linux/arch/x86/include/asm/bitops.h
David Howells ca3d30cc02 x86_64, asm: Optimise fls(), ffs() and fls64()
fls(N), ffs(N) and fls64(N) can be optimised on x86_64.  Currently they use a
CMOV instruction after the BSR/BSF to set the destination register to -1 if the
value to be scanned was 0 (in which case BSR/BSF set the Z flag).

Instead, according to the AMD64 specification, we can make use of the fact that
BSR/BSF doesn't modify its output register if its input is 0.  By preloading
the output with -1 and incrementing the result, we achieve the desired result
without the need for a conditional check.

The Intel x86_64 specification, however, says that the result of BSR/BSF in
such a case is undefined.  That said, when queried, one of the Intel CPU
architects said that the behaviour on all Intel CPUs is that:

 (1) with BSRQ/BSFQ, the 64-bit destination register is written with its
     original value if the source is 0, thus, in essence, giving the effect we
     want.  And,

 (2) with BSRL/BSFL, the lower half of the 64-bit destination register is
     written with its original value if the source is 0, and the upper half is
     cleared, thus giving us the effect we want (we return a 4-byte int).

Further, it was indicated that they (Intel) are unlikely to get away with
changing the behaviour.

It might be possible to optimise the 32-bit versions of these functions, but
there's a lot more variation, and so the effective non-destructive property of
BSRL/BSRF cannot be relied on.

[ hpa: specifically, some 486 chips are known to NOT have this property. ]

I have benchmarked these functions on my Core2 Duo test machine using the
following program:

	#include <stdlib.h>
	#include <stdio.h>

	#ifndef __x86_64__
	#error
	#endif

	#define PAGE_SHIFT 12

	typedef unsigned long long __u64, u64;
	typedef unsigned int __u32, u32;
	#define noinline	__attribute__((noinline))

	static __always_inline int fls64(__u64 x)
	{
		long bitpos = -1;

		asm("bsrq %1,%0"
		    : "+r" (bitpos)
		    : "rm" (x));
		return bitpos + 1;
	}

	static inline unsigned long __fls(unsigned long word)
	{
		asm("bsr %1,%0"
		    : "=r" (word)
		    : "rm" (word));
		return word;
	}
	static __always_inline int old_fls64(__u64 x)
	{
		if (x == 0)
			return 0;
		return __fls(x) + 1;
	}

	static noinline // __attribute__((const))
	int old_get_order(unsigned long size)
	{
		int order;

		size = (size - 1) >> (PAGE_SHIFT - 1);
		order = -1;
		do {
			size >>= 1;
			order++;
		} while (size);
		return order;
	}

	static inline __attribute__((const))
	int get_order_old_fls64(unsigned long size)
	{
		int order;
		size--;
		size >>= PAGE_SHIFT;
		order = old_fls64(size);
		return order;
	}

	static inline __attribute__((const))
	int get_order(unsigned long size)
	{
		int order;
		size--;
		size >>= PAGE_SHIFT;
		order = fls64(size);
		return order;
	}

	unsigned long prevent_optimise_out;

	static noinline unsigned long test_old_get_order(void)
	{
		unsigned long n, total = 0;
		long rep, loop;

		for (rep = 1000000; rep > 0; rep--) {
			for (loop = 0; loop <= 16384; loop += 4) {
				n = 1UL << loop;
				total += old_get_order(n);
			}
		}
		return total;
	}

	static noinline unsigned long test_get_order_old_fls64(void)
	{
		unsigned long n, total = 0;
		long rep, loop;

		for (rep = 1000000; rep > 0; rep--) {
			for (loop = 0; loop <= 16384; loop += 4) {
				n = 1UL << loop;
				total += get_order_old_fls64(n);
			}
		}
		return total;
	}

	static noinline unsigned long test_get_order(void)
	{
		unsigned long n, total = 0;
		long rep, loop;

		for (rep = 1000000; rep > 0; rep--) {
			for (loop = 0; loop <= 16384; loop += 4) {
				n = 1UL << loop;
				total += get_order(n);
			}
		}
		return total;
	}

	int main(int argc, char **argv)
	{
		unsigned long total;

		switch (argc) {
		case 1:  total = test_old_get_order();		break;
		case 2:  total = test_get_order_old_fls64();	break;
		default: total = test_get_order();		break;
		}
		prevent_optimise_out = total;
		return 0;
	}

This allows me to test the use of the old fls64() implementation and the new
fls64() implementation and also to contrast these to the out-of-line loop-based
implementation of get_order().  The results were:

	warthog>time ./get_order
	real    1m37.191s
	user    1m36.313s
	sys     0m0.861s
	warthog>time ./get_order x
	real    0m16.892s
	user    0m16.586s
	sys     0m0.287s
	warthog>time ./get_order x x
	real    0m7.731s
	user    0m7.727s
	sys     0m0.002s

Using the current upstream fls64() as a basis for an inlined get_order() [the
second result above] is much faster than using the current out-of-line
loop-based get_order() [the first result above].

Using my optimised inline fls64()-based get_order() [the third result above]
is even faster still.

[ hpa: changed the selection of 32 vs 64 bits to use CONFIG_X86_64
  instead of comparing BITS_PER_LONG, updated comments, rebased manually
  on top of 83d99df7c4 x86, bitops: Move fls64.h inside __KERNEL__ ]

Signed-off-by: David Howells <dhowells@redhat.com>
Link: http://lkml.kernel.org/r/20111213145654.14362.39868.stgit@warthog.procyon.org.uk
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2011-12-15 15:16:49 -08:00

515 lines
13 KiB
C

#ifndef _ASM_X86_BITOPS_H
#define _ASM_X86_BITOPS_H
/*
* Copyright 1992, Linus Torvalds.
*
* Note: inlines with more than a single statement should be marked
* __always_inline to avoid problems with older gcc's inlining heuristics.
*/
#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 BITOP_ADDR(x) "=m" (*(volatile long *) (x))
#else
#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
#endif
#define ADDR BITOP_ADDR(addr)
/*
* We do the locked ops that don't return the old value as
* a mask operation on a byte.
*/
#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr))
#define CONST_MASK_ADDR(nr, addr) BITOP_ADDR((void *)(addr) + ((nr)>>3))
#define CONST_MASK(nr) (1 << ((nr) & 7))
/**
* 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 __always_inline void
set_bit(unsigned int nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "orb %1,%0"
: CONST_MASK_ADDR(nr, addr)
: "iq" ((u8)CONST_MASK(nr))
: "memory");
} else {
asm volatile(LOCK_PREFIX "bts %1,%0"
: BITOP_ADDR(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 __always_inline void
clear_bit(int nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "andb %1,%0"
: CONST_MASK_ADDR(nr, addr)
: "iq" ((u8)~CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX "btr %1,%0"
: BITOP_ADDR(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)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "xorb %1,%0"
: CONST_MASK_ADDR(nr, addr)
: "iq" ((u8)CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX "btc %1,%0"
: BITOP_ADDR(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 __always_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 __always_inline int constant_test_bit(unsigned 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" (*(unsigned long *)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)))
/**
* __ffs - find first set bit in word
* @word: The word to search
*
* Undefined if no bit exists, so code should check against 0 first.
*/
static inline unsigned long __ffs(unsigned long word)
{
asm("bsf %1,%0"
: "=r" (word)
: "rm" (word));
return word;
}
/**
* ffz - find first zero bit in word
* @word: The word to search
*
* Undefined if no zero exists, so code should check against ~0UL first.
*/
static inline unsigned long ffz(unsigned long word)
{
asm("bsf %1,%0"
: "=r" (word)
: "r" (~word));
return word;
}
/*
* __fls: find last set bit in word
* @word: The word to search
*
* Undefined if no set bit exists, so code should check against 0 first.
*/
static inline unsigned long __fls(unsigned long word)
{
asm("bsr %1,%0"
: "=r" (word)
: "rm" (word));
return word;
}
#undef ADDR
#ifdef __KERNEL__
/**
* ffs - find first set bit in word
* @x: the word to search
*
* This is defined the same way as the libc and compiler builtin ffs
* routines, therefore differs in spirit from the other bitops.
*
* ffs(value) returns 0 if value is 0 or the position of the first
* set bit if value is nonzero. The first (least significant) bit
* is at position 1.
*/
static inline int ffs(int x)
{
int r;
#ifdef CONFIG_X86_64
/*
* AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the
* dest reg is undefined if x==0, but their CPU architect says its
* value is written to set it to the same as before, except that the
* top 32 bits will be cleared.
*
* We cannot do this on 32 bits because at the very least some
* 486 CPUs did not behave this way.
*/
long tmp = -1;
asm("bsfl %1,%0"
: "=r" (r)
: "rm" (x), "0" (tmp));
#elif defined(CONFIG_X86_CMOV)
asm("bsfl %1,%0\n\t"
"cmovzl %2,%0"
: "=&r" (r) : "rm" (x), "r" (-1));
#else
asm("bsfl %1,%0\n\t"
"jnz 1f\n\t"
"movl $-1,%0\n"
"1:" : "=r" (r) : "rm" (x));
#endif
return r + 1;
}
/**
* fls - find last set bit in word
* @x: the word to search
*
* This is defined in a similar way as the libc and compiler builtin
* ffs, but returns the position of the most significant set bit.
*
* fls(value) returns 0 if value is 0 or the position of the last
* set bit if value is nonzero. The last (most significant) bit is
* at position 32.
*/
static inline int fls(int x)
{
int r;
#ifdef CONFIG_X86_64
/*
* AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the
* dest reg is undefined if x==0, but their CPU architect says its
* value is written to set it to the same as before, except that the
* top 32 bits will be cleared.
*
* We cannot do this on 32 bits because at the very least some
* 486 CPUs did not behave this way.
*/
long tmp = -1;
asm("bsrl %1,%0"
: "=r" (r)
: "rm" (x), "0" (tmp));
#elif defined(CONFIG_X86_CMOV)
asm("bsrl %1,%0\n\t"
"cmovzl %2,%0"
: "=&r" (r) : "rm" (x), "rm" (-1));
#else
asm("bsrl %1,%0\n\t"
"jnz 1f\n\t"
"movl $-1,%0\n"
"1:" : "=r" (r) : "rm" (x));
#endif
return r + 1;
}
/**
* fls64 - find last set bit in a 64-bit word
* @x: the word to search
*
* This is defined in a similar way as the libc and compiler builtin
* ffsll, but returns the position of the most significant set bit.
*
* fls64(value) returns 0 if value is 0 or the position of the last
* set bit if value is nonzero. The last (most significant) bit is
* at position 64.
*/
#ifdef CONFIG_X86_64
static __always_inline int fls64(__u64 x)
{
long bitpos = -1;
/*
* AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
* dest reg is undefined if x==0, but their CPU architect says its
* value is written to set it to the same as before.
*/
asm("bsrq %1,%0"
: "+r" (bitpos)
: "rm" (x));
return bitpos + 1;
}
#else
#include <asm-generic/bitops/fls64.h>
#endif
#include <asm-generic/bitops/find.h>
#include <asm-generic/bitops/sched.h>
#define ARCH_HAS_FAST_MULTIPLIER 1
#include <asm/arch_hweight.h>
#include <asm-generic/bitops/const_hweight.h>
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic-setbit.h>
#endif /* __KERNEL__ */
#endif /* _ASM_X86_BITOPS_H */