bitops: unify non-atomic bitops prototypes across architectures

Currently, there is a mess with the prototypes of the non-atomic
bitops across the different architectures:

ret	bool, int, unsigned long
nr	int, long, unsigned int, unsigned long
addr	volatile unsigned long *, volatile void *

Thankfully, it doesn't provoke any bugs, but can sometimes make
the compiler angry when it's not handy at all.
Adjust all the prototypes to the following standard:

ret	bool				retval can be only 0 or 1
nr	unsigned long			native; signed makes no sense
addr	volatile unsigned long *	bitmaps are arrays of ulongs

Next, some architectures don't define 'arch_' versions as they don't
support instrumentation, others do. To make sure there is always the
same set of callables present and to ease any potential future
changes, make them all follow the rule:
 * architecture-specific files define only 'arch_' versions;
 * non-prefixed versions can be defined only in asm-generic files;
and place the non-prefixed definitions into a new file in
asm-generic to be included by non-instrumented architectures.

Finally, add some static assertions in order to prevent people from
making a mess in this room again.
I also used the %__always_inline attribute consistently, so that
they always get resolved to the actual operations.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Yury Norov <yury.norov@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>

7 files changed, 153 insertions, 111 deletions

diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h
index e1d8483a45f2..492c7713ddae 100644
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -46,8 +46,8 @@ set_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static inline void
-__set_bit(unsigned long nr, volatile void * addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	int *m = ((int *) addr) + (nr >> 5);
 
@@ -82,8 +82,8 @@ clear_bit_unlock(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static __inline__ void
-__clear_bit(unsigned long nr, volatile void * addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	int *m = ((int *) addr) + (nr >> 5);
 
@@ -94,7 +94,7 @@ static inline void
 __clear_bit_unlock(unsigned long nr, volatile void * addr)
 {
 	smp_mb();
-	__clear_bit(nr, addr);
+	arch___clear_bit(nr, addr);
 }
 
 static inline void
@@ -118,8 +118,8 @@ change_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static __inline__ void
-__change_bit(unsigned long nr, volatile void * addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	int *m = ((int *) addr) + (nr >> 5);
 
@@ -186,8 +186,8 @@ test_and_set_bit_lock(unsigned long nr, volatile void *addr)
 /*
  * WARNING: non atomic version.
  */
-static inline int
-__test_and_set_bit(unsigned long nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = 1 << (nr & 0x1f);
 	int *m = ((int *) addr) + (nr >> 5);
@@ -230,8 +230,8 @@ test_and_clear_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static inline int
-__test_and_clear_bit(unsigned long nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = 1 << (nr & 0x1f);
 	int *m = ((int *) addr) + (nr >> 5);
@@ -272,8 +272,8 @@ test_and_change_bit(unsigned long nr, volatile void * addr)
 /*
  * WARNING: non atomic version.
  */
-static __inline__ int
-__test_and_change_bit(unsigned long nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = 1 << (nr & 0x1f);
 	int *m = ((int *) addr) + (nr >> 5);
@@ -283,8 +283,8 @@ __test_and_change_bit(unsigned long nr, volatile void * addr)
 	return (old & mask) != 0;
 }
 
-static inline int
-test_bit(int nr, const volatile void * addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
@@ -450,6 +450,8 @@ sched_find_first_bit(const unsigned long b[2])
 	return __ffs(tmp) + ofs;
 }
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index 75d6ba3643b8..da500471ac73 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -127,38 +127,45 @@ static inline void change_bit(int nr, volatile void *addr)
  * be atomic, particularly for things like slab_lock and slab_unlock.
  *
  */
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	test_and_clear_bit(nr, addr);
 }
 
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	test_and_set_bit(nr, addr);
 }
 
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	test_and_change_bit(nr, addr);
 }
 
 /*  Apparently, at least some of these are allowed to be non-atomic  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	return test_and_clear_bit(nr, addr);
 }
 
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
 
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	return test_and_change_bit(nr, addr);
 }
 
-static inline int __test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	int retval;
 
@@ -172,8 +179,6 @@ static inline int __test_bit(int nr, const volatile unsigned long *addr)
 	return retval;
 }
 
-#define test_bit(nr, addr) __test_bit(nr, addr)
-
 /*
  * ffz - find first zero in word.
  * @word: The word to search
@@ -271,6 +276,7 @@ static inline unsigned long __fls(unsigned long word)
 }
 
 #include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 577be93c0818..9f62af7fd7c4 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -53,7 +53,7 @@ set_bit (int nr, volatile void *addr)
 }
 
 /**
- * __set_bit - Set a bit in memory
+ * arch___set_bit - Set a bit in memory
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -61,8 +61,8 @@ set_bit (int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static __inline__ void
-__set_bit (int nr, volatile void *addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	*((__u32 *) addr + (nr >> 5)) |= (1 << (nr & 31));
 }
@@ -135,7 +135,7 @@ __clear_bit_unlock(int nr, void *addr)
 }
 
 /**
- * __clear_bit - Clears a bit in memory (non-atomic version)
+ * arch___clear_bit - Clears a bit in memory (non-atomic version)
  * @nr: the bit to clear
  * @addr: the address to start counting from
  *
@@ -143,8 +143,8 @@ __clear_bit_unlock(int nr, void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static __inline__ void
-__clear_bit (int nr, volatile void *addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	*((__u32 *) addr + (nr >> 5)) &= ~(1 << (nr & 31));
 }
@@ -175,7 +175,7 @@ change_bit (int nr, volatile void *addr)
 }
 
 /**
- * __change_bit - Toggle a bit in memory
+ * arch___change_bit - Toggle a bit in memory
  * @nr: the bit to toggle
  * @addr: the address to start counting from
  *
@@ -183,8 +183,8 @@ change_bit (int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static __inline__ void
-__change_bit (int nr, volatile void *addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	*((__u32 *) addr + (nr >> 5)) ^= (1 << (nr & 31));
 }
@@ -224,7 +224,7 @@ test_and_set_bit (int nr, volatile void *addr)
 #define test_and_set_bit_lock test_and_set_bit
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -232,8 +232,8 @@ test_and_set_bit (int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static __inline__ int
-__test_and_set_bit (int nr, volatile void *addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__u32 *p = (__u32 *) addr + (nr >> 5);
 	__u32 m = 1 << (nr & 31);
@@ -269,7 +269,7 @@ test_and_clear_bit (int nr, volatile void *addr)
 }
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
@@ -277,8 +277,8 @@ test_and_clear_bit (int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static __inline__ int
-__test_and_clear_bit(int nr, volatile void * addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__u32 *p = (__u32 *) addr + (nr >> 5);
 	__u32 m = 1 << (nr & 31);
@@ -314,14 +314,14 @@ test_and_change_bit (int nr, volatile void *addr)
 }
 
 /**
- * __test_and_change_bit - Change a bit and return its old value
+ * arch___test_and_change_bit - Change a bit and return its old value
  * @nr: Bit to change
  * @addr: Address to count from
  *
  * This operation is non-atomic and can be reordered.
  */
-static __inline__ int
-__test_and_change_bit (int nr, void *addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	__u32 old, bit = (1 << (nr & 31));
 	__u32 *m = (__u32 *) addr + (nr >> 5);
@@ -331,8 +331,8 @@ __test_and_change_bit (int nr, void *addr)
 	return (old & bit) != 0;
 }
 
-static __inline__ int
-test_bit (int nr, const volatile void *addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
@@ -443,6 +443,8 @@ static __inline__ unsigned long __arch_hweight64(unsigned long x)
 
 #ifdef __KERNEL__
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 51283db53667..71495faf2a90 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -65,8 +65,11 @@ static inline void bfset_mem_set_bit(int nr, volatile unsigned long *vaddr)
 				bfset_mem_set_bit(nr, vaddr))
 #endif
 
-#define __set_bit(nr, vaddr)	set_bit(nr, vaddr)
-
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	set_bit(nr, addr);
+}
 
 static inline void bclr_reg_clear_bit(int nr, volatile unsigned long *vaddr)
 {
@@ -105,8 +108,11 @@ static inline void bfclr_mem_clear_bit(int nr, volatile unsigned long *vaddr)
 				bfclr_mem_clear_bit(nr, vaddr))
 #endif
 
-#define __clear_bit(nr, vaddr)	clear_bit(nr, vaddr)
-
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	clear_bit(nr, addr);
+}
 
 static inline void bchg_reg_change_bit(int nr, volatile unsigned long *vaddr)
 {
@@ -145,14 +151,17 @@ static inline void bfchg_mem_change_bit(int nr, volatile unsigned long *vaddr)
 				bfchg_mem_change_bit(nr, vaddr))
 #endif
 
-#define __change_bit(nr, vaddr)	change_bit(nr, vaddr)
-
-
-static inline int test_bit(int nr, const volatile unsigned long *vaddr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
+	change_bit(nr, addr);
 }
 
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	return (addr[nr >> 5] & (1UL << (nr & 31))) != 0;
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
@@ -201,8 +210,11 @@ static inline int bfset_mem_test_and_set_bit(int nr,
 					bfset_mem_test_and_set_bit(nr, vaddr))
 #endif
 
-#define __test_and_set_bit(nr, vaddr)	test_and_set_bit(nr, vaddr)
-
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	return test_and_set_bit(nr, addr);
+}
 
 static inline int bclr_reg_test_and_clear_bit(int nr,
 					      volatile unsigned long *vaddr)
@@ -251,8 +263,11 @@ static inline int bfclr_mem_test_and_clear_bit(int nr,
 					bfclr_mem_test_and_clear_bit(nr, vaddr))
 #endif
 
-#define __test_and_clear_bit(nr, vaddr)	test_and_clear_bit(nr, vaddr)
-
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	return test_and_clear_bit(nr, addr);
+}
 
 static inline int bchg_reg_test_and_change_bit(int nr,
 					       volatile unsigned long *vaddr)
@@ -301,8 +316,11 @@ static inline int bfchg_mem_test_and_change_bit(int nr,
 					bfchg_mem_test_and_change_bit(nr, vaddr))
 #endif
 
-#define __test_and_change_bit(nr, vaddr) test_and_change_bit(nr, vaddr)
-
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	return test_and_change_bit(nr, addr);
+}
 
 /*
  *	The true 68020 and more advanced processors support the "bfffo"
@@ -522,6 +540,7 @@ static inline int __fls(int x)
 #define clear_bit_unlock	clear_bit
 #define __clear_bit_unlock	clear_bit_unlock
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 191dc7898b0f..9a7d15da966e 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -113,75 +113,76 @@ static inline bool arch_test_and_change_bit(unsigned long nr,
 	return old & mask;
 }
 
-static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	*addr |= mask;
+	*p |= mask;
 }
 
-static inline void arch___clear_bit(unsigned long nr,
-				    volatile unsigned long *ptr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	*addr &= ~mask;
+	*p &= ~mask;
 }
 
-static inline void arch___change_bit(unsigned long nr,
-				     volatile unsigned long *ptr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	*addr ^= mask;
+	*p ^= mask;
 }
 
-static inline bool arch___test_and_set_bit(unsigned long nr,
-					   volatile unsigned long *ptr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 	unsigned long old;
 
-	old = *addr;
-	*addr |= mask;
+	old = *p;
+	*p |= mask;
 	return old & mask;
 }
 
-static inline bool arch___test_and_clear_bit(unsigned long nr,
-					     volatile unsigned long *ptr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 	unsigned long old;
 
-	old = *addr;
-	*addr &= ~mask;
+	old = *p;
+	*p &= ~mask;
 	return old & mask;
 }
 
-static inline bool arch___test_and_change_bit(unsigned long nr,
-					      volatile unsigned long *ptr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
-	unsigned long *addr = __bitops_word(nr, ptr);
+	unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 	unsigned long old;
 
-	old = *addr;
-	*addr ^= mask;
+	old = *p;
+	*p ^= mask;
 	return old & mask;
 }
 
-static inline bool arch_test_bit(unsigned long nr,
-				 const volatile unsigned long *ptr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
-	const volatile unsigned long *addr = __bitops_word(nr, ptr);
+	const volatile unsigned long *p = __bitops_word(nr, addr);
 	unsigned long mask = __bitops_mask(nr);
 
-	return *addr & mask;
+	return *p & mask;
 }
 
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h
index cfe5465acce7..565a85d8b7fb 100644
--- a/arch/sh/include/asm/bitops-op32.h
+++ b/arch/sh/include/asm/bitops-op32.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_SH_BITOPS_OP32_H
 #define __ASM_SH_BITOPS_OP32_H
 
+#include <linux/bits.h>
+
 /*
  * The bit modifying instructions on SH-2A are only capable of working
  * with a 3-bit immediate, which signifies the shift position for the bit
@@ -16,7 +18,8 @@
 #define BYTE_OFFSET(nr)		((nr) % BITS_PER_BYTE)
 #endif
 
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
 		__asm__ __volatile__ (
@@ -33,7 +36,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
 	}
 }
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
 		__asm__ __volatile__ (
@@ -52,7 +56,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __change_bit - Toggle a bit in memory
+ * arch___change_bit - Toggle a bit in memory
  * @nr: the bit to change
  * @addr: the address to start counting from
  *
@@ -60,7 +64,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
 		__asm__ __volatile__ (
@@ -79,7 +84,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -87,7 +92,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -98,7 +104,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
@@ -106,7 +112,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -117,8 +124,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-					    volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -129,13 +136,16 @@ static inline int __test_and_change_bit(int nr,
 }
 
 /**
- * test_bit - Determine whether a bit is set
+ * arch_test_bit - Determine whether a bit is set
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+#include <asm-generic/bitops/non-instrumented-non-atomic.h>
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index a288ecd230ab..973c6bd17f98 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -63,7 +63,7 @@ arch_set_bit(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline void
-arch___set_bit(long nr, volatile unsigned long *addr)
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
@@ -89,7 +89,7 @@ arch_clear_bit_unlock(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline void
-arch___clear_bit(long nr, volatile unsigned long *addr)
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
@@ -114,7 +114,7 @@ arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline void
-arch___change_bit(long nr, volatile unsigned long *addr)
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
@@ -145,7 +145,7 @@ arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline bool
-arch___test_and_set_bit(long nr, volatile unsigned long *addr)
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -171,7 +171,7 @@ arch_test_and_clear_bit(long nr, volatile unsigned long *addr)
  * this without also updating arch/x86/kernel/kvm.c
  */
 static __always_inline bool
-arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -183,7 +183,7 @@ arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
 }
 
 static __always_inline bool
-arch___test_and_change_bit(long nr, volatile unsigned long *addr)
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -219,10 +219,12 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	return oldbit;
 }
 
-#define arch_test_bit(nr, addr)			\
-	(__builtin_constant_p((nr))		\
-	 ? constant_test_bit((nr), (addr))	\
-	 : variable_test_bit((nr), (addr)))
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
 
 /**
  * __ffs - find first set bit in word