1alloc_hugepages(2)            System Calls Manual           alloc_hugepages(2)
2
3
4

NAME

6       alloc_hugepages, free_hugepages - allocate or free huge pages
7

SYNOPSIS

9       void *syscall(SYS_alloc_hugepages, int key, void addr[.len], size_t len,
10                     int prot, int flag);
11       int syscall(SYS_free_hugepages, void *addr);
12
13       Note:  glibc provides no wrappers for these system calls, necessitating
14       the use of syscall(2).
15

DESCRIPTION

17       The system calls alloc_hugepages() and free_hugepages() were introduced
18       in  Linux  2.5.36 and removed again in Linux 2.5.54.  They existed only
19       on i386 and ia64  (when  built  with  CONFIG_HUGETLB_PAGE).   In  Linux
20       2.4.20,  the  syscall  numbers exist, but the calls fail with the error
21       ENOSYS.
22
23       On i386 the memory  management  hardware  knows  about  ordinary  pages
24       (4 KiB)  and  huge pages (2 or 4 MiB).  Similarly ia64 knows about huge
25       pages of several sizes.  These system calls serve  to  map  huge  pages
26       into the process's memory or to free them again.  Huge pages are locked
27       into memory, and are not swapped.
28
29       The key argument is an identifier.  When zero the  pages  are  private,
30       and not inherited by children.  When positive the pages are shared with
31       other applications using the same key,  and  inherited  by  child  pro‐
32       cesses.
33
34       The  addr argument of free_hugepages() tells which page is being freed:
35       it was the return value of a call to alloc_hugepages().  (The memory is
36       first  actually freed when all users have released it.)  The addr argu‐
37       ment of alloc_hugepages() is a hint, that the kernel  may  or  may  not
38       follow.  Addresses must be properly aligned.
39
40       The  len  argument is the length of the required segment.  It must be a
41       multiple of the huge page size.
42
43       The prot argument specifies the memory protection of the  segment.   It
44       is one of PROT_READ, PROT_WRITE, PROT_EXEC.
45
46       The flag argument is ignored, unless key is positive.  In that case, if
47       flag is IPC_CREAT, then a new huge page segment is  created  when  none
48       with  the  given  key existed.  If this flag is not set, then ENOENT is
49       returned when no segment with the given key exists.
50

RETURN VALUE

52       On success, alloc_hugepages() returns the  allocated  virtual  address,
53       and free_hugepages() returns zero.  On error, -1 is returned, and errno
54       is set to indicate the error.
55

ERRORS

57       ENOSYS The system call is not supported on this kernel.
58

FILES

60       /proc/sys/vm/nr_hugepages
61              Number of configured hugetlb pages.  This can be read and  writ‐
62              ten.
63
64       /proc/meminfo
65              Gives  info  on  the  number  of configured hugetlb pages and on
66              their   size   in   the   three    variables    HugePages_Total,
67              HugePages_Free, Hugepagesize.
68

STANDARDS

70       Linux on Intel processors.
71

HISTORY

73       These  system calls are gone; they existed only in Linux 2.5.36 through
74       to Linux 2.5.54.
75

NOTES

77       Now the hugetlbfs filesystem can be used  instead.   Memory  backed  by
78       huge  pages  (if the CPU supports them) is obtained by using mmap(2) to
79       map files in this virtual filesystem.
80
81       The maximal number of huge pages can be specified using the  hugepages=
82       boot parameter.
83
84
85
86Linux man-pages 6.04              2023-03-30                alloc_hugepages(2)
Impressum