linux/mm/swap.c
Johannes Weiner 0a31bc97c8 mm: memcontrol: rewrite uncharge API
The memcg uncharging code that is involved towards the end of a page's
lifetime - truncation, reclaim, swapout, migration - is impressively
complicated and fragile.

Because anonymous and file pages were always charged before they had their
page->mapping established, uncharges had to happen when the page type
could still be known from the context; as in unmap for anonymous, page
cache removal for file and shmem pages, and swap cache truncation for swap
pages.  However, these operations happen well before the page is actually
freed, and so a lot of synchronization is necessary:

- Charging, uncharging, page migration, and charge migration all need
  to take a per-page bit spinlock as they could race with uncharging.

- Swap cache truncation happens during both swap-in and swap-out, and
  possibly repeatedly before the page is actually freed.  This means
  that the memcg swapout code is called from many contexts that make
  no sense and it has to figure out the direction from page state to
  make sure memory and memory+swap are always correctly charged.

- On page migration, the old page might be unmapped but then reused,
  so memcg code has to prevent untimely uncharging in that case.
  Because this code - which should be a simple charge transfer - is so
  special-cased, it is not reusable for replace_page_cache().

But now that charged pages always have a page->mapping, introduce
mem_cgroup_uncharge(), which is called after the final put_page(), when we
know for sure that nobody is looking at the page anymore.

For page migration, introduce mem_cgroup_migrate(), which is called after
the migration is successful and the new page is fully rmapped.  Because
the old page is no longer uncharged after migration, prevent double
charges by decoupling the page's memcg association (PCG_USED and
pc->mem_cgroup) from the page holding an actual charge.  The new bits
PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
to the new page during migration.

mem_cgroup_migrate() is suitable for replace_page_cache() as well,
which gets rid of mem_cgroup_replace_page_cache().  However, care
needs to be taken because both the source and the target page can
already be charged and on the LRU when fuse is splicing: grab the page
lock on the charge moving side to prevent changing pc->mem_cgroup of a
page under migration.  Also, the lruvecs of both pages change as we
uncharge the old and charge the new during migration, and putback may
race with us, so grab the lru lock and isolate the pages iff on LRU to
prevent races and ensure the pages are on the right lruvec afterward.

Swap accounting is massively simplified: because the page is no longer
uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
before the final put_page() in page reclaim.

Finally, page_cgroup changes are now protected by whatever protection the
page itself offers: anonymous pages are charged under the page table lock,
whereas page cache insertions, swapin, and migration hold the page lock.
Uncharging happens under full exclusion with no outstanding references.
Charging and uncharging also ensure that the page is off-LRU, which
serializes against charge migration.  Remove the very costly page_cgroup
lock and set pc->flags non-atomically.

[mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
[vdavydov@parallels.com: fix flags definition]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Tested-by: Jet Chen <jet.chen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 15:57:17 -07:00

1155 lines
32 KiB
C

/*
* linux/mm/swap.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* This file contains the default values for the operation of the
* Linux VM subsystem. Fine-tuning documentation can be found in
* Documentation/sysctl/vm.txt.
* Started 18.12.91
* Swap aging added 23.2.95, Stephen Tweedie.
* Buffermem limits added 12.3.98, Rik van Riel.
*/
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/mm_inline.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/backing-dev.h>
#include <linux/memcontrol.h>
#include <linux/gfp.h>
#include <linux/uio.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/pagemap.h>
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
/*
* This path almost never happens for VM activity - pages are normally
* freed via pagevecs. But it gets used by networking.
*/
static void __page_cache_release(struct page *page)
{
if (PageLRU(page)) {
struct zone *zone = page_zone(page);
struct lruvec *lruvec;
unsigned long flags;
spin_lock_irqsave(&zone->lru_lock, flags);
lruvec = mem_cgroup_page_lruvec(page, zone);
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(page));
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
mem_cgroup_uncharge(page);
}
static void __put_single_page(struct page *page)
{
__page_cache_release(page);
free_hot_cold_page(page, false);
}
static void __put_compound_page(struct page *page)
{
compound_page_dtor *dtor;
__page_cache_release(page);
dtor = get_compound_page_dtor(page);
(*dtor)(page);
}
/**
* Two special cases here: we could avoid taking compound_lock_irqsave
* and could skip the tail refcounting(in _mapcount).
*
* 1. Hugetlbfs page:
*
* PageHeadHuge will remain true until the compound page
* is released and enters the buddy allocator, and it could
* not be split by __split_huge_page_refcount().
*
* So if we see PageHeadHuge set, and we have the tail page pin,
* then we could safely put head page.
*
* 2. Slab THP page:
*
* PG_slab is cleared before the slab frees the head page, and
* tail pin cannot be the last reference left on the head page,
* because the slab code is free to reuse the compound page
* after a kfree/kmem_cache_free without having to check if
* there's any tail pin left. In turn all tail pinsmust be always
* released while the head is still pinned by the slab code
* and so we know PG_slab will be still set too.
*
* So if we see PageSlab set, and we have the tail page pin,
* then we could safely put head page.
*/
static __always_inline
void put_unrefcounted_compound_page(struct page *page_head, struct page *page)
{
/*
* If @page is a THP tail, we must read the tail page
* flags after the head page flags. The
* __split_huge_page_refcount side enforces write memory barriers
* between clearing PageTail and before the head page
* can be freed and reallocated.
*/
smp_rmb();
if (likely(PageTail(page))) {
/*
* __split_huge_page_refcount cannot race
* here, see the comment above this function.
*/
VM_BUG_ON_PAGE(!PageHead(page_head), page_head);
VM_BUG_ON_PAGE(page_mapcount(page) != 0, page);
if (put_page_testzero(page_head)) {
/*
* If this is the tail of a slab THP page,
* the tail pin must not be the last reference
* held on the page, because the PG_slab cannot
* be cleared before all tail pins (which skips
* the _mapcount tail refcounting) have been
* released.
*
* If this is the tail of a hugetlbfs page,
* the tail pin may be the last reference on
* the page instead, because PageHeadHuge will
* not go away until the compound page enters
* the buddy allocator.
*/
VM_BUG_ON_PAGE(PageSlab(page_head), page_head);
__put_compound_page(page_head);
}
} else
/*
* __split_huge_page_refcount run before us,
* @page was a THP tail. The split @page_head
* has been freed and reallocated as slab or
* hugetlbfs page of smaller order (only
* possible if reallocated as slab on x86).
*/
if (put_page_testzero(page))
__put_single_page(page);
}
static __always_inline
void put_refcounted_compound_page(struct page *page_head, struct page *page)
{
if (likely(page != page_head && get_page_unless_zero(page_head))) {
unsigned long flags;
/*
* @page_head wasn't a dangling pointer but it may not
* be a head page anymore by the time we obtain the
* lock. That is ok as long as it can't be freed from
* under us.
*/
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
/*
* The @page_head may have been freed
* and reallocated as a compound page
* of smaller order and then freed
* again. All we know is that it
* cannot have become: a THP page, a
* compound page of higher order, a
* tail page. That is because we
* still hold the refcount of the
* split THP tail and page_head was
* the THP head before the split.
*/
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
return;
}
VM_BUG_ON_PAGE(page_head != page->first_page, page);
/*
* We can release the refcount taken by
* get_page_unless_zero() now that
* __split_huge_page_refcount() is blocked on the
* compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON_PAGE(1, page_head);
/* __split_huge_page_refcount will wait now */
VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page);
atomic_dec(&page->_mapcount);
VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head);
VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
} else {
/* @page_head is a dangling pointer */
VM_BUG_ON_PAGE(PageTail(page), page);
goto out_put_single;
}
}
static void put_compound_page(struct page *page)
{
struct page *page_head;
/*
* We see the PageCompound set and PageTail not set, so @page maybe:
* 1. hugetlbfs head page, or
* 2. THP head page.
*/
if (likely(!PageTail(page))) {
if (put_page_testzero(page)) {
/*
* By the time all refcounts have been released
* split_huge_page cannot run anymore from under us.
*/
if (PageHead(page))
__put_compound_page(page);
else
__put_single_page(page);
}
return;
}
/*
* We see the PageCompound set and PageTail set, so @page maybe:
* 1. a tail hugetlbfs page, or
* 2. a tail THP page, or
* 3. a split THP page.
*
* Case 3 is possible, as we may race with
* __split_huge_page_refcount tearing down a THP page.
*/
page_head = compound_head_by_tail(page);
if (!__compound_tail_refcounted(page_head))
put_unrefcounted_compound_page(page_head, page);
else
put_refcounted_compound_page(page_head, page);
}
void put_page(struct page *page)
{
if (unlikely(PageCompound(page)))
put_compound_page(page);
else if (put_page_testzero(page))
__put_single_page(page);
}
EXPORT_SYMBOL(put_page);
/*
* This function is exported but must not be called by anything other
* than get_page(). It implements the slow path of get_page().
*/
bool __get_page_tail(struct page *page)
{
/*
* This takes care of get_page() if run on a tail page
* returned by one of the get_user_pages/follow_page variants.
* get_user_pages/follow_page itself doesn't need the compound
* lock because it runs __get_page_tail_foll() under the
* proper PT lock that already serializes against
* split_huge_page().
*/
unsigned long flags;
bool got;
struct page *page_head = compound_head(page);
/* Ref to put_compound_page() comment. */
if (!__compound_tail_refcounted(page_head)) {
smp_rmb();
if (likely(PageTail(page))) {
/*
* This is a hugetlbfs page or a slab
* page. __split_huge_page_refcount
* cannot race here.
*/
VM_BUG_ON_PAGE(!PageHead(page_head), page_head);
__get_page_tail_foll(page, true);
return true;
} else {
/*
* __split_huge_page_refcount run
* before us, "page" was a THP
* tail. The split page_head has been
* freed and reallocated as slab or
* hugetlbfs page of smaller order
* (only possible if reallocated as
* slab on x86).
*/
return false;
}
}
got = false;
if (likely(page != page_head && get_page_unless_zero(page_head))) {
/*
* page_head wasn't a dangling pointer but it
* may not be a head page anymore by the time
* we obtain the lock. That is ok as long as it
* can't be freed from under us.
*/
flags = compound_lock_irqsave(page_head);
/* here __split_huge_page_refcount won't run anymore */
if (likely(PageTail(page))) {
__get_page_tail_foll(page, false);
got = true;
}
compound_unlock_irqrestore(page_head, flags);
if (unlikely(!got))
put_page(page_head);
}
return got;
}
EXPORT_SYMBOL(__get_page_tail);
/**
* put_pages_list() - release a list of pages
* @pages: list of pages threaded on page->lru
*
* Release a list of pages which are strung together on page.lru. Currently
* used by read_cache_pages() and related error recovery code.
*/
void put_pages_list(struct list_head *pages)
{
while (!list_empty(pages)) {
struct page *victim;
victim = list_entry(pages->prev, struct page, lru);
list_del(&victim->lru);
page_cache_release(victim);
}
}
EXPORT_SYMBOL(put_pages_list);
/*
* get_kernel_pages() - pin kernel pages in memory
* @kiov: An array of struct kvec structures
* @nr_segs: number of segments to pin
* @write: pinning for read/write, currently ignored
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_segs long.
*
* Returns number of pages pinned. This may be fewer than the number
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno. Each page returned must be released
* with a put_page() call when it is finished with.
*/
int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
struct page **pages)
{
int seg;
for (seg = 0; seg < nr_segs; seg++) {
if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
return seg;
pages[seg] = kmap_to_page(kiov[seg].iov_base);
page_cache_get(pages[seg]);
}
return seg;
}
EXPORT_SYMBOL_GPL(get_kernel_pages);
/*
* get_kernel_page() - pin a kernel page in memory
* @start: starting kernel address
* @write: pinning for read/write, currently ignored
* @pages: array that receives pointer to the page pinned.
* Must be at least nr_segs long.
*
* Returns 1 if page is pinned. If the page was not pinned, returns
* -errno. The page returned must be released with a put_page() call
* when it is finished with.
*/
int get_kernel_page(unsigned long start, int write, struct page **pages)
{
const struct kvec kiov = {
.iov_base = (void *)start,
.iov_len = PAGE_SIZE
};
return get_kernel_pages(&kiov, 1, write, pages);
}
EXPORT_SYMBOL_GPL(get_kernel_page);
static void pagevec_lru_move_fn(struct pagevec *pvec,
void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
void *arg)
{
int i;
struct zone *zone = NULL;
struct lruvec *lruvec;
unsigned long flags = 0;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
(*move_fn)(page, lruvec, arg);
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec,
void *arg)
{
int *pgmoved = arg;
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
enum lru_list lru = page_lru_base_type(page);
list_move_tail(&page->lru, &lruvec->lists[lru]);
(*pgmoved)++;
}
}
/*
* pagevec_move_tail() must be called with IRQ disabled.
* Otherwise this may cause nasty races.
*/
static void pagevec_move_tail(struct pagevec *pvec)
{
int pgmoved = 0;
pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved);
__count_vm_events(PGROTATED, pgmoved);
}
/*
* Writeback is about to end against a page which has been marked for immediate
* reclaim. If it still appears to be reclaimable, move it to the tail of the
* inactive list.
*/
void rotate_reclaimable_page(struct page *page)
{
if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
!PageUnevictable(page) && PageLRU(page)) {
struct pagevec *pvec;
unsigned long flags;
page_cache_get(page);
local_irq_save(flags);
pvec = this_cpu_ptr(&lru_rotate_pvecs);
if (!pagevec_add(pvec, page))
pagevec_move_tail(pvec);
local_irq_restore(flags);
}
}
static void update_page_reclaim_stat(struct lruvec *lruvec,
int file, int rotated)
{
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
reclaim_stat->recent_scanned[file]++;
if (rotated)
reclaim_stat->recent_rotated[file]++;
}
static void __activate_page(struct page *page, struct lruvec *lruvec,
void *arg)
{
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
int file = page_is_file_cache(page);
int lru = page_lru_base_type(page);
del_page_from_lru_list(page, lruvec, lru);
SetPageActive(page);
lru += LRU_ACTIVE;
add_page_to_lru_list(page, lruvec, lru);
trace_mm_lru_activate(page);
__count_vm_event(PGACTIVATE);
update_page_reclaim_stat(lruvec, file, 1);
}
}
#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
static void activate_page_drain(int cpu)
{
struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, __activate_page, NULL);
}
static bool need_activate_page_drain(int cpu)
{
return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
}
void activate_page(struct page *page)
{
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
page_cache_get(page);
if (!pagevec_add(pvec, page))
pagevec_lru_move_fn(pvec, __activate_page, NULL);
put_cpu_var(activate_page_pvecs);
}
}
#else
static inline void activate_page_drain(int cpu)
{
}
static bool need_activate_page_drain(int cpu)
{
return false;
}
void activate_page(struct page *page)
{
struct zone *zone = page_zone(page);
spin_lock_irq(&zone->lru_lock);
__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
spin_unlock_irq(&zone->lru_lock);
}
#endif
static void __lru_cache_activate_page(struct page *page)
{
struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
int i;
/*
* Search backwards on the optimistic assumption that the page being
* activated has just been added to this pagevec. Note that only
* the local pagevec is examined as a !PageLRU page could be in the
* process of being released, reclaimed, migrated or on a remote
* pagevec that is currently being drained. Furthermore, marking
* a remote pagevec's page PageActive potentially hits a race where
* a page is marked PageActive just after it is added to the inactive
* list causing accounting errors and BUG_ON checks to trigger.
*/
for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
struct page *pagevec_page = pvec->pages[i];
if (pagevec_page == page) {
SetPageActive(page);
break;
}
}
put_cpu_var(lru_add_pvec);
}
/*
* Mark a page as having seen activity.
*
* inactive,unreferenced -> inactive,referenced
* inactive,referenced -> active,unreferenced
* active,unreferenced -> active,referenced
*
* When a newly allocated page is not yet visible, so safe for non-atomic ops,
* __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
*/
void mark_page_accessed(struct page *page)
{
if (!PageActive(page) && !PageUnevictable(page) &&
PageReferenced(page)) {
/*
* If the page is on the LRU, queue it for activation via
* activate_page_pvecs. Otherwise, assume the page is on a
* pagevec, mark it active and it'll be moved to the active
* LRU on the next drain.
*/
if (PageLRU(page))
activate_page(page);
else
__lru_cache_activate_page(page);
ClearPageReferenced(page);
if (page_is_file_cache(page))
workingset_activation(page);
} else if (!PageReferenced(page)) {
SetPageReferenced(page);
}
}
EXPORT_SYMBOL(mark_page_accessed);
static void __lru_cache_add(struct page *page)
{
struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
page_cache_get(page);
if (!pagevec_space(pvec))
__pagevec_lru_add(pvec);
pagevec_add(pvec, page);
put_cpu_var(lru_add_pvec);
}
/**
* lru_cache_add: add a page to the page lists
* @page: the page to add
*/
void lru_cache_add_anon(struct page *page)
{
if (PageActive(page))
ClearPageActive(page);
__lru_cache_add(page);
}
void lru_cache_add_file(struct page *page)
{
if (PageActive(page))
ClearPageActive(page);
__lru_cache_add(page);
}
EXPORT_SYMBOL(lru_cache_add_file);
/**
* lru_cache_add - add a page to a page list
* @page: the page to be added to the LRU.
*
* Queue the page for addition to the LRU via pagevec. The decision on whether
* to add the page to the [in]active [file|anon] list is deferred until the
* pagevec is drained. This gives a chance for the caller of lru_cache_add()
* have the page added to the active list using mark_page_accessed().
*/
void lru_cache_add(struct page *page)
{
VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
VM_BUG_ON_PAGE(PageLRU(page), page);
__lru_cache_add(page);
}
/**
* add_page_to_unevictable_list - add a page to the unevictable list
* @page: the page to be added to the unevictable list
*
* Add page directly to its zone's unevictable list. To avoid races with
* tasks that might be making the page evictable, through eg. munlock,
* munmap or exit, while it's not on the lru, we want to add the page
* while it's locked or otherwise "invisible" to other tasks. This is
* difficult to do when using the pagevec cache, so bypass that.
*/
void add_page_to_unevictable_list(struct page *page)
{
struct zone *zone = page_zone(page);
struct lruvec *lruvec;
spin_lock_irq(&zone->lru_lock);
lruvec = mem_cgroup_page_lruvec(page, zone);
ClearPageActive(page);
SetPageUnevictable(page);
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
spin_unlock_irq(&zone->lru_lock);
}
/**
* lru_cache_add_active_or_unevictable
* @page: the page to be added to LRU
* @vma: vma in which page is mapped for determining reclaimability
*
* Place @page on the active or unevictable LRU list, depending on its
* evictability. Note that if the page is not evictable, it goes
* directly back onto it's zone's unevictable list, it does NOT use a
* per cpu pagevec.
*/
void lru_cache_add_active_or_unevictable(struct page *page,
struct vm_area_struct *vma)
{
VM_BUG_ON_PAGE(PageLRU(page), page);
if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
SetPageActive(page);
lru_cache_add(page);
return;
}
if (!TestSetPageMlocked(page)) {
/*
* We use the irq-unsafe __mod_zone_page_stat because this
* counter is not modified from interrupt context, and the pte
* lock is held(spinlock), which implies preemption disabled.
*/
__mod_zone_page_state(page_zone(page), NR_MLOCK,
hpage_nr_pages(page));
count_vm_event(UNEVICTABLE_PGMLOCKED);
}
add_page_to_unevictable_list(page);
}
/*
* If the page can not be invalidated, it is moved to the
* inactive list to speed up its reclaim. It is moved to the
* head of the list, rather than the tail, to give the flusher
* threads some time to write it out, as this is much more
* effective than the single-page writeout from reclaim.
*
* If the page isn't page_mapped and dirty/writeback, the page
* could reclaim asap using PG_reclaim.
*
* 1. active, mapped page -> none
* 2. active, dirty/writeback page -> inactive, head, PG_reclaim
* 3. inactive, mapped page -> none
* 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
* 5. inactive, clean -> inactive, tail
* 6. Others -> none
*
* In 4, why it moves inactive's head, the VM expects the page would
* be write it out by flusher threads as this is much more effective
* than the single-page writeout from reclaim.
*/
static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
void *arg)
{
int lru, file;
bool active;
if (!PageLRU(page))
return;
if (PageUnevictable(page))
return;
/* Some processes are using the page */
if (page_mapped(page))
return;
active = PageActive(page);
file = page_is_file_cache(page);
lru = page_lru_base_type(page);
del_page_from_lru_list(page, lruvec, lru + active);
ClearPageActive(page);
ClearPageReferenced(page);
add_page_to_lru_list(page, lruvec, lru);
if (PageWriteback(page) || PageDirty(page)) {
/*
* PG_reclaim could be raced with end_page_writeback
* It can make readahead confusing. But race window
* is _really_ small and it's non-critical problem.
*/
SetPageReclaim(page);
} else {
/*
* The page's writeback ends up during pagevec
* We moves tha page into tail of inactive.
*/
list_move_tail(&page->lru, &lruvec->lists[lru]);
__count_vm_event(PGROTATED);
}
if (active)
__count_vm_event(PGDEACTIVATE);
update_page_reclaim_stat(lruvec, file, 0);
}
/*
* Drain pages out of the cpu's pagevecs.
* Either "cpu" is the current CPU, and preemption has already been
* disabled; or "cpu" is being hot-unplugged, and is already dead.
*/
void lru_add_drain_cpu(int cpu)
{
struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
if (pagevec_count(pvec))
__pagevec_lru_add(pvec);
pvec = &per_cpu(lru_rotate_pvecs, cpu);
if (pagevec_count(pvec)) {
unsigned long flags;
/* No harm done if a racing interrupt already did this */
local_irq_save(flags);
pagevec_move_tail(pvec);
local_irq_restore(flags);
}
pvec = &per_cpu(lru_deactivate_pvecs, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
activate_page_drain(cpu);
}
/**
* deactivate_page - forcefully deactivate a page
* @page: page to deactivate
*
* This function hints the VM that @page is a good reclaim candidate,
* for example if its invalidation fails due to the page being dirty
* or under writeback.
*/
void deactivate_page(struct page *page)
{
/*
* In a workload with many unevictable page such as mprotect, unevictable
* page deactivation for accelerating reclaim is pointless.
*/
if (PageUnevictable(page))
return;
if (likely(get_page_unless_zero(page))) {
struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
if (!pagevec_add(pvec, page))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
put_cpu_var(lru_deactivate_pvecs);
}
}
void lru_add_drain(void)
{
lru_add_drain_cpu(get_cpu());
put_cpu();
}
static void lru_add_drain_per_cpu(struct work_struct *dummy)
{
lru_add_drain();
}
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
void lru_add_drain_all(void)
{
static DEFINE_MUTEX(lock);
static struct cpumask has_work;
int cpu;
mutex_lock(&lock);
get_online_cpus();
cpumask_clear(&has_work);
for_each_online_cpu(cpu) {
struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
schedule_work_on(cpu, work);
cpumask_set_cpu(cpu, &has_work);
}
}
for_each_cpu(cpu, &has_work)
flush_work(&per_cpu(lru_add_drain_work, cpu));
put_online_cpus();
mutex_unlock(&lock);
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_inactive_list(): we recheck
* the page count inside the lock to see whether shrink_inactive_list()
* grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
* will free it.
*/
void release_pages(struct page **pages, int nr, bool cold)
{
int i;
LIST_HEAD(pages_to_free);
struct zone *zone = NULL;
struct lruvec *lruvec;
unsigned long uninitialized_var(flags);
mem_cgroup_uncharge_start();
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(page));
}
mem_cgroup_uncharge(page);
/* Clear Active bit in case of parallel mark_page_accessed */
__ClearPageActive(page);
list_add(&page->lru, &pages_to_free);
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
mem_cgroup_uncharge_end();
free_hot_cold_page_list(&pages_to_free, cold);
}
EXPORT_SYMBOL(release_pages);
/*
* The pages which we're about to release may be in the deferred lru-addition
* queues. That would prevent them from really being freed right now. That's
* OK from a correctness point of view but is inefficient - those pages may be
* cache-warm and we want to give them back to the page allocator ASAP.
*
* So __pagevec_release() will drain those queues here. __pagevec_lru_add()
* and __pagevec_lru_add_active() call release_pages() directly to avoid
* mutual recursion.
*/
void __pagevec_release(struct pagevec *pvec)
{
lru_add_drain();
release_pages(pvec->pages, pagevec_count(pvec), pvec->cold);
pagevec_reinit(pvec);
}
EXPORT_SYMBOL(__pagevec_release);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *list)
{
const int file = 0;
VM_BUG_ON_PAGE(!PageHead(page), page);
VM_BUG_ON_PAGE(PageCompound(page_tail), page);
VM_BUG_ON_PAGE(PageLRU(page_tail), page);
VM_BUG_ON(NR_CPUS != 1 &&
!spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
if (!list)
SetPageLRU(page_tail);
if (likely(PageLRU(page)))
list_add_tail(&page_tail->lru, &page->lru);
else if (list) {
/* page reclaim is reclaiming a huge page */
get_page(page_tail);
list_add_tail(&page_tail->lru, list);
} else {
struct list_head *list_head;
/*
* Head page has not yet been counted, as an hpage,
* so we must account for each subpage individually.
*
* Use the standard add function to put page_tail on the list,
* but then correct its position so they all end up in order.
*/
add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
list_head = page_tail->lru.prev;
list_move_tail(&page_tail->lru, list_head);
}
if (!PageUnevictable(page))
update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
void *arg)
{
int file = page_is_file_cache(page);
int active = PageActive(page);
enum lru_list lru = page_lru(page);
VM_BUG_ON_PAGE(PageLRU(page), page);
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, lru);
update_page_reclaim_stat(lruvec, file, active);
trace_mm_lru_insertion(page, lru);
}
/*
* Add the passed pages to the LRU, then drop the caller's refcount
* on them. Reinitialises the caller's pagevec.
*/
void __pagevec_lru_add(struct pagevec *pvec)
{
pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL);
}
EXPORT_SYMBOL(__pagevec_lru_add);
/**
* pagevec_lookup_entries - gang pagecache lookup
* @pvec: Where the resulting entries are placed
* @mapping: The address_space to search
* @start: The starting entry index
* @nr_entries: The maximum number of entries
* @indices: The cache indices corresponding to the entries in @pvec
*
* pagevec_lookup_entries() will search for and return a group of up
* to @nr_entries pages and shadow entries in the mapping. All
* entries are placed in @pvec. pagevec_lookup_entries() takes a
* reference against actual pages in @pvec.
*
* The search returns a group of mapping-contiguous entries with
* ascending indexes. There may be holes in the indices due to
* not-present entries.
*
* pagevec_lookup_entries() returns the number of entries which were
* found.
*/
unsigned pagevec_lookup_entries(struct pagevec *pvec,
struct address_space *mapping,
pgoff_t start, unsigned nr_pages,
pgoff_t *indices)
{
pvec->nr = find_get_entries(mapping, start, nr_pages,
pvec->pages, indices);
return pagevec_count(pvec);
}
/**
* pagevec_remove_exceptionals - pagevec exceptionals pruning
* @pvec: The pagevec to prune
*
* pagevec_lookup_entries() fills both pages and exceptional radix
* tree entries into the pagevec. This function prunes all
* exceptionals from @pvec without leaving holes, so that it can be
* passed on to page-only pagevec operations.
*/
void pagevec_remove_exceptionals(struct pagevec *pvec)
{
int i, j;
for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
if (!radix_tree_exceptional_entry(page))
pvec->pages[j++] = page;
}
pvec->nr = j;
}
/**
* pagevec_lookup - gang pagecache lookup
* @pvec: Where the resulting pages are placed
* @mapping: The address_space to search
* @start: The starting page index
* @nr_pages: The maximum number of pages
*
* pagevec_lookup() will search for and return a group of up to @nr_pages pages
* in the mapping. The pages are placed in @pvec. pagevec_lookup() takes a
* reference against the pages in @pvec.
*
* The search returns a group of mapping-contiguous pages with ascending
* indexes. There may be holes in the indices due to not-present pages.
*
* pagevec_lookup() returns the number of pages which were found.
*/
unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
pgoff_t start, unsigned nr_pages)
{
pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup);
unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
pgoff_t *index, int tag, unsigned nr_pages)
{
pvec->nr = find_get_pages_tag(mapping, index, tag,
nr_pages, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_tag);
/*
* Perform any setup for the swap system
*/
void __init swap_setup(void)
{
unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
#ifdef CONFIG_SWAP
int i;
if (bdi_init(swapper_spaces[0].backing_dev_info))
panic("Failed to init swap bdi");
for (i = 0; i < MAX_SWAPFILES; i++) {
spin_lock_init(&swapper_spaces[i].tree_lock);
INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
}
#endif
/* Use a smaller cluster for small-memory machines */
if (megs < 16)
page_cluster = 2;
else
page_cluster = 3;
/*
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
}