mb(9) - NetBSD Manual Pages

MB(9)                  NetBSD Kernel Developer's Manual                  MB(9)


NAME

     mb, mb_memory, mb_read, mb_write -- memory barriers


SYNOPSIS

     #include <sys/lock.h>

     void
     mb_memory(void);

     void
     mb_read(void);

     void
     mb_write(void);


DESCRIPTION

     Many types of processor can execute instructions in a different order
     than issued by the compiler or assembler.  On a uniprocessor system, out
     of order execution is transparent to the programmer, operating system and
     applications, as the processor must ensure that it is self consistent.

     On multiprocessor systems, out of order execution can present a problem
     where locks are not used to guarantee atomicity of access, because loads
     and stores issued by any given processor can appear on the system bus
     (and thus appear to other processors) in an unpredictable order.

     mb_memory(), mb_read(), and mb_write() can be used to control the order
     in which memory accesses occur, and thus the order in which those
     accesses become visible to other processors.  They can be used to imple-
     ment ``lockless'' access to data structures where the necessary barrier
     conditions are well understood.

     Memory barriers can be computationally expensive, as they are considered
     ``serializing'' operations and may stall further execution until the pro-
     cessor has drained internal buffers and re-synchronized.

     The memory barrier primitives control only the order of memory access.
     They provide no guarantee that stores have been flushed to the bus, or
     that loads have been made from the bus.

     The memory barrier primitives are guaranteed only to prevent reordering
     of accesses to main memory.  They do not provide any guarantee of order-
     ing when used with device memory (for example, loads or stores to or from
     a PCI device).  To guarantee ordering of access to device memory, the
     bus_dma(9) and bus_space(9) interfaces should be used.


FUNCTIONS

     mb_memory()
           Issue a full memory barrier, ordering all memory accesses.  Causes
           all loads and stores preceding the call to mb_memory() to complete
           before further memory accesses can be made.

     mb_read()
           Issue a read memory barrier, ordering all loads from memory.
           Causes all loads preceding the call to mb_read() to complete before
           further loads can be made.  Stores may be reordered ahead of or
           behind a call to mb_read().

     mb_write()
           Issue a write memory barrier, ordering all stores to memory.
           Causes all stores preceding the call to mb_write() to complete
           before further stores can be made.  Loads may be reordered ahead of
           or behind a call to mb_write().


SEE ALSO

     __insn_barrier(3), bus_dma(9), bus_space(9), mutex(9), rwlock(9)


HISTORY

     The memory barrier primitives first appeared in NetBSD 5.0.

NetBSD 8.1                      January 2, 2011                     NetBSD 8.1