Merge branch 'locking/arch-atomic' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into aarch64/for-next/core

Merge in PeterZ's logical atomic ops so that we can implement them in
our subsequent LSE atomics.

52 files changed, 696 insertions, 916 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 8f8eafbedd7c..e8c956098424 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -29,13 +29,13 @@
  * branch back to restart the operation.
  */
 
-#define ATOMIC_OP(op)							\
+#define ATOMIC_OP(op, asm_op)						\
 static __inline__ void atomic_##op(int i, atomic_t * v)			\
 {									\
 	unsigned long temp;						\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
-	"	" #op "l %0,%2,%0\n"					\
+	"	" #asm_op " %0,%2,%0\n"					\
 	"	stl_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -45,15 +45,15 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			\
 	:"Ir" (i), "m" (v->counter));					\
 }									\
 
-#define ATOMIC_OP_RETURN(op)						\
+#define ATOMIC_OP_RETURN(op, asm_op)					\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	long temp, result;						\
 	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
-	"	" #op "l %0,%3,%2\n"					\
-	"	" #op "l %0,%3,%0\n"					\
+	"	" #asm_op " %0,%3,%2\n"					\
+	"	" #asm_op " %0,%3,%0\n"					\
 	"	stl_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -65,13 +65,13 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return result;							\
 }
 
-#define ATOMIC64_OP(op)							\
+#define ATOMIC64_OP(op, asm_op)						\
 static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 {									\
 	unsigned long temp;						\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
-	"	" #op "q %0,%2,%0\n"					\
+	"	" #asm_op " %0,%2,%0\n"					\
 	"	stq_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -81,15 +81,15 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 	:"Ir" (i), "m" (v->counter));					\
 }									\
 
-#define ATOMIC64_OP_RETURN(op)						\
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
 static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
 {									\
 	long temp, result;						\
 	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
-	"	" #op "q %0,%3,%2\n"					\
-	"	" #op "q %0,%3,%0\n"					\
+	"	" #asm_op " %0,%3,%2\n"					\
+	"	" #asm_op " %0,%3,%0\n"					\
 	"	stq_c %0,%1\n"						\
 	"	beq %0,2f\n"						\
 	".subsection 2\n"						\
@@ -101,15 +101,27 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
 	return result;							\
 }
 
-#define ATOMIC_OPS(opg)							\
-	ATOMIC_OP(opg)							\
-	ATOMIC_OP_RETURN(opg)						\
-	ATOMIC64_OP(opg)						\
-	ATOMIC64_OP_RETURN(opg)
+#define ATOMIC_OPS(op)							\
+	ATOMIC_OP(op, op##l)						\
+	ATOMIC_OP_RETURN(op, op##l)					\
+	ATOMIC64_OP(op, op##q)						\
+	ATOMIC64_OP_RETURN(op, op##q)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+#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
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 03484cb4d16d..d8a85e706fba 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -143,9 +143,13 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
-ATOMIC_OP(and, &=, and)
 
-#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v))
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(andnot, &= ~, bic)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index e22c11970b7b..82b75a7cb762 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -194,6 +194,13 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 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
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -321,6 +328,13 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 ATOMIC64_OPS(add, adds, adc)
 ATOMIC64_OPS(sub, subs, sbc)
 
+#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)
+
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 7047051ded40..866a71fca9a3 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -85,6 +85,13 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 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
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -183,6 +190,13 @@ static inline long atomic64_##op##_return(long i, atomic64_t *v)	\
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, sub)
 
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(andnot, bic)
+ATOMIC64_OP(or, orr)
+ATOMIC64_OP(xor, eor)
+
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index 2d07ce1c5327..97c9bdf83409 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -44,6 +44,18 @@ static inline int __atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OP_RETURN(sub, sub, rKs21)
 ATOMIC_OP_RETURN(add, add, r)
 
+#define ATOMIC_OP(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_OP(and, and)
+ATOMIC_OP(or, or)
+ATOMIC_OP(xor, eor)
+
+#undef ATOMIC_OP
 #undef ATOMIC_OP_RETURN
 
 /*
diff --git a/arch/blackfin/include/asm/atomic.h b/arch/blackfin/include/asm/atomic.h
index a107a98e9978..1c1c42330c99 100644
--- a/arch/blackfin/include/asm/atomic.h
+++ b/arch/blackfin/include/asm/atomic.h
@@ -16,19 +16,21 @@
 #include <linux/types.h>
 
 asmlinkage int __raw_uncached_fetch_asm(const volatile int *ptr);
-asmlinkage int __raw_atomic_update_asm(volatile int *ptr, int value);
-asmlinkage int __raw_atomic_clear_asm(volatile int *ptr, int value);
-asmlinkage int __raw_atomic_set_asm(volatile int *ptr, int value);
+asmlinkage int __raw_atomic_add_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);
 asmlinkage int __raw_atomic_xor_asm(volatile int *ptr, int value);
 asmlinkage int __raw_atomic_test_asm(const volatile int *ptr, int value);
 
 #define atomic_read(v) __raw_uncached_fetch_asm(&(v)->counter)
 
-#define atomic_add_return(i, v) __raw_atomic_update_asm(&(v)->counter, i)
-#define atomic_sub_return(i, v) __raw_atomic_update_asm(&(v)->counter, -(i))
+#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_clear_mask(m, v) __raw_atomic_clear_asm(&(v)->counter, m)
-#define atomic_set_mask(m, v)   __raw_atomic_set_asm(&(v)->counter, m)
+#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)
 
 #endif
 
diff --git a/arch/blackfin/kernel/bfin_ksyms.c b/arch/blackfin/kernel/bfin_ksyms.c
index c446591b961d..a401c27b69b4 100644
--- a/arch/blackfin/kernel/bfin_ksyms.c
+++ b/arch/blackfin/kernel/bfin_ksyms.c
@@ -83,11 +83,12 @@ EXPORT_SYMBOL(insl);
 EXPORT_SYMBOL(insl_16);
 
 #ifdef CONFIG_SMP
-EXPORT_SYMBOL(__raw_atomic_update_asm);
-EXPORT_SYMBOL(__raw_atomic_clear_asm);
-EXPORT_SYMBOL(__raw_atomic_set_asm);
+EXPORT_SYMBOL(__raw_atomic_add_asm);
+EXPORT_SYMBOL(__raw_atomic_and_asm);
+EXPORT_SYMBOL(__raw_atomic_or_asm);
 EXPORT_SYMBOL(__raw_atomic_xor_asm);
 EXPORT_SYMBOL(__raw_atomic_test_asm);
+
 EXPORT_SYMBOL(__raw_xchg_1_asm);
 EXPORT_SYMBOL(__raw_xchg_2_asm);
 EXPORT_SYMBOL(__raw_xchg_4_asm);
diff --git a/arch/blackfin/mach-bf561/atomic.S b/arch/blackfin/mach-bf561/atomic.S
index 2a08df8e8c4c..26fccb5568b9 100644
--- a/arch/blackfin/mach-bf561/atomic.S
+++ b/arch/blackfin/mach-bf561/atomic.S
@@ -587,10 +587,10 @@ ENDPROC(___raw_write_unlock_asm)
  * r0 = ptr
  * r1 = value
  *
- * Add a signed value to a 32bit word and return the new value atomically.
+ * ADD a signed value to a 32bit word and return the new value atomically.
  * Clobbers: r3:0, p1:0
  */
-ENTRY(___raw_atomic_update_asm)
+ENTRY(___raw_atomic_add_asm)
 	p1 = r0;
 	r3 = r1;
 	[--sp] = rets;
@@ -603,19 +603,19 @@ ENTRY(___raw_atomic_update_asm)
 	r0 = r3;
 	rets = [sp++];
 	rts;
-ENDPROC(___raw_atomic_update_asm)
+ENDPROC(___raw_atomic_add_asm)
 
 /*
  * r0 = ptr
  * r1 = mask
  *
- * Clear the mask bits from a 32bit word and return the old 32bit value
+ * AND the mask bits from a 32bit word and return the old 32bit value
  * atomically.
  * Clobbers: r3:0, p1:0
  */
-ENTRY(___raw_atomic_clear_asm)
+ENTRY(___raw_atomic_and_asm)
 	p1 = r0;
-	r3 = ~r1;
+	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
 	r2 = [p1];
@@ -627,17 +627,17 @@ ENTRY(___raw_atomic_clear_asm)
 	r0 = r3;
 	rets = [sp++];
 	rts;
-ENDPROC(___raw_atomic_clear_asm)
+ENDPROC(___raw_atomic_and_asm)
 
 /*
  * r0 = ptr
  * r1 = mask
  *
- * Set the mask bits into a 32bit word and return the old 32bit value
+ * OR the mask bits into a 32bit word and return the old 32bit value
  * atomically.
  * Clobbers: r3:0, p1:0
  */
-ENTRY(___raw_atomic_set_asm)
+ENTRY(___raw_atomic_or_asm)
 	p1 = r0;
 	r3 = r1;
 	[--sp] = rets;
@@ -651,7 +651,7 @@ ENTRY(___raw_atomic_set_asm)
 	r0 = r3;
 	rets = [sp++];
 	rts;
-ENDPROC(___raw_atomic_set_asm)
+ENDPROC(___raw_atomic_or_asm)
 
 /*
  * r0 = ptr
@@ -787,7 +787,7 @@ ENTRY(___raw_bit_set_asm)
 	r2 = r1;
 	r1 = 1;
 	r1 <<= r2;
-	jump ___raw_atomic_set_asm
+	jump ___raw_atomic_or_asm
 ENDPROC(___raw_bit_set_asm)
 
 /*
@@ -798,10 +798,10 @@ ENDPROC(___raw_bit_set_asm)
  * Clobbers: r3:0, p1:0
  */
 ENTRY(___raw_bit_clear_asm)
-	r2 = r1;
-	r1 = 1;
-	r1 <<= r2;
-	jump ___raw_atomic_clear_asm
+	r2 = 1;
+	r2 <<= r1;
+	r1 = ~r2;
+	jump ___raw_atomic_and_asm
 ENDPROC(___raw_bit_clear_asm)
 
 /*
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 1c7259597395..0030e21cfceb 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -195,7 +195,7 @@ void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg)
 	local_irq_save(flags);
 	for_each_cpu(cpu, cpumask) {
 		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
-		atomic_set_mask((1 << msg), &bfin_ipi_data->bits);
+		atomic_or((1 << msg), &bfin_ipi_data->bits);
 		atomic_inc(&bfin_ipi_data->count);
 	}
 	local_irq_restore(flags);
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 102190a61d65..0da689def4cc 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -15,7 +15,6 @@
 #define _ASM_ATOMIC_H
 
 #include <linux/types.h>
-#include <asm/spr-regs.h>
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
@@ -23,6 +22,8 @@
 #error not SMP safe
 #endif
 
+#include <asm/atomic_defs.h>
+
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
@@ -34,56 +35,26 @@
 #define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = (i))
 
-#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-static inline int atomic_add_return(int i, atomic_t *v)
+static inline int atomic_inc_return(atomic_t *v)
 {
-	unsigned long val;
+	return __atomic_add_return(1, &v->counter);
+}
 
-	asm("0:						\n"
-	    "	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-	    "	ckeq		icc3,cc7		\n"
-	    "	ld.p		%M0,%1			\n"	/* LD.P/ORCR must be atomic */
-	    "	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-	    "	add%I2		%1,%2,%1		\n"
-	    "	cst.p		%1,%M0		,cc3,#1	\n"
-	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* clear ICC3.Z if store happens */
-	    "	beq		icc3,#0,0b		\n"
-	    : "+U"(v->counter), "=&r"(val)
-	    : "NPr"(i)
-	    : "memory", "cc7", "cc3", "icc3"
-	    );
+static inline int atomic_dec_return(atomic_t *v)
+{
+	return __atomic_sub_return(1, &v->counter);
+}
 
-	return val;
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	return __atomic_add_return(i, &v->counter);
 }
 
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
-	unsigned long val;
-
-	asm("0:						\n"
-	    "	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-	    "	ckeq		icc3,cc7		\n"
-	    "	ld.p		%M0,%1			\n"	/* LD.P/ORCR must be atomic */
-	    "	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-	    "	sub%I2		%1,%2,%1		\n"
-	    "	cst.p		%1,%M0		,cc3,#1	\n"
-	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* clear ICC3.Z if store happens */
-	    "	beq		icc3,#0,0b		\n"
-	    : "+U"(v->counter), "=&r"(val)
-	    : "NPr"(i)
-	    : "memory", "cc7", "cc3", "icc3"
-	    );
-
-	return val;
+	return __atomic_sub_return(i, &v->counter);
 }
 
-#else
-
-extern int atomic_add_return(int i, atomic_t *v);
-extern int atomic_sub_return(int i, atomic_t *v);
-
-#endif
-
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	return atomic_add_return(i, v) < 0;
@@ -101,17 +72,14 @@ static inline void atomic_sub(int i, atomic_t *v)
 
 static inline void atomic_inc(atomic_t *v)
 {
-	atomic_add_return(1, v);
+	atomic_inc_return(v);
 }
 
 static inline void atomic_dec(atomic_t *v)
 {
-	atomic_sub_return(1, v);
+	atomic_dec_return(v);
 }
 
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
 #define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
 #define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
@@ -120,18 +88,19 @@ static inline void atomic_dec(atomic_t *v)
  * 64-bit atomic ops
  */
 typedef struct {
-	volatile long long counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-static inline long long atomic64_read(atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
 	long long counter;
 
 	asm("ldd%I1 %M1,%0"
 	    : "=e"(counter)
 	    : "m"(v->counter));
+
 	return counter;
 }
 
@@ -142,10 +111,25 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 		     : "e"(i));
 }
 
-extern long long atomic64_inc_return(atomic64_t *v);
-extern long long atomic64_dec_return(atomic64_t *v);
-extern long long atomic64_add_return(long long i, atomic64_t *v);
-extern long long atomic64_sub_return(long long i, atomic64_t *v);
+static inline long long atomic64_inc_return(atomic64_t *v)
+{
+	return __atomic64_add_return(1, &v->counter);
+}
+
+static inline long long atomic64_dec_return(atomic64_t *v)
+{
+	return __atomic64_sub_return(1, &v->counter);
+}
+
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
+{
+	return __atomic64_add_return(i, &v->counter);
+}
+
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+{
+	return __atomic64_sub_return(i, &v->counter);
+}
 
 static inline long long atomic64_add_negative(long long i, atomic64_t *v)
 {
@@ -176,6 +160,7 @@ static inline void atomic64_dec(atomic64_t *v)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_inc_return((v)) == 0)
 
+
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&(v)->counter, old, new))
 #define atomic_xchg(v, new)		(xchg(&(v)->counter, new))
 #define atomic64_cmpxchg(v, old, new)	(__cmpxchg_64(old, new, &(v)->counter))
@@ -196,5 +181,21 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	(void)__atomic32_fetch_##op(i, &v->counter);			\
+}									\
+									\
+static inline void atomic64_##op(long long i, atomic64_t *v)		\
+{									\
+	(void)__atomic64_fetch_##op(i, &v->counter);			\
+}
+
+ATOMIC_OP(or)
+ATOMIC_OP(and)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/frv/include/asm/atomic_defs.h b/arch/frv/include/asm/atomic_defs.h
new file mode 100644
index 000000000000..36e126d2f801
--- /dev/null
+++ b/arch/frv/include/asm/atomic_defs.h
@@ -0,0 +1,172 @@
+
+#include <asm/spr-regs.h>
+
+#ifdef __ATOMIC_LIB__
+
+#ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
+
+#define ATOMIC_QUALS
+#define ATOMIC_EXPORT(x)	EXPORT_SYMBOL(x)
+
+#else /* !OUTOFLINE && LIB */
+
+#define ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)
+
+#endif /* OUTOFLINE */
+
+#else /* !__ATOMIC_LIB__ */
+
+#define ATOMIC_EXPORT(x)
+
+#ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
+
+#define ATOMIC_OP_RETURN(op)						\
+extern int __atomic_##op##_return(int i, int *v);			\
+extern long long __atomic64_##op##_return(long long i, long long *v);
+
+#define ATOMIC_FETCH_OP(op)						\
+extern int __atomic32_fetch_##op(int i, int *v);			\
+extern long long __atomic64_fetch_##op(long long i, long long *v);
+
+#else /* !OUTOFLINE && !LIB */
+
+#define ATOMIC_QUALS	static inline
+
+#endif /* OUTOFLINE */
+#endif /* __ATOMIC_LIB__ */
+
+
+/*
+ * Note on the 64 bit inline asm variants...
+ *
+ * CSTD is a conditional instruction and needs a constrained memory reference.
+ * Normally 'U' provides the correct constraints for conditional instructions
+ * and this is used for the 32 bit version, however 'U' does not appear to work
+ * for 64 bit values (gcc-4.9)
+ *
+ * The exact constraint is that conditional instructions cannot deal with an
+ * immediate displacement in the memory reference, so what we do is we read the
+ * address through a volatile cast into a local variable in order to insure we
+ * _have_ to compute the correct address without displacement. This allows us
+ * to use the regular 'm' for the memory address.
+ *
+ * Furthermore, the %Ln operand, which prints the low word register (r+1),
+ * really only works for registers, this means we cannot allow immediate values
+ * for the 64 bit versions -- like we do for the 32 bit ones.
+ *
+ */
+
+#ifndef ATOMIC_OP_RETURN
+#define ATOMIC_OP_RETURN(op)						\
+ATOMIC_QUALS int __atomic_##op##_return(int i, int *v)			\
+{									\
+	int val;							\
+									\
+	asm volatile(							\
+	    "0:						\n"		\
+	    "	orcc		gr0,gr0,gr0,icc3	\n"		\
+	    "	ckeq		icc3,cc7		\n"		\
+	    "	ld.p		%M0,%1			\n"		\
+	    "	orcr		cc7,cc7,cc3		\n"		\
+	    "   "#op"%I2	%1,%2,%1		\n"		\
+	    "	cst.p		%1,%M0		,cc3,#1	\n"		\
+	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"		\
+	    "	beq		icc3,#0,0b		\n"		\
+	    : "+U"(*v), "=&r"(val)					\
+	    : "NPr"(i)							\
+	    : "memory", "cc7", "cc3", "icc3"				\
+	    );								\
+									\
+	return val;							\
+}									\
+ATOMIC_EXPORT(__atomic_##op##_return);					\
+									\
+ATOMIC_QUALS long long __atomic64_##op##_return(long long i, long long *v)	\
+{									\
+	long long *__v = READ_ONCE(v);					\
+	long long val;							\
+									\
+	asm volatile(							\
+	    "0:						\n"		\
+	    "	orcc		gr0,gr0,gr0,icc3	\n"		\
+	    "	ckeq		icc3,cc7		\n"		\
+	    "	ldd.p		%M0,%1			\n"		\
+	    "	orcr		cc7,cc7,cc3		\n"		\
+	    "   "#op"cc		%L1,%L2,%L1,icc0	\n"		\
+	    "   "#op"x		%1,%2,%1,icc0		\n"		\
+	    "	cstd.p		%1,%M0		,cc3,#1	\n"		\
+	    "	corcc		gr29,gr29,gr0	,cc3,#1	\n"		\
+	    "	beq		icc3,#0,0b		\n"		\
+	    : "+m"(*__v), "=&e"(val)					\
+	    : "e"(i)							\
+	    : "memory", "cc7", "cc3", "icc0", "icc3"			\
+	    );								\
+									\
+	return val;							\
+}									\
+ATOMIC_EXPORT(__atomic64_##op##_return);
+#endif
+
+#ifndef ATOMIC_FETCH_OP
+#define ATOMIC_FETCH_OP(op)						\
+ATOMIC_QUALS int __atomic32_fetch_##op(int i, int *v)			\
+{									\
+	int old, tmp;							\
+									\
+	asm volatile(							\
+		"0:						\n"	\
+		"	orcc		gr0,gr0,gr0,icc3	\n"	\
+		"	ckeq		icc3,cc7		\n"	\
+		"	ld.p		%M0,%1			\n"	\
+		"	orcr		cc7,cc7,cc3		\n"	\
+		"	"#op"%I3	%1,%3,%2		\n"	\
+		"	cst.p		%2,%M0		,cc3,#1	\n"	\
+		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	\
+		"	beq		icc3,#0,0b		\n"	\
+		: "+U"(*v), "=&r"(old), "=r"(tmp)			\
+		: "NPr"(i)						\
+		: "memory", "cc7", "cc3", "icc3"			\
+		);							\
+									\
+	return old;							\
+}									\
+ATOMIC_EXPORT(__atomic32_fetch_##op);					\
+									\
+ATOMIC_QUALS long long __atomic64_fetch_##op(long long i, long long *v)	\
+{									\
+	long long *__v = READ_ONCE(v);					\
+	long long old, tmp;						\
+									\
+	asm volatile(							\
+		"0:						\n"	\
+		"	orcc		gr0,gr0,gr0,icc3	\n"	\
+		"	ckeq		icc3,cc7		\n"	\
+		"	ldd.p		%M0,%1			\n"	\
+		"	orcr		cc7,cc7,cc3		\n"	\
+		"	"#op"		%L1,%L3,%L2		\n"	\
+		"	"#op"		%1,%3,%2		\n"	\
+		"	cstd.p		%2,%M0		,cc3,#1	\n"	\
+		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	\
+		"	beq		icc3,#0,0b		\n"	\
+		: "+m"(*__v), "=&e"(old), "=e"(tmp)			\
+		: "e"(i)						\
+		: "memory", "cc7", "cc3", "icc3"			\
+		);							\
+									\
+	return old;							\
+}									\
+ATOMIC_EXPORT(__atomic64_fetch_##op);
+#endif
+
+ATOMIC_FETCH_OP(or)
+ATOMIC_FETCH_OP(and)
+ATOMIC_FETCH_OP(xor)
+
+ATOMIC_OP_RETURN(add)
+ATOMIC_OP_RETURN(sub)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_QUALS
+#undef ATOMIC_EXPORT
diff --git a/arch/frv/include/asm/bitops.h b/arch/frv/include/asm/bitops.h
index 96de220ef131..0df8e95e3715 100644
--- a/arch/frv/include/asm/bitops.h
+++ b/arch/frv/include/asm/bitops.h
@@ -25,109 +25,30 @@
 
 #include <asm-generic/bitops/ffz.h>
 
-#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-static inline
-unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v)
-{
-	unsigned long old, tmp;
-
-	asm volatile(
-		"0:						\n"
-		"	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-		"	ckeq		icc3,cc7		\n"
-		"	ld.p		%M0,%1			\n"	/* LD.P/ORCR are atomic */
-		"	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-		"	and%I3		%1,%3,%2		\n"
-		"	cst.p		%2,%M0		,cc3,#1	\n"	/* if store happens... */
-		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* ... clear ICC3.Z */
-		"	beq		icc3,#0,0b		\n"
-		: "+U"(*v), "=&r"(old), "=r"(tmp)
-		: "NPr"(~mask)
-		: "memory", "cc7", "cc3", "icc3"
-		);
-
-	return old;
-}
-
-static inline
-unsigned long atomic_test_and_OR_mask(unsigned long mask, volatile unsigned long *v)
-{
-	unsigned long old, tmp;
-
-	asm volatile(
-		"0:						\n"
-		"	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-		"	ckeq		icc3,cc7		\n"
-		"	ld.p		%M0,%1			\n"	/* LD.P/ORCR are atomic */
-		"	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-		"	or%I3		%1,%3,%2		\n"
-		"	cst.p		%2,%M0		,cc3,#1	\n"	/* if store happens... */
-		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* ... clear ICC3.Z */
-		"	beq		icc3,#0,0b		\n"
-		: "+U"(*v), "=&r"(old), "=r"(tmp)
-		: "NPr"(mask)
-		: "memory", "cc7", "cc3", "icc3"
-		);
-
-	return old;
-}
-
-static inline
-unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsigned long *v)
-{
-	unsigned long old, tmp;
-
-	asm volatile(
-		"0:						\n"
-		"	orcc		gr0,gr0,gr0,icc3	\n"	/* set ICC3.Z */
-		"	ckeq		icc3,cc7		\n"
-		"	ld.p		%M0,%1			\n"	/* LD.P/ORCR are atomic */
-		"	orcr		cc7,cc7,cc3		\n"	/* set CC3 to true */
-		"	xor%I3		%1,%3,%2		\n"
-		"	cst.p		%2,%M0		,cc3,#1	\n"	/* if store happens... */
-		"	corcc		gr29,gr29,gr0	,cc3,#1	\n"	/* ... clear ICC3.Z */
-		"	beq		icc3,#0,0b		\n"
-		: "+U"(*v), "=&r"(old), "=r"(tmp)
-		: "NPr"(mask)
-		: "memory", "cc7", "cc3", "icc3"
-		);
-
-	return old;
-}
-
-#else
-
-extern unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v);
-extern unsigned long atomic_test_and_OR_mask(unsigned long mask, volatile unsigned long *v);
-extern unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsigned long *v);
-
-#endif
-
-#define atomic_clear_mask(mask, v)	atomic_test_and_ANDNOT_mask((mask), (v))
-#define atomic_set_mask(mask, v)	atomic_test_and_OR_mask((mask), (v))
+#include <asm/atomic.h>
 
 static inline int test_and_clear_bit(unsigned long nr, volatile void *addr)
 {
-	volatile unsigned long *ptr = addr;
-	unsigned long mask = 1UL << (nr & 31);
+	unsigned int *ptr = (void *)addr;
+	unsigned int mask = 1UL << (nr & 31);
 	ptr += nr >> 5;
-	return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0;
+	return (__atomic32_fetch_and(~mask, ptr) & mask) != 0;
 }
 
 static inline int test_and_set_bit(unsigned long nr, volatile void *addr)
 {
-	volatile unsigned long *ptr = addr;
-	unsigned long mask = 1UL << (nr & 31);
+	unsigned int *ptr = (void *)addr;
+	unsigned int mask = 1UL << (nr & 31);
 	ptr += nr >> 5;
-	return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0;
+	return (__atomic32_fetch_or(mask, ptr) & mask) != 0;
 }
 
 static inline int test_and_change_bit(unsigned long nr, volatile void *addr)
 {
-	volatile unsigned long *ptr = addr;
-	unsigned long mask = 1UL << (nr & 31);
+	unsigned int *ptr = (void *)addr;
+	unsigned int mask = 1UL << (nr & 31);
 	ptr += nr >> 5;
-	return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0;
+	return (__atomic32_fetch_xor(mask, ptr) & mask) != 0;
 }
 
 static inline void clear_bit(unsigned long nr, volatile void *addr)
diff --git a/arch/frv/kernel/dma.c b/arch/frv/kernel/dma.c
index 156184e17e57..370dc9fa0b11 100644
--- a/arch/frv/kernel/dma.c
+++ b/arch/frv/kernel/dma.c
@@ -109,13 +109,13 @@ static struct frv_dma_channel frv_dma_channels[FRV_DMA_NCHANS] = {
 
 static DEFINE_RWLOCK(frv_dma_channels_lock);
 
-unsigned long frv_dma_inprogress;
+unsigned int frv_dma_inprogress;
 
 #define frv_clear_dma_inprogress(channel) \
-	atomic_clear_mask(1 << (channel), &frv_dma_inprogress);
+	(void)__atomic32_fetch_and(~(1 << (channel)), &frv_dma_inprogress);
 
 #define frv_set_dma_inprogress(channel) \
-	atomic_set_mask(1 << (channel), &frv_dma_inprogress);
+	(void)__atomic32_fetch_or(1 << (channel), &frv_dma_inprogress);
 
 /*****************************************************************************/
 /*
diff --git a/arch/frv/kernel/frv_ksyms.c b/arch/frv/kernel/frv_ksyms.c
index 86c516d96dcd..cdb4ce9960eb 100644
--- a/arch/frv/kernel/frv_ksyms.c
+++ b/arch/frv/kernel/frv_ksyms.c
@@ -58,11 +58,6 @@ EXPORT_SYMBOL(__outsl_ns);
 EXPORT_SYMBOL(__insl_ns);
 
 #ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
-EXPORT_SYMBOL(atomic_test_and_ANDNOT_mask);
-EXPORT_SYMBOL(atomic_test_and_OR_mask);
-EXPORT_SYMBOL(atomic_test_and_XOR_mask);
-EXPORT_SYMBOL(atomic_add_return);
-EXPORT_SYMBOL(atomic_sub_return);
 EXPORT_SYMBOL(__xchg_32);
 EXPORT_SYMBOL(__cmpxchg_32);
 #endif
diff --git a/arch/frv/lib/Makefile b/arch/frv/lib/Makefile
index 4ff2fb1e6b16..970e8b4f1a02 100644
--- a/arch/frv/lib/Makefile
+++ b/arch/frv/lib/Makefile
@@ -5,4 +5,4 @@
 lib-y := \
 	__ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o __ucmpdi2.o \
 	checksum.o memcpy.o memset.o atomic-ops.o atomic64-ops.o \
-	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o
+	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o atomic-lib.o
diff --git a/arch/frv/lib/atomic-lib.c b/arch/frv/lib/atomic-lib.c
new file mode 100644
index 000000000000..4d1b887c248b
--- /dev/null
+++ b/arch/frv/lib/atomic-lib.c
@@ -0,0 +1,7 @@
+
+#include <linux/export.h>
+#include <asm/atomic.h>
+
+#define __ATOMIC_LIB__
+
+#include <asm/atomic_defs.h>
diff --git a/arch/frv/lib/atomic-ops.S b/arch/frv/lib/atomic-ops.S
index 5e9e6ab5dd0e..b7439a960b5b 100644
--- a/arch/frv/lib/atomic-ops.S
+++ b/arch/frv/lib/atomic-ops.S
@@ -19,116 +19,6 @@
 
 ###############################################################################
 #
-# unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v);
-#
-###############################################################################
-	.globl		atomic_test_and_ANDNOT_mask
-        .type		atomic_test_and_ANDNOT_mask,@function
-atomic_test_and_ANDNOT_mask:
-	not.p		gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	and		gr8,gr10,gr11
-	cst.p		gr11,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_test_and_ANDNOT_mask, .-atomic_test_and_ANDNOT_mask
-
-###############################################################################
-#
-# unsigned long atomic_test_and_OR_mask(unsigned long mask, volatile unsigned long *v);
-#
-###############################################################################
-	.globl		atomic_test_and_OR_mask
-        .type		atomic_test_and_OR_mask,@function
-atomic_test_and_OR_mask:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	or		gr8,gr10,gr11
-	cst.p		gr11,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_test_and_OR_mask, .-atomic_test_and_OR_mask
-
-###############################################################################
-#
-# unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsigned long *v);
-#
-###############################################################################
-	.globl		atomic_test_and_XOR_mask
-        .type		atomic_test_and_XOR_mask,@function
-atomic_test_and_XOR_mask:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	xor		gr8,gr10,gr11
-	cst.p		gr11,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_test_and_XOR_mask, .-atomic_test_and_XOR_mask
-
-###############################################################################
-#
-# int atomic_add_return(int i, atomic_t *v)
-#
-###############################################################################
-	.globl		atomic_add_return
-        .type		atomic_add_return,@function
-atomic_add_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	add		gr8,gr10,gr8
-	cst.p		gr8,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_add_return, .-atomic_add_return
-
-###############################################################################
-#
-# int atomic_sub_return(int i, atomic_t *v)
-#
-###############################################################################
-	.globl		atomic_sub_return
-        .type		atomic_sub_return,@function
-atomic_sub_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ld.p		@(gr9,gr0),gr8			/* LD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	sub		gr8,gr10,gr8
-	cst.p		gr8,@(gr9,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic_sub_return, .-atomic_sub_return
-
-###############################################################################
-#
 # uint32_t __xchg_32(uint32_t i, uint32_t *v)
 #
 ###############################################################################
diff --git a/arch/frv/lib/atomic64-ops.S b/arch/frv/lib/atomic64-ops.S
index b6194eeac127..c4c472308a33 100644
--- a/arch/frv/lib/atomic64-ops.S
+++ b/arch/frv/lib/atomic64-ops.S
@@ -20,100 +20,6 @@
 
 ###############################################################################
 #
-# long long atomic64_inc_return(atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_inc_return
-        .type		atomic64_inc_return,@function
-atomic64_inc_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	addicc		gr9,#1,gr9,icc0
-	addxi		gr8,#0,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_inc_return, .-atomic64_inc_return
-
-###############################################################################
-#
-# long long atomic64_dec_return(atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_dec_return
-        .type		atomic64_dec_return,@function
-atomic64_dec_return:
-	or.p		gr8,gr8,gr10
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	subicc		gr9,#1,gr9,icc0
-	subxi		gr8,#0,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_dec_return, .-atomic64_dec_return
-
-###############################################################################
-#
-# long long atomic64_add_return(long long i, atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_add_return
-        .type		atomic64_add_return,@function
-atomic64_add_return:
-	or.p		gr8,gr8,gr4
-	or		gr9,gr9,gr5
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	addcc		gr9,gr5,gr9,icc0
-	addx		gr8,gr4,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_add_return, .-atomic64_add_return
-
-###############################################################################
-#
-# long long atomic64_sub_return(long long i, atomic64_t *v)
-#
-###############################################################################
-	.globl		atomic64_sub_return
-        .type		atomic64_sub_return,@function
-atomic64_sub_return:
-	or.p		gr8,gr8,gr4
-	or		gr9,gr9,gr5
-0:
-	orcc		gr0,gr0,gr0,icc3		/* set ICC3.Z */
-	ckeq		icc3,cc7
-	ldd.p		@(gr10,gr0),gr8			/* LDD.P/ORCR must be atomic */
-	orcr		cc7,cc7,cc3			/* set CC3 to true */
-	subcc		gr9,gr5,gr9,icc0
-	subx		gr8,gr4,gr8,icc0
-	cstd.p		gr8,@(gr10,gr0)		,cc3,#1
-	corcc		gr29,gr29,gr0		,cc3,#1	/* clear ICC3.Z if store happens */
-	beq		icc3,#0,0b
-	bralr
-
-	.size		atomic64_sub_return, .-atomic64_sub_return
-
-###############################################################################
-#
 # uint64_t __xchg_64(uint64_t i, uint64_t *v)
 #
 ###############################################################################
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 7ca73f8546cc..702ee539f87d 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -16,83 +16,52 @@
 
 #include <linux/kernel.h>
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
-
-	flags = arch_local_irq_save();
-	ret = v->counter += i;
-	arch_local_irq_restore(flags);
-	return ret;
+#define ATOMIC_OP_RETURN(op, c_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)	\
+{								\
+	h8300flags flags;					\
+	int ret;						\
+								\
+	flags = arch_local_irq_save();				\
+	ret = v->counter c_op i;				\
+	arch_local_irq_restore(flags);				\
+	return ret;						\
 }
 
-#define atomic_add(i, v) atomic_add_return(i, v)
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
-
-	flags = arch_local_irq_save();
-	ret = v->counter -= i;
-	arch_local_irq_restore(flags);
-	return ret;
+#define ATOMIC_OP(op, c_op)					\
+static inline void atomic_##op(int i, atomic_t *v)		\
+{								\
+	h8300flags flags;					\
+								\
+	flags = arch_local_irq_save();				\
+	v->counter c_op i;					\
+	arch_local_irq_restore(flags);				\
 }
 
-#define atomic_sub(i, v) atomic_sub_return(i, v)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
+ATOMIC_OP_RETURN(add, +=)
+ATOMIC_OP_RETURN(sub, -=)
 
-static inline int atomic_inc_return(atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or,  |=)
+ATOMIC_OP(xor, ^=)
 
-	flags = arch_local_irq_save();
-	v->counter++;
-	ret = v->counter;
-	arch_local_irq_restore(flags);
-	return ret;
-}
-
-#define atomic_inc(v) atomic_inc_return(v)
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
+#define atomic_add(i, v)		(void)atomic_add_return(i, v)
+#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
-static inline int atomic_dec_return(atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
+#define atomic_sub(i, v)		(void)atomic_sub_return(i, v)
+#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
 
-	flags = arch_local_irq_save();
-	--v->counter;
-	ret = v->counter;
-	arch_local_irq_restore(flags);
-	return ret;
-}
+#define atomic_inc_return(v)		atomic_add_return(1, v)
+#define atomic_dec_return(v)		atomic_sub_return(1, v)
 
-#define atomic_dec(v) atomic_dec_return(v)
+#define atomic_inc(v)			(void)atomic_inc_return(v)
+#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
 
-static inline int atomic_dec_and_test(atomic_t *v)
-{
-	h8300flags flags;
-	int ret;
-
-	flags = arch_local_irq_save();
-	--v->counter;
-	ret = v->counter;
-	arch_local_irq_restore(flags);
-	return ret == 0;
-}
+#define atomic_dec(v)			(void)atomic_dec_return(v)
+#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
@@ -120,40 +89,4 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return ret;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *v)
-{
-	unsigned char ccr;
-	unsigned long tmp;
-
-	__asm__ __volatile__("stc ccr,%w3\n\t"
-			     "orc #0x80,ccr\n\t"
-			     "mov.l %0,%1\n\t"
-			     "and.l %2,%1\n\t"
-			     "mov.l %1,%0\n\t"
-			     "ldc %w3,ccr"
-			     : "=m"(*v), "=r"(tmp)
-			     : "g"(~(mask)), "r"(ccr));
-}
-
-static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
-{
-	unsigned char ccr;
-	unsigned long tmp;
-
-	__asm__ __volatile__("stc ccr,%w3\n\t"
-			     "orc #0x80,ccr\n\t"
-			     "mov.l %0,%1\n\t"
-			     "or.l %2,%1\n\t"
-			     "mov.l %1,%0\n\t"
-			     "ldc %w3,ccr"
-			     : "=m"(*v), "=r"(tmp)
-			     : "g"(~(mask)), "r"(ccr));
-}
-
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()    barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc()    barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
 #endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 93d07025f183..811d61f6422d 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -132,6 +132,10 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 0bf03501fe5c..be4beeb77d57 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -45,8 +45,6 @@ ia64_atomic_##op (int i, atomic_t *v)					\
 ATOMIC_OP(add, +)
 ATOMIC_OP(sub, -)
 
-#undef ATOMIC_OP
-
 #define atomic_add_return(i,v)						\
 ({									\
 	int __ia64_aar_i = (i);						\
@@ -71,6 +69,16 @@ ATOMIC_OP(sub, -)
 		: ia64_atomic_sub(__ia64_asr_i, v);			\
 })
 
+ATOMIC_OP(and, &)
+ATOMIC_OP(or, |)
+ATOMIC_OP(xor, ^)
+
+#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)
+
+#undef ATOMIC_OP
+
 #define ATOMIC64_OP(op, c_op)						\
 static __inline__ long							\
 ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
@@ -89,8 +97,6 @@ ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
 ATOMIC64_OP(add, +)
 ATOMIC64_OP(sub, -)
 
-#undef ATOMIC64_OP
-
 #define atomic64_add_return(i,v)					\
 ({									\
 	long __ia64_aar_i = (i);					\
@@ -115,6 +121,16 @@ ATOMIC64_OP(sub, -)
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
 
+ATOMIC64_OP(and, &)
+ATOMIC64_OP(or, |)
+ATOMIC64_OP(xor, ^)
+
+#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)
+
+#undef ATOMIC64_OP
+
 #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index 31bb74adba08..025e2a170493 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -94,6 +94,10 @@ static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -239,45 +243,4 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
-static __inline__ void atomic_clear_mask(unsigned long  mask, atomic_t *addr)
-{
-	unsigned long flags;
-	unsigned long tmp;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-		"# atomic_clear_mask		\n\t"
-		DCACHE_CLEAR("%0", "r5", "%1")
-		M32R_LOCK" %0, @%1;		\n\t"
-		"and	%0, %2;			\n\t"
-		M32R_UNLOCK" %0, @%1;		\n\t"
-		: "=&r" (tmp)
-		: "r" (addr), "r" (~mask)
-		: "memory"
-		__ATOMIC_CLOBBER
-	);
-	local_irq_restore(flags);
-}
-
-static __inline__ void atomic_set_mask(unsigned long  mask, atomic_t *addr)
-{
-	unsigned long flags;
-	unsigned long tmp;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-		"# atomic_set_mask		\n\t"
-		DCACHE_CLEAR("%0", "r5", "%1")
-		M32R_LOCK" %0, @%1;		\n\t"
-		"or	%0, %2;			\n\t"
-		M32R_UNLOCK" %0, @%1;		\n\t"
-		: "=&r" (tmp)
-		: "r" (addr), "r" (mask)
-		: "memory"
-		__ATOMIC_CLOBBER
-	);
-	local_irq_restore(flags);
-}
-
 #endif	/* _ASM_M32R_ATOMIC_H */
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index c18ddc74ef9a..62d6961e7f2b 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -156,7 +156,7 @@ void smp_flush_cache_all(void)
 	cpumask_clear_cpu(smp_processor_id(), &cpumask);
 	spin_lock(&flushcache_lock);
 	mask=cpumask_bits(&cpumask);
-	atomic_set_mask(*mask, (atomic_t *)&flushcache_cpumask);
+	atomic_or(*mask, (atomic_t *)&flushcache_cpumask);
 	send_IPI_mask(&cpumask, INVALIDATE_CACHE_IPI, 0);
 	_flush_cache_copyback_all();
 	while (flushcache_cpumask)
@@ -407,7 +407,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	flush_vma = vma;
 	flush_va = va;
 	mask=cpumask_bits(&cpumask);
-	atomic_set_mask(*mask, (atomic_t *)&flush_cpumask);
+	atomic_or(*mask, (atomic_t *)&flush_cpumask);
 
 	/*
 	 * We have to send the IPI only to
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index e85f047fb072..039fac120cc0 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -77,6 +77,10 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, eor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -170,16 +174,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 	return c != 0;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *v)
-{
-	__asm__ __volatile__("andl %1,%0" : "+m" (*v) : ASM_DI (~(mask)));
-}
-
-static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
-{
-	__asm__ __volatile__("orl %1,%0" : "+m" (*v) : ASM_DI (mask));
-}
-
 static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index 948d8688643c..21c4c268b86c 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -74,44 +74,14 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	int temp;
-
-	asm volatile (
-		"1:	LNKGETD %0, [%1]\n"
-		"	AND	%0, %0, %2\n"
-		"	LNKSETD	[%1] %0\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ	1b\n"
-		: "=&d" (temp)
-		: "da" (&v->counter), "bd" (~mask)
-		: "cc");
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	int temp;
-
-	asm volatile (
-		"1:	LNKGETD %0, [%1]\n"
-		"	OR	%0, %0, %2\n"
-		"	LNKSETD	[%1], %0\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ	1b\n"
-		: "=&d" (temp)
-		: "da" (&v->counter), "bd" (mask)
-		: "cc");
-}
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int result, temp;
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index f5d5898c1020..f8efe380fe8b 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -68,31 +68,14 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	__global_lock1(flags);
-	fence();
-	v->counter &= ~mask;
-	__global_unlock1(flags);
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	__global_lock1(flags);
-	fence();
-	v->counter |= mask;
-	__global_unlock1(flags);
-}
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 26d436336f2e..4c42fd9af777 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -137,6 +137,10 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 ATOMIC_OPS(add, +=, addu)
 ATOMIC_OPS(sub, -=, subu)
 
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -416,6 +420,9 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 
 ATOMIC64_OPS(add, +=, daddu)
 ATOMIC64_OPS(sub, -=, dsubu)
+ATOMIC64_OP(and, &=, and)
+ATOMIC64_OP(or, |=, or)
+ATOMIC64_OP(xor, ^=, xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index 5be655e83e70..375e59140c9c 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -89,6 +89,10 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -127,73 +131,6 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-/**
- * atomic_clear_mask - Atomically clear bits in memory
- * @mask: Mask of the bits to be cleared
- * @v: pointer to word in memory
- *
- * Atomically clears the bits set in mask from the memory word specified.
- */
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-#ifdef CONFIG_SMP
-	int status;
-
-	asm volatile(
-		"1:	mov	%3,(_AAR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"
-		"	and	%4,%0		\n"
-		"	mov	%0,(_ADR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"	/* flush */
-		"	mov	(_ASR,%2),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=m"(*addr)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(addr), "r"(~mask)
-		: "memory", "cc");
-#else
-	unsigned long flags;
-
-	mask = ~mask;
-	flags = arch_local_cli_save();
-	*addr &= mask;
-	arch_local_irq_restore(flags);
-#endif
-}
-
-/**
- * atomic_set_mask - Atomically set bits in memory
- * @mask: Mask of the bits to be set
- * @v: pointer to word in memory
- *
- * Atomically sets the bits set in mask from the memory word specified.
- */
-static inline void atomic_set_mask(unsigned long mask, unsigned long *addr)
-{
-#ifdef CONFIG_SMP
-	int status;
-
-	asm volatile(
-		"1:	mov	%3,(_AAR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"
-		"	or	%4,%0		\n"
-		"	mov	%0,(_ADR,%2)	\n"
-		"	mov	(_ADR,%2),%0	\n"	/* flush */
-		"	mov	(_ASR,%2),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=m"(*addr)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(addr), "r"(mask)
-		: "memory", "cc");
-#else
-	unsigned long flags;
-
-	flags = arch_local_cli_save();
-	*addr |= mask;
-	arch_local_irq_restore(flags);
-#endif
-}
-
 #endif /* __KERNEL__ */
 #endif /* CONFIG_SMP */
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/mn10300/mm/tlb-smp.c b/arch/mn10300/mm/tlb-smp.c
index e5d0ef722bfa..9a39ea9031d4 100644
--- a/arch/mn10300/mm/tlb-smp.c
+++ b/arch/mn10300/mm/tlb-smp.c
@@ -119,7 +119,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	flush_mm = mm;
 	flush_va = va;
 #if NR_CPUS <= BITS_PER_LONG
-	atomic_set_mask(cpumask.bits[0], &flush_cpumask.bits[0]);
+	atomic_or(cpumask.bits[0], (atomic_t *)&flush_cpumask.bits[0]);
 #else
 #error Not supported.
 #endif
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 226f8ca993f6..2536965d00ea 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -126,6 +126,10 @@ static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
 
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -185,6 +189,9 @@ static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v)	\
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
+ATOMIC64_OP(and, &=)
+ATOMIC64_OP(or, |=)
+ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 512d2782b043..55f106ed12bf 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -67,6 +67,10 @@ static __inline__ int atomic_##op##_return(int a, atomic_t *v)		\
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)
 
+ATOMIC_OP(and, and)
+ATOMIC_OP(or, or)
+ATOMIC_OP(xor, xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -304,6 +308,9 @@ static __inline__ long atomic64_##op##_return(long a, atomic64_t *v)	\
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(or, or)
+ATOMIC64_OP(xor, xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7c6bb4b17b49..ed3ab509faca 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -596,25 +596,6 @@ _GLOBAL(copy_page)
 	b	2b
 
 /*
- * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
- * void atomic_set_mask(atomic_t mask, atomic_t *addr);
- */
-_GLOBAL(atomic_clear_mask)
-10:	lwarx	r5,0,r4
-	andc	r5,r5,r3
-	PPC405_ERR77(0,r4)
-	stwcx.	r5,0,r4
-	bne-	10b
-	blr
-_GLOBAL(atomic_set_mask)
-10:	lwarx	r5,0,r4
-	or	r5,r5,r3
-	PPC405_ERR77(0,r4)
-	stwcx.	r5,0,r4
-	bne-	10b
-	blr
-
-/*
  * Extended precision shifts.
  *
  * Updated to be valid for shift counts from 0 to 63 inclusive.
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index adbe3802e377..117fa5c921c1 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -27,6 +27,7 @@
 #define __ATOMIC_OR	"lao"
 #define __ATOMIC_AND	"lan"
 #define __ATOMIC_ADD	"laa"
+#define __ATOMIC_XOR	"lax"
 #define __ATOMIC_BARRIER "bcr	14,0\n"
 
 #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -49,6 +50,7 @@
 #define __ATOMIC_OR	"or"
 #define __ATOMIC_AND	"nr"
 #define __ATOMIC_ADD	"ar"
+#define __ATOMIC_XOR	"xr"
 #define __ATOMIC_BARRIER "\n"
 
 #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -118,15 +120,17 @@ static inline void atomic_add(int i, atomic_t *v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 #define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	__ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER);
+#define ATOMIC_OP(op, OP)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER);	\
 }
 
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	__ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER);
-}
+ATOMIC_OP(and, AND)
+ATOMIC_OP(or, OR)
+ATOMIC_OP(xor, XOR)
+
+#undef ATOMIC_OP
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -167,6 +171,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"laog"
 #define __ATOMIC64_AND	"lang"
 #define __ATOMIC64_ADD	"laag"
+#define __ATOMIC64_XOR	"laxg"
 #define __ATOMIC64_BARRIER "bcr	14,0\n"
 
 #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -189,6 +194,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"ogr"
 #define __ATOMIC64_AND	"ngr"
 #define __ATOMIC64_ADD	"agr"
+#define __ATOMIC64_XOR	"xgr"
 #define __ATOMIC64_BARRIER "\n"
 
 #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -247,16 +253,6 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	__ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
 }
 
-static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v)
-{
-	__ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER);
-}
-
-static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
-{
-	__ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER);
-}
-
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
 static inline long long atomic64_cmpxchg(atomic64_t *v,
@@ -270,6 +266,17 @@ static inline long long atomic64_cmpxchg(atomic64_t *v,
 	return old;
 }
 
+#define ATOMIC64_OP(op, OP)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	__ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER);	\
+}
+
+ATOMIC64_OP(and, AND)
+ATOMIC64_OP(or, OR)
+ATOMIC64_OP(xor, XOR)
+
+#undef ATOMIC64_OP
 #undef __ATOMIC64_LOOP
 
 static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 9e733d965e08..f5a0bd778ace 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -381,7 +381,7 @@ static void disable_sync_clock(void *dummy)
 	 * increase the "sequence" counter to avoid the race of an
 	 * etr event and the complete recovery against get_sync_clock.
 	 */
-	atomic_clear_mask(0x80000000, sw_ptr);
+	atomic_andnot(0x80000000, sw_ptr);
 	atomic_inc(sw_ptr);
 }
 
@@ -392,7 +392,7 @@ static void disable_sync_clock(void *dummy)
 static void enable_sync_clock(void)
 {
 	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
-	atomic_set_mask(0x80000000, sw_ptr);
+	atomic_or(0x80000000, sw_ptr);
 }
 
 /*
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c98d89708e99..57309e9cdd80 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -170,20 +170,20 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 
 static void __set_cpu_idle(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
 	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
 }
 
 static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
 	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
 }
 
 static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
-			  &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
+		    &vcpu->arch.sie_block->cpuflags);
 	vcpu->arch.sie_block->lctl = 0x0000;
 	vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
 
@@ -196,7 +196,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
 {
-	atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
 }
 
 static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
@@ -919,7 +919,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
 	spin_unlock(&li->lock);
 
 	/* clear pending external calls set by sigp interpretation facility */
-	atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags);
+	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
 	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
 }
 
@@ -1020,7 +1020,7 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 
 	li->irq.ext = irq->u.ext;
 	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1035,7 +1035,7 @@ static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
 		/* another external call is pending */
 		return -EBUSY;
 	}
-	atomic_set_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
 	return 0;
 }
 
@@ -1061,7 +1061,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
 	*extcall = irq->u.extcall;
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1133,7 +1133,7 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
 
 	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
 	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1177,7 +1177,7 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
 				   0, 0, 2);
 
 	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1190,7 +1190,7 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
 				   0, 0, 2);
 
 	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 	return 0;
 }
 
@@ -1369,13 +1369,13 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
 	spin_lock(&li->lock);
 	switch (type) {
 	case KVM_S390_MCHK:
-		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+		atomic_or(CPUSTAT_STOP_INT, li->cpuflags);
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
+		atomic_or(CPUSTAT_IO_INT, li->cpuflags);
 		break;
 	default:
-		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+		atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
 		break;
 	}
 	spin_unlock(&li->lock);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2078f92d15ac..b73302fb0507 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1215,12 +1215,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
-	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		save_fp_ctl(&vcpu->run->s.regs.fpc);
@@ -1320,9 +1320,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 						    CPUSTAT_STOPPED);
 
 	if (test_kvm_facility(vcpu->kvm, 78))
-		atomic_set_mask(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+		atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
 	else if (test_kvm_facility(vcpu->kvm, 8))
-		atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+		atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
 
 	kvm_s390_vcpu_setup_model(vcpu);
 
@@ -1422,24 +1422,24 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 
 void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+	atomic_or(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 	exit_sie(vcpu);
 }
 
 void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+	atomic_andnot(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 }
 
 static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
 	exit_sie(vcpu);
 }
 
 static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
 {
-	atomic_clear_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
 }
 
 /*
@@ -1448,7 +1448,7 @@ static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
  * return immediately. */
 void exit_sie(struct kvm_vcpu *vcpu)
 {
-	atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
 	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
 		cpu_relax();
 }
@@ -1672,19 +1672,19 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	if (dbg->control & KVM_GUESTDBG_ENABLE) {
 		vcpu->guest_debug = dbg->control;
 		/* enforce guest PER */
-		atomic_set_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
 
 		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
 			rc = kvm_s390_import_bp_data(vcpu, dbg);
 	} else {
-		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
 		vcpu->arch.guestdbg.last_bp = 0;
 	}
 
 	if (rc) {
 		vcpu->guest_debug = 0;
 		kvm_s390_clear_bp_data(vcpu);
-		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
 	}
 
 	return rc;
@@ -1771,7 +1771,7 @@ retry:
 	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
 		if (!ibs_enabled(vcpu)) {
 			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
-			atomic_set_mask(CPUSTAT_IBS,
+			atomic_or(CPUSTAT_IBS,
 					&vcpu->arch.sie_block->cpuflags);
 		}
 		goto retry;
@@ -1780,7 +1780,7 @@ retry:
 	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
 		if (ibs_enabled(vcpu)) {
 			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
-			atomic_clear_mask(CPUSTAT_IBS,
+			atomic_andnot(CPUSTAT_IBS,
 					  &vcpu->arch.sie_block->cpuflags);
 		}
 		goto retry;
@@ -2280,7 +2280,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 		__disable_ibs_on_all_vcpus(vcpu->kvm);
 	}
 
-	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 	/*
 	 * Another VCPU might have used IBS while we were offline.
 	 * Let's play safe and flush the VCPU at startup.
@@ -2306,7 +2306,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
 	kvm_s390_clear_stop_irq(vcpu);
 
-	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
index 97a5fda83450..b94df40e5f2d 100644
--- a/arch/sh/include/asm/atomic-grb.h
+++ b/arch/sh/include/asm/atomic-grb.h
@@ -48,47 +48,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	int tmp;
-	unsigned int _mask = ~mask;
-
-	__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  @%1,   %0      \n\t" /* load  old value */
-		"   and     %2,   %0      \n\t" /* add */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (_mask)
-		: "memory" , "r0", "r1");
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	int 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  @%1,   %0      \n\t" /* load  old value */
-		"   or      %2,   %0      \n\t" /* or */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (mask)
-		: "memory" , "r0", "r1");
-}
-
 #endif /* __ASM_SH_ATOMIC_GRB_H */
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 61d107523f06..23fcdad5773e 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -37,27 +37,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
+ATOMIC_OP(and, &=)
+ATOMIC_OP(or, |=)
+ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	v->counter &= ~mask;
-	raw_local_irq_restore(flags);
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	v->counter |= mask;
-	raw_local_irq_restore(flags);
-}
-
 #endif /* __ASM_SH_ATOMIC_IRQ_H */
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index 8575dccb9ef7..33d34b16d4d6 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -52,37 +52,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
-"	and	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (~mask), "r" (&v->counter)
-	: "t");
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_set_mask	\n"
-"	or	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (mask), "r" (&v->counter)
-	: "t");
-}
-
 #endif /* __ASM_SH_ATOMIC_LLSC_H */
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 0e69b7e7a439..7dcbebbcaec6 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -17,10 +17,12 @@
 #include <asm/barrier.h>
 #include <asm-generic/atomic64.h>
 
-
 #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_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 4082749913ce..917084ace49d 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -33,6 +33,10 @@ long atomic64_##op##_return(long, atomic64_t *);
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 71cd65ab200c..b9d63c0a7aab 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,22 +27,38 @@ static DEFINE_SPINLOCK(dummy);
 
 #endif /* SMP */
 
-#define ATOMIC_OP(op, cop)						\
+#define ATOMIC_OP_RETURN(op, c_op)					\
 int atomic_##op##_return(int i, atomic_t *v)				\
 {									\
 	int ret;							\
 	unsigned long flags;						\
 	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
 									\
-	ret = (v->counter cop i);					\
+	ret = (v->counter c_op i);					\
 									\
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
 	return ret;							\
 }									\
 EXPORT_SYMBOL(atomic_##op##_return);
 
-ATOMIC_OP(add, +=)
+#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, ^=)
 
+#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 05dac43907d1..d6b0363f345b 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -47,6 +47,9 @@ ENDPROC(atomic_##op##_return);
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
@@ -84,6 +87,9 @@ ENDPROC(atomic64_##op##_return);
 
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1d649a95660c..bb6005997268 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -111,6 +111,9 @@ EXPORT_SYMBOL(atomic64_##op##_return);
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index 1b109fad9fff..d320ce253d86 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -34,6 +34,19 @@ static inline void atomic_add(int i, atomic_t *v)
 	_atomic_xchg_add(&v->counter, i);
 }
 
+#define ATOMIC_OP(op)							\
+unsigned long _atomic_##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_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
 /**
  * atomic_add_return - add integer and return
  * @v: pointer of type atomic_t
@@ -113,6 +126,17 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	_atomic64_xchg_add(&v->counter, i);
 }
 
+#define ATOMIC64_OP(op)						\
+long long _atomic64_##op(long long *v, long long n);		\
+static inline void atomic64_##op(long long i, atomic64_t *v)	\
+{								\
+	_atomic64_##op(&v->counter, i);				\
+}
+
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
+
 /**
  * atomic64_add_return - add integer and return
  * @v: pointer of type atomic64_t
@@ -225,6 +249,7 @@ 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,
 						  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 long long __atomic64_cmpxchg(volatile long long *p, int *lock,
@@ -234,6 +259,9 @@ extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
 					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);
 
 /* 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 0496970cef82..096a56d6ead4 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -58,6 +58,26 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	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;
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch4(&v->counter, guess ^ i);
+	} while (guess != oldval);
+}
+
 /* Now the true 64-bit operations. */
 
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -91,6 +111,26 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 	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_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1, (v))
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index c89b211fd9e7..298df1e9912a 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -94,6 +94,12 @@ unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask)
 }
 EXPORT_SYMBOL(_atomic_or);
 
+unsigned long _atomic_and(volatile unsigned long *p, unsigned long mask)
+{
+	return __atomic_and((int *)p, __atomic_setup(p), mask).val;
+}
+EXPORT_SYMBOL(_atomic_and);
+
 unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask)
 {
 	return __atomic_andn((int *)p, __atomic_setup(p), mask).val;
@@ -136,6 +142,23 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
+long long _atomic64_and(long long *v, long long n)
+{
+	return __atomic64_and(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_and);
+
+long long _atomic64_or(long long *v, long long n)
+{
+	return __atomic64_or(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_or);
+
+long long _atomic64_xor(long long *v, long long n)
+{
+	return __atomic64_xor(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_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 6bda3132cd61..f611265633d6 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -178,6 +178,7 @@ atomic_op _xchg_add, 32, "add r24, r22, r2"
 atomic_op _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"
 
@@ -191,6 +192,9 @@ atomic_op 64_xchg_add_unless, 64, \
 	{ 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 }"
 
 	jrp     lr              /* happy backtracer */
 
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index e9168955c42f..fb52aa644aab 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -182,6 +182,21 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	asm volatile(LOCK_PREFIX #op"l %1,%0"				\
+			: "+m" (v->counter)				\
+			: "ir" (i)					\
+			: "memory");					\
+}
+
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
 /**
  * __atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
@@ -219,16 +234,6 @@ static __always_inline short int atomic_inc_short(short int *v)
 	return *v;
 }
 
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "andl %0,%1"			\
-		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "orl %0,%1"			\
-		     : : "r" ((unsigned)(mask)), "m" (*(addr))	\
-		     : "memory")
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index b154de75c90c..a11c30b77fb5 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -313,4 +313,18 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
+#define ATOMIC64_OP(op, c_op)						\
+static inline void atomic64_##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;						\
+}
+
+ATOMIC64_OP(and, &)
+ATOMIC64_OP(or, |)
+ATOMIC64_OP(xor, ^)
+
+#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 b965f9e03f2a..50e33eff58de 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -220,4 +220,19 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
+#define ATOMIC64_OP(op)							\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	asm volatile(LOCK_PREFIX #op"q %1,%0"				\
+			: "+m" (v->counter)				\
+			: "er" (i)					\
+			: "memory");					\
+}
+
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
+
+#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 00b7d46b35b8..e0be67936990 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -145,6 +145,10 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -250,75 +254,6 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       and     %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (~mask), "a" (v)
-			: "memory"
-			);
-#else
-	unsigned int all_f = -1;
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       xor     %1, %4, %3\n"
-			"       and     %0, %0, %4\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval), "=a" (mask)
-			: "a" (v), "a" (all_f), "1" (mask)
-			: "a15", "memory"
-			);
-#endif
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       or      %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (mask), "a" (v)
-			: "memory"
-			);
-#else
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       or      %0, %0, %1\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval)
-			: "a" (mask), "a" (v)
-			: "a15", "memory"
-			);
-#endif
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */