lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

mmap: handle mlocked pages during map, remap, unmap

Browse Source 
Originally by Nick Piggin <npiggin@suse.de>

Remove mlocked pages from the LRU using "unevictable infrastructure"
during mmap(), munmap(), mremap() and truncate().  Try to move back to
normal LRU lists on munmap() when last mlocked mapping removed.  Remove
PageMlocked() status when page truncated from file.

[akpm@linux-foundation.org: cleanup]
[kamezawa.hiroyu@jp.fujitsu.com: fix double unlock_page()]
[kosaki.motohiro@jp.fujitsu.com: split LRU: munlock rework]
[lee.schermerhorn@hp.com: mlock: fix __mlock_vma_pages_range comment block]
[akpm@linux-foundation.org: remove bogus kerneldoc token]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamewzawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Rik van Riel
2008-10-18 20:26:50 -07:00
committed by Linus Torvalds
parent 8edb08caf6
commit ba470de431
6 changed files with 180 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
mm/mremap.c
View File

@@ -24,6 +24,8 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include "internal.h"
static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
@@ -238,8 +240,8 @@ static unsigned long move_vma(struct vm_area_struct *vma,
if (vm_flags & VM_LOCKED) {
mm->locked_vm += new_len >> PAGE_SHIFT;
if (new_len > old_len)
make_pages_present(new_addr + old_len,
new_addr + new_len);
mlock_vma_pages_range(new_vma, new_addr + old_len,
new_addr + new_len);
}
return new_addr;
@@ -379,7 +381,7 @@ unsigned long do_mremap(unsigned long addr,
vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
if (vma->vm_flags & VM_LOCKED) {
mm->locked_vm += pages;
make_pages_present(addr + old_len,
mlock_vma_pages_range(vma, addr + old_len,
addr + new_len);
}
ret = addr;