arch-x86.h

Go to the documentation of this file.

/*-------------------------------------------------------------------------
 *
 * arch-x86.h
 *    Atomic operations considerations specific to intel x86
 *
 * Note that we actually require a 486 upwards because the 386 doesn't have
 * support for xadd and cmpxchg. Given that the 386 isn't supported anywhere
 * anymore that's not much of a restriction luckily.
 *
 * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * NOTES:
 *
 * src/include/port/atomics/arch-x86.h
 *
 *-------------------------------------------------------------------------
 */
 
/*
 * Both 32 and 64 bit x86 do not allow loads to be reordered with other loads,
 * or stores to be reordered with other stores, but a load can be performed
 * before a subsequent store.
 *
 * Technically, some x86-ish chips support uncached memory access and/or
 * special instructions that are weakly ordered.  In those cases we'd need
 * the read and write barriers to be lfence and sfence.  But since we don't
 * do those things, a compiler barrier should be enough.
 *
 * "lock; addl" has worked for longer than "mfence". It's also rumored to be
 * faster in many scenarios.
 */
 
#if defined(__GNUC__) || defined(__INTEL_COMPILER)
#if defined(__i386__)
#define pg_memory_barrier_impl()        \
    __asm__ __volatile__ ("lock; addl $0,0(%%esp)" : : : "memory", "cc")
#elif defined(__x86_64__)
#define pg_memory_barrier_impl()        \
    __asm__ __volatile__ ("lock; addl $0,0(%%rsp)" : : : "memory", "cc")
#endif
#endif /* defined(__GNUC__) || defined(__INTEL_COMPILER) */
 
#define pg_read_barrier_impl()      pg_compiler_barrier_impl()
#define pg_write_barrier_impl()     pg_compiler_barrier_impl()
 
/*
 * Provide implementation for atomics using inline assembly on x86 gcc. It's
 * nice to support older gcc's and the compare/exchange implementation here is
 * actually more efficient than the * __sync variant.
 */
#if defined(__GNUC__) || defined(__INTEL_COMPILER)
 
#define PG_HAVE_ATOMIC_FLAG_SUPPORT
typedef struct pg_atomic_flag
{
    volatile char value;
} pg_atomic_flag;
 
#define PG_HAVE_ATOMIC_U32_SUPPORT
typedef struct pg_atomic_uint32
{
    volatile uint32 value;
} pg_atomic_uint32;
 
/*
 * It's too complicated to write inline asm for 64bit types on 32bit and the
 * 486 can't do it anyway.
 */
#ifdef __x86_64__
#define PG_HAVE_ATOMIC_U64_SUPPORT
typedef struct pg_atomic_uint64
{
    /* alignment guaranteed due to being on a 64bit platform */
    volatile uint64 value;
} pg_atomic_uint64;
#endif  /* __x86_64__ */
 
#define PG_HAVE_ATOMIC_TEST_SET_FLAG
static inline bool
pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
{
    char        _res = 1;
 
    __asm__ __volatile__(
        "   lock            \n"
        "   xchgb   %0,%1   \n"
:       "+q"(_res), "+m"(ptr->value)
:
:       "memory");
    return _res == 0;
}
 
#define PG_HAVE_ATOMIC_CLEAR_FLAG
static inline void
pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr)
{
    /*
     * On a TSO architecture like x86 it's sufficient to use a compiler
     * barrier to achieve release semantics.
     */
    __asm__ __volatile__("" ::: "memory");
    ptr->value = 0;
}
 
#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
static inline bool
pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
                                    uint32 *expected, uint32 newval)
{
    char    ret;
 
    /*
     * Perform cmpxchg and use the zero flag which it implicitly sets when
     * equal to measure the success.
     */
    __asm__ __volatile__(
        "   lock                \n"
        "   cmpxchgl    %4,%5   \n"
        "   setz        %2      \n"
:       "=a" (*expected), "=m"(ptr->value), "=q" (ret)
:       "a" (*expected), "r" (newval), "m"(ptr->value)
:       "memory", "cc");
    return (bool) ret;
}
 
#define PG_HAVE_ATOMIC_FETCH_ADD_U32
static inline uint32
pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
{
    uint32 res;
    __asm__ __volatile__(
        "   lock                \n"
        "   xaddl   %0,%1       \n"
:       "=q"(res), "=m"(ptr->value)
:       "0" (add_), "m"(ptr->value)
:       "memory", "cc");
    return res;
}
 
#ifdef __x86_64__
 
#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
static inline bool
pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
                                    uint64 *expected, uint64 newval)
{
    char    ret;
 
    AssertPointerAlignment(expected, 8);
 
    /*
     * Perform cmpxchg and use the zero flag which it implicitly sets when
     * equal to measure the success.
     */
    __asm__ __volatile__(
        "   lock                \n"
        "   cmpxchgq    %4,%5   \n"
        "   setz        %2      \n"
:       "=a" (*expected), "=m"(ptr->value), "=q" (ret)
:       "a" (*expected), "r" (newval), "m"(ptr->value)
:       "memory", "cc");
    return (bool) ret;
}
 
#define PG_HAVE_ATOMIC_FETCH_ADD_U64
static inline uint64
pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
{
    uint64 res;
    __asm__ __volatile__(
        "   lock                \n"
        "   xaddq   %0,%1       \n"
:       "=q"(res), "=m"(ptr->value)
:       "0" (add_), "m"(ptr->value)
:       "memory", "cc");
    return res;
}
 
#endif /* __x86_64__ */
 
#endif /* defined(__GNUC__) || defined(__INTEL_COMPILER) */
 
/*
 * 8 byte reads / writes have single-copy atomicity on all x86-64 cpus.
 */
#if defined(__x86_64__)
#define PG_HAVE_8BYTE_SINGLE_COPY_ATOMICITY
#endif /* 8 byte single-copy atomicity */