Merge branch 'locking/arch-atomic' into locking/core, because the topic is ready

Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 572b228..498933a 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -46,10 +46,9 @@
 }									\
 
 #define ATOMIC_OP_RETURN(op, asm_op)					\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
+static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 {									\
 	long temp, result;						\
-	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -61,7 +60,23 @@
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_mb();							\
+	return result;							\
+}
+
+#define ATOMIC_FETCH_OP(op, asm_op)					\
+static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+{									\
+	long temp, result;						\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %2,%1\n"						\
+	"	" #asm_op " %2,%3,%0\n"					\
+	"	stl_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
 	return result;							\
 }
 
@@ -82,10 +97,9 @@
 }									\
 
 #define ATOMIC64_OP_RETURN(op, asm_op)					\
-static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
+static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v)	\
 {									\
 	long temp, result;						\
-	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -97,34 +111,77 @@
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_mb();							\
+	return result;							\
+}
+
+#define ATOMIC64_FETCH_OP(op, asm_op)					\
+static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)	\
+{									\
+	long temp, result;						\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %2,%1\n"						\
+	"	" #asm_op " %2,%3,%0\n"					\
+	"	stq_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
 	return result;							\
 }
 
 #define ATOMIC_OPS(op)							\
 	ATOMIC_OP(op, op##l)						\
 	ATOMIC_OP_RETURN(op, op##l)					\
+	ATOMIC_FETCH_OP(op, op##l)					\
 	ATOMIC64_OP(op, op##q)						\
-	ATOMIC64_OP_RETURN(op, op##q)
+	ATOMIC64_OP_RETURN(op, op##q)					\
+	ATOMIC64_FETCH_OP(op, op##q)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+
 #define atomic_andnot atomic_andnot
 #define atomic64_andnot atomic64_andnot
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(andnot, bic)
-ATOMIC_OP(or, bis)
-ATOMIC_OP(xor, xor)
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, bis)
-ATOMIC64_OP(xor, xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, asm)						\
+	ATOMIC_OP(op, asm)						\
+	ATOMIC_FETCH_OP(op, asm)					\
+	ATOMIC64_OP(op, asm)						\
+	ATOMIC64_FETCH_OP(op, asm)
+
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, bis)
+ATOMIC_OPS(xor, xor)
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
 
 #undef ATOMIC_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index dd68399..4e3c1b6 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -67,6 +67,33 @@
 	return val;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int val, orig;						\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %[orig], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[orig], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	: [val]	"=&r"	(val),						\
+	  [orig] "=&r" (orig)						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return orig;							\
+}
+
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
 #ifndef CONFIG_SMP
@@ -129,25 +156,44 @@
 	return temp;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	unsigned long orig;						\
+									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
+	atomic_ops_lock(flags);						\
+	orig = v->counter;						\
+	v->counter c_op i;						\
+	atomic_ops_unlock(flags);					\
+									\
+	return orig;							\
+}
+
 #endif /* !CONFIG_ARC_HAS_LLSC */
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
 #define atomic_andnot atomic_andnot
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(andnot, &= ~, bic)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(andnot, &= ~, bic)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
 
 #else /* CONFIG_ARC_PLAT_EZNPS */
 
@@ -208,22 +254,51 @@
 	return temp;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int temp = i;						\
+									\
+	/* Explicit full memory barrier needed before/after */		\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"	mov r2, %0\n"						\
+	"	mov r3, %1\n"						\
+	"       .word %2\n"						\
+	"	mov %0, r2"						\
+	: "+r"(temp)							\
+	: "r"(&v->counter), "i"(asm_op)					\
+	: "r2", "r3", "memory");					\
+									\
+	smp_mb();							\
+									\
+	return temp;							\
+}
+
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 #define atomic_sub(i, v) atomic_add(-(i), (v))
 #define atomic_sub_return(i, v) atomic_add_return(-(i), (v))
 
-ATOMIC_OP(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
 #define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-ATOMIC_OP(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
-ATOMIC_OP(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
+ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
+ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
 #endif /* CONFIG_ARC_PLAT_EZNPS */
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 9e10c45..66d0e21 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -77,8 +77,36 @@
 	return result;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+{									\
+	unsigned long tmp;						\
+	int result, val;						\
+									\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic_fetch_" #op "\n"			\
+"1:	ldrex	%0, [%4]\n"						\
+"	" #asm_op "	%1, %0, %5\n"					\
+"	strex	%2, %1, [%4]\n"						\
+"	teq	%2, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Qo" (v->counter)	\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+									\
+	return result;							\
+}
+
 #define atomic_add_return_relaxed	atomic_add_return_relaxed
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
 
 static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 {
@@ -159,6 +187,20 @@
 	return val;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	int val;							\
+									\
+	raw_local_irq_save(flags);					\
+	val = v->counter;						\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return val;							\
+}
+
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -187,19 +229,26 @@
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
 #define atomic_andnot atomic_andnot
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(andnot, &= ~, bic)
-ATOMIC_OP(or,  |=, orr)
-ATOMIC_OP(xor, ^=, eor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(andnot, &= ~, bic)
+ATOMIC_OPS(or,  |=, orr)
+ATOMIC_OPS(xor, ^=, eor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -317,24 +366,61 @@
 	return result;							\
 }
 
+#define ATOMIC64_FETCH_OP(op, op1, op2)					\
+static inline long long							\
+atomic64_fetch_##op##_relaxed(long long i, atomic64_t *v)		\
+{									\
+	long long result, val;						\
+	unsigned long tmp;						\
+									\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic64_fetch_" #op "\n"		\
+"1:	ldrexd	%0, %H0, [%4]\n"					\
+"	" #op1 " %Q1, %Q0, %Q5\n"					\
+"	" #op2 " %R1, %R0, %R5\n"					\
+"	strexd	%2, %1, %H1, [%4]\n"					\
+"	teq	%2, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Qo" (v->counter)	\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+									\
+	return result;							\
+}
+
 #define ATOMIC64_OPS(op, op1, op2)					\
 	ATOMIC64_OP(op, op1, op2)					\
-	ATOMIC64_OP_RETURN(op, op1, op2)
+	ATOMIC64_OP_RETURN(op, op1, op2)				\
+	ATOMIC64_FETCH_OP(op, op1, op2)
 
 ATOMIC64_OPS(add, adds, adc)
 ATOMIC64_OPS(sub, subs, sbc)
 
 #define atomic64_add_return_relaxed	atomic64_add_return_relaxed
 #define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_FETCH_OP(op, op1, op2)
 
 #define atomic64_andnot atomic64_andnot
 
-ATOMIC64_OP(and, and, and)
-ATOMIC64_OP(andnot, bic, bic)
-ATOMIC64_OP(or,  orr, orr)
-ATOMIC64_OP(xor, eor, eor)
+ATOMIC64_OPS(and, and, and)
+ATOMIC64_OPS(andnot, bic, bic)
+ATOMIC64_OPS(or,  orr, orr)
+ATOMIC64_OPS(xor, eor, eor)
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
 
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
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_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)
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(andnot, bic)
-ATOMIC_OP(or, orr)
-ATOMIC_OP(xor, eor)
-
-#undef ATOMIC_OPS_RLX
 #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_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, orr)
+ATOMIC_OPS(xor, eor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -140,26 +171,57 @@
 }									\
 __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)
 
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, orr)
-ATOMIC64_OP(xor, eor)
-
-#undef ATOMIC64_OPS_RLX
 #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_OPS(and, and)
+ATOMIC64_OPS(andnot, bic)
+ATOMIC64_OPS(or, orr)
+ATOMIC64_OPS(xor, eor)
+
+#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
+
+#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_xor(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(xor),
-	"	steor	%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)
 
-static inline void atomic_add(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(add),
-	"	stadd	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+#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 @@
 	: __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(        , al, "memory")
 
 #undef ATOMIC_OP_SUB_RETURN
+
+#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;							\
+}
+
+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")
+
+#undef ATOMIC_FETCH_OP_SUB
 #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 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_or(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(or),
-	"	stset	%[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_xor(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(xor),
-	"	steor	%[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)
 
-static inline void atomic64_add(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(add),
-	"	stadd	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+#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 @@
 	: __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 @@
 
 #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/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index d74fd8c..3d5ce38 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -41,21 +41,49 @@
 	return result;							\
 }
 
+#define ATOMIC_FETCH_OP(op, asm_op, asm_con)				\
+static inline int __atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	int result, val;						\
+									\
+	asm volatile(							\
+		"/* atomic_fetch_" #op " */\n"				\
+		"1:	ssrf	5\n"					\
+		"	ld.w	%0, %3\n"				\
+		"	mov	%1, %0\n"				\
+		"	" #asm_op "	%1, %4\n"			\
+		"	stcond	%2, %1\n"				\
+		"	brne	1b"					\
+		: "=&r" (result), "=&r" (val), "=o" (v->counter)	\
+		: "m" (v->counter), #asm_con (i)			\
+		: "cc");						\
+									\
+	return result;							\
+}
+
 ATOMIC_OP_RETURN(sub, sub, rKs21)
 ATOMIC_OP_RETURN(add, add, r)
+ATOMIC_FETCH_OP (sub, sub, rKs21)
+ATOMIC_FETCH_OP (add, add, r)
 
-#define ATOMIC_OP(op, asm_op)						\
+#define ATOMIC_OPS(op, asm_op)						\
 ATOMIC_OP_RETURN(op, asm_op, r)						\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	(void)__atomic_##op##_return(i, v);				\
+}									\
+ATOMIC_FETCH_OP(op, asm_op, r)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	return __atomic_fetch_##op(i, v);				\
 }
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(or, or)
-ATOMIC_OP(xor, eor)
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(or, or)
+ATOMIC_OPS(xor, eor)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
 /*
@@ -87,6 +115,14 @@
 	return __atomic_add_return(i, v);
 }
 
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	if (IS_21BIT_CONST(i))
+		return __atomic_fetch_sub(-i, v);
+
+	return __atomic_fetch_add(i, v);
+}
+
 /*
  * atomic_sub_return - subtract the atomic variable
  * @i: integer value to subtract
@@ -102,6 +138,14 @@
 	return __atomic_add_return(-i, v);
 }
 
+static inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	if (IS_21BIT_CONST(i))
+		return __atomic_fetch_sub(i, v);
+
+	return __atomic_fetch_add(-i, v);
+}
+
 /*
  * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
diff --git a/arch/blackfin/include/asm/atomic.h b/arch/blackfin/include/asm/atomic.h
index 1c1c423..63c7dec 100644
--- a/arch/blackfin/include/asm/atomic.h
+++ b/arch/blackfin/include/asm/atomic.h
@@ -17,6 +17,7 @@
 
 asmlinkage int __raw_uncached_fetch_asm(const volatile int *ptr);
 asmlinkage int __raw_atomic_add_asm(volatile int *ptr, int value);
+asmlinkage int __raw_atomic_xadd_asm(volatile int *ptr, int value);
 
 asmlinkage int __raw_atomic_and_asm(volatile int *ptr, int value);
 asmlinkage int __raw_atomic_or_asm(volatile int *ptr, int value);
@@ -28,10 +29,17 @@
 #define atomic_add_return(i, v) __raw_atomic_add_asm(&(v)->counter, i)
 #define atomic_sub_return(i, v) __raw_atomic_add_asm(&(v)->counter, -(i))
 
+#define atomic_fetch_add(i, v) __raw_atomic_xadd_asm(&(v)->counter, i)
+#define atomic_fetch_sub(i, v) __raw_atomic_xadd_asm(&(v)->counter, -(i))
+
 #define atomic_or(i, v)  (void)__raw_atomic_or_asm(&(v)->counter, i)
 #define atomic_and(i, v) (void)__raw_atomic_and_asm(&(v)->counter, i)
 #define atomic_xor(i, v) (void)__raw_atomic_xor_asm(&(v)->counter, i)
 
+#define atomic_fetch_or(i, v)  __raw_atomic_or_asm(&(v)->counter, i)
+#define atomic_fetch_and(i, v) __raw_atomic_and_asm(&(v)->counter, i)
+#define atomic_fetch_xor(i, v) __raw_atomic_xor_asm(&(v)->counter, i)
+
 #endif
 
 #include <asm-generic/atomic.h>
diff --git a/arch/blackfin/kernel/bfin_ksyms.c b/arch/blackfin/kernel/bfin_ksyms.c
index a401c27..68096e8 100644
--- a/arch/blackfin/kernel/bfin_ksyms.c
+++ b/arch/blackfin/kernel/bfin_ksyms.c
@@ -84,6 +84,7 @@
 
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(__raw_atomic_add_asm);
+EXPORT_SYMBOL(__raw_atomic_xadd_asm);
 EXPORT_SYMBOL(__raw_atomic_and_asm);
 EXPORT_SYMBOL(__raw_atomic_or_asm);
 EXPORT_SYMBOL(__raw_atomic_xor_asm);
diff --git a/arch/blackfin/mach-bf561/atomic.S b/arch/blackfin/mach-bf561/atomic.S
index 26fccb5..1e2989c 100644
--- a/arch/blackfin/mach-bf561/atomic.S
+++ b/arch/blackfin/mach-bf561/atomic.S
@@ -607,6 +607,28 @@
 
 /*
  * r0 = ptr
+ * r1 = value
+ *
+ * ADD a signed value to a 32bit word and return the old value atomically.
+ * Clobbers: r3:0, p1:0
+ */
+ENTRY(___raw_atomic_xadd_asm)
+	p1 = r0;
+	r3 = r1;
+	[--sp] = rets;
+	call _get_core_lock;
+	r3 = [p1];
+	r2 = r3 + r2;
+	[p1] = r2;
+	r1 = p1;
+	call _put_core_lock;
+	r0 = r3;
+	rets = [sp++];
+	rts;
+ENDPROC(___raw_atomic_add_asm)
+
+/*
+ * r0 = ptr
  * r1 = mask
  *
  * AND the mask bits from a 32bit word and return the old 32bit value
@@ -618,10 +640,9 @@
 	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
-	r2 = [p1];
-	r3 = r2 & r3;
-	[p1] = r3;
-	r3 = r2;
+	r3 = [p1];
+	r2 = r2 & r3;
+	[p1] = r2;
 	r1 = p1;
 	call _put_core_lock;
 	r0 = r3;
@@ -642,10 +663,9 @@
 	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
-	r2 = [p1];
-	r3 = r2 | r3;
-	[p1] = r3;
-	r3 = r2;
+	r3 = [p1];
+	r2 = r2 | r3;
+	[p1] = r2;
 	r1 = p1;
 	call _put_core_lock;
 	r0 = r3;
@@ -666,10 +686,9 @@
 	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
-	r2 = [p1];
-	r3 = r2 ^ r3;
-	[p1] = r3;
-	r3 = r2;
+	r3 = [p1];
+	r2 = r2 ^ r3;
+	[p1] = r2;
 	r1 = p1;
 	call _put_core_lock;
 	r0 = r3;
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 64f02d4..1c2a5e2 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -60,16 +60,6 @@
 	return atomic_add_return(i, v) < 0;
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	atomic_add_return(i, v);
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	atomic_sub_return(i, v);
-}
-
 static inline void atomic_inc(atomic_t *v)
 {
 	atomic_inc_return(v);
@@ -136,16 +126,6 @@
 	return atomic64_add_return(i, v) < 0;
 }
 
-static inline void atomic64_add(long long i, atomic64_t *v)
-{
-	atomic64_add_return(i, v);
-}
-
-static inline void atomic64_sub(long long i, atomic64_t *v)
-{
-	atomic64_sub_return(i, v);
-}
-
 static inline void atomic64_inc(atomic64_t *v)
 {
 	atomic64_inc_return(v);
@@ -182,11 +162,19 @@
 }
 
 #define ATOMIC_OP(op)							\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	return __atomic32_fetch_##op(i, &v->counter);			\
+}									\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	(void)__atomic32_fetch_##op(i, &v->counter);			\
 }									\
 									\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{									\
+	return __atomic64_fetch_##op(i, &v->counter);			\
+}									\
 static inline void atomic64_##op(long long i, atomic64_t *v)		\
 {									\
 	(void)__atomic64_fetch_##op(i, &v->counter);			\
@@ -195,6 +183,8 @@
 ATOMIC_OP(or)
 ATOMIC_OP(and)
 ATOMIC_OP(xor)
+ATOMIC_OP(add)
+ATOMIC_OP(sub)
 
 #undef ATOMIC_OP
 
diff --git a/arch/frv/include/asm/atomic_defs.h b/arch/frv/include/asm/atomic_defs.h
index 36e126d..d4912c8 100644
--- a/arch/frv/include/asm/atomic_defs.h
+++ b/arch/frv/include/asm/atomic_defs.h
@@ -162,6 +162,8 @@
 ATOMIC_FETCH_OP(or)
 ATOMIC_FETCH_OP(and)
 ATOMIC_FETCH_OP(xor)
+ATOMIC_FETCH_OP(add)
+ATOMIC_FETCH_OP(sub)
 
 ATOMIC_OP_RETURN(add)
 ATOMIC_OP_RETURN(sub)
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 4435a44..349a47a 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -28,6 +28,19 @@
 	return ret;						\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{								\
+	h8300flags flags;					\
+	int ret;						\
+								\
+	flags = arch_local_irq_save();				\
+	ret = v->counter;					\
+	v->counter c_op i;					\
+	arch_local_irq_restore(flags);				\
+	return ret;						\
+}
+
 #define ATOMIC_OP(op, c_op)					\
 static inline void atomic_##op(int i, atomic_t *v)		\
 {								\
@@ -41,17 +54,21 @@
 ATOMIC_OP_RETURN(add, +=)
 ATOMIC_OP_RETURN(sub, -=)
 
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or,  |=)
-ATOMIC_OP(xor, ^=)
+#define ATOMIC_OPS(op, c_op)					\
+	ATOMIC_OP(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or,  |=)
+ATOMIC_OPS(xor, ^=)
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
+
+#undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_add(i, v)		(void)atomic_add_return(i, v)
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-#define atomic_sub(i, v)		(void)atomic_sub_return(i, v)
 #define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
 
 #define atomic_inc_return(v)		atomic_add_return(1, v)
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 55696c4..a62ba36 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -110,7 +110,7 @@
 	);								\
 }									\
 
-#define ATOMIC_OP_RETURN(op)							\
+#define ATOMIC_OP_RETURN(op)						\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	int output;							\
@@ -127,16 +127,37 @@
 	return output;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int output, val;						\
+									\
+	__asm__ __volatile__ (						\
+		"1:	%0 = memw_locked(%2);\n"			\
+		"	%1 = "#op "(%0,%3);\n"				\
+		"	memw_locked(%2,P3)=%1;\n"			\
+		"	if !P3 jump 1b;\n"				\
+		: "=&r" (output), "=&r" (val)				\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory", "p3"					\
+	);								\
+	return output;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 8dfb5f6..f565ad3 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -42,8 +42,27 @@
 	return new;							\
 }
 
-ATOMIC_OP(add, +)
-ATOMIC_OP(sub, -)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static __inline__ int							\
+ia64_atomic_fetch_##op (int i, atomic_t *v)				\
+{									\
+	__s32 old, new;							\
+	CMPXCHG_BUGCHECK_DECL						\
+									\
+	do {								\
+		CMPXCHG_BUGCHECK(v);					\
+		old = atomic_read(v);					\
+		new = old c_op i;					\
+	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic_t)) != old); \
+	return old;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(add, +)
+ATOMIC_OPS(sub, -)
 
 #define atomic_add_return(i,v)						\
 ({									\
@@ -69,14 +88,44 @@
 		: ia64_atomic_sub(__ia64_asr_i, v);			\
 })
 
-ATOMIC_OP(and, &)
-ATOMIC_OP(or, |)
-ATOMIC_OP(xor, ^)
+#define atomic_fetch_add(i,v)						\
+({									\
+	int __ia64_aar_i = (i);						\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
+	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
+	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
+	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
+		: ia64_atomic_fetch_add(__ia64_aar_i, v);		\
+})
 
-#define atomic_and(i,v)	(void)ia64_atomic_and(i,v)
-#define atomic_or(i,v)	(void)ia64_atomic_or(i,v)
-#define atomic_xor(i,v)	(void)ia64_atomic_xor(i,v)
+#define atomic_fetch_sub(i,v)						\
+({									\
+	int __ia64_asr_i = (i);						\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
+	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
+	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
+	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
+		: ia64_atomic_fetch_sub(__ia64_asr_i, v);		\
+})
 
+ATOMIC_FETCH_OP(and, &)
+ATOMIC_FETCH_OP(or, |)
+ATOMIC_FETCH_OP(xor, ^)
+
+#define atomic_and(i,v)	(void)ia64_atomic_fetch_and(i,v)
+#define atomic_or(i,v)	(void)ia64_atomic_fetch_or(i,v)
+#define atomic_xor(i,v)	(void)ia64_atomic_fetch_xor(i,v)
+
+#define atomic_fetch_and(i,v)	ia64_atomic_fetch_and(i,v)
+#define atomic_fetch_or(i,v)	ia64_atomic_fetch_or(i,v)
+#define atomic_fetch_xor(i,v)	ia64_atomic_fetch_xor(i,v)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP
 
 #define ATOMIC64_OP(op, c_op)						\
@@ -94,8 +143,27 @@
 	return new;							\
 }
 
-ATOMIC64_OP(add, +)
-ATOMIC64_OP(sub, -)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static __inline__ long							\
+ia64_atomic64_fetch_##op (__s64 i, atomic64_t *v)			\
+{									\
+	__s64 old, new;							\
+	CMPXCHG_BUGCHECK_DECL						\
+									\
+	do {								\
+		CMPXCHG_BUGCHECK(v);					\
+		old = atomic64_read(v);					\
+		new = old c_op i;					\
+	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic64_t)) != old); \
+	return old;							\
+}
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(add, +)
+ATOMIC64_OPS(sub, -)
 
 #define atomic64_add_return(i,v)					\
 ({									\
@@ -121,14 +189,44 @@
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
 
-ATOMIC64_OP(and, &)
-ATOMIC64_OP(or, |)
-ATOMIC64_OP(xor, ^)
+#define atomic64_fetch_add(i,v)						\
+({									\
+	long __ia64_aar_i = (i);					\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
+	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
+	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
+	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
+		: ia64_atomic64_fetch_add(__ia64_aar_i, v);		\
+})
 
-#define atomic64_and(i,v)	(void)ia64_atomic64_and(i,v)
-#define atomic64_or(i,v)	(void)ia64_atomic64_or(i,v)
-#define atomic64_xor(i,v)	(void)ia64_atomic64_xor(i,v)
+#define atomic64_fetch_sub(i,v)						\
+({									\
+	long __ia64_asr_i = (i);					\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
+	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
+	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
+	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
+		: ia64_atomic64_fetch_sub(__ia64_asr_i, v);		\
+})
 
+ATOMIC64_FETCH_OP(and, &)
+ATOMIC64_FETCH_OP(or, |)
+ATOMIC64_FETCH_OP(xor, ^)
+
+#define atomic64_and(i,v)	(void)ia64_atomic64_fetch_and(i,v)
+#define atomic64_or(i,v)	(void)ia64_atomic64_fetch_or(i,v)
+#define atomic64_xor(i,v)	(void)ia64_atomic64_fetch_xor(i,v)
+
+#define atomic64_fetch_and(i,v)	ia64_atomic64_fetch_and(i,v)
+#define atomic64_fetch_or(i,v)	ia64_atomic64_fetch_or(i,v)
+#define atomic64_fetch_xor(i,v)	ia64_atomic64_fetch_xor(i,v)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index ea35160..640cc1c 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -89,16 +89,44 @@
 	return result;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static __inline__ int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int result, val;						\
+									\
+	local_irq_save(flags);						\
+	__asm__ __volatile__ (						\
+		"# atomic_fetch_" #op "		\n\t"			\
+		DCACHE_CLEAR("%0", "r4", "%2")				\
+		M32R_LOCK" %1, @%2;		\n\t"			\
+		"mv %0, %1			\n\t" 			\
+		#op " %1, %3;			\n\t"			\
+		M32R_UNLOCK" %1, @%2;		\n\t"			\
+		: "=&r" (result), "=&r" (val)				\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory"						\
+		__ATOMIC_CLOBBER					\
+	);								\
+	local_irq_restore(flags);					\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 4858178..cf4c3a7 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -53,6 +53,21 @@
 	return t;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int t, tmp;							\
+									\
+	__asm__ __volatile__(						\
+			"1:	movel %2,%1\n"				\
+			"	" #asm_op "l %3,%1\n"			\
+			"	casl %2,%1,%0\n"			\
+			"	jne 1b"					\
+			: "+m" (*v), "=&d" (t), "=&d" (tmp)		\
+			: "g" (i), "2" (atomic_read(v)));		\
+	return tmp;							\
+}
+
 #else
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
@@ -68,20 +83,41 @@
 	return t;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t * v)		\
+{									\
+	unsigned long flags;						\
+	int t;								\
+									\
+	local_irq_save(flags);						\
+	t = v->counter;							\
+	v->counter c_op i;						\
+	local_irq_restore(flags);					\
+									\
+	return t;							\
+}
+
 #endif /* CONFIG_RMW_INSNS */
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, eor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, eor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index 88fa25f..def2c64 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -69,16 +69,44 @@
 	return result;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int result, temp;						\
+									\
+	smp_mb();							\
+									\
+	asm volatile (							\
+		"1:	LNKGETD %1, [%2]\n"				\
+		"	" #op "	%0, %1, %3\n"				\
+		"	LNKSETD [%2], %0\n"				\
+		"	DEFR	%0, TXSTAT\n"				\
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"		\
+		"	CMPT	%0, #HI(0x02000000)\n"			\
+		"	BNZ 1b\n"					\
+		: "=&d" (temp), "=&d" (result)				\
+		: "da" (&v->counter), "bd" (i)				\
+		: "cc");						\
+									\
+	smp_mb();							\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index 0295d9b..6c1380a 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -64,15 +64,40 @@
 	return result;							\
 }
 
-#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long result;						\
+	unsigned long flags;						\
+									\
+	__global_lock1(flags);						\
+	result = v->counter;						\
+	fence();							\
+	v->counter c_op i;						\
+	__global_unlock1(flags);					\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_OP_RETURN(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or, |=)
+ATOMIC_OPS(xor, ^=)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 835b402..0ab176b 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -66,7 +66,7 @@
 			"	" #asm_op " %0, %2			\n"   \
 			"	sc	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)  \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -79,12 +79,10 @@
 }
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
+static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	smp_mb__before_llsc();						      \
-									      \
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
 		int temp;						      \
 									      \
@@ -125,23 +123,84 @@
 		raw_local_irq_restore(flags);				      \
 	}								      \
 									      \
-	smp_llsc_mb();							      \
+	return result;							      \
+}
+
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				      \
+static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
+{									      \
+	int result;							      \
+									      \
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+		int temp;						      \
+									      \
+		__asm__ __volatile__(					      \
+		"	.set	arch=r4000				\n"   \
+		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
+		"	" #asm_op " %0, %1, %3				\n"   \
+		"	sc	%0, %2					\n"   \
+		"	beqzl	%0, 1b					\n"   \
+		"	move	%0, %1					\n"   \
+		"	.set	mips0					\n"   \
+		: "=&r" (result), "=&r" (temp),				      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
+		: "Ir" (i));						      \
+	} else if (kernel_uses_llsc) {					      \
+		int temp;						      \
+									      \
+		do {							      \
+			__asm__ __volatile__(				      \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
+			"	ll	%1, %2	# atomic_fetch_" #op "	\n"   \
+			"	" #asm_op " %0, %1, %3			\n"   \
+			"	sc	%0, %2				\n"   \
+			"	.set	mips0				\n"   \
+			: "=&r" (result), "=&r" (temp),			      \
+			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i));					      \
+		} while (unlikely(!result));				      \
+									      \
+		result = temp;						      \
+	} else {							      \
+		unsigned long flags;					      \
+									      \
+		raw_local_irq_save(flags);				      \
+		result = v->counter;					      \
+		v->counter c_op i;					      \
+		raw_local_irq_restore(flags);				      \
+	}								      \
 									      \
 	return result;							      \
 }
 
 #define ATOMIC_OPS(op, c_op, asm_op)					      \
 	ATOMIC_OP(op, c_op, asm_op)					      \
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, addu)
 ATOMIC_OPS(sub, -=, subu)
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, xor)
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					      \
+	ATOMIC_OP(op, c_op, asm_op)					      \
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -362,12 +421,10 @@
 }
 
 #define ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
+static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 {									      \
 	long result;							      \
 									      \
-	smp_mb__before_llsc();						      \
-									      \
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
 		long temp;						      \
 									      \
@@ -409,22 +466,85 @@
 		raw_local_irq_restore(flags);				      \
 	}								      \
 									      \
-	smp_llsc_mb();							      \
+	return result;							      \
+}
+
+#define ATOMIC64_FETCH_OP(op, c_op, asm_op)				      \
+static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
+{									      \
+	long result;							      \
+									      \
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+		long temp;						      \
+									      \
+		__asm__ __volatile__(					      \
+		"	.set	arch=r4000				\n"   \
+		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
+		"	" #asm_op " %0, %1, %3				\n"   \
+		"	scd	%0, %2					\n"   \
+		"	beqzl	%0, 1b					\n"   \
+		"	move	%0, %1					\n"   \
+		"	.set	mips0					\n"   \
+		: "=&r" (result), "=&r" (temp),				      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
+		: "Ir" (i));						      \
+	} else if (kernel_uses_llsc) {					      \
+		long temp;						      \
+									      \
+		do {							      \
+			__asm__ __volatile__(				      \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
+			"	lld	%1, %2	# atomic64_fetch_" #op "\n"   \
+			"	" #asm_op " %0, %1, %3			\n"   \
+			"	scd	%0, %2				\n"   \
+			"	.set	mips0				\n"   \
+			: "=&r" (result), "=&r" (temp),			      \
+			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
+			: "memory");					      \
+		} while (unlikely(!result));				      \
+									      \
+		result = temp;						      \
+	} else {							      \
+		unsigned long flags;					      \
+									      \
+		raw_local_irq_save(flags);				      \
+		result = v->counter;					      \
+		v->counter c_op i;					      \
+		raw_local_irq_restore(flags);				      \
+	}								      \
 									      \
 	return result;							      \
 }
 
 #define ATOMIC64_OPS(op, c_op, asm_op)					      \
 	ATOMIC64_OP(op, c_op, asm_op)					      \
-	ATOMIC64_OP_RETURN(op, c_op, asm_op)
+	ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
+	ATOMIC64_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC64_OPS(add, +=, daddu)
 ATOMIC64_OPS(sub, -=, dsubu)
-ATOMIC64_OP(and, &=, and)
-ATOMIC64_OP(or, |=, or)
-ATOMIC64_OP(xor, ^=, xor)
+
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op, asm_op)					      \
+	ATOMIC64_OP(op, c_op, asm_op)					      \
+	ATOMIC64_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC64_OPS(and, &=, and)
+ATOMIC64_OPS(or, |=, or)
+ATOMIC64_OPS(xor, ^=, xor)
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index ce318d5..36389ef 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -84,16 +84,41 @@
 	return retval;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int retval, status;						\
+									\
+	asm volatile(							\
+		"1:	mov	%4,(_AAR,%3)	\n"			\
+		"	mov	(_ADR,%3),%1	\n"			\
+		"	mov	%1,%0		\n"			\
+		"	" #op "	%5,%0		\n"			\
+		"	mov	%0,(_ADR,%3)	\n"			\
+		"	mov	(_ADR,%3),%0	\n"	/* flush */	\
+		"	mov	(_ASR,%3),%0	\n"			\
+		"	or	%0,%0		\n"			\
+		"	bne	1b		\n"			\
+		: "=&r"(status), "=&r"(retval), "=m"(v->counter)	\
+		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(&v->counter), "r"(i)	\
+		: "memory", "cc");					\
+	return retval;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 1d10999..5394b9c 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -121,16 +121,39 @@
 	return ret;							\
 }
 
-#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static __inline__ int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	ret = v->counter;						\
+	v->counter c_op i;						\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+									\
+	return ret;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_OP_RETURN(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
 
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or, |=)
+ATOMIC_OPS(xor, ^=)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -185,15 +208,39 @@
 	return ret;							\
 }
 
-#define ATOMIC64_OPS(op, c_op) ATOMIC64_OP(op, c_op) ATOMIC64_OP_RETURN(op, c_op)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static __inline__ s64 atomic64_fetch_##op(s64 i, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	s64 ret;							\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	ret = v->counter;						\
+	v->counter c_op i;						\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+									\
+	return ret;							\
+}
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_OP_RETURN(op, c_op)					\
+	ATOMIC64_FETCH_OP(op, c_op)
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
-ATOMIC64_OP(and, &=)
-ATOMIC64_OP(or, |=)
-ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &=)
+ATOMIC64_OPS(or, |=)
+ATOMIC64_OPS(xor, ^=)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index ae0751e..f08d567 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -78,21 +78,53 @@
 	return t;							\
 }
 
+#define ATOMIC_FETCH_OP_RELAXED(op, asm_op)				\
+static inline int atomic_fetch_##op##_relaxed(int a, atomic_t *v)	\
+{									\
+	int res, t;							\
+									\
+	__asm__ __volatile__(						\
+"1:	lwarx	%0,0,%4		# atomic_fetch_" #op "_relaxed\n"	\
+	#asm_op " %1,%3,%0\n"						\
+	PPC405_ERR77(0, %4)						\
+"	stwcx.	%1,0,%4\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+									\
+	return res;							\
+}
+
 #define ATOMIC_OPS(op, asm_op)						\
 	ATOMIC_OP(op, asm_op)						\
-	ATOMIC_OP_RETURN_RELAXED(op, asm_op)
+	ATOMIC_OP_RETURN_RELAXED(op, asm_op)				\
+	ATOMIC_FETCH_OP_RELAXED(op, asm_op)
 
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(or, or)
-ATOMIC_OP(xor, xor)
-
 #define atomic_add_return_relaxed atomic_add_return_relaxed
 #define atomic_sub_return_relaxed atomic_sub_return_relaxed
 
+#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
+
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_FETCH_OP_RELAXED(op, asm_op)
+
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(or, or)
+ATOMIC_OPS(xor, xor)
+
+#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
+#define atomic_fetch_or_relaxed  atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP_RELAXED
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
@@ -329,20 +361,53 @@
 	return t;							\
 }
 
+#define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
+static inline long							\
+atomic64_fetch_##op##_relaxed(long a, atomic64_t *v)			\
+{									\
+	long res, t;							\
+									\
+	__asm__ __volatile__(						\
+"1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
+	#asm_op " %1,%3,%0\n"						\
+"	stdcx.	%1,0,%4\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+									\
+	return res;							\
+}
+
 #define ATOMIC64_OPS(op, asm_op)					\
 	ATOMIC64_OP(op, asm_op)						\
-	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)
+	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
+	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(or, or)
-ATOMIC64_OP(xor, xor)
 
 #define atomic64_add_return_relaxed atomic64_add_return_relaxed
 #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
 
+#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)
+
+ATOMIC64_OPS(and, and)
+ATOMIC64_OPS(or, or)
+ATOMIC64_OPS(xor, xor)
+
+#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
+#define atomic64_fetch_or_relaxed  atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
+
 #undef ATOPIC64_OPS
+#undef ATOMIC64_FETCH_OP_RELAXED
 #undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 911064a..d28cc2f 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -93,6 +93,11 @@
 	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i;
 }
 
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER);
+}
+
 static inline void atomic_add(int i, atomic_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
@@ -114,22 +119,27 @@
 #define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
+#define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
 #define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
 #define atomic_dec(_v)			atomic_sub(1, _v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 #define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
-#define ATOMIC_OP(op, OP)						\
+#define ATOMIC_OPS(op, OP)						\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	__ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER);	\
+}									\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	return __ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_BARRIER);	\
 }
 
-ATOMIC_OP(and, AND)
-ATOMIC_OP(or, OR)
-ATOMIC_OP(xor, XOR)
+ATOMIC_OPS(and, AND)
+ATOMIC_OPS(or, OR)
+ATOMIC_OPS(xor, XOR)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -236,6 +246,11 @@
 	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i;
 }
 
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+{
+	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER);
+}
+
 static inline void atomic64_add(long long i, atomic64_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
@@ -264,17 +279,21 @@
 	return old;
 }
 
-#define ATOMIC64_OP(op, OP)						\
+#define ATOMIC64_OPS(op, OP)						\
 static inline void atomic64_##op(long i, atomic64_t *v)			\
 {									\
 	__ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER);	\
+}									\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	return __ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_BARRIER); \
 }
 
-ATOMIC64_OP(and, AND)
-ATOMIC64_OP(or, OR)
-ATOMIC64_OP(xor, XOR)
+ATOMIC64_OPS(and, AND)
+ATOMIC64_OPS(or, OR)
+ATOMIC64_OPS(xor, XOR)
 
-#undef ATOMIC64_OP
+#undef ATOMIC64_OPS
 #undef __ATOMIC64_LOOP
 
 static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
@@ -315,6 +334,7 @@
 #define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
 #define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long long)(_i), _v)
+#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long long)(_i), _v)
 #define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
 #define atomic64_dec(_v)		atomic64_sub(1, _v)
diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
index b94df40..d755e96 100644
--- a/arch/sh/include/asm/atomic-grb.h
+++ b/arch/sh/include/asm/atomic-grb.h
@@ -43,16 +43,42 @@
 	return tmp;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int res, tmp;							\
+									\
+	__asm__ __volatile__ (						\
+		"   .align 2              \n\t"				\
+		"   mova    1f,   r0      \n\t" /* r0 = end point */	\
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */	\
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */	\
+		"   mov.l  @%2,   %0      \n\t" /* load old value */	\
+		"   mov     %0,   %1      \n\t" /* save old value */	\
+		" " #op "   %3,   %0      \n\t" /* $op */		\
+		"   mov.l   %0,   @%2     \n\t" /* store new value */	\
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */		\
+		: "=&r" (tmp), "=&r" (res), "+r"  (v)			\
+		: "r"   (i)						\
+		: "memory" , "r0", "r1");				\
+									\
+	return res;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 23fcdad..8e2da5f 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -33,15 +33,38 @@
 	return temp;							\
 }
 
-#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long temp, flags;					\
+									\
+	raw_local_irq_save(flags);					\
+	temp = v->counter;						\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return temp;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_OP_RETURN(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or, |=)
+ATOMIC_OPS(xor, ^=)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index 33d34b1..caea2c4 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -48,15 +48,39 @@
 	return temp;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long res, temp;					\
+									\
+	__asm__ __volatile__ (						\
+"1:	movli.l @%3, %0		! atomic_fetch_" #op "	\n"		\
+"	mov %0, %1					\n"		\
+"	" #op "	%2, %0					\n"		\
+"	movco.l	%0, @%3					\n"		\
+"	bf	1b					\n"		\
+"	synco						\n"		\
+	: "=&z" (temp), "=&z" (res)					\
+	: "r" (i), "r" (&v->counter)					\
+	: "t");								\
+									\
+	return res;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7dcbebb..ee3f11c 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,9 +20,10 @@
 #define ATOMIC_INIT(i)  { (i) }
 
 int atomic_add_return(int, atomic_t *);
-void atomic_and(int, atomic_t *);
-void atomic_or(int, atomic_t *);
-void atomic_xor(int, atomic_t *);
+int atomic_fetch_add(int, atomic_t *);
+int atomic_fetch_and(int, atomic_t *);
+int atomic_fetch_or(int, atomic_t *);
+int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
@@ -35,7 +36,13 @@
 #define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
 #define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
+#define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
+#define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
+#define atomic_xor(i, v)	((void)atomic_fetch_xor((i), (v)))
+
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
+#define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
+
 #define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
 #define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f2fbf9e..24827a3 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -28,16 +28,24 @@
 int atomic_##op##_return(int, atomic_t *);				\
 long atomic64_##op##_return(long, atomic64_t *);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+int atomic_fetch_##op(int, atomic_t *);					\
+long atomic64_fetch_##op(long, atomic64_t *);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index b9d63c0..2c37332 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,6 +27,21 @@
 
 #endif /* SMP */
 
+#define ATOMIC_FETCH_OP(op, c_op)					\
+int atomic_fetch_##op(int i, atomic_t *v)				\
+{									\
+	int ret;							\
+	unsigned long flags;						\
+	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
+									\
+	ret = v->counter;						\
+	v->counter c_op i;						\
+									\
+	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
+	return ret;							\
+}									\
+EXPORT_SYMBOL(atomic_fetch_##op);
+
 #define ATOMIC_OP_RETURN(op, c_op)					\
 int atomic_##op##_return(int i, atomic_t *v)				\
 {									\
@@ -41,25 +56,15 @@
 }									\
 EXPORT_SYMBOL(atomic_##op##_return);
 
-#define ATOMIC_OP(op, c_op)						\
-void atomic_##op(int i, atomic_t *v)					\
-{									\
-	unsigned long flags;						\
-	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
-									\
-	v->counter c_op i;						\
-									\
-	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
-}									\
-EXPORT_SYMBOL(atomic_##op);
-
 ATOMIC_OP_RETURN(add, +=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
 
+ATOMIC_FETCH_OP(add, +=)
+ATOMIC_FETCH_OP(and, &=)
+ATOMIC_FETCH_OP(or, |=)
+ATOMIC_FETCH_OP(xor, ^=)
+
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
 
 int atomic_xchg(atomic_t *v, int new)
 {
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index d6b0363..a5c5a02 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -9,10 +9,11 @@
 
 	.text
 
-	/* Two versions of the atomic routines, one that
+	/* Three versions of the atomic routines, one that
 	 * does not return a value and does not perform
-	 * memory barriers, and a second which returns
-	 * a value and does the barriers.
+	 * memory barriers, and a two which return
+	 * a value, the new and old value resp. and does the
+	 * barriers.
 	 */
 
 #define ATOMIC_OP(op)							\
@@ -43,15 +44,34 @@
 2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
 ENDPROC(atomic_##op##_return);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */	\
+	BACKOFF_SETUP(%o2);						\
+1:	lduw	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	cas	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 sra	%g1, 0, %o0;						\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -83,15 +103,34 @@
 2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
 ENDPROC(atomic64_##op##_return);
 
-#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op)						\
+ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */	\
+	BACKOFF_SETUP(%o2);						\
+1:	ldx	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	casx	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 mov	%g1, %o0;						\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic64_fetch_##op);
+
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
 
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 8eb454c..de5e978 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -107,15 +107,24 @@
 EXPORT_SYMBOL(atomic_##op##_return);					\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+EXPORT_SYMBOL(atomic_fetch_##op);					\
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index 9fc0107..8dda3c8 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -46,6 +46,8 @@
  */
 #define atomic_sub_return(i, v)		atomic_add_return((int)(-(i)), (v))
 
+#define atomic_fetch_sub(i, v)		atomic_fetch_add(-(int)(i), (v))
+
 /**
  * atomic_sub - subtract integer from atomic variable
  * @i: integer value to subtract
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index d320ce2..a937742 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -34,18 +34,29 @@
 	_atomic_xchg_add(&v->counter, i);
 }
 
-#define ATOMIC_OP(op)							\
-unsigned long _atomic_##op(volatile unsigned long *p, unsigned long mask); \
+#define ATOMIC_OPS(op)							\
+unsigned long _atomic_fetch_##op(volatile unsigned long *p, unsigned long mask); \
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	_atomic_##op((unsigned long *)&v->counter, i);			\
+	_atomic_fetch_##op((unsigned long *)&v->counter, i);		\
+}									\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	smp_mb();							\
+	return _atomic_fetch_##op((unsigned long *)&v->counter, i);	\
 }
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	smp_mb();
+	return _atomic_xchg_add(&v->counter, i);
+}
 
 /**
  * atomic_add_return - add integer and return
@@ -126,16 +137,29 @@
 	_atomic64_xchg_add(&v->counter, i);
 }
 
-#define ATOMIC64_OP(op)						\
-long long _atomic64_##op(long long *v, long long n);		\
+#define ATOMIC64_OPS(op)					\
+long long _atomic64_fetch_##op(long long *v, long long n);	\
 static inline void atomic64_##op(long long i, atomic64_t *v)	\
 {								\
-	_atomic64_##op(&v->counter, i);				\
+	_atomic64_fetch_##op(&v->counter, i);			\
+}								\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{								\
+	smp_mb();						\
+	return _atomic64_fetch_##op(&v->counter, i);		\
 }
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+{
+	smp_mb();
+	return _atomic64_xchg_add(&v->counter, i);
+}
 
 /**
  * atomic64_add_return - add integer and return
@@ -186,6 +210,7 @@
 #define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
@@ -193,7 +218,6 @@
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
-
 #endif /* !__ASSEMBLY__ */
 
 /*
@@ -242,16 +266,16 @@
 	unsigned long val;
 	int err;
 };
-extern struct __get_user __atomic_cmpxchg(volatile int *p,
+extern struct __get_user __atomic32_cmpxchg(volatile int *p,
 					  int *lock, int o, int n);
-extern struct __get_user __atomic_xchg(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xchg_add(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
+extern struct __get_user __atomic32_xchg(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_xchg_add(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_xchg_add_unless(volatile int *p,
 						  int *lock, int o, int n);
-extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_and(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_or(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_and(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_andn(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_xor(volatile int *p, int *lock, int n);
 extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
 					long long o, long long n);
 extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
@@ -259,9 +283,9 @@
 					long long n);
 extern long long __atomic64_xchg_add_unless(volatile long long *p,
 					int *lock, long long o, long long n);
-extern long long __atomic64_and(volatile long long *p, int *lock, long long n);
-extern long long __atomic64_or(volatile long long *p, int *lock, long long n);
-extern long long __atomic64_xor(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_and(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_or(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_xor(volatile long long *p, int *lock, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index b0531a6..4cefa0c 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -32,11 +32,6 @@
  * on any routine which updates memory and returns a value.
  */
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	__insn_fetchadd4((void *)&v->counter, i);
-}
-
 /*
  * Note a subtlety of the locking here.  We are required to provide a
  * full memory barrier before and after the operation.  However, we
@@ -59,28 +54,39 @@
 	return val;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#define ATOMIC_OPS(op)							\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int val;							\
+	smp_mb();							\
+	val = __insn_fetch##op##4((void *)&v->counter, i);		\
+	smp_mb();							\
+	return val;							\
+}									\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__insn_fetch##op##4((void *)&v->counter, i);			\
+}
+
+ATOMIC_OPS(add)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+
+#undef ATOMIC_OPS
+
+static inline int atomic_fetch_xor(int i, atomic_t *v)
 {
 	int guess, oldval = v->counter;
+	smp_mb();
 	do {
-		if (oldval == u)
-			break;
 		guess = oldval;
-		oldval = cmpxchg(&v->counter, guess, guess + a);
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch4(&v->counter, guess ^ i);
 	} while (guess != oldval);
+	smp_mb();
 	return oldval;
 }
 
-static inline void atomic_and(int i, atomic_t *v)
-{
-	__insn_fetchand4((void *)&v->counter, i);
-}
-
-static inline void atomic_or(int i, atomic_t *v)
-{
-	__insn_fetchor4((void *)&v->counter, i);
-}
-
 static inline void atomic_xor(int i, atomic_t *v)
 {
 	int guess, oldval = v->counter;
@@ -91,6 +97,18 @@
 	} while (guess != oldval);
 }
 
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int guess, oldval = v->counter;
+	do {
+		if (oldval == u)
+			break;
+		guess = oldval;
+		oldval = cmpxchg(&v->counter, guess, guess + a);
+	} while (guess != oldval);
+	return oldval;
+}
+
 /* Now the true 64-bit operations. */
 
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -98,11 +116,6 @@
 #define atomic64_read(v)	READ_ONCE((v)->counter)
 #define atomic64_set(v, i)	WRITE_ONCE((v)->counter, (i))
 
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-	__insn_fetchadd((void *)&v->counter, i);
-}
-
 static inline long atomic64_add_return(long i, atomic64_t *v)
 {
 	int val;
@@ -112,6 +125,49 @@
 	return val;
 }
 
+#define ATOMIC64_OPS(op)						\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	long val;							\
+	smp_mb();							\
+	val = __insn_fetch##op((void *)&v->counter, i);			\
+	smp_mb();							\
+	return val;							\
+}									\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	__insn_fetch##op((void *)&v->counter, i);			\
+}
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+
+#undef ATOMIC64_OPS
+
+static inline long atomic64_fetch_xor(long i, atomic64_t *v)
+{
+	long guess, oldval = v->counter;
+	smp_mb();
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch(&v->counter, guess ^ i);
+	} while (guess != oldval);
+	smp_mb();
+	return oldval;
+}
+
+static inline void atomic64_xor(long i, atomic64_t *v)
+{
+	long guess, oldval = v->counter;
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch(&v->counter, guess ^ i);
+	} while (guess != oldval);
+}
+
 static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 {
 	long guess, oldval = v->counter;
@@ -124,27 +180,8 @@
 	return oldval != u;
 }
 
-static inline void atomic64_and(long i, atomic64_t *v)
-{
-	__insn_fetchand((void *)&v->counter, i);
-}
-
-static inline void atomic64_or(long i, atomic64_t *v)
-{
-	__insn_fetchor((void *)&v->counter, i);
-}
-
-static inline void atomic64_xor(long i, atomic64_t *v)
-{
-	long guess, oldval = v->counter;
-	do {
-		guess = oldval;
-		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
-		oldval = __insn_cmpexch(&v->counter, guess ^ i);
-	} while (guess != oldval);
-}
-
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
diff --git a/arch/tile/include/asm/bitops_32.h b/arch/tile/include/asm/bitops_32.h
index bbf7b66..d1406a9 100644
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -19,9 +19,9 @@
 #include <asm/barrier.h>
 
 /* Tile-specific routines to support <asm/bitops.h>. */
-unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask);
-unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask);
-unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_or(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_andn(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_xor(volatile unsigned long *p, unsigned long mask);
 
 /**
  * set_bit - Atomically set a bit in memory
@@ -35,7 +35,7 @@
  */
 static inline void set_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_or(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_or(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -54,7 +54,7 @@
  */
 static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_andn(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_andn(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -69,7 +69,7 @@
  */
 static inline void change_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_xor(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_xor(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -85,7 +85,7 @@
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_or(addr, mask) & mask) != 0;
+	return (_atomic_fetch_or(addr, mask) & mask) != 0;
 }
 
 /**
@@ -101,7 +101,7 @@
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_andn(addr, mask) & mask) != 0;
+	return (_atomic_fetch_andn(addr, mask) & mask) != 0;
 }
 
 /**
@@ -118,7 +118,7 @@
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_xor(addr, mask) & mask) != 0;
+	return (_atomic_fetch_xor(addr, mask) & mask) != 0;
 }
 
 #include <asm-generic/bitops/ext2-atomic.h>
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index 1a6ef1b..e64a1b7 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -80,16 +80,16 @@
 		ret = gu.err;						\
 	}
 
-#define __futex_set() __futex_call(__atomic_xchg)
-#define __futex_add() __futex_call(__atomic_xchg_add)
-#define __futex_or() __futex_call(__atomic_or)
-#define __futex_andn() __futex_call(__atomic_andn)
-#define __futex_xor() __futex_call(__atomic_xor)
+#define __futex_set() __futex_call(__atomic32_xchg)
+#define __futex_add() __futex_call(__atomic32_xchg_add)
+#define __futex_or() __futex_call(__atomic32_fetch_or)
+#define __futex_andn() __futex_call(__atomic32_fetch_andn)
+#define __futex_xor() __futex_call(__atomic32_fetch_xor)
 
 #define __futex_cmpxchg()						\
 	{								\
-		struct __get_user gu = __atomic_cmpxchg((u32 __force *)uaddr, \
-							lock, oldval, oparg); \
+		struct __get_user gu = __atomic32_cmpxchg((u32 __force *)uaddr, \
+							  lock, oldval, oparg); \
 		val = gu.val;						\
 		ret = gu.err;						\
 	}
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index 298df1e..f812880 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -61,13 +61,13 @@
 
 int _atomic_xchg(int *v, int n)
 {
-	return __atomic_xchg(v, __atomic_setup(v), n).val;
+	return __atomic32_xchg(v, __atomic_setup(v), n).val;
 }
 EXPORT_SYMBOL(_atomic_xchg);
 
 int _atomic_xchg_add(int *v, int i)
 {
-	return __atomic_xchg_add(v, __atomic_setup(v), i).val;
+	return __atomic32_xchg_add(v, __atomic_setup(v), i).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add);
 
@@ -78,39 +78,39 @@
 	 * to use the first argument consistently as the "old value"
 	 * in the assembly, as is done for _atomic_cmpxchg().
 	 */
-	return __atomic_xchg_add_unless(v, __atomic_setup(v), u, a).val;
+	return __atomic32_xchg_add_unless(v, __atomic_setup(v), u, a).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add_unless);
 
 int _atomic_cmpxchg(int *v, int o, int n)
 {
-	return __atomic_cmpxchg(v, __atomic_setup(v), o, n).val;
+	return __atomic32_cmpxchg(v, __atomic_setup(v), o, n).val;
 }
 EXPORT_SYMBOL(_atomic_cmpxchg);
 
-unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_or(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_or((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_or((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_or);
+EXPORT_SYMBOL(_atomic_fetch_or);
 
-unsigned long _atomic_and(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_and(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_and((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_and((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_and);
+EXPORT_SYMBOL(_atomic_fetch_and);
 
-unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_andn(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_andn((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_andn((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_andn);
+EXPORT_SYMBOL(_atomic_fetch_andn);
 
-unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_xor(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_xor((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_xor((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_xor);
+EXPORT_SYMBOL(_atomic_fetch_xor);
 
 
 long long _atomic64_xchg(long long *v, long long n)
@@ -142,23 +142,23 @@
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
-long long _atomic64_and(long long *v, long long n)
+long long _atomic64_fetch_and(long long *v, long long n)
 {
-	return __atomic64_and(v, __atomic_setup(v), n);
+	return __atomic64_fetch_and(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_and);
+EXPORT_SYMBOL(_atomic64_fetch_and);
 
-long long _atomic64_or(long long *v, long long n)
+long long _atomic64_fetch_or(long long *v, long long n)
 {
-	return __atomic64_or(v, __atomic_setup(v), n);
+	return __atomic64_fetch_or(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_or);
+EXPORT_SYMBOL(_atomic64_fetch_or);
 
-long long _atomic64_xor(long long *v, long long n)
+long long _atomic64_fetch_xor(long long *v, long long n)
 {
-	return __atomic64_xor(v, __atomic_setup(v), n);
+	return __atomic64_fetch_xor(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_xor);
+EXPORT_SYMBOL(_atomic64_fetch_xor);
 
 /*
  * If any of the atomic or futex routines hit a bad address (not in
diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index f611265..1a70e6c 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -172,15 +172,20 @@
 	.endif
 	.endm
 
-atomic_op _cmpxchg, 32, "seq r26, r22, r2; { bbns r26, 3f; move r24, r3 }"
-atomic_op _xchg, 32, "move r24, r2"
-atomic_op _xchg_add, 32, "add r24, r22, r2"
-atomic_op _xchg_add_unless, 32, \
+
+/*
+ * Use __atomic32 prefix to avoid collisions with GCC builtin __atomic functions.
+ */
+
+atomic_op 32_cmpxchg, 32, "seq r26, r22, r2; { bbns r26, 3f; move r24, r3 }"
+atomic_op 32_xchg, 32, "move r24, r2"
+atomic_op 32_xchg_add, 32, "add r24, r22, r2"
+atomic_op 32_xchg_add_unless, 32, \
 	"sne r26, r22, r2; { bbns r26, 3f; add r24, r22, r3 }"
-atomic_op _or, 32, "or r24, r22, r2"
-atomic_op _and, 32, "and r24, r22, r2"
-atomic_op _andn, 32, "nor r2, r2, zero; and r24, r22, r2"
-atomic_op _xor, 32, "xor r24, r22, r2"
+atomic_op 32_fetch_or, 32, "or r24, r22, r2"
+atomic_op 32_fetch_and, 32, "and r24, r22, r2"
+atomic_op 32_fetch_andn, 32, "nor r2, r2, zero; and r24, r22, r2"
+atomic_op 32_fetch_xor, 32, "xor r24, r22, r2"
 
 atomic_op 64_cmpxchg, 64, "{ seq r26, r22, r2; seq r27, r23, r3 }; \
 	{ bbns r26, 3f; move r24, r4 }; { bbns r27, 3f; move r25, r5 }"
@@ -192,9 +197,9 @@
 	{ bbns r26, 3f; add r24, r22, r4 }; \
 	{ bbns r27, 3f; add r25, r23, r5 }; \
 	slt_u r26, r24, r22; add r25, r25, r26"
-atomic_op 64_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
-atomic_op 64_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
-atomic_op 64_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
+atomic_op 64_fetch_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
+atomic_op 64_fetch_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
+atomic_op 64_fetch_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
 
 	jrp     lr              /* happy backtracer */
 
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 3e86742..a58b998 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -171,6 +171,16 @@
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
+static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	return xadd(&v->counter, i);
+}
+
+static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	return xadd(&v->counter, -i);
+}
+
 static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	return cmpxchg(&v->counter, old, new);
@@ -190,10 +200,29 @@
 			: "memory");					\
 }
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	int old, val = atomic_read(v);					\
+	for (;;) {							\
+		old = atomic_cmpxchg(v, val, val c_op i);		\
+		if (old == val)						\
+			break;						\
+		val = old;						\
+	}								\
+	return old;							\
+}
 
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op)							\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &)
+ATOMIC_OPS(or , |)
+ATOMIC_OPS(xor, ^)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP
 
 /**
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a984111..71d7705 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -320,10 +320,29 @@
 		c = old;						\
 }
 
-ATOMIC64_OP(and, &)
-ATOMIC64_OP(or, |)
-ATOMIC64_OP(xor, ^)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{									\
+	long long old, c = 0;						\
+	while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c)		\
+		c = old;						\
+	return old;							\
+}
 
+ATOMIC64_FETCH_OP(add, +)
+
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &)
+ATOMIC64_OPS(or, |)
+ATOMIC64_OPS(xor, ^)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0373510..70eed0e 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -158,6 +158,16 @@
 	return atomic64_add_return(-i, v);
 }
 
+static inline long atomic64_fetch_add(long i, atomic64_t *v)
+{
+	return xadd(&v->counter, i);
+}
+
+static inline long atomic64_fetch_sub(long i, atomic64_t *v)
+{
+	return xadd(&v->counter, -i);
+}
+
 #define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
 #define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
 
@@ -229,10 +239,29 @@
 			: "memory");					\
 }
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	long old, val = atomic64_read(v);				\
+	for (;;) {							\
+		old = atomic64_cmpxchg(v, val, val c_op i);		\
+		if (old == val)						\
+			break;						\
+		val = old;						\
+	}								\
+	return old;							\
+}
 
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op)							\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &)
+ATOMIC64_OPS(or, |)
+ATOMIC64_OPS(xor, ^)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index fd8017c..e7a23f2 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -98,6 +98,26 @@
 	return result;							\
 }
 
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t * v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	__asm__ __volatile__(						\
+			"1:     l32i    %1, %3, 0\n"			\
+			"       wsr     %1, scompare1\n"		\
+			"       " #op " %0, %1, %2\n"			\
+			"       s32c1i  %0, %3, 0\n"			\
+			"       bne     %0, %1, 1b\n"			\
+			: "=&a" (result), "=&a" (tmp)			\
+			: "a" (i), "a" (v)				\
+			: "memory"					\
+			);						\
+									\
+	return result;							\
+}
+
 #else /* XCHAL_HAVE_S32C1I */
 
 #define ATOMIC_OP(op)							\
@@ -138,18 +158,42 @@
 	return vval;							\
 }
 
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t * v)		\
+{									\
+	unsigned int tmp, vval;						\
+									\
+	__asm__ __volatile__(						\
+			"       rsil    a15,"__stringify(TOPLEVEL)"\n"	\
+			"       l32i    %0, %3, 0\n"			\
+			"       " #op " %1, %0, %2\n"			\
+			"       s32i    %1, %3, 0\n"			\
+			"       wsr     a15, ps\n"			\
+			"       rsync\n"				\
+			: "=&a" (vval), "=&a" (tmp)			\
+			: "a" (i), "a" (v)				\
+			: "a15", "memory"				\
+			);						\
+									\
+	return vval;							\
+}
+
 #endif /* XCHAL_HAVE_S32C1I */
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) ATOMIC_OP_RETURN(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 5e1f345..2d0d3cf 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -112,6 +112,40 @@
 	ATOMIC_LONG_PFX(_dec)(v);
 }
 
+#define ATOMIC_LONG_FETCH_OP(op, mo)					\
+static inline long							\
+atomic_long_fetch_##op##mo(long i, atomic_long_t *l)			\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(i, v);		\
+}
+
+ATOMIC_LONG_FETCH_OP(add, )
+ATOMIC_LONG_FETCH_OP(add, _relaxed)
+ATOMIC_LONG_FETCH_OP(add, _acquire)
+ATOMIC_LONG_FETCH_OP(add, _release)
+ATOMIC_LONG_FETCH_OP(sub, )
+ATOMIC_LONG_FETCH_OP(sub, _relaxed)
+ATOMIC_LONG_FETCH_OP(sub, _acquire)
+ATOMIC_LONG_FETCH_OP(sub, _release)
+ATOMIC_LONG_FETCH_OP(and, )
+ATOMIC_LONG_FETCH_OP(and, _relaxed)
+ATOMIC_LONG_FETCH_OP(and, _acquire)
+ATOMIC_LONG_FETCH_OP(and, _release)
+ATOMIC_LONG_FETCH_OP(andnot, )
+ATOMIC_LONG_FETCH_OP(andnot, _relaxed)
+ATOMIC_LONG_FETCH_OP(andnot, _acquire)
+ATOMIC_LONG_FETCH_OP(andnot, _release)
+ATOMIC_LONG_FETCH_OP(or, )
+ATOMIC_LONG_FETCH_OP(or, _relaxed)
+ATOMIC_LONG_FETCH_OP(or, _acquire)
+ATOMIC_LONG_FETCH_OP(or, _release)
+ATOMIC_LONG_FETCH_OP(xor, )
+ATOMIC_LONG_FETCH_OP(xor, _relaxed)
+ATOMIC_LONG_FETCH_OP(xor, _acquire)
+ATOMIC_LONG_FETCH_OP(xor, _release)
+
 #define ATOMIC_LONG_OP(op)						\
 static __always_inline void						\
 atomic_long_##op(long i, atomic_long_t *l)				\
@@ -124,9 +158,9 @@
 ATOMIC_LONG_OP(add)
 ATOMIC_LONG_OP(sub)
 ATOMIC_LONG_OP(and)
+ATOMIC_LONG_OP(andnot)
 ATOMIC_LONG_OP(or)
 ATOMIC_LONG_OP(xor)
-ATOMIC_LONG_OP(andnot)
 
 #undef ATOMIC_LONG_OP
 
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 74f1a37..9ed8b98 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -61,6 +61,18 @@
 	return c c_op i;						\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+									\
+	return c;							\
+}
+
 #else
 
 #include <linux/irqflags.h>
@@ -88,6 +100,20 @@
 	return ret;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = v->counter;						\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
 #endif /* CONFIG_SMP */
 
 #ifndef atomic_add_return
@@ -98,6 +124,26 @@
 ATOMIC_OP_RETURN(sub, -)
 #endif
 
+#ifndef atomic_fetch_add
+ATOMIC_FETCH_OP(add, +)
+#endif
+
+#ifndef atomic_fetch_sub
+ATOMIC_FETCH_OP(sub, -)
+#endif
+
+#ifndef atomic_fetch_and
+ATOMIC_FETCH_OP(and, &)
+#endif
+
+#ifndef atomic_fetch_or
+ATOMIC_FETCH_OP(or, |)
+#endif
+
+#ifndef atomic_fetch_xor
+ATOMIC_FETCH_OP(xor, ^)
+#endif
+
 #ifndef atomic_and
 ATOMIC_OP(and, &)
 #endif
@@ -110,6 +156,7 @@
 ATOMIC_OP(xor, ^)
 #endif
 
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index d48e78c..dad68bf 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -27,16 +27,23 @@
 #define ATOMIC64_OP_RETURN(op)						\
 extern long long atomic64_##op##_return(long long a, atomic64_t *v);
 
-#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op)						\
+extern long long atomic64_fetch_##op(long long a, atomic64_t *v);
+
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
 
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index e451534..12d910d 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -163,6 +163,154 @@
 #endif
 #endif /* atomic_dec_return_relaxed */
 
+
+/* atomic_fetch_add_relaxed */
+#ifndef atomic_fetch_add_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add
+#define atomic_fetch_add_acquire	atomic_fetch_add
+#define atomic_fetch_add_release	atomic_fetch_add
+
+#else /* atomic_fetch_add_relaxed */
+
+#ifndef atomic_fetch_add_acquire
+#define atomic_fetch_add_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_add, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_add_release
+#define atomic_fetch_add_release(...)					\
+	__atomic_op_release(atomic_fetch_add, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_add
+#define atomic_fetch_add(...)						\
+	__atomic_op_fence(atomic_fetch_add, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_add_relaxed */
+
+/* atomic_fetch_sub_relaxed */
+#ifndef atomic_fetch_sub_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub
+#define atomic_fetch_sub_acquire	atomic_fetch_sub
+#define atomic_fetch_sub_release	atomic_fetch_sub
+
+#else /* atomic_fetch_sub_relaxed */
+
+#ifndef atomic_fetch_sub_acquire
+#define atomic_fetch_sub_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_sub, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_sub_release
+#define atomic_fetch_sub_release(...)					\
+	__atomic_op_release(atomic_fetch_sub, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_sub
+#define atomic_fetch_sub(...)						\
+	__atomic_op_fence(atomic_fetch_sub, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_sub_relaxed */
+
+/* atomic_fetch_or_relaxed */
+#ifndef atomic_fetch_or_relaxed
+#define atomic_fetch_or_relaxed	atomic_fetch_or
+#define atomic_fetch_or_acquire	atomic_fetch_or
+#define atomic_fetch_or_release	atomic_fetch_or
+
+#else /* atomic_fetch_or_relaxed */
+
+#ifndef atomic_fetch_or_acquire
+#define atomic_fetch_or_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_or, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_or_release
+#define atomic_fetch_or_release(...)					\
+	__atomic_op_release(atomic_fetch_or, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_or
+#define atomic_fetch_or(...)						\
+	__atomic_op_fence(atomic_fetch_or, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_or_relaxed */
+
+/* atomic_fetch_and_relaxed */
+#ifndef atomic_fetch_and_relaxed
+#define atomic_fetch_and_relaxed	atomic_fetch_and
+#define atomic_fetch_and_acquire	atomic_fetch_and
+#define atomic_fetch_and_release	atomic_fetch_and
+
+#else /* atomic_fetch_and_relaxed */
+
+#ifndef atomic_fetch_and_acquire
+#define atomic_fetch_and_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_and, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_and_release
+#define atomic_fetch_and_release(...)					\
+	__atomic_op_release(atomic_fetch_and, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_and
+#define atomic_fetch_and(...)						\
+	__atomic_op_fence(atomic_fetch_and, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_and_relaxed */
+
+#ifdef atomic_andnot
+/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_fetch_andnot_relaxed
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire	atomic_fetch_andnot
+#define atomic_fetch_andnot_release	atomic_fetch_andnot
+
+#else /* atomic_fetch_andnot_relaxed */
+
+#ifndef atomic_fetch_andnot_acquire
+#define atomic_fetch_andnot_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_andnot, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_andnot_release
+#define atomic_fetch_andnot_release(...)					\
+	__atomic_op_release(atomic_fetch_andnot, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(...)						\
+	__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_andnot_relaxed */
+#endif /* atomic_andnot */
+
+/* atomic_fetch_xor_relaxed */
+#ifndef atomic_fetch_xor_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor
+#define atomic_fetch_xor_acquire	atomic_fetch_xor
+#define atomic_fetch_xor_release	atomic_fetch_xor
+
+#else /* atomic_fetch_xor_relaxed */
+
+#ifndef atomic_fetch_xor_acquire
+#define atomic_fetch_xor_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_xor, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_xor_release
+#define atomic_fetch_xor_release(...)					\
+	__atomic_op_release(atomic_fetch_xor, __VA_ARGS__)
+#endif
+
+#ifndef atomic_fetch_xor
+#define atomic_fetch_xor(...)						\
+	__atomic_op_fence(atomic_fetch_xor, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_xor_relaxed */
+
+
 /* atomic_xchg_relaxed */
 #ifndef atomic_xchg_relaxed
 #define  atomic_xchg_relaxed		atomic_xchg
@@ -211,6 +359,214 @@
 #endif
 #endif /* atomic_cmpxchg_relaxed */
 
+/* cmpxchg_relaxed */
+#ifndef cmpxchg_relaxed
+#define  cmpxchg_relaxed		cmpxchg
+#define  cmpxchg_acquire		cmpxchg
+#define  cmpxchg_release		cmpxchg
+
+#else /* cmpxchg_relaxed */
+
+#ifndef cmpxchg_acquire
+#define  cmpxchg_acquire(...)						\
+	__atomic_op_acquire(cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef cmpxchg_release
+#define  cmpxchg_release(...)						\
+	__atomic_op_release(cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef cmpxchg
+#define  cmpxchg(...)							\
+	__atomic_op_fence(cmpxchg, __VA_ARGS__)
+#endif
+#endif /* cmpxchg_relaxed */
+
+/* cmpxchg64_relaxed */
+#ifndef cmpxchg64_relaxed
+#define  cmpxchg64_relaxed		cmpxchg64
+#define  cmpxchg64_acquire		cmpxchg64
+#define  cmpxchg64_release		cmpxchg64
+
+#else /* cmpxchg64_relaxed */
+
+#ifndef cmpxchg64_acquire
+#define  cmpxchg64_acquire(...)						\
+	__atomic_op_acquire(cmpxchg64, __VA_ARGS__)
+#endif
+
+#ifndef cmpxchg64_release
+#define  cmpxchg64_release(...)						\
+	__atomic_op_release(cmpxchg64, __VA_ARGS__)
+#endif
+
+#ifndef cmpxchg64
+#define  cmpxchg64(...)							\
+	__atomic_op_fence(cmpxchg64, __VA_ARGS__)
+#endif
+#endif /* cmpxchg64_relaxed */
+
+/* xchg_relaxed */
+#ifndef xchg_relaxed
+#define  xchg_relaxed			xchg
+#define  xchg_acquire			xchg
+#define  xchg_release			xchg
+
+#else /* xchg_relaxed */
+
+#ifndef xchg_acquire
+#define  xchg_acquire(...)		__atomic_op_acquire(xchg, __VA_ARGS__)
+#endif
+
+#ifndef xchg_release
+#define  xchg_release(...)		__atomic_op_release(xchg, __VA_ARGS__)
+#endif
+
+#ifndef xchg
+#define  xchg(...)			__atomic_op_fence(xchg, __VA_ARGS__)
+#endif
+#endif /* xchg_relaxed */
+
+/**
+ * atomic_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as @v was not already @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+	return __atomic_add_unless(v, a, u) != u;
+}
+
+/**
+ * atomic_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1, so long as @v is non-zero.
+ * Returns non-zero if @v was non-zero, and zero otherwise.
+ */
+#ifndef atomic_inc_not_zero
+#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
+#endif
+
+#ifndef atomic_andnot
+static inline void atomic_andnot(int i, atomic_t *v)
+{
+	atomic_and(~i, v);
+}
+
+static inline int atomic_fetch_andnot(int i, atomic_t *v)
+{
+	return atomic_fetch_and(~i, v);
+}
+
+static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
+{
+	return atomic_fetch_and_relaxed(~i, v);
+}
+
+static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
+{
+	return atomic_fetch_and_acquire(~i, v);
+}
+
+static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
+{
+	return atomic_fetch_and_release(~i, v);
+}
+#endif
+
+/**
+ * atomic_inc_not_zero_hint - increment if not null
+ * @v: pointer of type atomic_t
+ * @hint: probable value of the atomic before the increment
+ *
+ * This version of atomic_inc_not_zero() gives a hint of probable
+ * value of the atomic. This helps processor to not read the memory
+ * before doing the atomic read/modify/write cycle, lowering
+ * number of bus transactions on some arches.
+ *
+ * Returns: 0 if increment was not done, 1 otherwise.
+ */
+#ifndef atomic_inc_not_zero_hint
+static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
+{
+	int val, c = hint;
+
+	/* sanity test, should be removed by compiler if hint is a constant */
+	if (!hint)
+		return atomic_inc_not_zero(v);
+
+	do {
+		val = atomic_cmpxchg(v, c, c + 1);
+		if (val == c)
+			return 1;
+		c = val;
+	} while (c);
+
+	return 0;
+}
+#endif
+
+#ifndef atomic_inc_unless_negative
+static inline int atomic_inc_unless_negative(atomic_t *p)
+{
+	int v, v1;
+	for (v = 0; v >= 0; v = v1) {
+		v1 = atomic_cmpxchg(p, v, v + 1);
+		if (likely(v1 == v))
+			return 1;
+	}
+	return 0;
+}
+#endif
+
+#ifndef atomic_dec_unless_positive
+static inline int atomic_dec_unless_positive(atomic_t *p)
+{
+	int v, v1;
+	for (v = 0; v <= 0; v = v1) {
+		v1 = atomic_cmpxchg(p, v, v - 1);
+		if (likely(v1 == v))
+			return 1;
+	}
+	return 0;
+}
+#endif
+
+/*
+ * atomic_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+#ifndef atomic_dec_if_positive
+static inline int atomic_dec_if_positive(atomic_t *v)
+{
+	int c, old, dec;
+	c = atomic_read(v);
+	for (;;) {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+		old = atomic_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return dec;
+}
+#endif
+
+#ifdef CONFIG_GENERIC_ATOMIC64
+#include <asm-generic/atomic64.h>
+#endif
+
 #ifndef atomic64_read_acquire
 #define  atomic64_read_acquire(v)	smp_load_acquire(&(v)->counter)
 #endif
@@ -316,6 +672,154 @@
 #endif
 #endif /* atomic64_dec_return_relaxed */
 
+
+/* atomic64_fetch_add_relaxed */
+#ifndef atomic64_fetch_add_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add
+#define atomic64_fetch_add_acquire	atomic64_fetch_add
+#define atomic64_fetch_add_release	atomic64_fetch_add
+
+#else /* atomic64_fetch_add_relaxed */
+
+#ifndef atomic64_fetch_add_acquire
+#define atomic64_fetch_add_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_add, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_add_release
+#define atomic64_fetch_add_release(...)					\
+	__atomic_op_release(atomic64_fetch_add, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_add
+#define atomic64_fetch_add(...)						\
+	__atomic_op_fence(atomic64_fetch_add, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_add_relaxed */
+
+/* atomic64_fetch_sub_relaxed */
+#ifndef atomic64_fetch_sub_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub
+#define atomic64_fetch_sub_acquire	atomic64_fetch_sub
+#define atomic64_fetch_sub_release	atomic64_fetch_sub
+
+#else /* atomic64_fetch_sub_relaxed */
+
+#ifndef atomic64_fetch_sub_acquire
+#define atomic64_fetch_sub_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_sub, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_sub_release
+#define atomic64_fetch_sub_release(...)					\
+	__atomic_op_release(atomic64_fetch_sub, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_sub
+#define atomic64_fetch_sub(...)						\
+	__atomic_op_fence(atomic64_fetch_sub, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_sub_relaxed */
+
+/* atomic64_fetch_or_relaxed */
+#ifndef atomic64_fetch_or_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or
+#define atomic64_fetch_or_acquire	atomic64_fetch_or
+#define atomic64_fetch_or_release	atomic64_fetch_or
+
+#else /* atomic64_fetch_or_relaxed */
+
+#ifndef atomic64_fetch_or_acquire
+#define atomic64_fetch_or_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_or, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_or_release
+#define atomic64_fetch_or_release(...)					\
+	__atomic_op_release(atomic64_fetch_or, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_or
+#define atomic64_fetch_or(...)						\
+	__atomic_op_fence(atomic64_fetch_or, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_or_relaxed */
+
+/* atomic64_fetch_and_relaxed */
+#ifndef atomic64_fetch_and_relaxed
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and
+#define atomic64_fetch_and_acquire	atomic64_fetch_and
+#define atomic64_fetch_and_release	atomic64_fetch_and
+
+#else /* atomic64_fetch_and_relaxed */
+
+#ifndef atomic64_fetch_and_acquire
+#define atomic64_fetch_and_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_and, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_and_release
+#define atomic64_fetch_and_release(...)					\
+	__atomic_op_release(atomic64_fetch_and, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_and
+#define atomic64_fetch_and(...)						\
+	__atomic_op_fence(atomic64_fetch_and, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_and_relaxed */
+
+#ifdef atomic64_andnot
+/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release	atomic64_fetch_andnot
+
+#else /* atomic64_fetch_andnot_relaxed */
+
+#ifndef atomic64_fetch_andnot_acquire
+#define atomic64_fetch_andnot_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_andnot, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_andnot_release
+#define atomic64_fetch_andnot_release(...)					\
+	__atomic_op_release(atomic64_fetch_andnot, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(...)						\
+	__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_andnot_relaxed */
+#endif /* atomic64_andnot */
+
+/* atomic64_fetch_xor_relaxed */
+#ifndef atomic64_fetch_xor_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor
+#define atomic64_fetch_xor_acquire	atomic64_fetch_xor
+#define atomic64_fetch_xor_release	atomic64_fetch_xor
+
+#else /* atomic64_fetch_xor_relaxed */
+
+#ifndef atomic64_fetch_xor_acquire
+#define atomic64_fetch_xor_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_xor, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_xor_release
+#define atomic64_fetch_xor_release(...)					\
+	__atomic_op_release(atomic64_fetch_xor, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_xor
+#define atomic64_fetch_xor(...)						\
+	__atomic_op_fence(atomic64_fetch_xor, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_xor_relaxed */
+
+
 /* atomic64_xchg_relaxed */
 #ifndef atomic64_xchg_relaxed
 #define  atomic64_xchg_relaxed		atomic64_xchg
@@ -364,230 +868,31 @@
 #endif
 #endif /* atomic64_cmpxchg_relaxed */
 
-/* cmpxchg_relaxed */
-#ifndef cmpxchg_relaxed
-#define  cmpxchg_relaxed		cmpxchg
-#define  cmpxchg_acquire		cmpxchg
-#define  cmpxchg_release		cmpxchg
-
-#else /* cmpxchg_relaxed */
-
-#ifndef cmpxchg_acquire
-#define  cmpxchg_acquire(...)						\
-	__atomic_op_acquire(cmpxchg, __VA_ARGS__)
-#endif
-
-#ifndef cmpxchg_release
-#define  cmpxchg_release(...)						\
-	__atomic_op_release(cmpxchg, __VA_ARGS__)
-#endif
-
-#ifndef cmpxchg
-#define  cmpxchg(...)							\
-	__atomic_op_fence(cmpxchg, __VA_ARGS__)
-#endif
-#endif /* cmpxchg_relaxed */
-
-/* cmpxchg64_relaxed */
-#ifndef cmpxchg64_relaxed
-#define  cmpxchg64_relaxed		cmpxchg64
-#define  cmpxchg64_acquire		cmpxchg64
-#define  cmpxchg64_release		cmpxchg64
-
-#else /* cmpxchg64_relaxed */
-
-#ifndef cmpxchg64_acquire
-#define  cmpxchg64_acquire(...)						\
-	__atomic_op_acquire(cmpxchg64, __VA_ARGS__)
-#endif
-
-#ifndef cmpxchg64_release
-#define  cmpxchg64_release(...)						\
-	__atomic_op_release(cmpxchg64, __VA_ARGS__)
-#endif
-
-#ifndef cmpxchg64
-#define  cmpxchg64(...)							\
-	__atomic_op_fence(cmpxchg64, __VA_ARGS__)
-#endif
-#endif /* cmpxchg64_relaxed */
-
-/* xchg_relaxed */
-#ifndef xchg_relaxed
-#define  xchg_relaxed			xchg
-#define  xchg_acquire			xchg
-#define  xchg_release			xchg
-
-#else /* xchg_relaxed */
-
-#ifndef xchg_acquire
-#define  xchg_acquire(...)		__atomic_op_acquire(xchg, __VA_ARGS__)
-#endif
-
-#ifndef xchg_release
-#define  xchg_release(...)		__atomic_op_release(xchg, __VA_ARGS__)
-#endif
-
-#ifndef xchg
-#define  xchg(...)			__atomic_op_fence(xchg, __VA_ARGS__)
-#endif
-#endif /* xchg_relaxed */
-
-/**
- * atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
-	return __atomic_add_unless(v, a, u) != u;
-}
-
-/**
- * atomic_inc_not_zero - increment unless the number is zero
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
- */
-#ifndef atomic_inc_not_zero
-#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
-#endif
-
-#ifndef atomic_andnot
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	atomic_and(~i, v);
-}
-#endif
-
-static inline __deprecated void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	atomic_andnot(mask, v);
-}
-
-static inline __deprecated void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	atomic_or(mask, v);
-}
-
-/**
- * atomic_inc_not_zero_hint - increment if not null
- * @v: pointer of type atomic_t
- * @hint: probable value of the atomic before the increment
- *
- * This version of atomic_inc_not_zero() gives a hint of probable
- * value of the atomic. This helps processor to not read the memory
- * before doing the atomic read/modify/write cycle, lowering
- * number of bus transactions on some arches.
- *
- * Returns: 0 if increment was not done, 1 otherwise.
- */
-#ifndef atomic_inc_not_zero_hint
-static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
-{
-	int val, c = hint;
-
-	/* sanity test, should be removed by compiler if hint is a constant */
-	if (!hint)
-		return atomic_inc_not_zero(v);
-
-	do {
-		val = atomic_cmpxchg(v, c, c + 1);
-		if (val == c)
-			return 1;
-		c = val;
-	} while (c);
-
-	return 0;
-}
-#endif
-
-#ifndef atomic_inc_unless_negative
-static inline int atomic_inc_unless_negative(atomic_t *p)
-{
-	int v, v1;
-	for (v = 0; v >= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v + 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
-}
-#endif
-
-#ifndef atomic_dec_unless_positive
-static inline int atomic_dec_unless_positive(atomic_t *p)
-{
-	int v, v1;
-	for (v = 0; v <= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v - 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
-}
-#endif
-
-/*
- * atomic_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-#ifndef atomic_dec_if_positive
-static inline int atomic_dec_if_positive(atomic_t *v)
-{
-	int c, old, dec;
-	c = atomic_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-#endif
-
-/**
- * atomic_fetch_or - perform *p |= mask and return old value of *p
- * @mask: mask to OR on the atomic_t
- * @p: pointer to atomic_t
- */
-#ifndef atomic_fetch_or
-static inline int atomic_fetch_or(int mask, atomic_t *p)
-{
-	int old, val = atomic_read(p);
-
-	for (;;) {
-		old = atomic_cmpxchg(p, val, val | mask);
-		if (old == val)
-			break;
-		val = old;
-	}
-
-	return old;
-}
-#endif
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#include <asm-generic/atomic64.h>
-#endif
-
 #ifndef atomic64_andnot
 static inline void atomic64_andnot(long long i, atomic64_t *v)
 {
 	atomic64_and(~i, v);
 }
+
+static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and(~i, v);
+}
+
+static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and_relaxed(~i, v);
+}
+
+static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and_acquire(~i, v);
+}
+
+static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and_release(~i, v);
+}
 #endif
 
 #include <asm-generic/atomic-long.h>
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index fec0823..19248dd 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -93,7 +93,7 @@
 	 * that accesses can't leak upwards out of our subsequent critical
 	 * section in the case that the lock is currently held for write.
 	 */
-	cnts = atomic_add_return_acquire(_QR_BIAS, &lock->cnts) - _QR_BIAS;
+	cnts = atomic_fetch_add_acquire(_QR_BIAS, &lock->cnts);
 	rspin_until_writer_unlock(lock, cnts);
 
 	/*
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 21ede57..37649e6 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -112,12 +112,12 @@
 #else /* _Q_PENDING_BITS == 8 */
 static __always_inline void set_pending(struct qspinlock *lock)
 {
-	atomic_set_mask(_Q_PENDING_VAL, &lock->val);
+	atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
 static __always_inline void clear_pending(struct qspinlock *lock)
 {
-	atomic_clear_mask(_Q_PENDING_VAL, &lock->val);
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
 }
 
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 2031281..447e08d 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -153,7 +153,7 @@
 	if (wake_type != RWSEM_WAKE_READ_OWNED) {
 		adjustment = RWSEM_ACTIVE_READ_BIAS;
  try_reader_grant:
-		oldcount = atomic_long_add_return(adjustment, &sem->count) - adjustment;
+		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
 
 		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
 			/*
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 2886eba..53c2d5e 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -96,17 +96,41 @@
 }									\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+long long atomic64_fetch_##op(long long a, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+	long long val;							\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	val = v->counter;						\
+	v->counter c_op a;						\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+	return val;							\
+}									\
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
 #define ATOMIC64_OPS(op, c_op)						\
 	ATOMIC64_OP(op, c_op)						\
-	ATOMIC64_OP_RETURN(op, c_op)
+	ATOMIC64_OP_RETURN(op, c_op)					\
+	ATOMIC64_FETCH_OP(op, c_op)
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
-ATOMIC64_OP(and, &=)
-ATOMIC64_OP(or, |=)
-ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_OP_RETURN(op, c_op)					\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &=)
+ATOMIC64_OPS(or, |=)
+ATOMIC64_OPS(xor, ^=)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 1234818..dbb3691 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -53,11 +53,25 @@
 	BUG_ON(atomic##bit##_read(&v) != r);			\
 } while (0)
 
+#define TEST_FETCH(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	r c_op val;						\
+	BUG_ON(atomic##bit##_##op(val, &v) != v0);		\
+	BUG_ON(atomic##bit##_read(&v) != r);			\
+} while (0)
+
 #define RETURN_FAMILY_TEST(bit, op, c_op, val)			\
 do {								\
 	FAMILY_TEST(TEST_RETURN, bit, op, c_op, val);		\
 } while (0)
 
+#define FETCH_FAMILY_TEST(bit, op, c_op, val)			\
+do {								\
+	FAMILY_TEST(TEST_FETCH, bit, op, c_op, val);		\
+} while (0)
+
 #define TEST_ARGS(bit, op, init, ret, expect, args...)		\
 do {								\
 	atomic##bit##_set(&v, init);				\
@@ -114,6 +128,16 @@
 	RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
 	RETURN_FAMILY_TEST(, sub_return, -=, -one);
 
+	FETCH_FAMILY_TEST(, fetch_add, +=, onestwos);
+	FETCH_FAMILY_TEST(, fetch_add, +=, -one);
+	FETCH_FAMILY_TEST(, fetch_sub, -=, onestwos);
+	FETCH_FAMILY_TEST(, fetch_sub, -=, -one);
+
+	FETCH_FAMILY_TEST(, fetch_or,  |=, v1);
+	FETCH_FAMILY_TEST(, fetch_and, &=, v1);
+	FETCH_FAMILY_TEST(, fetch_andnot, &= ~, v1);
+	FETCH_FAMILY_TEST(, fetch_xor, ^=, v1);
+
 	INC_RETURN_FAMILY_TEST(, v0);
 	DEC_RETURN_FAMILY_TEST(, v0);
 
@@ -154,6 +178,16 @@
 	RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
 	RETURN_FAMILY_TEST(64, sub_return, -=, -one);
 
+	FETCH_FAMILY_TEST(64, fetch_add, +=, onestwos);
+	FETCH_FAMILY_TEST(64, fetch_add, +=, -one);
+	FETCH_FAMILY_TEST(64, fetch_sub, -=, onestwos);
+	FETCH_FAMILY_TEST(64, fetch_sub, -=, -one);
+
+	FETCH_FAMILY_TEST(64, fetch_or,  |=, v1);
+	FETCH_FAMILY_TEST(64, fetch_and, &=, v1);
+	FETCH_FAMILY_TEST(64, fetch_andnot, &= ~, v1);
+	FETCH_FAMILY_TEST(64, fetch_xor, ^=, v1);
+
 	INIT(v0);
 	atomic64_inc(&v);
 	r += one;