Seth Woolley's Man Viewer

alloc_hugepages(2) - alloc_hugepages, free_hugepages, alloc_hugepages, free_hugepages - allocate or free huge pages - man 2 alloc_hugepages

([section] manual, -k keyword, -K [section] search, -f whatis)
man plain no title

ALLOC_HUGEPAGES(2)         Linux Programmer's Manual        ALLOC_HUGEPAGES(2)

       alloc_hugepages, free_hugepages - allocate or free huge pages

       void  *alloc_hugepages(int  key,  void *addr, size_t len, int prot, int

       int free_hugepages(void *addr);

       The system calls alloc_hugepages and free_hugepages were introduced  in(1,8)
       Linux  2.5.36  and  removed again in(1,8) 2.5.54.  They existed only on i386
       and ia64 (when built with CONFIG_HUGETLB_PAGE).  In  Linux  2.4.20  the
       syscall numbers exist, but the calls return ENOSYS.

       On  i386  the  memory management hardware knows about ordinary pages (4
       KiB) and huge pages (2 or 4 MiB). Similarly ia64 knows about huge pages
       of  several  sizes. These system calls serve to map huge pages into the
       process' memory or to free them again.  Huge pages are locked into mem-
       ory, and are not swapped.

       The  key  parameter  is an identifier. When zero the pages are private,
       and not inherited by children.  When positive the pages are shared with
       other  applications  using  the  same  key, and inherited by child pro-

       The addr parameter of free_hugepages() tells which page is being  freed
       -  it was the return value of a call to alloc_hugepages().  (The memory
       is first actually freed when all users(1,5) have  released  it.)   The  addr
       parameter  of  alloc_hugepages()  is a hint, that the kernel may or may
       not follow.  Addresses must be properly aligned.

       The len parameter is the length of the required segment. It must  be  a
       multiple of the huge page size.

       The  prot parameter specifies the memory protection of the segment.  It
       is one of PROT_READ, PROT_WRITE, PROT_EXEC.

       The flag parameter is ignored, unless key is positive. In that case, if(3,n)
       flag  is  IPC_CREAT,  then a new huge page segment is created when none
       with the given key existed. If this flag is not  set(7,n,1 builtins),  then  ENOENT  is
       returned when no segment with the given key exists.

       On  success, alloc_hugepages returns the allocated virtual(5,8) address, and
       free_hugepages returns zero. On error(8,n), -1 is returned, and errno is set(7,n,1 builtins)

       ENOSYS The system call is not supported on this kernel.

       These  calls  existed  only  in(1,8) Linux 2.5.36 - 2.5.54.  These calls are
       specific to Linux on Intel processors, and should not be used  in(1,8)  pro-
       grams  intended  to  be  portable.  Indeed, the system call numbers are
       marked for reuse, so programs using these may do something random(3,4,6) on  a
       future kernel.

       /proc(5,n)/sys/vm/nr_hugepages Number of configured hugetlb pages.  This can
       be read(2,n,1 builtins) and written.

       /proc(5,n)/meminfo Gives info(1,5,n) on the number of configured hugetlb pages  and
       on  their  size in(1,8) the three variables HugePages_Total, HugePages_Free,

       The system calls are gone. Now the hugetlbfs  filesystem  can  be  used
       instead.   Memory  backed  by  huge pages (if(3,n) the CPU supports them) is
       obtained by mmap'ing files in(1,8) this virtual(5,8) filesystem.

       The maximal number of huge pages can be specified using the  hugepages=
       boot parameter.

Linux 2.5.36                      2003-02-02                ALLOC_HUGEPAGES(2)

References for this manual (incoming links)