2009-09-22 08:01:57 +08:00
|
|
|
#ifndef __LINUX_KSM_H
|
|
|
|
|
#define __LINUX_KSM_H
|
|
|
|
|
/*
|
|
|
|
|
* Memory merging support.
|
|
|
|
|
*
|
|
|
|
|
* This code enables dynamic sharing of identical pages found in different
|
|
|
|
|
* memory areas, even if they are not shared by fork().
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/bitops.h>
|
|
|
|
|
#include <linux/mm.h>
|
|
|
|
|
#include <linux/sched.h>
|
2009-09-22 08:02:01 +08:00
|
|
|
#include <linux/vmstat.h>
|
2009-09-22 08:01:57 +08:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_KSM
|
|
|
|
|
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
|
|
|
|
|
unsigned long end, int advice, unsigned long *vm_flags);
|
|
|
|
|
int __ksm_enter(struct mm_struct *mm);
|
ksm: fix deadlock with munlock in exit_mmap
Rawhide users have reported hang at startup when cryptsetup is run: the
same problem can be simply reproduced by running a program int main() {
mlockall(MCL_CURRENT | MCL_FUTURE); return 0; }
The problem is that exit_mmap() applies munlock_vma_pages_all() to
clean up VM_LOCKED areas, and its current implementation (stupidly)
tries to fault in absent pages, for example where PROT_NONE prevented
them being faulted in when mlocking. Whereas the "ksm: fix oom
deadlock" patch, knowing there's a race by which KSM might try to fault
in pages after exit_mmap() had finally zapped the range, backs out of
such faults doing nothing when its ksm_test_exit() notices mm_users 0.
So revert that part of "ksm: fix oom deadlock" which moved the
ksm_exit() call from before exit_mmap() to the middle of exit_mmap();
and remove those ksm_test_exit() checks from the page fault paths, so
allowing the munlocking to proceed without interference.
ksm_exit, if there are rmap_items still chained on this mm slot, takes
mmap_sem write side: so preventing KSM from working on an mm while
exit_mmap runs. And KSM will bail out as soon as it notices that
mm_users is already zero, thanks to its internal ksm_test_exit checks.
So that when a task is killed by OOM killer or the user, KSM will not
indefinitely prevent it from running exit_mmap to release its memory.
This does break a part of what "ksm: fix oom deadlock" was trying to
achieve. When unmerging KSM (echo 2 >/sys/kernel/mm/ksm), and even
when ksmd itself has to cancel a KSM page, it is possible that the
first OOM-kill victim would be the KSM process being faulted: then its
memory won't be freed until a second victim has been selected (freeing
memory for the unmerging fault to complete).
But the OOM killer is already liable to kill a second victim once the
intended victim's p->mm goes to NULL: so there's not much point in
rejecting this KSM patch before fixing that OOM behaviour. It is very
much more important to allow KSM users to boot up, than to haggle over
an unlikely and poorly supported OOM case.
We also intend to fix munlocking to not fault pages: at which point
this patch _could_ be reverted; though that would be controversial, so
we hope to find a better solution.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Justin M. Forbes <jforbes@redhat.com>
Acked-for-now-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:02:22 +08:00
|
|
|
void __ksm_exit(struct mm_struct *mm);
|
2009-09-22 08:01:57 +08:00
|
|
|
|
|
|
|
|
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
|
|
|
|
|
{
|
|
|
|
|
if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
|
|
|
|
|
return __ksm_enter(mm);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
ksm: fix deadlock with munlock in exit_mmap
Rawhide users have reported hang at startup when cryptsetup is run: the
same problem can be simply reproduced by running a program int main() {
mlockall(MCL_CURRENT | MCL_FUTURE); return 0; }
The problem is that exit_mmap() applies munlock_vma_pages_all() to
clean up VM_LOCKED areas, and its current implementation (stupidly)
tries to fault in absent pages, for example where PROT_NONE prevented
them being faulted in when mlocking. Whereas the "ksm: fix oom
deadlock" patch, knowing there's a race by which KSM might try to fault
in pages after exit_mmap() had finally zapped the range, backs out of
such faults doing nothing when its ksm_test_exit() notices mm_users 0.
So revert that part of "ksm: fix oom deadlock" which moved the
ksm_exit() call from before exit_mmap() to the middle of exit_mmap();
and remove those ksm_test_exit() checks from the page fault paths, so
allowing the munlocking to proceed without interference.
ksm_exit, if there are rmap_items still chained on this mm slot, takes
mmap_sem write side: so preventing KSM from working on an mm while
exit_mmap runs. And KSM will bail out as soon as it notices that
mm_users is already zero, thanks to its internal ksm_test_exit checks.
So that when a task is killed by OOM killer or the user, KSM will not
indefinitely prevent it from running exit_mmap to release its memory.
This does break a part of what "ksm: fix oom deadlock" was trying to
achieve. When unmerging KSM (echo 2 >/sys/kernel/mm/ksm), and even
when ksmd itself has to cancel a KSM page, it is possible that the
first OOM-kill victim would be the KSM process being faulted: then its
memory won't be freed until a second victim has been selected (freeing
memory for the unmerging fault to complete).
But the OOM killer is already liable to kill a second victim once the
intended victim's p->mm goes to NULL: so there's not much point in
rejecting this KSM patch before fixing that OOM behaviour. It is very
much more important to allow KSM users to boot up, than to haggle over
an unlikely and poorly supported OOM case.
We also intend to fix munlocking to not fault pages: at which point
this patch _could_ be reverted; though that would be controversial, so
we hope to find a better solution.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Justin M. Forbes <jforbes@redhat.com>
Acked-for-now-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:02:22 +08:00
|
|
|
static inline void ksm_exit(struct mm_struct *mm)
|
2009-09-22 08:01:57 +08:00
|
|
|
{
|
|
|
|
|
if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
|
ksm: fix deadlock with munlock in exit_mmap
Rawhide users have reported hang at startup when cryptsetup is run: the
same problem can be simply reproduced by running a program int main() {
mlockall(MCL_CURRENT | MCL_FUTURE); return 0; }
The problem is that exit_mmap() applies munlock_vma_pages_all() to
clean up VM_LOCKED areas, and its current implementation (stupidly)
tries to fault in absent pages, for example where PROT_NONE prevented
them being faulted in when mlocking. Whereas the "ksm: fix oom
deadlock" patch, knowing there's a race by which KSM might try to fault
in pages after exit_mmap() had finally zapped the range, backs out of
such faults doing nothing when its ksm_test_exit() notices mm_users 0.
So revert that part of "ksm: fix oom deadlock" which moved the
ksm_exit() call from before exit_mmap() to the middle of exit_mmap();
and remove those ksm_test_exit() checks from the page fault paths, so
allowing the munlocking to proceed without interference.
ksm_exit, if there are rmap_items still chained on this mm slot, takes
mmap_sem write side: so preventing KSM from working on an mm while
exit_mmap runs. And KSM will bail out as soon as it notices that
mm_users is already zero, thanks to its internal ksm_test_exit checks.
So that when a task is killed by OOM killer or the user, KSM will not
indefinitely prevent it from running exit_mmap to release its memory.
This does break a part of what "ksm: fix oom deadlock" was trying to
achieve. When unmerging KSM (echo 2 >/sys/kernel/mm/ksm), and even
when ksmd itself has to cancel a KSM page, it is possible that the
first OOM-kill victim would be the KSM process being faulted: then its
memory won't be freed until a second victim has been selected (freeing
memory for the unmerging fault to complete).
But the OOM killer is already liable to kill a second victim once the
intended victim's p->mm goes to NULL: so there's not much point in
rejecting this KSM patch before fixing that OOM behaviour. It is very
much more important to allow KSM users to boot up, than to haggle over
an unlikely and poorly supported OOM case.
We also intend to fix munlocking to not fault pages: at which point
this patch _could_ be reverted; though that would be controversial, so
we hope to find a better solution.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Justin M. Forbes <jforbes@redhat.com>
Acked-for-now-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:02:22 +08:00
|
|
|
__ksm_exit(mm);
|
2009-09-22 08:01:57 +08:00
|
|
|
}
|
2009-09-22 08:02:01 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* A KSM page is one of those write-protected "shared pages" or "merged pages"
|
|
|
|
|
* which KSM maps into multiple mms, wherever identical anonymous page content
|
|
|
|
|
* is found in VM_MERGEABLE vmas. It's a PageAnon page, with NULL anon_vma.
|
|
|
|
|
*/
|
|
|
|
|
static inline int PageKsm(struct page *page)
|
|
|
|
|
{
|
|
|
|
|
return ((unsigned long)page->mapping == PAGE_MAPPING_ANON);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* But we have to avoid the checking which page_add_anon_rmap() performs.
|
|
|
|
|
*/
|
|
|
|
|
static inline void page_add_ksm_rmap(struct page *page)
|
|
|
|
|
{
|
|
|
|
|
if (atomic_inc_and_test(&page->_mapcount)) {
|
|
|
|
|
page->mapping = (void *) PAGE_MAPPING_ANON;
|
|
|
|
|
__inc_zone_page_state(page, NR_ANON_PAGES);
|
|
|
|
|
}
|
|
|
|
|
}
|
2009-09-22 08:01:57 +08:00
|
|
|
#else /* !CONFIG_KSM */
|
|
|
|
|
|
|
|
|
|
static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
|
|
|
|
|
unsigned long end, int advice, unsigned long *vm_flags)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
ksm: fix deadlock with munlock in exit_mmap
Rawhide users have reported hang at startup when cryptsetup is run: the
same problem can be simply reproduced by running a program int main() {
mlockall(MCL_CURRENT | MCL_FUTURE); return 0; }
The problem is that exit_mmap() applies munlock_vma_pages_all() to
clean up VM_LOCKED areas, and its current implementation (stupidly)
tries to fault in absent pages, for example where PROT_NONE prevented
them being faulted in when mlocking. Whereas the "ksm: fix oom
deadlock" patch, knowing there's a race by which KSM might try to fault
in pages after exit_mmap() had finally zapped the range, backs out of
such faults doing nothing when its ksm_test_exit() notices mm_users 0.
So revert that part of "ksm: fix oom deadlock" which moved the
ksm_exit() call from before exit_mmap() to the middle of exit_mmap();
and remove those ksm_test_exit() checks from the page fault paths, so
allowing the munlocking to proceed without interference.
ksm_exit, if there are rmap_items still chained on this mm slot, takes
mmap_sem write side: so preventing KSM from working on an mm while
exit_mmap runs. And KSM will bail out as soon as it notices that
mm_users is already zero, thanks to its internal ksm_test_exit checks.
So that when a task is killed by OOM killer or the user, KSM will not
indefinitely prevent it from running exit_mmap to release its memory.
This does break a part of what "ksm: fix oom deadlock" was trying to
achieve. When unmerging KSM (echo 2 >/sys/kernel/mm/ksm), and even
when ksmd itself has to cancel a KSM page, it is possible that the
first OOM-kill victim would be the KSM process being faulted: then its
memory won't be freed until a second victim has been selected (freeing
memory for the unmerging fault to complete).
But the OOM killer is already liable to kill a second victim once the
intended victim's p->mm goes to NULL: so there's not much point in
rejecting this KSM patch before fixing that OOM behaviour. It is very
much more important to allow KSM users to boot up, than to haggle over
an unlikely and poorly supported OOM case.
We also intend to fix munlocking to not fault pages: at which point
this patch _could_ be reverted; though that would be controversial, so
we hope to find a better solution.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Justin M. Forbes <jforbes@redhat.com>
Acked-for-now-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:02:22 +08:00
|
|
|
static inline void ksm_exit(struct mm_struct *mm)
|
2009-09-22 08:01:57 +08:00
|
|
|
{
|
|
|
|
|
}
|
2009-09-22 08:02:01 +08:00
|
|
|
|
|
|
|
|
static inline int PageKsm(struct page *page)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* No stub required for page_add_ksm_rmap(page) */
|
2009-09-22 08:01:57 +08:00
|
|
|
#endif /* !CONFIG_KSM */
|
|
|
|
|
|
|
|
|
|
#endif
|