linux/arch/x86/include/asm/barrier.h

#ifndef _ASM_X86_BARRIER_H
#define _ASM_X86_BARRIER_H

#include <asm/alternative.h>
#include <asm/nops.h>

/*
 * Force strict CPU ordering.
 * And yes, this is required on UP too when we're talking
 * to devices.
 */

#ifdef CONFIG_X86_32
/*
 * Some non-Intel clones support out of order store. wmb() ceases to be a
 * nop for these.
 */
#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
#else
#define mb() 	asm volatile("mfence":::"memory")
#define rmb()	asm volatile("lfence":::"memory")
#define wmb()	asm volatile("sfence" ::: "memory")
#endif

/**
 * read_barrier_depends - Flush all pending reads that subsequents reads
 * depend on.
 *
 * No data-dependent reads from memory-like regions are ever reordered
 * over this barrier.  All reads preceding this primitive are guaranteed
 * to access memory (but not necessarily other CPUs' caches) before any
 * reads following this primitive that depend on the data return by
 * any of the preceding reads.  This primitive is much lighter weight than
 * rmb() on most CPUs, and is never heavier weight than is
 * rmb().
 *
 * These ordering constraints are respected by both the local CPU
 * and the compiler.
 *
 * Ordering is not guaranteed by anything other than these primitives,
 * not even by data dependencies.  See the documentation for
 * memory_barrier() for examples and URLs to more information.
 *
 * For example, the following code would force ordering (the initial
 * value of "a" is zero, "b" is one, and "p" is "&a"):
 *
 * <programlisting>
 *	CPU 0				CPU 1
 *
 *	b = 2;
 *	memory_barrier();
 *	p = &b;				q = p;
 *					read_barrier_depends();
 *					d = *q;
 * </programlisting>
 *
 * because the read of "*q" depends on the read of "p" and these
 * two reads are separated by a read_barrier_depends().  However,
 * the following code, with the same initial values for "a" and "b":
 *
 * <programlisting>
 *	CPU 0				CPU 1
 *
 *	a = 2;
 *	memory_barrier();
 *	b = 3;				y = b;
 *					read_barrier_depends();
 *					x = a;
 * </programlisting>
 *
 * does not enforce ordering, since there is no data dependency between
 * the read of "a" and the read of "b".  Therefore, on some CPUs, such
 * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
 * in cases like this where there are no data dependencies.
 **/

#define read_barrier_depends()	do { } while (0)

#ifdef CONFIG_SMP
#define smp_mb()	mb()
#ifdef CONFIG_X86_PPRO_FENCE
# define smp_rmb()	rmb()
#else
# define smp_rmb()	barrier()
#endif
#ifdef CONFIG_X86_OOSTORE
# define smp_wmb() 	wmb()
#else
# define smp_wmb()	barrier()
#endif
#define smp_read_barrier_depends()	read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
#define smp_mb()	barrier()
#define smp_rmb()	barrier()
#define smp_wmb()	barrier()
#define smp_read_barrier_depends()	do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif /* SMP */

#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)

/*
 * For either of these options x86 doesn't have a strong TSO memory
 * model and we should fall back to full barriers.
 */

#define smp_store_release(p, v)						\
do {									\
	compiletime_assert_atomic_type(*p);				\
	smp_mb();							\
	ACCESS_ONCE(*p) = (v);						\
} while (0)

#define smp_load_acquire(p)						\
({									\
	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
	compiletime_assert_atomic_type(*p);				\
	smp_mb();							\
	___p1;								\
})

#else /* regular x86 TSO memory ordering */

#define smp_store_release(p, v)						\
do {									\
	compiletime_assert_atomic_type(*p);				\
	barrier();							\
	ACCESS_ONCE(*p) = (v);						\
} while (0)

#define smp_load_acquire(p)						\
({									\
	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
	compiletime_assert_atomic_type(*p);				\
	barrier();							\
	___p1;								\
})

#endif

/*
 * Stop RDTSC speculation. This is needed when you need to use RDTSC
 * (or get_cycles or vread that possibly accesses the TSC) in a defined
 * code region.
 *
 * (Could use an alternative three way for this if there was one.)
 */
static __always_inline void rdtsc_barrier(void)
{
	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
}

#endif /* _ASM_X86_BARRIER_H */