ATOMIC_OPS(3) BSD Library Functions Manual ATOMIC_OPS(3)NAMEatomic_ops — atomic memory operations
SYNOPSIS
#include <sys/atomic.h>
DESCRIPTION
The atomic_ops family of functions provide atomic memory operations.
There are 7 classes of atomic memory operations available:
atomic_add(3) These functions perform atomic addition.
atomic_and(3) These functions perform atomic logical “and”.
atomic_cas(3) These functions perform atomic compare-and-swap.
atomic_dec(3) These functions perform atomic decrement.
atomic_inc(3) These functions perform atomic increment.
atomic_or(3) These functions perform atomic logical “or”.
atomic_swap(3) These functions perform atomic swap.
Synchronization Mechanisms
Where the architecture does not provide hardware support for atomic com‐
pare and swap (CAS), atomicity is provided by a restartable sequence or
by a spinlock. The chosen method is not ordinarily distinguishable by or
visible to users of the interface. The following architectures can be
assumed to provide CAS in hardware: alpha, amd64, i386, powerpc, pow‐
erpc64, sparc64.
Scope and Restrictions
If hardware CAS is available, the atomic operations are globally atomic:
operations within a memory region shared between processes are guaranteed
to be performed atomically. If hardware CAS is not available, it may
only be assumed that the operations are atomic with respect to threads in
the same process. Additionally, if hardware CAS is not available, the
atomic operations must not be used within a signal handler.
Users of atomic memory operations should not make assumptions about how
the memory access is performed (specifically, the width of the memory
access). For this reason, applications making use of atomic memory oper‐
ations should limit their use to regular memory. The results of using
atomic memory operations on anything other than regular memory are unde‐
fined.
Users of atomic memory operations should take care to modify any given
memory location either entirely with atomic operations or entirely with
some other synchronization mechanism. Intermixing of atomic operations
with other synchronization mechanisms for the same memory location
results in undefined behavior.
Visibility and Ordering of Memory Accesses
If hardware CAS is available, stores to the target memory location by an
atomic operation will reach global visibility before the operation com‐
pletes. If hardware CAS is not available, the store may not reach global
visibility until some time after the atomic operation has completed.
However, in all cases a subsequent atomic operation on the same memory
cell will be delayed until the result of any preceeding operation has
reached global visibility.
Atomic operations are strongly ordered with respect to each other. The
global visibility of other loads and stores before and after an atomic
operation is undefined. Applications that require synchronization of
loads and stores with respect to an atomic operation must use memory bar‐
riers. See membar_ops(3).
Performance
Because atomic memory operations require expensive synchronization at the
hardware level, applications should take care to minimize their use. In
certain cases, it may be more appropriate to use a mutex, especially if
more than one memory location will be modified.
SEE ALSOatomic_add(3), atomic_and(3), atomic_cas(3), atomic_dec(3),
atomic_inc(3), atomic_or(3), atomic_swap(3), membar_ops(3)HISTORY
The atomic_ops functions first appeared in NetBSD 5.0.
BSD April 14, 2010 BSD
