2006-03-22 16:09:12 +08:00
|
|
|
/*
|
|
|
|
* Memory Migration functionality - linux/mm/migration.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
|
|
|
|
*
|
|
|
|
* Page migration was first developed in the context of the memory hotplug
|
|
|
|
* project. The main authors of the migration code are:
|
|
|
|
*
|
|
|
|
* IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
|
|
|
|
* Hirokazu Takahashi <taka@valinux.co.jp>
|
|
|
|
* Dave Hansen <haveblue@us.ibm.com>
|
|
|
|
* Christoph Lameter <clameter@sgi.com>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/migrate.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/swap.h>
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
#include <linux/swapops.h>
|
2006-03-22 16:09:12 +08:00
|
|
|
#include <linux/pagemap.h>
|
2006-04-11 13:52:57 +08:00
|
|
|
#include <linux/buffer_head.h>
|
2006-03-22 16:09:12 +08:00
|
|
|
#include <linux/mm_inline.h>
|
|
|
|
#include <linux/pagevec.h>
|
|
|
|
#include <linux/rmap.h>
|
|
|
|
#include <linux/topology.h>
|
|
|
|
#include <linux/cpu.h>
|
|
|
|
#include <linux/cpuset.h>
|
2006-06-23 17:03:38 +08:00
|
|
|
#include <linux/writeback.h>
|
2006-06-23 17:03:55 +08:00
|
|
|
#include <linux/mempolicy.h>
|
|
|
|
#include <linux/vmalloc.h>
|
2006-06-23 17:04:02 +08:00
|
|
|
#include <linux/security.h>
|
2006-03-22 16:09:12 +08:00
|
|
|
|
|
|
|
#include "internal.h"
|
|
|
|
|
|
|
|
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Isolate one page from the LRU lists. If successful put it onto
|
|
|
|
* the indicated list with elevated page count.
|
|
|
|
*
|
|
|
|
* Result:
|
|
|
|
* -EBUSY: page not on LRU list
|
|
|
|
* 0: page removed from LRU list and added to the specified list.
|
|
|
|
*/
|
|
|
|
int isolate_lru_page(struct page *page, struct list_head *pagelist)
|
|
|
|
{
|
|
|
|
int ret = -EBUSY;
|
|
|
|
|
|
|
|
if (PageLRU(page)) {
|
|
|
|
struct zone *zone = page_zone(page);
|
|
|
|
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
|
|
if (PageLRU(page)) {
|
|
|
|
ret = 0;
|
|
|
|
get_page(page);
|
|
|
|
ClearPageLRU(page);
|
|
|
|
if (PageActive(page))
|
|
|
|
del_page_from_active_list(zone, page);
|
|
|
|
else
|
|
|
|
del_page_from_inactive_list(zone, page);
|
|
|
|
list_add_tail(&page->lru, pagelist);
|
|
|
|
}
|
|
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2006-06-23 17:03:55 +08:00
|
|
|
* migrate_prep() needs to be called before we start compiling a list of pages
|
|
|
|
* to be migrated using isolate_lru_page().
|
2006-03-22 16:09:12 +08:00
|
|
|
*/
|
|
|
|
int migrate_prep(void)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Clear the LRU lists so pages can be isolated.
|
|
|
|
* Note that pages may be moved off the LRU after we have
|
|
|
|
* drained them. Those pages will fail to migrate like other
|
|
|
|
* pages that may be busy.
|
|
|
|
*/
|
|
|
|
lru_add_drain_all();
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void move_to_lru(struct page *page)
|
|
|
|
{
|
|
|
|
if (PageActive(page)) {
|
|
|
|
/*
|
|
|
|
* lru_cache_add_active checks that
|
|
|
|
* the PG_active bit is off.
|
|
|
|
*/
|
|
|
|
ClearPageActive(page);
|
|
|
|
lru_cache_add_active(page);
|
|
|
|
} else {
|
|
|
|
lru_cache_add(page);
|
|
|
|
}
|
|
|
|
put_page(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Add isolated pages on the list back to the LRU.
|
|
|
|
*
|
|
|
|
* returns the number of pages put back.
|
|
|
|
*/
|
|
|
|
int putback_lru_pages(struct list_head *l)
|
|
|
|
{
|
|
|
|
struct page *page;
|
|
|
|
struct page *page2;
|
|
|
|
int count = 0;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(page, page2, l, lru) {
|
2006-06-23 17:03:51 +08:00
|
|
|
list_del(&page->lru);
|
2006-03-22 16:09:12 +08:00
|
|
|
move_to_lru(page);
|
|
|
|
count++;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
static inline int is_swap_pte(pte_t pte)
|
|
|
|
{
|
|
|
|
return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Restore a potential migration pte to a working pte entry
|
|
|
|
*/
|
2006-06-23 17:03:38 +08:00
|
|
|
static void remove_migration_pte(struct vm_area_struct *vma,
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
struct page *old, struct page *new)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
|
|
swp_entry_t entry;
|
|
|
|
pgd_t *pgd;
|
|
|
|
pud_t *pud;
|
|
|
|
pmd_t *pmd;
|
|
|
|
pte_t *ptep, pte;
|
|
|
|
spinlock_t *ptl;
|
2006-06-23 17:03:38 +08:00
|
|
|
unsigned long addr = page_address_in_vma(new, vma);
|
|
|
|
|
|
|
|
if (addr == -EFAULT)
|
|
|
|
return;
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
|
|
|
|
pgd = pgd_offset(mm, addr);
|
|
|
|
if (!pgd_present(*pgd))
|
|
|
|
return;
|
|
|
|
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
|
|
if (!pud_present(*pud))
|
|
|
|
return;
|
|
|
|
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
|
|
if (!pmd_present(*pmd))
|
|
|
|
return;
|
|
|
|
|
|
|
|
ptep = pte_offset_map(pmd, addr);
|
|
|
|
|
|
|
|
if (!is_swap_pte(*ptep)) {
|
|
|
|
pte_unmap(ptep);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
ptl = pte_lockptr(mm, pmd);
|
|
|
|
spin_lock(ptl);
|
|
|
|
pte = *ptep;
|
|
|
|
if (!is_swap_pte(pte))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
entry = pte_to_swp_entry(pte);
|
|
|
|
|
|
|
|
if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
get_page(new);
|
|
|
|
pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
|
|
|
|
if (is_write_migration_entry(entry))
|
|
|
|
pte = pte_mkwrite(pte);
|
|
|
|
set_pte_at(mm, addr, ptep, pte);
|
2006-06-23 17:03:38 +08:00
|
|
|
|
|
|
|
if (PageAnon(new))
|
|
|
|
page_add_anon_rmap(new, vma, addr);
|
|
|
|
else
|
|
|
|
page_add_file_rmap(new);
|
|
|
|
|
|
|
|
/* No need to invalidate - it was non-present before */
|
|
|
|
update_mmu_cache(vma, addr, pte);
|
|
|
|
lazy_mmu_prot_update(pte);
|
|
|
|
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
out:
|
|
|
|
pte_unmap_unlock(ptep, ptl);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2006-06-23 17:03:38 +08:00
|
|
|
* Note that remove_file_migration_ptes will only work on regular mappings,
|
|
|
|
* Nonlinear mappings do not use migration entries.
|
|
|
|
*/
|
|
|
|
static void remove_file_migration_ptes(struct page *old, struct page *new)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
struct address_space *mapping = page_mapping(new);
|
|
|
|
struct prio_tree_iter iter;
|
|
|
|
pgoff_t pgoff = new->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
|
|
|
|
|
|
|
|
if (!mapping)
|
|
|
|
return;
|
|
|
|
|
|
|
|
spin_lock(&mapping->i_mmap_lock);
|
|
|
|
|
|
|
|
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff)
|
|
|
|
remove_migration_pte(vma, old, new);
|
|
|
|
|
|
|
|
spin_unlock(&mapping->i_mmap_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
* Must hold mmap_sem lock on at least one of the vmas containing
|
|
|
|
* the page so that the anon_vma cannot vanish.
|
|
|
|
*/
|
2006-06-23 17:03:38 +08:00
|
|
|
static void remove_anon_migration_ptes(struct page *old, struct page *new)
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
{
|
|
|
|
struct anon_vma *anon_vma;
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
unsigned long mapping;
|
|
|
|
|
|
|
|
mapping = (unsigned long)new->mapping;
|
|
|
|
|
|
|
|
if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We hold the mmap_sem lock. So no need to call page_lock_anon_vma.
|
|
|
|
*/
|
|
|
|
anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON);
|
|
|
|
spin_lock(&anon_vma->lock);
|
|
|
|
|
|
|
|
list_for_each_entry(vma, &anon_vma->head, anon_vma_node)
|
2006-06-23 17:03:38 +08:00
|
|
|
remove_migration_pte(vma, old, new);
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
|
|
|
|
spin_unlock(&anon_vma->lock);
|
|
|
|
}
|
|
|
|
|
2006-06-23 17:03:38 +08:00
|
|
|
/*
|
|
|
|
* Get rid of all migration entries and replace them by
|
|
|
|
* references to the indicated page.
|
|
|
|
*/
|
|
|
|
static void remove_migration_ptes(struct page *old, struct page *new)
|
|
|
|
{
|
|
|
|
if (PageAnon(new))
|
|
|
|
remove_anon_migration_ptes(old, new);
|
|
|
|
else
|
|
|
|
remove_file_migration_ptes(old, new);
|
|
|
|
}
|
|
|
|
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
|
|
|
/*
|
|
|
|
* Something used the pte of a page under migration. We need to
|
|
|
|
* get to the page and wait until migration is finished.
|
|
|
|
* When we return from this function the fault will be retried.
|
|
|
|
*
|
|
|
|
* This function is called from do_swap_page().
|
|
|
|
*/
|
|
|
|
void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
|
|
|
|
unsigned long address)
|
|
|
|
{
|
|
|
|
pte_t *ptep, pte;
|
|
|
|
spinlock_t *ptl;
|
|
|
|
swp_entry_t entry;
|
|
|
|
struct page *page;
|
|
|
|
|
|
|
|
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
|
|
|
|
pte = *ptep;
|
|
|
|
if (!is_swap_pte(pte))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
entry = pte_to_swp_entry(pte);
|
|
|
|
if (!is_migration_entry(entry))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
page = migration_entry_to_page(entry);
|
|
|
|
|
|
|
|
get_page(page);
|
|
|
|
pte_unmap_unlock(ptep, ptl);
|
|
|
|
wait_on_page_locked(page);
|
|
|
|
put_page(page);
|
|
|
|
return;
|
|
|
|
out:
|
|
|
|
pte_unmap_unlock(ptep, ptl);
|
|
|
|
}
|
|
|
|
|
2006-03-22 16:09:12 +08:00
|
|
|
/*
|
2006-06-23 17:03:32 +08:00
|
|
|
* Replace the page in the mapping.
|
2006-06-23 17:03:29 +08:00
|
|
|
*
|
|
|
|
* The number of remaining references must be:
|
|
|
|
* 1 for anonymous pages without a mapping
|
|
|
|
* 2 for pages with a mapping
|
|
|
|
* 3 for pages with a mapping and PagePrivate set.
|
2006-03-22 16:09:12 +08:00
|
|
|
*/
|
2006-06-23 17:03:33 +08:00
|
|
|
static int migrate_page_move_mapping(struct address_space *mapping,
|
|
|
|
struct page *newpage, struct page *page)
|
2006-03-22 16:09:12 +08:00
|
|
|
{
|
2006-12-07 12:33:44 +08:00
|
|
|
void **pslot;
|
2006-03-22 16:09:12 +08:00
|
|
|
|
2006-06-23 17:03:37 +08:00
|
|
|
if (!mapping) {
|
2007-04-24 05:41:09 +08:00
|
|
|
/* Anonymous page without mapping */
|
2006-06-23 17:03:37 +08:00
|
|
|
if (page_count(page) != 1)
|
|
|
|
return -EAGAIN;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-03-22 16:09:12 +08:00
|
|
|
write_lock_irq(&mapping->tree_lock);
|
|
|
|
|
2006-12-07 12:33:44 +08:00
|
|
|
pslot = radix_tree_lookup_slot(&mapping->page_tree,
|
|
|
|
page_index(page));
|
2006-03-22 16:09:12 +08:00
|
|
|
|
2006-06-23 17:03:37 +08:00
|
|
|
if (page_count(page) != 2 + !!PagePrivate(page) ||
|
2006-12-07 12:33:44 +08:00
|
|
|
(struct page *)radix_tree_deref_slot(pslot) != page) {
|
2006-03-22 16:09:12 +08:00
|
|
|
write_unlock_irq(&mapping->tree_lock);
|
2006-04-11 13:52:57 +08:00
|
|
|
return -EAGAIN;
|
2006-03-22 16:09:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now we know that no one else is looking at the page.
|
|
|
|
*/
|
2006-12-07 12:33:44 +08:00
|
|
|
get_page(newpage); /* add cache reference */
|
2006-06-23 17:03:37 +08:00
|
|
|
#ifdef CONFIG_SWAP
|
2006-03-22 16:09:12 +08:00
|
|
|
if (PageSwapCache(page)) {
|
|
|
|
SetPageSwapCache(newpage);
|
|
|
|
set_page_private(newpage, page_private(page));
|
|
|
|
}
|
2006-06-23 17:03:37 +08:00
|
|
|
#endif
|
2006-03-22 16:09:12 +08:00
|
|
|
|
2006-12-07 12:33:44 +08:00
|
|
|
radix_tree_replace_slot(pslot, newpage);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Drop cache reference from old page.
|
|
|
|
* We know this isn't the last reference.
|
|
|
|
*/
|
2006-03-22 16:09:12 +08:00
|
|
|
__put_page(page);
|
2006-12-07 12:33:44 +08:00
|
|
|
|
2007-04-24 05:41:09 +08:00
|
|
|
/*
|
|
|
|
* If moved to a different zone then also account
|
|
|
|
* the page for that zone. Other VM counters will be
|
|
|
|
* taken care of when we establish references to the
|
|
|
|
* new page and drop references to the old page.
|
|
|
|
*
|
|
|
|
* Note that anonymous pages are accounted for
|
|
|
|
* via NR_FILE_PAGES and NR_ANON_PAGES if they
|
|
|
|
* are mapped to swap space.
|
|
|
|
*/
|
|
|
|
__dec_zone_page_state(page, NR_FILE_PAGES);
|
|
|
|
__inc_zone_page_state(newpage, NR_FILE_PAGES);
|
|
|
|
|
2006-03-22 16:09:12 +08:00
|
|
|
write_unlock_irq(&mapping->tree_lock);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Copy the page to its new location
|
|
|
|
*/
|
2006-06-23 17:03:29 +08:00
|
|
|
static void migrate_page_copy(struct page *newpage, struct page *page)
|
2006-03-22 16:09:12 +08:00
|
|
|
{
|
|
|
|
copy_highpage(newpage, page);
|
|
|
|
|
|
|
|
if (PageError(page))
|
|
|
|
SetPageError(newpage);
|
|
|
|
if (PageReferenced(page))
|
|
|
|
SetPageReferenced(newpage);
|
|
|
|
if (PageUptodate(page))
|
|
|
|
SetPageUptodate(newpage);
|
|
|
|
if (PageActive(page))
|
|
|
|
SetPageActive(newpage);
|
|
|
|
if (PageChecked(page))
|
|
|
|
SetPageChecked(newpage);
|
|
|
|
if (PageMappedToDisk(page))
|
|
|
|
SetPageMappedToDisk(newpage);
|
|
|
|
|
|
|
|
if (PageDirty(page)) {
|
|
|
|
clear_page_dirty_for_io(page);
|
|
|
|
set_page_dirty(newpage);
|
|
|
|
}
|
|
|
|
|
2006-06-23 17:03:37 +08:00
|
|
|
#ifdef CONFIG_SWAP
|
2006-03-22 16:09:12 +08:00
|
|
|
ClearPageSwapCache(page);
|
2006-06-23 17:03:37 +08:00
|
|
|
#endif
|
2006-03-22 16:09:12 +08:00
|
|
|
ClearPageActive(page);
|
|
|
|
ClearPagePrivate(page);
|
|
|
|
set_page_private(page, 0);
|
|
|
|
page->mapping = NULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If any waiters have accumulated on the new page then
|
|
|
|
* wake them up.
|
|
|
|
*/
|
|
|
|
if (PageWriteback(newpage))
|
|
|
|
end_page_writeback(newpage);
|
|
|
|
}
|
|
|
|
|
2006-06-23 17:03:28 +08:00
|
|
|
/************************************************************
|
|
|
|
* Migration functions
|
|
|
|
***********************************************************/
|
|
|
|
|
|
|
|
/* Always fail migration. Used for mappings that are not movable */
|
2006-06-23 17:03:33 +08:00
|
|
|
int fail_migrate_page(struct address_space *mapping,
|
|
|
|
struct page *newpage, struct page *page)
|
2006-06-23 17:03:28 +08:00
|
|
|
{
|
|
|
|
return -EIO;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(fail_migrate_page);
|
|
|
|
|
2006-03-22 16:09:12 +08:00
|
|
|
/*
|
|
|
|
* Common logic to directly migrate a single page suitable for
|
|
|
|
* pages that do not use PagePrivate.
|
|
|
|
*
|
|
|
|
* Pages are locked upon entry and exit.
|
|
|
|
*/
|
2006-06-23 17:03:33 +08:00
|
|
|
int migrate_page(struct address_space *mapping,
|
|
|
|
struct page *newpage, struct page *page)
|
2006-03-22 16:09:12 +08:00
|
|
|
{
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
BUG_ON(PageWriteback(page)); /* Writeback must be complete */
|
|
|
|
|
2006-06-23 17:03:33 +08:00
|
|
|
rc = migrate_page_move_mapping(mapping, newpage, page);
|
2006-03-22 16:09:12 +08:00
|
|
|
|
|
|
|
if (rc)
|
|
|
|
return rc;
|
|
|
|
|
|
|
|
migrate_page_copy(newpage, page);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(migrate_page);
|
|
|
|
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
#ifdef CONFIG_BLOCK
|
2006-06-23 17:03:28 +08:00
|
|
|
/*
|
|
|
|
* Migration function for pages with buffers. This function can only be used
|
|
|
|
* if the underlying filesystem guarantees that no other references to "page"
|
|
|
|
* exist.
|
|
|
|
*/
|
2006-06-23 17:03:33 +08:00
|
|
|
int buffer_migrate_page(struct address_space *mapping,
|
|
|
|
struct page *newpage, struct page *page)
|
2006-06-23 17:03:28 +08:00
|
|
|
{
|
|
|
|
struct buffer_head *bh, *head;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
if (!page_has_buffers(page))
|
2006-06-23 17:03:33 +08:00
|
|
|
return migrate_page(mapping, newpage, page);
|
2006-06-23 17:03:28 +08:00
|
|
|
|
|
|
|
head = page_buffers(page);
|
|
|
|
|
2006-06-23 17:03:33 +08:00
|
|
|
rc = migrate_page_move_mapping(mapping, newpage, page);
|
2006-06-23 17:03:28 +08:00
|
|
|
|
|
|
|
if (rc)
|
|
|
|
return rc;
|
|
|
|
|
|
|
|
bh = head;
|
|
|
|
do {
|
|
|
|
get_bh(bh);
|
|
|
|
lock_buffer(bh);
|
|
|
|
bh = bh->b_this_page;
|
|
|
|
|
|
|
|
} while (bh != head);
|
|
|
|
|
|
|
|
ClearPagePrivate(page);
|
|
|
|
set_page_private(newpage, page_private(page));
|
|
|
|
set_page_private(page, 0);
|
|
|
|
put_page(page);
|
|
|
|
get_page(newpage);
|
|
|
|
|
|
|
|
bh = head;
|
|
|
|
do {
|
|
|
|
set_bh_page(bh, newpage, bh_offset(bh));
|
|
|
|
bh = bh->b_this_page;
|
|
|
|
|
|
|
|
} while (bh != head);
|
|
|
|
|
|
|
|
SetPagePrivate(newpage);
|
|
|
|
|
|
|
|
migrate_page_copy(newpage, page);
|
|
|
|
|
|
|
|
bh = head;
|
|
|
|
do {
|
|
|
|
unlock_buffer(bh);
|
|
|
|
put_bh(bh);
|
|
|
|
bh = bh->b_this_page;
|
|
|
|
|
|
|
|
} while (bh != head);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(buffer_migrate_page);
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
#endif
|
2006-06-23 17:03:28 +08:00
|
|
|
|
2006-06-23 17:03:38 +08:00
|
|
|
/*
|
|
|
|
* Writeback a page to clean the dirty state
|
|
|
|
*/
|
|
|
|
static int writeout(struct address_space *mapping, struct page *page)
|
2006-06-23 17:03:33 +08:00
|
|
|
{
|
2006-06-23 17:03:38 +08:00
|
|
|
struct writeback_control wbc = {
|
|
|
|
.sync_mode = WB_SYNC_NONE,
|
|
|
|
.nr_to_write = 1,
|
|
|
|
.range_start = 0,
|
|
|
|
.range_end = LLONG_MAX,
|
|
|
|
.nonblocking = 1,
|
|
|
|
.for_reclaim = 1
|
|
|
|
};
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
if (!mapping->a_ops->writepage)
|
|
|
|
/* No write method for the address space */
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (!clear_page_dirty_for_io(page))
|
|
|
|
/* Someone else already triggered a write */
|
|
|
|
return -EAGAIN;
|
|
|
|
|
2006-06-23 17:03:33 +08:00
|
|
|
/*
|
2006-06-23 17:03:38 +08:00
|
|
|
* A dirty page may imply that the underlying filesystem has
|
|
|
|
* the page on some queue. So the page must be clean for
|
|
|
|
* migration. Writeout may mean we loose the lock and the
|
|
|
|
* page state is no longer what we checked for earlier.
|
|
|
|
* At this point we know that the migration attempt cannot
|
|
|
|
* be successful.
|
2006-06-23 17:03:33 +08:00
|
|
|
*/
|
2006-06-23 17:03:38 +08:00
|
|
|
remove_migration_ptes(page, page);
|
2006-06-23 17:03:33 +08:00
|
|
|
|
2006-06-23 17:03:38 +08:00
|
|
|
rc = mapping->a_ops->writepage(page, &wbc);
|
|
|
|
if (rc < 0)
|
|
|
|
/* I/O Error writing */
|
|
|
|
return -EIO;
|
2006-06-23 17:03:33 +08:00
|
|
|
|
2006-06-23 17:03:38 +08:00
|
|
|
if (rc != AOP_WRITEPAGE_ACTIVATE)
|
|
|
|
/* unlocked. Relock */
|
|
|
|
lock_page(page);
|
|
|
|
|
|
|
|
return -EAGAIN;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Default handling if a filesystem does not provide a migration function.
|
|
|
|
*/
|
|
|
|
static int fallback_migrate_page(struct address_space *mapping,
|
|
|
|
struct page *newpage, struct page *page)
|
|
|
|
{
|
|
|
|
if (PageDirty(page))
|
|
|
|
return writeout(mapping, page);
|
2006-06-23 17:03:33 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Buffers may be managed in a filesystem specific way.
|
|
|
|
* We must have no buffers or drop them.
|
|
|
|
*/
|
2006-08-30 02:05:58 +08:00
|
|
|
if (PagePrivate(page) &&
|
2006-06-23 17:03:33 +08:00
|
|
|
!try_to_release_page(page, GFP_KERNEL))
|
|
|
|
return -EAGAIN;
|
|
|
|
|
|
|
|
return migrate_page(mapping, newpage, page);
|
|
|
|
}
|
|
|
|
|
2006-06-23 17:03:51 +08:00
|
|
|
/*
|
|
|
|
* Move a page to a newly allocated page
|
|
|
|
* The page is locked and all ptes have been successfully removed.
|
|
|
|
*
|
|
|
|
* The new page will have replaced the old page if this function
|
|
|
|
* is successful.
|
|
|
|
*/
|
|
|
|
static int move_to_new_page(struct page *newpage, struct page *page)
|
|
|
|
{
|
|
|
|
struct address_space *mapping;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Block others from accessing the page when we get around to
|
|
|
|
* establishing additional references. We are the only one
|
|
|
|
* holding a reference to the new page at this point.
|
|
|
|
*/
|
|
|
|
if (TestSetPageLocked(newpage))
|
|
|
|
BUG();
|
|
|
|
|
|
|
|
/* Prepare mapping for the new page.*/
|
|
|
|
newpage->index = page->index;
|
|
|
|
newpage->mapping = page->mapping;
|
|
|
|
|
|
|
|
mapping = page_mapping(page);
|
|
|
|
if (!mapping)
|
|
|
|
rc = migrate_page(mapping, newpage, page);
|
|
|
|
else if (mapping->a_ops->migratepage)
|
|
|
|
/*
|
|
|
|
* Most pages have a mapping and most filesystems
|
|
|
|
* should provide a migration function. Anonymous
|
|
|
|
* pages are part of swap space which also has its
|
|
|
|
* own migration function. This is the most common
|
|
|
|
* path for page migration.
|
|
|
|
*/
|
|
|
|
rc = mapping->a_ops->migratepage(mapping,
|
|
|
|
newpage, page);
|
|
|
|
else
|
|
|
|
rc = fallback_migrate_page(mapping, newpage, page);
|
|
|
|
|
|
|
|
if (!rc)
|
|
|
|
remove_migration_ptes(page, newpage);
|
|
|
|
else
|
|
|
|
newpage->mapping = NULL;
|
|
|
|
|
|
|
|
unlock_page(newpage);
|
|
|
|
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Obtain the lock on page, remove all ptes and migrate the page
|
|
|
|
* to the newly allocated page in newpage.
|
|
|
|
*/
|
2006-06-23 17:03:53 +08:00
|
|
|
static int unmap_and_move(new_page_t get_new_page, unsigned long private,
|
|
|
|
struct page *page, int force)
|
2006-06-23 17:03:51 +08:00
|
|
|
{
|
|
|
|
int rc = 0;
|
2006-06-23 17:03:55 +08:00
|
|
|
int *result = NULL;
|
|
|
|
struct page *newpage = get_new_page(page, private, &result);
|
2006-06-23 17:03:53 +08:00
|
|
|
|
|
|
|
if (!newpage)
|
|
|
|
return -ENOMEM;
|
2006-06-23 17:03:51 +08:00
|
|
|
|
|
|
|
if (page_count(page) == 1)
|
|
|
|
/* page was freed from under us. So we are done. */
|
2006-06-23 17:03:53 +08:00
|
|
|
goto move_newpage;
|
2006-06-23 17:03:51 +08:00
|
|
|
|
|
|
|
rc = -EAGAIN;
|
|
|
|
if (TestSetPageLocked(page)) {
|
|
|
|
if (!force)
|
2006-06-23 17:03:53 +08:00
|
|
|
goto move_newpage;
|
2006-06-23 17:03:51 +08:00
|
|
|
lock_page(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (PageWriteback(page)) {
|
|
|
|
if (!force)
|
|
|
|
goto unlock;
|
|
|
|
wait_on_page_writeback(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Establish migration ptes or remove ptes
|
|
|
|
*/
|
2006-06-25 20:46:49 +08:00
|
|
|
try_to_unmap(page, 1);
|
|
|
|
if (!page_mapped(page))
|
|
|
|
rc = move_to_new_page(newpage, page);
|
2006-06-23 17:03:51 +08:00
|
|
|
|
|
|
|
if (rc)
|
|
|
|
remove_migration_ptes(page, page);
|
2006-06-25 20:46:49 +08:00
|
|
|
|
2006-06-23 17:03:51 +08:00
|
|
|
unlock:
|
|
|
|
unlock_page(page);
|
2006-06-23 17:03:53 +08:00
|
|
|
|
2006-06-23 17:03:51 +08:00
|
|
|
if (rc != -EAGAIN) {
|
2006-06-23 17:03:52 +08:00
|
|
|
/*
|
|
|
|
* A page that has been migrated has all references
|
|
|
|
* removed and will be freed. A page that has not been
|
|
|
|
* migrated will have kepts its references and be
|
|
|
|
* restored.
|
|
|
|
*/
|
|
|
|
list_del(&page->lru);
|
|
|
|
move_to_lru(page);
|
2006-06-23 17:03:51 +08:00
|
|
|
}
|
2006-06-23 17:03:53 +08:00
|
|
|
|
|
|
|
move_newpage:
|
|
|
|
/*
|
|
|
|
* Move the new page to the LRU. If migration was not successful
|
|
|
|
* then this will free the page.
|
|
|
|
*/
|
|
|
|
move_to_lru(newpage);
|
2006-06-23 17:03:55 +08:00
|
|
|
if (result) {
|
|
|
|
if (rc)
|
|
|
|
*result = rc;
|
|
|
|
else
|
|
|
|
*result = page_to_nid(newpage);
|
|
|
|
}
|
2006-06-23 17:03:51 +08:00
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
2006-03-22 16:09:12 +08:00
|
|
|
/*
|
|
|
|
* migrate_pages
|
|
|
|
*
|
2006-06-23 17:03:53 +08:00
|
|
|
* The function takes one list of pages to migrate and a function
|
|
|
|
* that determines from the page to be migrated and the private data
|
|
|
|
* the target of the move and allocates the page.
|
2006-03-22 16:09:12 +08:00
|
|
|
*
|
|
|
|
* The function returns after 10 attempts or if no pages
|
|
|
|
* are movable anymore because to has become empty
|
2006-06-23 17:03:52 +08:00
|
|
|
* or no retryable pages exist anymore. All pages will be
|
|
|
|
* retruned to the LRU or freed.
|
2006-03-22 16:09:12 +08:00
|
|
|
*
|
2006-06-23 17:03:53 +08:00
|
|
|
* Return: Number of pages not migrated or error code.
|
2006-03-22 16:09:12 +08:00
|
|
|
*/
|
2006-06-23 17:03:53 +08:00
|
|
|
int migrate_pages(struct list_head *from,
|
|
|
|
new_page_t get_new_page, unsigned long private)
|
2006-03-22 16:09:12 +08:00
|
|
|
{
|
2006-06-23 17:03:51 +08:00
|
|
|
int retry = 1;
|
2006-03-22 16:09:12 +08:00
|
|
|
int nr_failed = 0;
|
|
|
|
int pass = 0;
|
|
|
|
struct page *page;
|
|
|
|
struct page *page2;
|
|
|
|
int swapwrite = current->flags & PF_SWAPWRITE;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
if (!swapwrite)
|
|
|
|
current->flags |= PF_SWAPWRITE;
|
|
|
|
|
2006-06-23 17:03:51 +08:00
|
|
|
for(pass = 0; pass < 10 && retry; pass++) {
|
|
|
|
retry = 0;
|
2006-03-22 16:09:12 +08:00
|
|
|
|
2006-06-23 17:03:51 +08:00
|
|
|
list_for_each_entry_safe(page, page2, from, lru) {
|
|
|
|
cond_resched();
|
2006-06-23 17:03:33 +08:00
|
|
|
|
2006-06-23 17:03:53 +08:00
|
|
|
rc = unmap_and_move(get_new_page, private,
|
|
|
|
page, pass > 2);
|
2006-06-23 17:03:33 +08:00
|
|
|
|
2006-06-23 17:03:51 +08:00
|
|
|
switch(rc) {
|
2006-06-23 17:03:53 +08:00
|
|
|
case -ENOMEM:
|
|
|
|
goto out;
|
2006-06-23 17:03:51 +08:00
|
|
|
case -EAGAIN:
|
2006-06-23 17:03:33 +08:00
|
|
|
retry++;
|
2006-06-23 17:03:51 +08:00
|
|
|
break;
|
|
|
|
case 0:
|
|
|
|
break;
|
|
|
|
default:
|
2006-06-23 17:03:33 +08:00
|
|
|
/* Permanent failure */
|
|
|
|
nr_failed++;
|
2006-06-23 17:03:51 +08:00
|
|
|
break;
|
2006-06-23 17:03:33 +08:00
|
|
|
}
|
2006-03-22 16:09:12 +08:00
|
|
|
}
|
|
|
|
}
|
2006-06-23 17:03:53 +08:00
|
|
|
rc = 0;
|
|
|
|
out:
|
2006-03-22 16:09:12 +08:00
|
|
|
if (!swapwrite)
|
|
|
|
current->flags &= ~PF_SWAPWRITE;
|
|
|
|
|
2006-06-23 17:03:52 +08:00
|
|
|
putback_lru_pages(from);
|
2006-03-22 16:09:12 +08:00
|
|
|
|
2006-06-23 17:03:53 +08:00
|
|
|
if (rc)
|
|
|
|
return rc;
|
2006-03-22 16:09:12 +08:00
|
|
|
|
2006-06-23 17:03:53 +08:00
|
|
|
return nr_failed + retry;
|
2006-03-22 16:09:12 +08:00
|
|
|
}
|
2006-06-23 17:03:53 +08:00
|
|
|
|
2006-06-23 17:03:55 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
/*
|
|
|
|
* Move a list of individual pages
|
|
|
|
*/
|
|
|
|
struct page_to_node {
|
|
|
|
unsigned long addr;
|
|
|
|
struct page *page;
|
|
|
|
int node;
|
|
|
|
int status;
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct page *new_page_node(struct page *p, unsigned long private,
|
|
|
|
int **result)
|
|
|
|
{
|
|
|
|
struct page_to_node *pm = (struct page_to_node *)private;
|
|
|
|
|
|
|
|
while (pm->node != MAX_NUMNODES && pm->page != p)
|
|
|
|
pm++;
|
|
|
|
|
|
|
|
if (pm->node == MAX_NUMNODES)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
*result = &pm->status;
|
|
|
|
|
2006-09-26 14:31:46 +08:00
|
|
|
return alloc_pages_node(pm->node, GFP_HIGHUSER | GFP_THISNODE, 0);
|
2006-06-23 17:03:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Move a set of pages as indicated in the pm array. The addr
|
|
|
|
* field must be set to the virtual address of the page to be moved
|
|
|
|
* and the node number must contain a valid target node.
|
|
|
|
*/
|
|
|
|
static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm,
|
|
|
|
int migrate_all)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct page_to_node *pp;
|
|
|
|
LIST_HEAD(pagelist);
|
|
|
|
|
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Build a list of pages to migrate
|
|
|
|
*/
|
|
|
|
migrate_prep();
|
|
|
|
for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
struct page *page;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A valid page pointer that will not match any of the
|
|
|
|
* pages that will be moved.
|
|
|
|
*/
|
|
|
|
pp->page = ZERO_PAGE(0);
|
|
|
|
|
|
|
|
err = -EFAULT;
|
|
|
|
vma = find_vma(mm, pp->addr);
|
2007-03-05 16:30:33 +08:00
|
|
|
if (!vma || !vma_migratable(vma))
|
2006-06-23 17:03:55 +08:00
|
|
|
goto set_status;
|
|
|
|
|
|
|
|
page = follow_page(vma, pp->addr, FOLL_GET);
|
|
|
|
err = -ENOENT;
|
|
|
|
if (!page)
|
|
|
|
goto set_status;
|
|
|
|
|
|
|
|
if (PageReserved(page)) /* Check for zero page */
|
|
|
|
goto put_and_set;
|
|
|
|
|
|
|
|
pp->page = page;
|
|
|
|
err = page_to_nid(page);
|
|
|
|
|
|
|
|
if (err == pp->node)
|
|
|
|
/*
|
|
|
|
* Node already in the right place
|
|
|
|
*/
|
|
|
|
goto put_and_set;
|
|
|
|
|
|
|
|
err = -EACCES;
|
|
|
|
if (page_mapcount(page) > 1 &&
|
|
|
|
!migrate_all)
|
|
|
|
goto put_and_set;
|
|
|
|
|
|
|
|
err = isolate_lru_page(page, &pagelist);
|
|
|
|
put_and_set:
|
|
|
|
/*
|
|
|
|
* Either remove the duplicate refcount from
|
|
|
|
* isolate_lru_page() or drop the page ref if it was
|
|
|
|
* not isolated.
|
|
|
|
*/
|
|
|
|
put_page(page);
|
|
|
|
set_status:
|
|
|
|
pp->status = err;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!list_empty(&pagelist))
|
|
|
|
err = migrate_pages(&pagelist, new_page_node,
|
|
|
|
(unsigned long)pm);
|
|
|
|
else
|
|
|
|
err = -ENOENT;
|
|
|
|
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Determine the nodes of a list of pages. The addr in the pm array
|
|
|
|
* must have been set to the virtual address of which we want to determine
|
|
|
|
* the node number.
|
|
|
|
*/
|
|
|
|
static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm)
|
|
|
|
{
|
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
|
|
|
|
for ( ; pm->node != MAX_NUMNODES; pm++) {
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
struct page *page;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = -EFAULT;
|
|
|
|
vma = find_vma(mm, pm->addr);
|
|
|
|
if (!vma)
|
|
|
|
goto set_status;
|
|
|
|
|
|
|
|
page = follow_page(vma, pm->addr, 0);
|
|
|
|
err = -ENOENT;
|
|
|
|
/* Use PageReserved to check for zero page */
|
|
|
|
if (!page || PageReserved(page))
|
|
|
|
goto set_status;
|
|
|
|
|
|
|
|
err = page_to_nid(page);
|
|
|
|
set_status:
|
|
|
|
pm->status = err;
|
|
|
|
}
|
|
|
|
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Move a list of pages in the address space of the currently executing
|
|
|
|
* process.
|
|
|
|
*/
|
|
|
|
asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
|
|
|
|
const void __user * __user *pages,
|
|
|
|
const int __user *nodes,
|
|
|
|
int __user *status, int flags)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
int i;
|
|
|
|
struct task_struct *task;
|
|
|
|
nodemask_t task_nodes;
|
|
|
|
struct mm_struct *mm;
|
|
|
|
struct page_to_node *pm = NULL;
|
|
|
|
|
|
|
|
/* Check flags */
|
|
|
|
if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
/* Find the mm_struct */
|
|
|
|
read_lock(&tasklist_lock);
|
|
|
|
task = pid ? find_task_by_pid(pid) : current;
|
|
|
|
if (!task) {
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
mm = get_task_mm(task);
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
|
|
if (!mm)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if this process has the right to modify the specified
|
|
|
|
* process. The right exists if the process has administrative
|
|
|
|
* capabilities, superuser privileges or the same
|
|
|
|
* userid as the target process.
|
|
|
|
*/
|
|
|
|
if ((current->euid != task->suid) && (current->euid != task->uid) &&
|
|
|
|
(current->uid != task->suid) && (current->uid != task->uid) &&
|
|
|
|
!capable(CAP_SYS_NICE)) {
|
|
|
|
err = -EPERM;
|
|
|
|
goto out2;
|
|
|
|
}
|
|
|
|
|
2006-06-23 17:04:02 +08:00
|
|
|
err = security_task_movememory(task);
|
|
|
|
if (err)
|
|
|
|
goto out2;
|
|
|
|
|
|
|
|
|
2006-06-23 17:03:55 +08:00
|
|
|
task_nodes = cpuset_mems_allowed(task);
|
|
|
|
|
|
|
|
/* Limit nr_pages so that the multiplication may not overflow */
|
|
|
|
if (nr_pages >= ULONG_MAX / sizeof(struct page_to_node) - 1) {
|
|
|
|
err = -E2BIG;
|
|
|
|
goto out2;
|
|
|
|
}
|
|
|
|
|
|
|
|
pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node));
|
|
|
|
if (!pm) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
goto out2;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Get parameters from user space and initialize the pm
|
|
|
|
* array. Return various errors if the user did something wrong.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
|
|
const void *p;
|
|
|
|
|
|
|
|
err = -EFAULT;
|
|
|
|
if (get_user(p, pages + i))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
pm[i].addr = (unsigned long)p;
|
|
|
|
if (nodes) {
|
|
|
|
int node;
|
|
|
|
|
|
|
|
if (get_user(node, nodes + i))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = -ENODEV;
|
|
|
|
if (!node_online(node))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = -EACCES;
|
|
|
|
if (!node_isset(node, task_nodes))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
pm[i].node = node;
|
2006-11-03 14:07:28 +08:00
|
|
|
} else
|
|
|
|
pm[i].node = 0; /* anything to not match MAX_NUMNODES */
|
2006-06-23 17:03:55 +08:00
|
|
|
}
|
|
|
|
/* End marker */
|
|
|
|
pm[nr_pages].node = MAX_NUMNODES;
|
|
|
|
|
|
|
|
if (nodes)
|
|
|
|
err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL);
|
|
|
|
else
|
|
|
|
err = do_pages_stat(mm, pm);
|
|
|
|
|
|
|
|
if (err >= 0)
|
|
|
|
/* Return status information */
|
|
|
|
for (i = 0; i < nr_pages; i++)
|
|
|
|
if (put_user(pm[i].status, status + i))
|
|
|
|
err = -EFAULT;
|
|
|
|
|
|
|
|
out:
|
|
|
|
vfree(pm);
|
|
|
|
out2:
|
|
|
|
mmput(mm);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2006-06-25 20:46:48 +08:00
|
|
|
/*
|
|
|
|
* Call migration functions in the vma_ops that may prepare
|
|
|
|
* memory in a vm for migration. migration functions may perform
|
|
|
|
* the migration for vmas that do not have an underlying page struct.
|
|
|
|
*/
|
|
|
|
int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
|
|
|
|
const nodemask_t *from, unsigned long flags)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
|
|
|
|
if (vma->vm_ops && vma->vm_ops->migrate) {
|
|
|
|
err = vma->vm_ops->migrate(vma, to, from, flags);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|