1ALLOC_HUGEPAGES(2)         Linux Programmer's Manual        ALLOC_HUGEPAGES(2)
2
3
4

NAME

6       alloc_hugepages, free_hugepages - allocate or free huge pages
7

SYNOPSIS

9       void *alloc_hugepages(int key, void *addr, size_t len,
10                             int prot, int flag);
11
12       int free_hugepages(void *addr);
13

DESCRIPTION

15       The system calls alloc_hugepages() and free_hugepages() were introduced
16       in Linux 2.5.36 and removed again in 2.5.54.  They existed only on i386
17       and  ia64  (when  built with CONFIG_HUGETLB_PAGE).  In Linux 2.4.20 the
18       syscall numbers exist, but the calls return ENOSYS.
19
20       On i386 the memory management hardware knows about  ordinary  pages  (4
21       KiB) and huge pages (2 or 4 MiB). Similarly ia64 knows about huge pages
22       of several sizes. These system calls serve to map huge pages  into  the
23       process' memory or to free them again.  Huge pages are locked into mem‐
24       ory, and are not swapped.
25
26       The key parameter is an identifier. When zero the  pages  are  private,
27       and not inherited by children.  When positive the pages are shared with
28       other applications using the same key,  and  inherited  by  child  pro‐
29       cesses.
30
31       The addr parameter of free_hugepages() tells which page is being freed:
32       it was the return value of a call to alloc_hugepages().  (The memory is
33       first actually freed when all users have released it.)  The addr param‐
34       eter of alloc_hugepages() is a hint, that the kernel  may  or  may  not
35       follow.  Addresses must be properly aligned.
36
37       The  len  parameter is the length of the required segment. It must be a
38       multiple of the huge page size.
39
40       The prot parameter specifies the memory protection of the segment.   It
41       is one of PROT_READ, PROT_WRITE, PROT_EXEC.
42
43       The flag parameter is ignored, unless key is positive. In that case, if
44       flag is IPC_CREAT, then a new huge page segment is  created  when  none
45       with  the  given  key  existed. If this flag is not set, then ENOENT is
46       returned when no segment with the given key exists.
47

RETURN VALUE

49       On success, alloc_hugepages() returns the  allocated  virtual  address,
50       and  free_hugepages() returns zero. On error, -1 is returned, and errno
51       is set appropriately.
52

ERRORS

54       ENOSYS The system call is not supported on this kernel.
55

CONFORMING TO

57       These calls existed only in Linux  2.5.36  through  to  2.5.54.   These
58       calls are specific to Linux on Intel processors, and should not be used
59       in programs intended to be portable. Indeed, the  system  call  numbers
60       are  marked  for reuse, so programs using these may do something random
61       on a future kernel.
62

FILES

64       /proc/sys/vm/nr_hugepages Number of configured hugetlb pages.  This can
65       be read and written.
66
67       /proc/meminfo  Gives info on the number of configured hugetlb pages and
68       on their size in the three variables  HugePages_Total,  HugePages_Free,
69       Hugepagesize.
70

NOTES

72       The  system  calls  are  gone. Now the hugetlbfs filesystem can be used
73       instead.  Memory backed by huge pages (if the  CPU  supports  them)  is
74       obtained by using mmap() to map files in this virtual filesystem.
75
76       The  maximal number of huge pages can be specified using the hugepages=
77       boot parameter.
78
79
80
81
82Linux 2.5.36                      2003-02-02                ALLOC_HUGEPAGES(2)
Impressum