[PATCH 1/3] x86: partial unification of asm-x86/bitops.h

[PATCH 1/3] x86: partial unification of asm-x86/bitops.h

[Jeremy Fitzhardinge]

[-- Attachment #1: x86-unify-bitops_h.patch --]
[-- Type: text/plain, Size: 26616 bytes --]

This unifies the set/clear/test bit functions of asm/bitops.h.

I have not attempted to merge the bit-finding functions, since they
rely on the machine word size and can't be easily restructured to work
generically without a lot of #ifdefs.  In particular, the 64-bit code
can assume the presence of conditional move instructions, whereas
32-bit needs to be more careful.

The inline assembly for the bit operations has been changed to remove
explicit sizing hints on the instructions, so the assembler will pick
the appropriate instruction forms depending on the architecture and
the context.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>

---
 include/asm-x86/bitops.h    |  315 +++++++++++++++++++++++++++++++++++++++++++
 include/asm-x86/bitops_32.h |  308 ------------------------------------------
 include/asm-x86/bitops_64.h |  297 ----------------------------------------
 3 files changed, 315 insertions(+), 605 deletions(-)

===================================================================
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -1,5 +1,320 @@
+#ifndef _ASM_X86_BITOPS_H
+#define _ASM_X86_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <linux/compiler.h>
+#include <asm/alternative.h>
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
+/* Technically wrong, but this avoids compilation errors on some gcc
+   versions. */
+#define ADDR "=m" (*(volatile long *) addr)
+#else
+#define ADDR "+m" (*(volatile long *) addr)
+#endif
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile(LOCK_PREFIX "bts %1,%0"
+		     : ADDR
+		     : "Ir" (nr) : "memory");
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * 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 unsigned long *addr)
+{
+	asm volatile("bts %1,%0"
+		     : ADDR
+		     : "Ir" (nr) : "memory");
+}
+
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile(LOCK_PREFIX "btr %1,%0"
+		     : ADDR
+		     : "Ir" (nr));
+}
+
+/*
+ * clear_bit_unlock - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and implies release semantics before the memory
+ * operation. It can be used for an unlock.
+ */
+static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+{
+	barrier();
+	clear_bit(nr, addr);
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+}
+
+/*
+ * __clear_bit_unlock - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * __clear_bit() is non-atomic and implies release semantics before the memory
+ * operation. It can be used for an unlock if no other CPUs can concurrently
+ * modify other bits in the word.
+ *
+ * No memory barrier is required here, because x86 cannot reorder stores past
+ * older loads. Same principle as spin_unlock.
+ */
+static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+{
+	barrier();
+	__clear_bit(nr, addr);
+}
+
+#define smp_mb__before_clear_bit()	barrier()
+#define smp_mb__after_clear_bit()	barrier()
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * 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)
+{
+	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile(LOCK_PREFIX "btc %1,%0"
+		     : ADDR : "Ir" (nr));
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This is the same as test_and_set_bit on x86.
+ */
+static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+{
+	return test_and_set_bit(nr, addr);
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * 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)
+{
+	int oldbit;
+
+	asm("bts %2,%1\n\t"
+	    "sbb %0,%0"
+	    : "=r" (oldbit), ADDR
+	    : "Ir" (nr));
+	return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * 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)
+{
+	int oldbit;
+
+	asm volatile("btr %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr));
+	return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("btc %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
+{
+	return ((1UL << (nr % BITS_PER_LONG)) & (addr[nr / BITS_PER_LONG])) != 0;
+}
+
+static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("bt %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit)
+		     : "m" (*addr), "Ir" (nr));
+
+	return oldbit;
+}
+
+#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static int test_bit(int nr, const volatile unsigned long *addr);
+#endif
+
+#define test_bit(nr,addr)			\
+	(__builtin_constant_p(nr) ?		\
+	 constant_test_bit((nr),(addr)) :	\
+	 variable_test_bit((nr),(addr)))
+
+#undef ADDR
+
 #ifdef CONFIG_X86_32
 # include "bitops_32.h"
 #else
 # include "bitops_64.h"
 #endif
+
+#endif	/* _ASM_X86_BITOPS_H */
===================================================================
--- a/include/asm-x86/bitops_32.h
+++ b/include/asm-x86/bitops_32.h
@@ -4,314 +4,6 @@
 /*
  * Copyright 1992, Linus Torvalds.
  */
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <linux/compiler.h>
-#include <asm/alternative.h>
-
-/*
- * These have to be done with inline assembly: that way the bit-setting
- * is guaranteed to be atomic. All bit operations return 0 if the bit
- * was cleared before the operation and != 0 if it was not.
- *
- * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
- */
-
-#define ADDR (*(volatile long *) addr)
-
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile unsigned long *addr)
-{
-	__asm__ __volatile__( LOCK_PREFIX
-		"btsl %1,%0"
-		:"+m" (ADDR)
-		:"Ir" (nr));
-}
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * 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 unsigned long *addr)
-{
-	__asm__(
-		"btsl %1,%0"
-		:"+m" (ADDR)
-		:"Ir" (nr));
-}
-
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
-{
-	__asm__ __volatile__( LOCK_PREFIX
-		"btrl %1,%0"
-		:"+m" (ADDR)
-		:"Ir" (nr));
-}
-
-/*
- * clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and implies release semantics before the memory
- * operation. It can be used for an unlock.
- */
-static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
-{
-	barrier();
-	clear_bit(nr, addr);
-}
-
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
-{
-	__asm__ __volatile__(
-		"btrl %1,%0"
-		:"+m" (ADDR)
-		:"Ir" (nr));
-}
-
-/*
- * __clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * __clear_bit() is non-atomic and implies release semantics before the memory
- * operation. It can be used for an unlock if no other CPUs can concurrently
- * modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
- */
-static inline void __clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
-{
-	barrier();
-	__clear_bit(nr, addr);
-}
-
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * 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)
-{
-	__asm__ __volatile__(
-		"btcl %1,%0"
-		:"+m" (ADDR)
-		:"Ir" (nr));
-}
-
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered. It may be
- * reordered on other architectures than x86.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
-{
-	__asm__ __volatile__( LOCK_PREFIX
-		"btcl %1,%0"
-		:"+m" (ADDR)
-		:"Ir" (nr));
-}
-
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.  
- * It may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__( LOCK_PREFIX
-		"btsl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"+m" (ADDR)
-		:"Ir" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * test_and_set_bit_lock - Set a bit and return its old value for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is the same as test_and_set_bit on x86.
- */
-static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
-{
-	return test_and_set_bit(nr, addr);
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.  
- * 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)
-{
-	int oldbit;
-
-	__asm__(
-		"btsl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"+m" (ADDR)
-		:"Ir" (nr));
-	return oldbit;
-}
-
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__( LOCK_PREFIX
-		"btrl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"+m" (ADDR)
-		:"Ir" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.  
- * 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)
-{
-	int oldbit;
-
-	__asm__(
-		"btrl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"+m" (ADDR)
-		:"Ir" (nr));
-	return oldbit;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__(
-		"btcl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"+m" (ADDR)
-		:"Ir" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.  
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__( LOCK_PREFIX
-		"btcl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"+m" (ADDR)
-		:"Ir" (nr) : "memory");
-	return oldbit;
-}
-
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static int test_bit(int nr, const volatile void *addr);
-#endif
-
-static __always_inline int constant_test_bit(int nr, const volatile unsigned long *addr)
-{
-	return ((1UL << (nr & 31)) & (addr[nr >> 5])) != 0;
-}
-
-static inline int variable_test_bit(int nr, const volatile unsigned long *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__(
-		"btl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit)
-		:"m" (ADDR),"Ir" (nr));
-	return oldbit;
-}
-
-#define test_bit(nr, addr) \
-	(__builtin_constant_p(nr) ? \
-		constant_test_bit((nr), (addr)) : \
-		variable_test_bit((nr), (addr)))
-
-#undef ADDR
 
 /**
  * find_first_zero_bit - find the first zero bit in a memory region
===================================================================
--- a/include/asm-x86/bitops_64.h
+++ b/include/asm-x86/bitops_64.h
@@ -4,303 +4,6 @@
 /*
  * Copyright 1992, Linus Torvalds.
  */
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <asm/alternative.h>
-
-#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
-/* Technically wrong, but this avoids compilation errors on some gcc
-   versions. */
-#define ADDR "=m" (*(volatile long *) addr)
-#else
-#define ADDR "+m" (*(volatile long *) addr)
-#endif
-
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile void *addr)
-{
-	__asm__ __volatile__( LOCK_PREFIX
-		"btsl %1,%0"
-		:ADDR
-		:"dIr" (nr) : "memory");
-}
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * 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)
-{
-	__asm__ volatile(
-		"btsl %1,%0"
-		:ADDR
-		:"dIr" (nr) : "memory");
-}
-
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile void *addr)
-{
-	__asm__ __volatile__( LOCK_PREFIX
-		"btrl %1,%0"
-		:ADDR
-		:"dIr" (nr));
-}
-
-/*
- * clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and implies release semantics before the memory
- * operation. It can be used for an unlock.
- */
-static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
-{
-	barrier();
-	clear_bit(nr, addr);
-}
-
-static inline void __clear_bit(int nr, volatile void *addr)
-{
-	__asm__ __volatile__(
-		"btrl %1,%0"
-		:ADDR
-		:"dIr" (nr));
-}
-
-/*
- * __clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * __clear_bit() is non-atomic and implies release semantics before the memory
- * operation. It can be used for an unlock if no other CPUs can concurrently
- * modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
- */
-static inline void __clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
-{
-	barrier();
-	__clear_bit(nr, addr);
-}
-
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * 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)
-{
-	__asm__ __volatile__(
-		"btcl %1,%0"
-		:ADDR
-		:"dIr" (nr));
-}
-
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile void *addr)
-{
-	__asm__ __volatile__( LOCK_PREFIX
-		"btcl %1,%0"
-		:ADDR
-		:"dIr" (nr));
-}
-
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.  
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile void *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__( LOCK_PREFIX
-		"btsl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),ADDR
-		:"dIr" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * test_and_set_bit_lock - Set a bit and return its old value for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is the same as test_and_set_bit on x86.
- */
-static inline int test_and_set_bit_lock(int nr, volatile void *addr)
-{
-	return test_and_set_bit(nr, addr);
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.  
- * 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)
-{
-	int oldbit;
-
-	__asm__(
-		"btsl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),ADDR
-		:"dIr" (nr));
-	return oldbit;
-}
-
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.  
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile void *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__( LOCK_PREFIX
-		"btrl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),ADDR
-		:"dIr" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.  
- * 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)
-{
-	int oldbit;
-
-	__asm__(
-		"btrl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),ADDR
-		:"dIr" (nr));
-	return oldbit;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile void *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__(
-		"btcl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),ADDR
-		:"dIr" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.  
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile void *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__( LOCK_PREFIX
-		"btcl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),ADDR
-		:"dIr" (nr) : "memory");
-	return oldbit;
-}
-
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static int test_bit(int nr, const volatile void *addr);
-#endif
-
-static inline int constant_test_bit(int nr, const volatile void *addr)
-{
-	return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
-}
-
-static inline int variable_test_bit(int nr, volatile const void *addr)
-{
-	int oldbit;
-
-	__asm__ __volatile__(
-		"btl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit)
-		:"m" (*(volatile long *)addr),"dIr" (nr));
-	return oldbit;
-}
-
-#define test_bit(nr,addr) \
-(__builtin_constant_p(nr) ? \
- constant_test_bit((nr),(addr)) : \
- variable_test_bit((nr),(addr)))
-
-#undef ADDR
 
 extern long find_first_zero_bit(const unsigned long *addr, unsigned long size);
 extern long find_next_zero_bit(const unsigned long *addr, long size, long offset);

-- 

Re: [PATCH 1/3] x86: partial unification of asm-x86/bitops.h

[Ingo Molnar]

* Jeremy Fitzhardinge <jeremy@goop.org> wrote:

> This unifies the set/clear/test bit functions of asm/bitops.h.

great! I've added your 3 patches to x86.git. It built and booted fine.

	Ingo

[PATCH 2/3] x86: clean up bitops-related warnings

[Jeremy Fitzhardinge]

[-- Attachment #1: x86-bitops-warning-cleanup.patch --]
[-- Type: text/plain, Size: 7573 bytes --]

Add casts to appropriate places to silence spurious bitops warnings.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Andi Kleen <ak@suse.de>

---
 arch/x86/kernel/setup_64.c   |   31 ++++++++++++++++---------------
 arch/x86/kernel/smpboot_64.c |    4 ++--
 arch/x86/mm/numa_64.c        |    2 +-
 include/asm-x86/cpufeature.h |    2 +-
 include/asm-x86/numa_64.h    |    2 +-
 include/linux/thread_info.h  |   10 +++++-----
 6 files changed, 26 insertions(+), 25 deletions(-)

===================================================================
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -685,19 +685,19 @@ static void __cpuinit init_amd(struct cp
 
 	/* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
 	   3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
-	clear_bit(0*32+31, &c->x86_capability);
+	clear_bit(0*32+31, (unsigned long *)&c->x86_capability);
 
 	/* On C+ stepping K8 rep microcode works well for copy/memset */
 	level = cpuid_eax(1);
 	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
 			     level >= 0x0f58))
-		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
+		set_bit(X86_FEATURE_REP_GOOD, (unsigned long *)&c->x86_capability);
 	if (c->x86 == 0x10 || c->x86 == 0x11)
-		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
+		set_bit(X86_FEATURE_REP_GOOD, (unsigned long *)&c->x86_capability);
 
 	/* Enable workaround for FXSAVE leak */
 	if (c->x86 >= 6)
-		set_bit(X86_FEATURE_FXSAVE_LEAK, &c->x86_capability);
+		set_bit(X86_FEATURE_FXSAVE_LEAK, (unsigned long *)&c->x86_capability);
 
 	level = get_model_name(c);
 	if (!level) {
@@ -713,7 +713,7 @@ static void __cpuinit init_amd(struct cp
 
 	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
 	if (c->x86_power & (1<<8))
-		set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+		set_bit(X86_FEATURE_CONSTANT_TSC, (unsigned long *)&c->x86_capability);
 
 	/* Multi core CPU? */
 	if (c->extended_cpuid_level >= 0x80000008)
@@ -726,14 +726,14 @@ static void __cpuinit init_amd(struct cp
 		num_cache_leaves = 3;
 
 	if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
-		set_bit(X86_FEATURE_K8, &c->x86_capability);
+		set_bit(X86_FEATURE_K8, (unsigned long *)&c->x86_capability);
 
 	/* RDTSC can be speculated around */
-	clear_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
+	clear_bit(X86_FEATURE_SYNC_RDTSC, (unsigned long *)&c->x86_capability);
 
 	/* Family 10 doesn't support C states in MWAIT so don't use it */
 	if (c->x86 == 0x10 && !force_mwait)
-		clear_bit(X86_FEATURE_MWAIT, &c->x86_capability);
+		clear_bit(X86_FEATURE_MWAIT, (unsigned long *)&c->x86_capability);
 
 	if (c->x86 == 0x10)
 		fam10h_check_enable_mmcfg(c);
@@ -838,16 +838,17 @@ static void __cpuinit init_intel(struct 
 		unsigned eax = cpuid_eax(10);
 		/* Check for version and the number of counters */
 		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
-			set_bit(X86_FEATURE_ARCH_PERFMON, &c->x86_capability);
+			set_bit(X86_FEATURE_ARCH_PERFMON,
+				(unsigned long *)&c->x86_capability);
 	}
 
 	if (cpu_has_ds) {
 		unsigned int l1, l2;
 		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
 		if (!(l1 & (1<<11)))
-			set_bit(X86_FEATURE_BTS, c->x86_capability);
+			set_bit(X86_FEATURE_BTS, (unsigned long *)c->x86_capability);
 		if (!(l1 & (1<<12)))
-			set_bit(X86_FEATURE_PEBS, c->x86_capability);
+			set_bit(X86_FEATURE_PEBS, (unsigned long *)c->x86_capability);
 	}
 
 	n = c->extended_cpuid_level;
@@ -866,13 +867,13 @@ static void __cpuinit init_intel(struct 
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
-		set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+		set_bit(X86_FEATURE_CONSTANT_TSC, (unsigned long *)&c->x86_capability);
 	if (c->x86 == 6)
-		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
+		set_bit(X86_FEATURE_REP_GOOD, (unsigned long *)&c->x86_capability);
 	if (c->x86 == 15)
-		set_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
+		set_bit(X86_FEATURE_SYNC_RDTSC, (unsigned long *)&c->x86_capability);
 	else
-		clear_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
+		clear_bit(X86_FEATURE_SYNC_RDTSC, (unsigned long *)&c->x86_capability);
 	c->x86_max_cores = intel_num_cpu_cores(c);
 
 	srat_detect_node();
===================================================================
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -691,7 +691,7 @@ do_rest:
 	}
 	if (boot_error) {
 		cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */
-		clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */
+		clear_bit(cpu, (unsigned long *)&cpu_initialized); /* was set by cpu_init() */
 		clear_node_cpumask(cpu); /* was set by numa_add_cpu */
 		cpu_clear(cpu, cpu_present_map);
 		cpu_clear(cpu, cpu_possible_map);
@@ -1023,7 +1023,7 @@ void remove_cpu_from_maps(void)
 
 	cpu_clear(cpu, cpu_callout_map);
 	cpu_clear(cpu, cpu_callin_map);
-	clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */
+	clear_bit(cpu, (unsigned long *)&cpu_initialized); /* was set by cpu_init() */
 	clear_node_cpumask(cpu);
 }
 
===================================================================
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -549,7 +549,7 @@ void __init numa_initmem_init(unsigned l
 
 __cpuinit void numa_add_cpu(int cpu)
 {
-	set_bit(cpu, &node_to_cpumask_map[cpu_to_node(cpu)]);
+	set_bit(cpu, (unsigned long *)&node_to_cpumask_map[cpu_to_node(cpu)]);
 }
 
 void __cpuinit numa_set_node(int cpu, int node)
===================================================================
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -124,7 +124,7 @@
 	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
 	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) )	\
 	  ? 1 :								\
-	  test_bit(bit, (c)->x86_capability))
+	 test_bit(bit, (unsigned long *)(c)->x86_capability))
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
===================================================================
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -32,7 +32,7 @@ extern void __init init_cpu_to_node(void
 
 static inline void clear_node_cpumask(int cpu)
 {
-	clear_bit(cpu, &node_to_cpumask_map[cpu_to_node(cpu)]);
+	clear_bit(cpu, (unsigned long *)&node_to_cpumask_map[cpu_to_node(cpu)]);
 }
 
 #else
===================================================================
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -29,27 +29,27 @@ extern long do_no_restart_syscall(struct
 
 static inline void set_ti_thread_flag(struct thread_info *ti, int flag)
 {
-	set_bit(flag,&ti->flags);
+	set_bit(flag, (unsigned long *)&ti->flags);
 }
 
 static inline void clear_ti_thread_flag(struct thread_info *ti, int flag)
 {
-	clear_bit(flag,&ti->flags);
+	clear_bit(flag, (unsigned long *)&ti->flags);
 }
 
 static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag)
 {
-	return test_and_set_bit(flag,&ti->flags);
+	return test_and_set_bit(flag, (unsigned long *)&ti->flags);
 }
 
 static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag)
 {
-	return test_and_clear_bit(flag,&ti->flags);
+	return test_and_clear_bit(flag, (unsigned long *)&ti->flags);
 }
 
 static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 {
-	return test_bit(flag,&ti->flags);
+	return test_bit(flag, (unsigned long *)&ti->flags);
 }
 
 #define set_thread_flag(flag) \

-- 

Re: [PATCH 2/3] x86: clean up bitops-related warnings

[Andi Kleen]

On Wednesday 28 November 2007 00:01:26 Jeremy Fitzhardinge wrote:
> Add casts to appropriate places to silence spurious bitops warnings.

Looks a bit ugly. Perhaps it would be better to define standard wrappers

clear_bit_unaligned/any/bettername() etc. ?

-Andi

Re: [PATCH 2/3] x86: clean up bitops-related warnings

[Jeremy Fitzhardinge]

Andi Kleen wrote:
> On Wednesday 28 November 2007 00:01:26 Jeremy Fitzhardinge wrote:
>   
>> Add casts to appropriate places to silence spurious bitops warnings.
>>     
>
> Looks a bit ugly. Perhaps it would be better to define standard wrappers
>
> clear_bit_unaligned/any/bettername() etc. ?

Well, most of the casts are already in wrapper functions.  The
setup_64.c ones are ugly, but the following patch cleans them up.

    J

[PATCH 3/3] x86: add set/clear_cpu_cap operations

[Jeremy Fitzhardinge]

[-- Attachment #1: x86-set-clear-cpu_caps.patch --]
[-- Type: text/plain, Size: 10982 bytes --]

The patch to suppress bitops-related warnings added a pile of ugly
casts.  Many of these were related to the management of x86 CPU
capabilities.  Clean these up by adding specific set/clear_cpu_cap
macros, and use them consistently.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Andi Kleen <ak@suse.de>

---
 arch/x86/kernel/alternative.c              |   13 ++++++------
 arch/x86/kernel/apic_32.c                  |    8 +++----
 arch/x86/kernel/apic_64.c                  |    2 -
 arch/x86/kernel/cpu/addon_cpuid_features.c |    2 -
 arch/x86/kernel/cpu/mcheck/mce_64.c        |    2 -
 arch/x86/kernel/setup_32.c                 |    2 -
 arch/x86/kernel/setup_64.c                 |   29 +++++++++++++---------------
 arch/x86/kernel/vmi_32.c                   |   10 ++++-----
 include/asm-x86/cpufeature.h               |    5 +++-
 9 files changed, 38 insertions(+), 35 deletions(-)

===================================================================
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -356,15 +356,15 @@ void alternatives_smp_switch(int smp)
 	spin_lock_irqsave(&smp_alt, flags);
 	if (smp) {
 		printk(KERN_INFO "SMP alternatives: switching to SMP code\n");
-		clear_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
-		clear_bit(X86_FEATURE_UP, cpu_data(0).x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
+		clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
 		list_for_each_entry(mod, &smp_alt_modules, next)
 			alternatives_smp_lock(mod->locks, mod->locks_end,
 					      mod->text, mod->text_end);
 	} else {
 		printk(KERN_INFO "SMP alternatives: switching to UP code\n");
-		set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
-		set_bit(X86_FEATURE_UP, cpu_data(0).x86_capability);
+		set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
+		set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
 		list_for_each_entry(mod, &smp_alt_modules, next)
 			alternatives_smp_unlock(mod->locks, mod->locks_end,
 						mod->text, mod->text_end);
@@ -431,8 +431,9 @@ void __init alternative_instructions(voi
 	if (smp_alt_once) {
 		if (1 == num_possible_cpus()) {
 			printk(KERN_INFO "SMP alternatives: switching to UP code\n");
-			set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
-			set_bit(X86_FEATURE_UP, cpu_data(0).x86_capability);
+			set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
+			set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
+
 			alternatives_smp_unlock(__smp_locks, __smp_locks_end,
 						_text, _etext);
 		}
===================================================================
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1078,7 +1078,7 @@ static int __init detect_init_APIC (void
 		printk(KERN_WARNING "Could not enable APIC!\n");
 		return -1;
 	}
-	set_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
 
 	/* The BIOS may have set up the APIC at some other address */
@@ -1168,7 +1168,7 @@ int __init APIC_init_uniprocessor (void)
 int __init APIC_init_uniprocessor (void)
 {
 	if (enable_local_apic < 0)
-		clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 
 	if (!smp_found_config && !cpu_has_apic)
 		return -1;
@@ -1180,7 +1180,7 @@ int __init APIC_init_uniprocessor (void)
 	    APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
 		printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
 		       boot_cpu_physical_apicid);
-		clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 		return -1;
 	}
 
@@ -1536,7 +1536,7 @@ static int __init parse_nolapic(char *ar
 static int __init parse_nolapic(char *arg)
 {
 	enable_local_apic = -1;
-	clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 	return 0;
 }
 early_param("nolapic", parse_nolapic);
===================================================================
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -1193,7 +1193,7 @@ static __init int setup_disableapic(char
 static __init int setup_disableapic(char *str)
 {
 	disable_apic = 1;
-	clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 	return 0;
 }
 early_param("disableapic", setup_disableapic);
===================================================================
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -45,6 +45,6 @@ void __cpuinit init_scattered_cpuid_feat
 			&regs[CR_ECX], &regs[CR_EDX]);
 
 		if (regs[cb->reg] & (1 << cb->bit))
-			set_bit(cb->feature, c->x86_capability);
+			set_cpu_cap(c, cb->feature);
 	}
 }
===================================================================
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -80,7 +80,7 @@ void mce_log(struct mce *mce)
 			/* When the buffer fills up discard new entries. Assume
 			   that the earlier errors are the more interesting. */
 			if (entry >= MCE_LOG_LEN) {
-				set_bit(MCE_OVERFLOW, &mcelog.flags);
+				set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags);
 				return;
 			}
 			/* Old left over entry. Skip. */
===================================================================
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -238,7 +238,7 @@ static int __init parse_mem(char *arg)
 		return -EINVAL;
 
 	if (strcmp(arg, "nopentium") == 0) {
-		clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PSE);
 		disable_pse = 1;
 	} else {
 		/* If the user specifies memory size, we
===================================================================
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -691,13 +691,13 @@ static void __cpuinit init_amd(struct cp
 	level = cpuid_eax(1);
 	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
 			     level >= 0x0f58))
-		set_bit(X86_FEATURE_REP_GOOD, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 	if (c->x86 == 0x10 || c->x86 == 0x11)
-		set_bit(X86_FEATURE_REP_GOOD, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
 	/* Enable workaround for FXSAVE leak */
 	if (c->x86 >= 6)
-		set_bit(X86_FEATURE_FXSAVE_LEAK, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
 
 	level = get_model_name(c);
 	if (!level) {
@@ -713,7 +713,7 @@ static void __cpuinit init_amd(struct cp
 
 	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
 	if (c->x86_power & (1<<8))
-		set_bit(X86_FEATURE_CONSTANT_TSC, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 
 	/* Multi core CPU? */
 	if (c->extended_cpuid_level >= 0x80000008)
@@ -726,14 +726,14 @@ static void __cpuinit init_amd(struct cp
 		num_cache_leaves = 3;
 
 	if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
-		set_bit(X86_FEATURE_K8, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_K8);
 
 	/* RDTSC can be speculated around */
-	clear_bit(X86_FEATURE_SYNC_RDTSC, (unsigned long *)&c->x86_capability);
+	clear_cpu_cap(c, X86_FEATURE_SYNC_RDTSC);
 
 	/* Family 10 doesn't support C states in MWAIT so don't use it */
 	if (c->x86 == 0x10 && !force_mwait)
-		clear_bit(X86_FEATURE_MWAIT, (unsigned long *)&c->x86_capability);
+		clear_cpu_cap(c, X86_FEATURE_MWAIT);
 
 	if (c->x86 == 0x10)
 		fam10h_check_enable_mmcfg(c);
@@ -838,17 +838,16 @@ static void __cpuinit init_intel(struct 
 		unsigned eax = cpuid_eax(10);
 		/* Check for version and the number of counters */
 		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
-			set_bit(X86_FEATURE_ARCH_PERFMON,
-				(unsigned long *)&c->x86_capability);
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
 	}
 
 	if (cpu_has_ds) {
 		unsigned int l1, l2;
 		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
 		if (!(l1 & (1<<11)))
-			set_bit(X86_FEATURE_BTS, (unsigned long *)c->x86_capability);
+			set_cpu_cap(c, X86_FEATURE_BTS);
 		if (!(l1 & (1<<12)))
-			set_bit(X86_FEATURE_PEBS, (unsigned long *)c->x86_capability);
+			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
 	n = c->extended_cpuid_level;
@@ -867,13 +866,13 @@ static void __cpuinit init_intel(struct 
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
-		set_bit(X86_FEATURE_CONSTANT_TSC, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 	if (c->x86 == 6)
-		set_bit(X86_FEATURE_REP_GOOD, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 	if (c->x86 == 15)
-		set_bit(X86_FEATURE_SYNC_RDTSC, (unsigned long *)&c->x86_capability);
+		set_cpu_cap(c, X86_FEATURE_SYNC_RDTSC);
 	else
-		clear_bit(X86_FEATURE_SYNC_RDTSC, (unsigned long *)&c->x86_capability);
+		clear_cpu_cap(c, X86_FEATURE_SYNC_RDTSC);
 	c->x86_max_cores = intel_num_cpu_cores(c);
 
 	srat_detect_node();
===================================================================
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -963,19 +963,19 @@ static int __init parse_vmi(char *arg)
 		return -EINVAL;
 
 	if (!strcmp(arg, "disable_pge")) {
-		clear_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
 		disable_pge = 1;
 	} else if (!strcmp(arg, "disable_pse")) {
-		clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PSE);
 		disable_pse = 1;
 	} else if (!strcmp(arg, "disable_sep")) {
-		clear_bit(X86_FEATURE_SEP, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_SEP);
 		disable_sep = 1;
 	} else if (!strcmp(arg, "disable_tsc")) {
-		clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC);
 		disable_tsc = 1;
 	} else if (!strcmp(arg, "disable_mtrr")) {
-		clear_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability);
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_MTRR);
 		disable_mtrr = 1;
 	} else if (!strcmp(arg, "disable_timer")) {
 		disable_vmi_timer = 1;
===================================================================
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -124,8 +124,11 @@
 	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
 	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) )	\
 	  ? 1 :								\
-	 test_bit(bit, (unsigned long *)(c)->x86_capability))
+	 test_bit(bit, (unsigned long *)((c)->x86_capability)))
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
+
+#define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
+#define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
 #define cpu_has_vme		boot_cpu_has(X86_FEATURE_VME)

--