mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 02:39:48 +00:00
![Lisa Du](/assets/img/avatar_default.png)
This patch is based on KOSAKI's work and I add a little more description, please refer https://lkml.org/lkml/2012/6/14/74. Currently, I found system can enter a state that there are lots of free pages in a zone but only order-0 and order-1 pages which means the zone is heavily fragmented, then high order allocation could make direct reclaim path's long stall(ex, 60 seconds) especially in no swap and no compaciton enviroment. This problem happened on v3.4, but it seems issue still lives in current tree, the reason is do_try_to_free_pages enter live lock: kswapd will go to sleep if the zones have been fully scanned and are still not balanced. As kswapd thinks there's little point trying all over again to avoid infinite loop. Instead it changes order from high-order to 0-order because kswapd think order-0 is the most important. Look at73ce02e9
in detail. If watermarks are ok, kswapd will go back to sleep and may leave zone->all_unreclaimable =3D 0. It assume high-order users can still perform direct reclaim if they wish. Direct reclaim continue to reclaim for a high order which is not a COSTLY_ORDER without oom-killer until kswapd turn on zone->all_unreclaimble= . This is because to avoid too early oom-kill. So it means direct_reclaim depends on kswapd to break this loop. In worst case, direct-reclaim may continue to page reclaim forever when kswapd sleeps forever until someone like watchdog detect and finally kill the process. As described in: http://thread.gmane.org/gmane.linux.kernel.mm/103737 We can't turn on zone->all_unreclaimable from direct reclaim path because direct reclaim path don't take any lock and this way is racy. Thus this patch removes zone->all_unreclaimable field completely and recalculates zone reclaimable state every time. Note: we can't take the idea that direct-reclaim see zone->pages_scanned directly and kswapd continue to use zone->all_unreclaimable. Because, it is racy. commit929bea7c71
(vmscan: all_unreclaimable() use zone->all_unreclaimable as a name) describes the detail. [akpm@linux-foundation.org: uninline zone_reclaimable_pages() and zone_reclaimable()] Cc: Aaditya Kumar <aaditya.kumar.30@gmail.com> Cc: Ying Han <yinghan@google.com> Cc: Nick Piggin <npiggin@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux.com> Cc: Bob Liu <lliubbo@gmail.com> Cc: Neil Zhang <zhangwm@marvell.com> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Reviewed-by: Michal Hocko <mhocko@suse.cz> Acked-by: Minchan Kim <minchan@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Lisa Du <cldu@marvell.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1774 lines
45 KiB
C
1774 lines
45 KiB
C
/*
|
|
* 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
|
|
*/
|
|
|
|
#include <linux/migrate.h>
|
|
#include <linux/export.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/mm_inline.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/pagevec.h>
|
|
#include <linux/ksm.h>
|
|
#include <linux/rmap.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/cpuset.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/security.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/hugetlb_cgroup.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/balloon_compaction.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/migrate.h>
|
|
|
|
#include "internal.h"
|
|
|
|
/*
|
|
* migrate_prep() needs to be called before we start compiling a list of pages
|
|
* to be migrated using isolate_lru_page(). If scheduling work on other CPUs is
|
|
* undesirable, use migrate_prep_local()
|
|
*/
|
|
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;
|
|
}
|
|
|
|
/* Do the necessary work of migrate_prep but not if it involves other CPUs */
|
|
int migrate_prep_local(void)
|
|
{
|
|
lru_add_drain();
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Add isolated pages on the list back to the LRU under page lock
|
|
* to avoid leaking evictable pages back onto unevictable list.
|
|
*/
|
|
void putback_lru_pages(struct list_head *l)
|
|
{
|
|
struct page *page;
|
|
struct page *page2;
|
|
|
|
list_for_each_entry_safe(page, page2, l, lru) {
|
|
list_del(&page->lru);
|
|
dec_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
putback_lru_page(page);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Put previously isolated pages back onto the appropriate lists
|
|
* from where they were once taken off for compaction/migration.
|
|
*
|
|
* This function shall be used instead of putback_lru_pages(),
|
|
* whenever the isolated pageset has been built by isolate_migratepages_range()
|
|
*/
|
|
void putback_movable_pages(struct list_head *l)
|
|
{
|
|
struct page *page;
|
|
struct page *page2;
|
|
|
|
list_for_each_entry_safe(page, page2, l, lru) {
|
|
if (unlikely(PageHuge(page))) {
|
|
putback_active_hugepage(page);
|
|
continue;
|
|
}
|
|
list_del(&page->lru);
|
|
dec_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
if (unlikely(balloon_page_movable(page)))
|
|
balloon_page_putback(page);
|
|
else
|
|
putback_lru_page(page);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Restore a potential migration pte to a working pte entry
|
|
*/
|
|
static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
|
|
unsigned long addr, void *old)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
swp_entry_t entry;
|
|
pmd_t *pmd;
|
|
pte_t *ptep, pte;
|
|
spinlock_t *ptl;
|
|
|
|
if (unlikely(PageHuge(new))) {
|
|
ptep = huge_pte_offset(mm, addr);
|
|
if (!ptep)
|
|
goto out;
|
|
ptl = &mm->page_table_lock;
|
|
} else {
|
|
pmd = mm_find_pmd(mm, addr);
|
|
if (!pmd)
|
|
goto out;
|
|
if (pmd_trans_huge(*pmd))
|
|
goto out;
|
|
|
|
ptep = pte_offset_map(pmd, addr);
|
|
|
|
/*
|
|
* Peek to check is_swap_pte() before taking ptlock? No, we
|
|
* can race mremap's move_ptes(), which skips anon_vma lock.
|
|
*/
|
|
|
|
ptl = pte_lockptr(mm, pmd);
|
|
}
|
|
|
|
spin_lock(ptl);
|
|
pte = *ptep;
|
|
if (!is_swap_pte(pte))
|
|
goto unlock;
|
|
|
|
entry = pte_to_swp_entry(pte);
|
|
|
|
if (!is_migration_entry(entry) ||
|
|
migration_entry_to_page(entry) != old)
|
|
goto unlock;
|
|
|
|
get_page(new);
|
|
pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
|
|
if (is_write_migration_entry(entry))
|
|
pte = pte_mkwrite(pte);
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
if (PageHuge(new)) {
|
|
pte = pte_mkhuge(pte);
|
|
pte = arch_make_huge_pte(pte, vma, new, 0);
|
|
}
|
|
#endif
|
|
flush_dcache_page(new);
|
|
set_pte_at(mm, addr, ptep, pte);
|
|
|
|
if (PageHuge(new)) {
|
|
if (PageAnon(new))
|
|
hugepage_add_anon_rmap(new, vma, addr);
|
|
else
|
|
page_dup_rmap(new);
|
|
} else 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, ptep);
|
|
unlock:
|
|
pte_unmap_unlock(ptep, ptl);
|
|
out:
|
|
return SWAP_AGAIN;
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
rmap_walk(new, remove_migration_pte, old);
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
|
|
spinlock_t *ptl)
|
|
{
|
|
pte_t pte;
|
|
swp_entry_t entry;
|
|
struct page *page;
|
|
|
|
spin_lock(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);
|
|
|
|
/*
|
|
* Once radix-tree replacement of page migration started, page_count
|
|
* *must* be zero. And, we don't want to call wait_on_page_locked()
|
|
* against a page without get_page().
|
|
* So, we use get_page_unless_zero(), here. Even failed, page fault
|
|
* will occur again.
|
|
*/
|
|
if (!get_page_unless_zero(page))
|
|
goto out;
|
|
pte_unmap_unlock(ptep, ptl);
|
|
wait_on_page_locked(page);
|
|
put_page(page);
|
|
return;
|
|
out:
|
|
pte_unmap_unlock(ptep, ptl);
|
|
}
|
|
|
|
void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
|
|
unsigned long address)
|
|
{
|
|
spinlock_t *ptl = pte_lockptr(mm, pmd);
|
|
pte_t *ptep = pte_offset_map(pmd, address);
|
|
__migration_entry_wait(mm, ptep, ptl);
|
|
}
|
|
|
|
void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
spinlock_t *ptl = &(mm)->page_table_lock;
|
|
__migration_entry_wait(mm, pte, ptl);
|
|
}
|
|
|
|
#ifdef CONFIG_BLOCK
|
|
/* Returns true if all buffers are successfully locked */
|
|
static bool buffer_migrate_lock_buffers(struct buffer_head *head,
|
|
enum migrate_mode mode)
|
|
{
|
|
struct buffer_head *bh = head;
|
|
|
|
/* Simple case, sync compaction */
|
|
if (mode != MIGRATE_ASYNC) {
|
|
do {
|
|
get_bh(bh);
|
|
lock_buffer(bh);
|
|
bh = bh->b_this_page;
|
|
|
|
} while (bh != head);
|
|
|
|
return true;
|
|
}
|
|
|
|
/* async case, we cannot block on lock_buffer so use trylock_buffer */
|
|
do {
|
|
get_bh(bh);
|
|
if (!trylock_buffer(bh)) {
|
|
/*
|
|
* We failed to lock the buffer and cannot stall in
|
|
* async migration. Release the taken locks
|
|
*/
|
|
struct buffer_head *failed_bh = bh;
|
|
put_bh(failed_bh);
|
|
bh = head;
|
|
while (bh != failed_bh) {
|
|
unlock_buffer(bh);
|
|
put_bh(bh);
|
|
bh = bh->b_this_page;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
bh = bh->b_this_page;
|
|
} while (bh != head);
|
|
return true;
|
|
}
|
|
#else
|
|
static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
|
|
enum migrate_mode mode)
|
|
{
|
|
return true;
|
|
}
|
|
#endif /* CONFIG_BLOCK */
|
|
|
|
/*
|
|
* Replace the page in the mapping.
|
|
*
|
|
* 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/PagePrivate2 set.
|
|
*/
|
|
static int migrate_page_move_mapping(struct address_space *mapping,
|
|
struct page *newpage, struct page *page,
|
|
struct buffer_head *head, enum migrate_mode mode)
|
|
{
|
|
int expected_count = 0;
|
|
void **pslot;
|
|
|
|
if (!mapping) {
|
|
/* Anonymous page without mapping */
|
|
if (page_count(page) != 1)
|
|
return -EAGAIN;
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
|
|
spin_lock_irq(&mapping->tree_lock);
|
|
|
|
pslot = radix_tree_lookup_slot(&mapping->page_tree,
|
|
page_index(page));
|
|
|
|
expected_count = 2 + page_has_private(page);
|
|
if (page_count(page) != expected_count ||
|
|
radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
if (!page_freeze_refs(page, expected_count)) {
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
/*
|
|
* In the async migration case of moving a page with buffers, lock the
|
|
* buffers using trylock before the mapping is moved. If the mapping
|
|
* was moved, we later failed to lock the buffers and could not move
|
|
* the mapping back due to an elevated page count, we would have to
|
|
* block waiting on other references to be dropped.
|
|
*/
|
|
if (mode == MIGRATE_ASYNC && head &&
|
|
!buffer_migrate_lock_buffers(head, mode)) {
|
|
page_unfreeze_refs(page, expected_count);
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
/*
|
|
* Now we know that no one else is looking at the page.
|
|
*/
|
|
get_page(newpage); /* add cache reference */
|
|
if (PageSwapCache(page)) {
|
|
SetPageSwapCache(newpage);
|
|
set_page_private(newpage, page_private(page));
|
|
}
|
|
|
|
radix_tree_replace_slot(pslot, newpage);
|
|
|
|
/*
|
|
* Drop cache reference from old page by unfreezing
|
|
* to one less reference.
|
|
* We know this isn't the last reference.
|
|
*/
|
|
page_unfreeze_refs(page, expected_count - 1);
|
|
|
|
/*
|
|
* 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);
|
|
if (!PageSwapCache(page) && PageSwapBacked(page)) {
|
|
__dec_zone_page_state(page, NR_SHMEM);
|
|
__inc_zone_page_state(newpage, NR_SHMEM);
|
|
}
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
|
|
/*
|
|
* The expected number of remaining references is the same as that
|
|
* of migrate_page_move_mapping().
|
|
*/
|
|
int migrate_huge_page_move_mapping(struct address_space *mapping,
|
|
struct page *newpage, struct page *page)
|
|
{
|
|
int expected_count;
|
|
void **pslot;
|
|
|
|
if (!mapping) {
|
|
if (page_count(page) != 1)
|
|
return -EAGAIN;
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
|
|
spin_lock_irq(&mapping->tree_lock);
|
|
|
|
pslot = radix_tree_lookup_slot(&mapping->page_tree,
|
|
page_index(page));
|
|
|
|
expected_count = 2 + page_has_private(page);
|
|
if (page_count(page) != expected_count ||
|
|
radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
if (!page_freeze_refs(page, expected_count)) {
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
get_page(newpage);
|
|
|
|
radix_tree_replace_slot(pslot, newpage);
|
|
|
|
page_unfreeze_refs(page, expected_count - 1);
|
|
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
|
|
/*
|
|
* Copy the page to its new location
|
|
*/
|
|
void migrate_page_copy(struct page *newpage, struct page *page)
|
|
{
|
|
if (PageHuge(page) || PageTransHuge(page))
|
|
copy_huge_page(newpage, page);
|
|
else
|
|
copy_highpage(newpage, page);
|
|
|
|
if (PageError(page))
|
|
SetPageError(newpage);
|
|
if (PageReferenced(page))
|
|
SetPageReferenced(newpage);
|
|
if (PageUptodate(page))
|
|
SetPageUptodate(newpage);
|
|
if (TestClearPageActive(page)) {
|
|
VM_BUG_ON(PageUnevictable(page));
|
|
SetPageActive(newpage);
|
|
} else if (TestClearPageUnevictable(page))
|
|
SetPageUnevictable(newpage);
|
|
if (PageChecked(page))
|
|
SetPageChecked(newpage);
|
|
if (PageMappedToDisk(page))
|
|
SetPageMappedToDisk(newpage);
|
|
|
|
if (PageDirty(page)) {
|
|
clear_page_dirty_for_io(page);
|
|
/*
|
|
* Want to mark the page and the radix tree as dirty, and
|
|
* redo the accounting that clear_page_dirty_for_io undid,
|
|
* but we can't use set_page_dirty because that function
|
|
* is actually a signal that all of the page has become dirty.
|
|
* Whereas only part of our page may be dirty.
|
|
*/
|
|
if (PageSwapBacked(page))
|
|
SetPageDirty(newpage);
|
|
else
|
|
__set_page_dirty_nobuffers(newpage);
|
|
}
|
|
|
|
mlock_migrate_page(newpage, page);
|
|
ksm_migrate_page(newpage, page);
|
|
/*
|
|
* Please do not reorder this without considering how mm/ksm.c's
|
|
* get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
|
|
*/
|
|
ClearPageSwapCache(page);
|
|
ClearPagePrivate(page);
|
|
set_page_private(page, 0);
|
|
|
|
/*
|
|
* If any waiters have accumulated on the new page then
|
|
* wake them up.
|
|
*/
|
|
if (PageWriteback(newpage))
|
|
end_page_writeback(newpage);
|
|
}
|
|
|
|
/************************************************************
|
|
* Migration functions
|
|
***********************************************************/
|
|
|
|
/* Always fail migration. Used for mappings that are not movable */
|
|
int fail_migrate_page(struct address_space *mapping,
|
|
struct page *newpage, struct page *page)
|
|
{
|
|
return -EIO;
|
|
}
|
|
EXPORT_SYMBOL(fail_migrate_page);
|
|
|
|
/*
|
|
* Common logic to directly migrate a single page suitable for
|
|
* pages that do not use PagePrivate/PagePrivate2.
|
|
*
|
|
* Pages are locked upon entry and exit.
|
|
*/
|
|
int migrate_page(struct address_space *mapping,
|
|
struct page *newpage, struct page *page,
|
|
enum migrate_mode mode)
|
|
{
|
|
int rc;
|
|
|
|
BUG_ON(PageWriteback(page)); /* Writeback must be complete */
|
|
|
|
rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
|
|
|
|
if (rc != MIGRATEPAGE_SUCCESS)
|
|
return rc;
|
|
|
|
migrate_page_copy(newpage, page);
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
EXPORT_SYMBOL(migrate_page);
|
|
|
|
#ifdef CONFIG_BLOCK
|
|
/*
|
|
* Migration function for pages with buffers. This function can only be used
|
|
* if the underlying filesystem guarantees that no other references to "page"
|
|
* exist.
|
|
*/
|
|
int buffer_migrate_page(struct address_space *mapping,
|
|
struct page *newpage, struct page *page, enum migrate_mode mode)
|
|
{
|
|
struct buffer_head *bh, *head;
|
|
int rc;
|
|
|
|
if (!page_has_buffers(page))
|
|
return migrate_page(mapping, newpage, page, mode);
|
|
|
|
head = page_buffers(page);
|
|
|
|
rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
|
|
|
|
if (rc != MIGRATEPAGE_SUCCESS)
|
|
return rc;
|
|
|
|
/*
|
|
* In the async case, migrate_page_move_mapping locked the buffers
|
|
* with an IRQ-safe spinlock held. In the sync case, the buffers
|
|
* need to be locked now
|
|
*/
|
|
if (mode != MIGRATE_ASYNC)
|
|
BUG_ON(!buffer_migrate_lock_buffers(head, mode));
|
|
|
|
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 MIGRATEPAGE_SUCCESS;
|
|
}
|
|
EXPORT_SYMBOL(buffer_migrate_page);
|
|
#endif
|
|
|
|
/*
|
|
* Writeback a page to clean the dirty state
|
|
*/
|
|
static int writeout(struct address_space *mapping, struct page *page)
|
|
{
|
|
struct writeback_control wbc = {
|
|
.sync_mode = WB_SYNC_NONE,
|
|
.nr_to_write = 1,
|
|
.range_start = 0,
|
|
.range_end = LLONG_MAX,
|
|
.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;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
remove_migration_ptes(page, page);
|
|
|
|
rc = mapping->a_ops->writepage(page, &wbc);
|
|
|
|
if (rc != AOP_WRITEPAGE_ACTIVATE)
|
|
/* unlocked. Relock */
|
|
lock_page(page);
|
|
|
|
return (rc < 0) ? -EIO : -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, enum migrate_mode mode)
|
|
{
|
|
if (PageDirty(page)) {
|
|
/* Only writeback pages in full synchronous migration */
|
|
if (mode != MIGRATE_SYNC)
|
|
return -EBUSY;
|
|
return writeout(mapping, page);
|
|
}
|
|
|
|
/*
|
|
* Buffers may be managed in a filesystem specific way.
|
|
* We must have no buffers or drop them.
|
|
*/
|
|
if (page_has_private(page) &&
|
|
!try_to_release_page(page, GFP_KERNEL))
|
|
return -EAGAIN;
|
|
|
|
return migrate_page(mapping, newpage, page, mode);
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*
|
|
* Return value:
|
|
* < 0 - error code
|
|
* MIGRATEPAGE_SUCCESS - success
|
|
*/
|
|
static int move_to_new_page(struct page *newpage, struct page *page,
|
|
int remap_swapcache, enum migrate_mode mode)
|
|
{
|
|
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 (!trylock_page(newpage))
|
|
BUG();
|
|
|
|
/* Prepare mapping for the new page.*/
|
|
newpage->index = page->index;
|
|
newpage->mapping = page->mapping;
|
|
if (PageSwapBacked(page))
|
|
SetPageSwapBacked(newpage);
|
|
|
|
mapping = page_mapping(page);
|
|
if (!mapping)
|
|
rc = migrate_page(mapping, newpage, page, mode);
|
|
else if (mapping->a_ops->migratepage)
|
|
/*
|
|
* Most pages have a mapping and most filesystems provide a
|
|
* migratepage callback. Anonymous pages are part of swap
|
|
* space which also has its own migratepage callback. This
|
|
* is the most common path for page migration.
|
|
*/
|
|
rc = mapping->a_ops->migratepage(mapping,
|
|
newpage, page, mode);
|
|
else
|
|
rc = fallback_migrate_page(mapping, newpage, page, mode);
|
|
|
|
if (rc != MIGRATEPAGE_SUCCESS) {
|
|
newpage->mapping = NULL;
|
|
} else {
|
|
if (remap_swapcache)
|
|
remove_migration_ptes(page, newpage);
|
|
page->mapping = NULL;
|
|
}
|
|
|
|
unlock_page(newpage);
|
|
|
|
return rc;
|
|
}
|
|
|
|
static int __unmap_and_move(struct page *page, struct page *newpage,
|
|
int force, enum migrate_mode mode)
|
|
{
|
|
int rc = -EAGAIN;
|
|
int remap_swapcache = 1;
|
|
struct mem_cgroup *mem;
|
|
struct anon_vma *anon_vma = NULL;
|
|
|
|
if (!trylock_page(page)) {
|
|
if (!force || mode == MIGRATE_ASYNC)
|
|
goto out;
|
|
|
|
/*
|
|
* It's not safe for direct compaction to call lock_page.
|
|
* For example, during page readahead pages are added locked
|
|
* to the LRU. Later, when the IO completes the pages are
|
|
* marked uptodate and unlocked. However, the queueing
|
|
* could be merging multiple pages for one bio (e.g.
|
|
* mpage_readpages). If an allocation happens for the
|
|
* second or third page, the process can end up locking
|
|
* the same page twice and deadlocking. Rather than
|
|
* trying to be clever about what pages can be locked,
|
|
* avoid the use of lock_page for direct compaction
|
|
* altogether.
|
|
*/
|
|
if (current->flags & PF_MEMALLOC)
|
|
goto out;
|
|
|
|
lock_page(page);
|
|
}
|
|
|
|
/* charge against new page */
|
|
mem_cgroup_prepare_migration(page, newpage, &mem);
|
|
|
|
if (PageWriteback(page)) {
|
|
/*
|
|
* Only in the case of a full synchronous migration is it
|
|
* necessary to wait for PageWriteback. In the async case,
|
|
* the retry loop is too short and in the sync-light case,
|
|
* the overhead of stalling is too much
|
|
*/
|
|
if (mode != MIGRATE_SYNC) {
|
|
rc = -EBUSY;
|
|
goto uncharge;
|
|
}
|
|
if (!force)
|
|
goto uncharge;
|
|
wait_on_page_writeback(page);
|
|
}
|
|
/*
|
|
* By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
|
|
* we cannot notice that anon_vma is freed while we migrates a page.
|
|
* This get_anon_vma() delays freeing anon_vma pointer until the end
|
|
* of migration. File cache pages are no problem because of page_lock()
|
|
* File Caches may use write_page() or lock_page() in migration, then,
|
|
* just care Anon page here.
|
|
*/
|
|
if (PageAnon(page) && !PageKsm(page)) {
|
|
/*
|
|
* Only page_lock_anon_vma_read() understands the subtleties of
|
|
* getting a hold on an anon_vma from outside one of its mms.
|
|
*/
|
|
anon_vma = page_get_anon_vma(page);
|
|
if (anon_vma) {
|
|
/*
|
|
* Anon page
|
|
*/
|
|
} else if (PageSwapCache(page)) {
|
|
/*
|
|
* We cannot be sure that the anon_vma of an unmapped
|
|
* swapcache page is safe to use because we don't
|
|
* know in advance if the VMA that this page belonged
|
|
* to still exists. If the VMA and others sharing the
|
|
* data have been freed, then the anon_vma could
|
|
* already be invalid.
|
|
*
|
|
* To avoid this possibility, swapcache pages get
|
|
* migrated but are not remapped when migration
|
|
* completes
|
|
*/
|
|
remap_swapcache = 0;
|
|
} else {
|
|
goto uncharge;
|
|
}
|
|
}
|
|
|
|
if (unlikely(balloon_page_movable(page))) {
|
|
/*
|
|
* A ballooned page does not need any special attention from
|
|
* physical to virtual reverse mapping procedures.
|
|
* Skip any attempt to unmap PTEs or to remap swap cache,
|
|
* in order to avoid burning cycles at rmap level, and perform
|
|
* the page migration right away (proteced by page lock).
|
|
*/
|
|
rc = balloon_page_migrate(newpage, page, mode);
|
|
goto uncharge;
|
|
}
|
|
|
|
/*
|
|
* Corner case handling:
|
|
* 1. When a new swap-cache page is read into, it is added to the LRU
|
|
* and treated as swapcache but it has no rmap yet.
|
|
* Calling try_to_unmap() against a page->mapping==NULL page will
|
|
* trigger a BUG. So handle it here.
|
|
* 2. An orphaned page (see truncate_complete_page) might have
|
|
* fs-private metadata. The page can be picked up due to memory
|
|
* offlining. Everywhere else except page reclaim, the page is
|
|
* invisible to the vm, so the page can not be migrated. So try to
|
|
* free the metadata, so the page can be freed.
|
|
*/
|
|
if (!page->mapping) {
|
|
VM_BUG_ON(PageAnon(page));
|
|
if (page_has_private(page)) {
|
|
try_to_free_buffers(page);
|
|
goto uncharge;
|
|
}
|
|
goto skip_unmap;
|
|
}
|
|
|
|
/* Establish migration ptes or remove ptes */
|
|
try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
|
|
|
|
skip_unmap:
|
|
if (!page_mapped(page))
|
|
rc = move_to_new_page(newpage, page, remap_swapcache, mode);
|
|
|
|
if (rc && remap_swapcache)
|
|
remove_migration_ptes(page, page);
|
|
|
|
/* Drop an anon_vma reference if we took one */
|
|
if (anon_vma)
|
|
put_anon_vma(anon_vma);
|
|
|
|
uncharge:
|
|
mem_cgroup_end_migration(mem, page, newpage,
|
|
(rc == MIGRATEPAGE_SUCCESS ||
|
|
rc == MIGRATEPAGE_BALLOON_SUCCESS));
|
|
unlock_page(page);
|
|
out:
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* Obtain the lock on page, remove all ptes and migrate the page
|
|
* to the newly allocated page in newpage.
|
|
*/
|
|
static int unmap_and_move(new_page_t get_new_page, unsigned long private,
|
|
struct page *page, int force, enum migrate_mode mode)
|
|
{
|
|
int rc = 0;
|
|
int *result = NULL;
|
|
struct page *newpage = get_new_page(page, private, &result);
|
|
|
|
if (!newpage)
|
|
return -ENOMEM;
|
|
|
|
if (page_count(page) == 1) {
|
|
/* page was freed from under us. So we are done. */
|
|
goto out;
|
|
}
|
|
|
|
if (unlikely(PageTransHuge(page)))
|
|
if (unlikely(split_huge_page(page)))
|
|
goto out;
|
|
|
|
rc = __unmap_and_move(page, newpage, force, mode);
|
|
|
|
if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) {
|
|
/*
|
|
* A ballooned page has been migrated already.
|
|
* Now, it's the time to wrap-up counters,
|
|
* handle the page back to Buddy and return.
|
|
*/
|
|
dec_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
balloon_page_free(page);
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
out:
|
|
if (rc != -EAGAIN) {
|
|
/*
|
|
* 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);
|
|
dec_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
putback_lru_page(page);
|
|
}
|
|
/*
|
|
* Move the new page to the LRU. If migration was not successful
|
|
* then this will free the page.
|
|
*/
|
|
putback_lru_page(newpage);
|
|
if (result) {
|
|
if (rc)
|
|
*result = rc;
|
|
else
|
|
*result = page_to_nid(newpage);
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* Counterpart of unmap_and_move_page() for hugepage migration.
|
|
*
|
|
* This function doesn't wait the completion of hugepage I/O
|
|
* because there is no race between I/O and migration for hugepage.
|
|
* Note that currently hugepage I/O occurs only in direct I/O
|
|
* where no lock is held and PG_writeback is irrelevant,
|
|
* and writeback status of all subpages are counted in the reference
|
|
* count of the head page (i.e. if all subpages of a 2MB hugepage are
|
|
* under direct I/O, the reference of the head page is 512 and a bit more.)
|
|
* This means that when we try to migrate hugepage whose subpages are
|
|
* doing direct I/O, some references remain after try_to_unmap() and
|
|
* hugepage migration fails without data corruption.
|
|
*
|
|
* There is also no race when direct I/O is issued on the page under migration,
|
|
* because then pte is replaced with migration swap entry and direct I/O code
|
|
* will wait in the page fault for migration to complete.
|
|
*/
|
|
static int unmap_and_move_huge_page(new_page_t get_new_page,
|
|
unsigned long private, struct page *hpage,
|
|
int force, enum migrate_mode mode)
|
|
{
|
|
int rc = 0;
|
|
int *result = NULL;
|
|
struct page *new_hpage = get_new_page(hpage, private, &result);
|
|
struct anon_vma *anon_vma = NULL;
|
|
|
|
/*
|
|
* Movability of hugepages depends on architectures and hugepage size.
|
|
* This check is necessary because some callers of hugepage migration
|
|
* like soft offline and memory hotremove don't walk through page
|
|
* tables or check whether the hugepage is pmd-based or not before
|
|
* kicking migration.
|
|
*/
|
|
if (!hugepage_migration_support(page_hstate(hpage)))
|
|
return -ENOSYS;
|
|
|
|
if (!new_hpage)
|
|
return -ENOMEM;
|
|
|
|
rc = -EAGAIN;
|
|
|
|
if (!trylock_page(hpage)) {
|
|
if (!force || mode != MIGRATE_SYNC)
|
|
goto out;
|
|
lock_page(hpage);
|
|
}
|
|
|
|
if (PageAnon(hpage))
|
|
anon_vma = page_get_anon_vma(hpage);
|
|
|
|
try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
|
|
|
|
if (!page_mapped(hpage))
|
|
rc = move_to_new_page(new_hpage, hpage, 1, mode);
|
|
|
|
if (rc)
|
|
remove_migration_ptes(hpage, hpage);
|
|
|
|
if (anon_vma)
|
|
put_anon_vma(anon_vma);
|
|
|
|
if (!rc)
|
|
hugetlb_cgroup_migrate(hpage, new_hpage);
|
|
|
|
unlock_page(hpage);
|
|
out:
|
|
if (rc != -EAGAIN)
|
|
putback_active_hugepage(hpage);
|
|
put_page(new_hpage);
|
|
if (result) {
|
|
if (rc)
|
|
*result = rc;
|
|
else
|
|
*result = page_to_nid(new_hpage);
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* migrate_pages - migrate the pages specified in a list, to the free pages
|
|
* supplied as the target for the page migration
|
|
*
|
|
* @from: The list of pages to be migrated.
|
|
* @get_new_page: The function used to allocate free pages to be used
|
|
* as the target of the page migration.
|
|
* @private: Private data to be passed on to get_new_page()
|
|
* @mode: The migration mode that specifies the constraints for
|
|
* page migration, if any.
|
|
* @reason: The reason for page migration.
|
|
*
|
|
* The function returns after 10 attempts or if no pages are movable any more
|
|
* because the list has become empty or no retryable pages exist any more.
|
|
* The caller should call putback_lru_pages() to return pages to the LRU
|
|
* or free list only if ret != 0.
|
|
*
|
|
* Returns the number of pages that were not migrated, or an error code.
|
|
*/
|
|
int migrate_pages(struct list_head *from, new_page_t get_new_page,
|
|
unsigned long private, enum migrate_mode mode, int reason)
|
|
{
|
|
int retry = 1;
|
|
int nr_failed = 0;
|
|
int nr_succeeded = 0;
|
|
int pass = 0;
|
|
struct page *page;
|
|
struct page *page2;
|
|
int swapwrite = current->flags & PF_SWAPWRITE;
|
|
int rc;
|
|
|
|
if (!swapwrite)
|
|
current->flags |= PF_SWAPWRITE;
|
|
|
|
for(pass = 0; pass < 10 && retry; pass++) {
|
|
retry = 0;
|
|
|
|
list_for_each_entry_safe(page, page2, from, lru) {
|
|
cond_resched();
|
|
|
|
if (PageHuge(page))
|
|
rc = unmap_and_move_huge_page(get_new_page,
|
|
private, page, pass > 2, mode);
|
|
else
|
|
rc = unmap_and_move(get_new_page, private,
|
|
page, pass > 2, mode);
|
|
|
|
switch(rc) {
|
|
case -ENOMEM:
|
|
goto out;
|
|
case -EAGAIN:
|
|
retry++;
|
|
break;
|
|
case MIGRATEPAGE_SUCCESS:
|
|
nr_succeeded++;
|
|
break;
|
|
default:
|
|
/* Permanent failure */
|
|
nr_failed++;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
rc = nr_failed + retry;
|
|
out:
|
|
if (nr_succeeded)
|
|
count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
|
|
if (nr_failed)
|
|
count_vm_events(PGMIGRATE_FAIL, nr_failed);
|
|
trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
|
|
|
|
if (!swapwrite)
|
|
current->flags &= ~PF_SWAPWRITE;
|
|
|
|
return rc;
|
|
}
|
|
|
|
#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;
|
|
|
|
if (PageHuge(p))
|
|
return alloc_huge_page_node(page_hstate(compound_head(p)),
|
|
pm->node);
|
|
else
|
|
return alloc_pages_exact_node(pm->node,
|
|
GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
* The pm array ends with node = MAX_NUMNODES.
|
|
*/
|
|
static int do_move_page_to_node_array(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
|
|
*/
|
|
for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
|
|
struct vm_area_struct *vma;
|
|
struct page *page;
|
|
|
|
err = -EFAULT;
|
|
vma = find_vma(mm, pp->addr);
|
|
if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma))
|
|
goto set_status;
|
|
|
|
page = follow_page(vma, pp->addr, FOLL_GET|FOLL_SPLIT);
|
|
|
|
err = PTR_ERR(page);
|
|
if (IS_ERR(page))
|
|
goto set_status;
|
|
|
|
err = -ENOENT;
|
|
if (!page)
|
|
goto set_status;
|
|
|
|
/* Use PageReserved to check for zero page */
|
|
if (PageReserved(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;
|
|
|
|
if (PageHuge(page)) {
|
|
isolate_huge_page(page, &pagelist);
|
|
goto put_and_set;
|
|
}
|
|
|
|
err = isolate_lru_page(page);
|
|
if (!err) {
|
|
list_add_tail(&page->lru, &pagelist);
|
|
inc_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
}
|
|
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;
|
|
}
|
|
|
|
err = 0;
|
|
if (!list_empty(&pagelist)) {
|
|
err = migrate_pages(&pagelist, new_page_node,
|
|
(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
|
|
if (err)
|
|
putback_movable_pages(&pagelist);
|
|
}
|
|
|
|
up_read(&mm->mmap_sem);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Migrate an array of page address onto an array of nodes and fill
|
|
* the corresponding array of status.
|
|
*/
|
|
static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
|
|
unsigned long nr_pages,
|
|
const void __user * __user *pages,
|
|
const int __user *nodes,
|
|
int __user *status, int flags)
|
|
{
|
|
struct page_to_node *pm;
|
|
unsigned long chunk_nr_pages;
|
|
unsigned long chunk_start;
|
|
int err;
|
|
|
|
err = -ENOMEM;
|
|
pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
|
|
if (!pm)
|
|
goto out;
|
|
|
|
migrate_prep();
|
|
|
|
/*
|
|
* Store a chunk of page_to_node array in a page,
|
|
* but keep the last one as a marker
|
|
*/
|
|
chunk_nr_pages = (PAGE_SIZE / sizeof(struct page_to_node)) - 1;
|
|
|
|
for (chunk_start = 0;
|
|
chunk_start < nr_pages;
|
|
chunk_start += chunk_nr_pages) {
|
|
int j;
|
|
|
|
if (chunk_start + chunk_nr_pages > nr_pages)
|
|
chunk_nr_pages = nr_pages - chunk_start;
|
|
|
|
/* fill the chunk pm with addrs and nodes from user-space */
|
|
for (j = 0; j < chunk_nr_pages; j++) {
|
|
const void __user *p;
|
|
int node;
|
|
|
|
err = -EFAULT;
|
|
if (get_user(p, pages + j + chunk_start))
|
|
goto out_pm;
|
|
pm[j].addr = (unsigned long) p;
|
|
|
|
if (get_user(node, nodes + j + chunk_start))
|
|
goto out_pm;
|
|
|
|
err = -ENODEV;
|
|
if (node < 0 || node >= MAX_NUMNODES)
|
|
goto out_pm;
|
|
|
|
if (!node_state(node, N_MEMORY))
|
|
goto out_pm;
|
|
|
|
err = -EACCES;
|
|
if (!node_isset(node, task_nodes))
|
|
goto out_pm;
|
|
|
|
pm[j].node = node;
|
|
}
|
|
|
|
/* End marker for this chunk */
|
|
pm[chunk_nr_pages].node = MAX_NUMNODES;
|
|
|
|
/* Migrate this chunk */
|
|
err = do_move_page_to_node_array(mm, pm,
|
|
flags & MPOL_MF_MOVE_ALL);
|
|
if (err < 0)
|
|
goto out_pm;
|
|
|
|
/* Return status information */
|
|
for (j = 0; j < chunk_nr_pages; j++)
|
|
if (put_user(pm[j].status, status + j + chunk_start)) {
|
|
err = -EFAULT;
|
|
goto out_pm;
|
|
}
|
|
}
|
|
err = 0;
|
|
|
|
out_pm:
|
|
free_page((unsigned long)pm);
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Determine the nodes of an array of pages and store it in an array of status.
|
|
*/
|
|
static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
|
|
const void __user **pages, int *status)
|
|
{
|
|
unsigned long i;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
unsigned long addr = (unsigned long)(*pages);
|
|
struct vm_area_struct *vma;
|
|
struct page *page;
|
|
int err = -EFAULT;
|
|
|
|
vma = find_vma(mm, addr);
|
|
if (!vma || addr < vma->vm_start)
|
|
goto set_status;
|
|
|
|
page = follow_page(vma, addr, 0);
|
|
|
|
err = PTR_ERR(page);
|
|
if (IS_ERR(page))
|
|
goto set_status;
|
|
|
|
err = -ENOENT;
|
|
/* Use PageReserved to check for zero page */
|
|
if (!page || PageReserved(page))
|
|
goto set_status;
|
|
|
|
err = page_to_nid(page);
|
|
set_status:
|
|
*status = err;
|
|
|
|
pages++;
|
|
status++;
|
|
}
|
|
|
|
up_read(&mm->mmap_sem);
|
|
}
|
|
|
|
/*
|
|
* Determine the nodes of a user array of pages and store it in
|
|
* a user array of status.
|
|
*/
|
|
static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
|
|
const void __user * __user *pages,
|
|
int __user *status)
|
|
{
|
|
#define DO_PAGES_STAT_CHUNK_NR 16
|
|
const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
|
|
int chunk_status[DO_PAGES_STAT_CHUNK_NR];
|
|
|
|
while (nr_pages) {
|
|
unsigned long chunk_nr;
|
|
|
|
chunk_nr = nr_pages;
|
|
if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
|
|
chunk_nr = DO_PAGES_STAT_CHUNK_NR;
|
|
|
|
if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages)))
|
|
break;
|
|
|
|
do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
|
|
|
|
if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
|
|
break;
|
|
|
|
pages += chunk_nr;
|
|
status += chunk_nr;
|
|
nr_pages -= chunk_nr;
|
|
}
|
|
return nr_pages ? -EFAULT : 0;
|
|
}
|
|
|
|
/*
|
|
* Move a list of pages in the address space of the currently executing
|
|
* process.
|
|
*/
|
|
SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
|
|
const void __user * __user *, pages,
|
|
const int __user *, nodes,
|
|
int __user *, status, int, flags)
|
|
{
|
|
const struct cred *cred = current_cred(), *tcred;
|
|
struct task_struct *task;
|
|
struct mm_struct *mm;
|
|
int err;
|
|
nodemask_t task_nodes;
|
|
|
|
/* 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 */
|
|
rcu_read_lock();
|
|
task = pid ? find_task_by_vpid(pid) : current;
|
|
if (!task) {
|
|
rcu_read_unlock();
|
|
return -ESRCH;
|
|
}
|
|
get_task_struct(task);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
tcred = __task_cred(task);
|
|
if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
|
|
!uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) &&
|
|
!capable(CAP_SYS_NICE)) {
|
|
rcu_read_unlock();
|
|
err = -EPERM;
|
|
goto out;
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
err = security_task_movememory(task);
|
|
if (err)
|
|
goto out;
|
|
|
|
task_nodes = cpuset_mems_allowed(task);
|
|
mm = get_task_mm(task);
|
|
put_task_struct(task);
|
|
|
|
if (!mm)
|
|
return -EINVAL;
|
|
|
|
if (nodes)
|
|
err = do_pages_move(mm, task_nodes, nr_pages, pages,
|
|
nodes, status, flags);
|
|
else
|
|
err = do_pages_stat(mm, nr_pages, pages, status);
|
|
|
|
mmput(mm);
|
|
return err;
|
|
|
|
out:
|
|
put_task_struct(task);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* 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 && !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;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
/*
|
|
* Returns true if this is a safe migration target node for misplaced NUMA
|
|
* pages. Currently it only checks the watermarks which crude
|
|
*/
|
|
static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
|
|
unsigned long nr_migrate_pages)
|
|
{
|
|
int z;
|
|
for (z = pgdat->nr_zones - 1; z >= 0; z--) {
|
|
struct zone *zone = pgdat->node_zones + z;
|
|
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
|
|
if (!zone_reclaimable(zone))
|
|
continue;
|
|
|
|
/* Avoid waking kswapd by allocating pages_to_migrate pages. */
|
|
if (!zone_watermark_ok(zone, 0,
|
|
high_wmark_pages(zone) +
|
|
nr_migrate_pages,
|
|
0, 0))
|
|
continue;
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
static struct page *alloc_misplaced_dst_page(struct page *page,
|
|
unsigned long data,
|
|
int **result)
|
|
{
|
|
int nid = (int) data;
|
|
struct page *newpage;
|
|
|
|
newpage = alloc_pages_exact_node(nid,
|
|
(GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
|
|
__GFP_NOMEMALLOC | __GFP_NORETRY |
|
|
__GFP_NOWARN) &
|
|
~GFP_IOFS, 0);
|
|
if (newpage)
|
|
page_nid_xchg_last(newpage, page_nid_last(page));
|
|
|
|
return newpage;
|
|
}
|
|
|
|
/*
|
|
* page migration rate limiting control.
|
|
* Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
|
|
* window of time. Default here says do not migrate more than 1280M per second.
|
|
* If a node is rate-limited then PTE NUMA updates are also rate-limited. However
|
|
* as it is faults that reset the window, pte updates will happen unconditionally
|
|
* if there has not been a fault since @pteupdate_interval_millisecs after the
|
|
* throttle window closed.
|
|
*/
|
|
static unsigned int migrate_interval_millisecs __read_mostly = 100;
|
|
static unsigned int pteupdate_interval_millisecs __read_mostly = 1000;
|
|
static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);
|
|
|
|
/* Returns true if NUMA migration is currently rate limited */
|
|
bool migrate_ratelimited(int node)
|
|
{
|
|
pg_data_t *pgdat = NODE_DATA(node);
|
|
|
|
if (time_after(jiffies, pgdat->numabalancing_migrate_next_window +
|
|
msecs_to_jiffies(pteupdate_interval_millisecs)))
|
|
return false;
|
|
|
|
if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
/* Returns true if the node is migrate rate-limited after the update */
|
|
bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages)
|
|
{
|
|
bool rate_limited = false;
|
|
|
|
/*
|
|
* Rate-limit the amount of data that is being migrated to a node.
|
|
* Optimal placement is no good if the memory bus is saturated and
|
|
* all the time is being spent migrating!
|
|
*/
|
|
spin_lock(&pgdat->numabalancing_migrate_lock);
|
|
if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
|
|
pgdat->numabalancing_migrate_nr_pages = 0;
|
|
pgdat->numabalancing_migrate_next_window = jiffies +
|
|
msecs_to_jiffies(migrate_interval_millisecs);
|
|
}
|
|
if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages)
|
|
rate_limited = true;
|
|
else
|
|
pgdat->numabalancing_migrate_nr_pages += nr_pages;
|
|
spin_unlock(&pgdat->numabalancing_migrate_lock);
|
|
|
|
return rate_limited;
|
|
}
|
|
|
|
int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
|
|
{
|
|
int page_lru;
|
|
|
|
VM_BUG_ON(compound_order(page) && !PageTransHuge(page));
|
|
|
|
/* Avoid migrating to a node that is nearly full */
|
|
if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page)))
|
|
return 0;
|
|
|
|
if (isolate_lru_page(page))
|
|
return 0;
|
|
|
|
/*
|
|
* migrate_misplaced_transhuge_page() skips page migration's usual
|
|
* check on page_count(), so we must do it here, now that the page
|
|
* has been isolated: a GUP pin, or any other pin, prevents migration.
|
|
* The expected page count is 3: 1 for page's mapcount and 1 for the
|
|
* caller's pin and 1 for the reference taken by isolate_lru_page().
|
|
*/
|
|
if (PageTransHuge(page) && page_count(page) != 3) {
|
|
putback_lru_page(page);
|
|
return 0;
|
|
}
|
|
|
|
page_lru = page_is_file_cache(page);
|
|
mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
|
|
hpage_nr_pages(page));
|
|
|
|
/*
|
|
* Isolating the page has taken another reference, so the
|
|
* caller's reference can be safely dropped without the page
|
|
* disappearing underneath us during migration.
|
|
*/
|
|
put_page(page);
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* Attempt to migrate a misplaced page to the specified destination
|
|
* node. Caller is expected to have an elevated reference count on
|
|
* the page that will be dropped by this function before returning.
|
|
*/
|
|
int migrate_misplaced_page(struct page *page, int node)
|
|
{
|
|
pg_data_t *pgdat = NODE_DATA(node);
|
|
int isolated;
|
|
int nr_remaining;
|
|
LIST_HEAD(migratepages);
|
|
|
|
/*
|
|
* Don't migrate pages that are mapped in multiple processes.
|
|
* TODO: Handle false sharing detection instead of this hammer
|
|
*/
|
|
if (page_mapcount(page) != 1)
|
|
goto out;
|
|
|
|
/*
|
|
* Rate-limit the amount of data that is being migrated to a node.
|
|
* Optimal placement is no good if the memory bus is saturated and
|
|
* all the time is being spent migrating!
|
|
*/
|
|
if (numamigrate_update_ratelimit(pgdat, 1))
|
|
goto out;
|
|
|
|
isolated = numamigrate_isolate_page(pgdat, page);
|
|
if (!isolated)
|
|
goto out;
|
|
|
|
list_add(&page->lru, &migratepages);
|
|
nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
|
|
node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
|
|
if (nr_remaining) {
|
|
putback_lru_pages(&migratepages);
|
|
isolated = 0;
|
|
} else
|
|
count_vm_numa_event(NUMA_PAGE_MIGRATE);
|
|
BUG_ON(!list_empty(&migratepages));
|
|
return isolated;
|
|
|
|
out:
|
|
put_page(page);
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_NUMA_BALANCING */
|
|
|
|
#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
/*
|
|
* Migrates a THP to a given target node. page must be locked and is unlocked
|
|
* before returning.
|
|
*/
|
|
int migrate_misplaced_transhuge_page(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, pmd_t entry,
|
|
unsigned long address,
|
|
struct page *page, int node)
|
|
{
|
|
unsigned long haddr = address & HPAGE_PMD_MASK;
|
|
pg_data_t *pgdat = NODE_DATA(node);
|
|
int isolated = 0;
|
|
struct page *new_page = NULL;
|
|
struct mem_cgroup *memcg = NULL;
|
|
int page_lru = page_is_file_cache(page);
|
|
|
|
/*
|
|
* Don't migrate pages that are mapped in multiple processes.
|
|
* TODO: Handle false sharing detection instead of this hammer
|
|
*/
|
|
if (page_mapcount(page) != 1)
|
|
goto out_dropref;
|
|
|
|
/*
|
|
* Rate-limit the amount of data that is being migrated to a node.
|
|
* Optimal placement is no good if the memory bus is saturated and
|
|
* all the time is being spent migrating!
|
|
*/
|
|
if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
|
|
goto out_dropref;
|
|
|
|
new_page = alloc_pages_node(node,
|
|
(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
|
|
if (!new_page)
|
|
goto out_fail;
|
|
|
|
page_nid_xchg_last(new_page, page_nid_last(page));
|
|
|
|
isolated = numamigrate_isolate_page(pgdat, page);
|
|
if (!isolated) {
|
|
put_page(new_page);
|
|
goto out_fail;
|
|
}
|
|
|
|
/* Prepare a page as a migration target */
|
|
__set_page_locked(new_page);
|
|
SetPageSwapBacked(new_page);
|
|
|
|
/* anon mapping, we can simply copy page->mapping to the new page: */
|
|
new_page->mapping = page->mapping;
|
|
new_page->index = page->index;
|
|
migrate_page_copy(new_page, page);
|
|
WARN_ON(PageLRU(new_page));
|
|
|
|
/* Recheck the target PMD */
|
|
spin_lock(&mm->page_table_lock);
|
|
if (unlikely(!pmd_same(*pmd, entry))) {
|
|
spin_unlock(&mm->page_table_lock);
|
|
|
|
/* Reverse changes made by migrate_page_copy() */
|
|
if (TestClearPageActive(new_page))
|
|
SetPageActive(page);
|
|
if (TestClearPageUnevictable(new_page))
|
|
SetPageUnevictable(page);
|
|
mlock_migrate_page(page, new_page);
|
|
|
|
unlock_page(new_page);
|
|
put_page(new_page); /* Free it */
|
|
|
|
unlock_page(page);
|
|
putback_lru_page(page);
|
|
|
|
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
|
|
isolated = 0;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* Traditional migration needs to prepare the memcg charge
|
|
* transaction early to prevent the old page from being
|
|
* uncharged when installing migration entries. Here we can
|
|
* save the potential rollback and start the charge transfer
|
|
* only when migration is already known to end successfully.
|
|
*/
|
|
mem_cgroup_prepare_migration(page, new_page, &memcg);
|
|
|
|
entry = mk_pmd(new_page, vma->vm_page_prot);
|
|
entry = pmd_mknonnuma(entry);
|
|
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
|
|
entry = pmd_mkhuge(entry);
|
|
|
|
page_add_new_anon_rmap(new_page, vma, haddr);
|
|
|
|
set_pmd_at(mm, haddr, pmd, entry);
|
|
update_mmu_cache_pmd(vma, address, &entry);
|
|
page_remove_rmap(page);
|
|
/*
|
|
* Finish the charge transaction under the page table lock to
|
|
* prevent split_huge_page() from dividing up the charge
|
|
* before it's fully transferred to the new page.
|
|
*/
|
|
mem_cgroup_end_migration(memcg, page, new_page, true);
|
|
spin_unlock(&mm->page_table_lock);
|
|
|
|
unlock_page(new_page);
|
|
unlock_page(page);
|
|
put_page(page); /* Drop the rmap reference */
|
|
put_page(page); /* Drop the LRU isolation reference */
|
|
|
|
count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
|
|
count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
|
|
|
|
out:
|
|
mod_zone_page_state(page_zone(page),
|
|
NR_ISOLATED_ANON + page_lru,
|
|
-HPAGE_PMD_NR);
|
|
return isolated;
|
|
|
|
out_fail:
|
|
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
|
|
out_dropref:
|
|
unlock_page(page);
|
|
put_page(page);
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_NUMA_BALANCING */
|
|
|
|
#endif /* CONFIG_NUMA */
|