  l, op, asm_op, "memory")		\
+	ATOMIC_FETCH_OP(        , al, op, asm_op, "memory")
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(add),
-	"	stadd	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+ATOMIC_FETCH_OPS(andnot, ldclr)
+ATOMIC_FETCH_OPS(or, ldset)
+ATOMIC_FETCH_OPS(xor, ldeor)
+ATOMIC_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_FETCH_OPS
 
 #define ATOMIC_OP_ADD_RETURN(name, mb, cl...)				\
 static inline int atomic_add_return##name(int i, atomic_t *v)		\
@@ -119,6 +122,33 @@ static inline void atomic_and(int i, atomic_t *v)
 	: __LL_SC_CLOBBERS);
 }
 
+#define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
+static inline int atomic_fetch_and##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC(fetch_and##name),				\
+	/* LSE atomics */						\
+	"	mvn	%w[i], %w[i]\n"					\
+	"	ldclr" #mb "	%w[i], %w[i], %[v]")			\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return w0;							\
+}
+
+ATOMIC_FETCH_OP_AND(_relaxed,   )
+ATOMIC_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC_FETCH_OP_AND(        , al, "memory")
+
+#undef ATOMIC_FETCH_OP_AND
+
 static inline void atomic_sub(int i, atomic_t *v)
 {
 	register int w0 asm ("w0") = i;
@@ -164,57 +194,87 @@ ATOMIC_OP_SUB_RETURN(_release,  l, "memory")
 ATOMIC_OP_SUB_RETURN(        , al, "memory")
 
 #undef ATOMIC_OP_SUB_RETURN
-#undef __LL_SC_ATOMIC
-
-#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
-
-static inline void atomic64_andnot(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(andnot),
-	"	stclr	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#define ATOMIC_FETCH_OP_SUB(name, mb, cl...)				\
+static inline int atomic_fetch_sub##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC(fetch_sub##name),				\
+	/* LSE atomics */						\
+	"	neg	%w[i], %w[i]\n"					\
+	"	ldadd" #mb "	%w[i], %w[i], %[v]")			\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return w0;							\
 }
 
-static inline void atomic64_or(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+ATOMIC_FETCH_OP_SUB(_relaxed,   )
+ATOMIC_FETCH_OP_SUB(_acquire,  a, "memory")
+ATOMIC_FETCH_OP_SUB(_release,  l, "memory")
+ATOMIC_FETCH_OP_SUB(        , al, "memory")
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(or),
-	"	stset	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#undef ATOMIC_FETCH_OP_SUB
+#undef __LL_SC_ATOMIC
+
+#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
+#define ATOMIC64_OP(op, asm_op)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	register long x0 asm ("x0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op),	\
+"	" #asm_op "	%[i], %[v]\n")					\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS);						\
 }
 
-static inline void atomic64_xor(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+ATOMIC64_OP(andnot, stclr)
+ATOMIC64_OP(or, stset)
+ATOMIC64_OP(xor, steor)
+ATOMIC64_OP(add, stadd)
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(xor),
-	"	steor	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#undef ATOMIC64_OP
+
+#define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
+static inline long atomic64_fetch_##op##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("x0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	__LL_SC_ATOMIC64(fetch_##op##name),				\
+	/* LSE atomics */						\
+"	" #asm_op #mb "	%[i], %[i], %[v]")				\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return x0;							\
 }
 
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+#define ATOMIC64_FETCH_OPS(op, asm_op)					\
+	ATOMIC64_FETCH_OP(_relaxed,   , op, asm_op)			\
+	ATOMIC64_FETCH_OP(_acquire,  a, op, asm_op, "memory")		\
+	ATOMIC64_FETCH_OP(_release,  l, op, asm_op, "memory")		\
+	ATOMIC64_FETCH_OP(        , al, op, asm_op, "memory")
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(add),
-	"	stadd	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+ATOMIC64_FETCH_OPS(andnot, ldclr)
+ATOMIC64_FETCH_OPS(or, ldset)
+ATOMIC64_FETCH_OPS(xor, ldeor)
+ATOMIC64_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_FETCH_OPS
 
 #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
 static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
@@ -260,6 +320,33 @@ static inline void atomic64_and(long i, atomic64_t *v)
 	: __LL_SC_CLOBBERS);
 }
 
+#define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
+static inline long atomic64_fetch_and##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("w0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC64(fetch_and##name),				\
+	/* LSE atomics */						\
+	"	mvn	%[i], %[i]\n"					\
+	"	ldclr" #mb "	%[i], %[i], %[v]")			\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return x0;							\
+}
+
+ATOMIC64_FETCH_OP_AND(_relaxed,   )
+ATOMIC64_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC64_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC64_FETCH_OP_AND(        , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_AND
+
 static inline void atomic64_sub(long i, atomic64_t *v)
 {
 	register long x0 asm ("x0") = i;
@@ -306,6 +393,33 @@ ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 
 #undef ATOMIC64_OP_SUB_RETURN
 
+#define ATOMIC64_FETCH_OP_SUB(name, mb, cl...)				\
+static inline long atomic64_fetch_sub##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("w0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC64(fetch_sub##name),				\
+	/* LSE atomics */						\
+	"	neg	%[i], %[i]\n"					\
+	"	ldadd" #mb "	%[i], %[i], %[v]")			\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return x0;							\
+}
+
+ATOMIC64_FETCH_OP_SUB(_relaxed,   )
+ATOMIC64_FETCH_OP_SUB(_acquire,  a, "memory")
+ATOMIC64_FETCH_OP_SUB(_release,  l, "memory")
+ATOMIC64_FETCH_OP_SUB(        , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_SUB
+
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
 	register long x0 asm ("x0") = (long)v;
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index dae5c49..4eea7f6 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -91,6 +91,19 @@ do {									\
 	__u.__val;							\
 })
 
+#define smp_cond_load_acquire(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	typeof(*ptr) VAL;						\
+	for (;;) {							\
+		VAL = smp_load_acquire(__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	VAL;								\
+})
+
 #include <asm-generic/barrier.h>
 
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 510c7b4..bd86a79 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -224,4 +224,55 @@ __CMPXCHG_GEN(_mb)
 	__ret;								\
 })
 
+#define __CMPWAIT_CASE(w, sz, name)					\
+static inline void __cmpwait_case_##name(volatile void *ptr,		\
+					 unsigned long val)		\
+{									\
+	unsigned long tmp;						\
+									\
+	asm volatile(							\
+	"	ldxr" #sz "\t%" #w "[tmp], %[v]\n"		\
+	"	eor	%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
+	"	cbnz	%" #w "[tmp], 1f\n"				\
+	"	wfe\n"							\
+	"1:"								\
+	: [tmp] "=&r" (tmp), [v] "+Q" (*(unsigned long *)ptr)		\
+	: [val] "r" (val));						\
+}
+
+__CMPWAIT_CASE(w, b, 1);
+__CMPWAIT_CASE(w, h, 2);
+__CMPWAIT_CASE(w,  , 4);
+__CMPWAIT_CASE( ,  , 8);
+
+#undef __CMPWAIT_CASE
+
+#define __CMPWAIT_GEN(sfx)						\
+static inline void __cmpwait##sfx(volatile void *ptr,			\
+				  unsigned long val,			\
+				  int size)				\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __cmpwait_case##sfx##_1(ptr, (u8)val);		\
+	case 2:								\
+		return __cmpwait_case##sfx##_2(ptr, (u16)val);		\
+	case 4:								\
+		return __cmpwait_case##sfx##_4(ptr, val);		\
+	case 8:								\
+		return __cmpwait_case##sfx##_8(ptr, val);		\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
+}
+
+__CMPWAIT_GEN()
+
+#undef __CMPWAIT_GEN
+
+#define __cmpwait_relaxed(ptr, val) \
+	__cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr)))
+
 #endif	/* __ASM_CMPXCHG_H */