UNMAP_KERNEL_RANGE_N(9) Memory Management in Linux UNMAP_KERNEL_RANGE_N(9)NAME
unmap_kernel_range_noflush - unmap kernel VM area
SYNOPSIS
void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
ARGUMENTS
addr
start of the VM area to unmap
size
size of the VM area to unmap
DESCRIPTION
Unmap PFN_UP(size) pages at addr. The VM area addr and size specify should have been allocated using get_vm_area and its friends.
NOTE
This function does NOT do any cache flushing. The caller is responsible for calling flush_cache_vunmap on to-be-mapped areas before calling
this function and flush_tlb_kernel_range after.
COPYRIGHT Kernel Hackers Manual 3.10 June 2014 UNMAP_KERNEL_RANGE_N(9)
Check Out this Related Man Page
mlock(3) Library Functions Manual mlock(3)NAME
mlock, munlock - Locks or unlocks a specified region in memory (P1003.1b)
LIBRARY
Realtime Library (librt.so, librt.a)
SYNOPSIS
#include <sys/mman.h>
int mlock (
const void *addr,
size_t len);
int munlock (
const void *addr,
size_t len);
PARAMETERS
*addr A pointer to the starting address of the region to lock or unlock. The addr argument must be a multiple of the page size returned
by the sysconf system call.
len The size of the memory region to lock or unlock. The value of len is rounded up to a multiple of the page size before decrementing
by 1.
DESCRIPTION
The mlock and munlock functions lock and unlock whole pages containing any part of the process address space starting at addr and continu-
ing for len bytes.
The mlock function guarantees all whole pages mapped by the range addr to addr+len-1 (inclusive) to be memory resident. (The area locked
is the same as if the len argument were rounded up to a multiple of the page size before decrementing by 1.)
The locked area remains locked until unlocked with a call to the munlock function, until the process calls the exec function, until an
address space associated with the lock is unmapped, or until the process terminates. A lock is not inherited across a fork or an exec.
The munlock function unlocks whole pages previously mapped by the range addr to addr+len-1 (inclusive), regardless of how many times the
mlock function was called by the process for any pages within the specified range.
A call to the munlock function does not affect pages that may be mapped into another process's address space or locked by another process.
You must have superuser privileges to call the mlock or munlock functions.
RETURN VALUES
On a successful call to the mlock function, a value of 0 (zero) is returned and the region becomes locked and memory resident. On an
unsuccessful call, a value of -1 is returned, no changes are made to any locks in the process address space, and errno is set to indicate
that an error occurred.
On a successful call to the munlock function, a value of 0 (zero) is returned and the memory is unlocked with respect to the process's
address space. On an unsuccessful call, a value of -1 is returned, none of the memory is unlocked, and errno is set to indicate that an
error occurred.
ERRORS
The mlock and munlock functions fail under the following conditions:
[EINVAL] The addr argument is not a multiple of the page size returned by sysconf.
[ENOMEM] Some or all of the address range specified by the addr and len arguments does not correspond to valid mapped pages in the
process's address space. For the mlock function, locking the pages mapped by the specified range would exceed an implemen-
tation-defined limit on the amount of memory that the process may lock.
If any of the following conditions occur, the mlock function fails:
[EAGAIN] Some or all of the memory identified by the operation could not be locked when the call was made.
[EPERM] The calling process does not have the appropriate privileges to perform the requested operation.
RELATED INFORMATION
Functions: exec(2), _exit(2), fork(2), munmap(2), sysconf(3)
Guide to Realtime Programming delim off
mlock(3)