#include <linux/memcontrol.h>
#include <linux/gfp.h>
#include <linux/uio.h>
+#include <linux/hugetlb.h>
+#include <linux/page_idle.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[NR_LRU_LISTS], lru_add_pvecs);
+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);
+static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
/*
* This path almost never happens for VM activity - pages are normally
spin_lock_irqsave(&zone->lru_lock, flags);
lruvec = mem_cgroup_page_lruvec(page, zone);
- VM_BUG_ON(!PageLRU(page));
+ 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, 0);
+ free_hot_cold_page(page, false);
}
static void __put_compound_page(struct page *page)
{
compound_page_dtor *dtor;
- __page_cache_release(page);
+ /*
+ * __page_cache_release() is supposed to be called for thp, not for
+ * hugetlb. This is because hugetlb page does never have PageLRU set
+ * (it's never listed to any LRU lists) and no memcg routines should
+ * be called for hugetlb (it has a separate hugetlb_cgroup.)
+ */
+ if (!PageHuge(page))
+ __page_cache_release(page);
dtor = get_compound_page_dtor(page);
(*dtor)(page);
}
-static void put_compound_page(struct page *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 (unlikely(PageTail(page))) {
- /* __split_huge_page_refcount can run under us */
- struct page *page_head = compound_trans_head(page);
-
- if (likely(page != page_head &&
- get_page_unless_zero(page_head))) {
- unsigned long flags;
-
- /*
- * THP can not break up slab pages so avoid taking
- * compound_lock(). Slab performs non-atomic bit ops
- * on page->flags for better performance. In particular
- * slab_unlock() in slub used to be a hot path. It is
- * still hot on arches that do not support
- * this_cpu_cmpxchg_double().
- */
- if (PageSlab(page_head)) {
- if (PageTail(page)) {
- if (put_page_testzero(page_head))
- VM_BUG_ON(1);
-
- atomic_dec(&page->_mapcount);
- goto skip_lock_tail;
- } else
- goto skip_lock;
- }
- /*
- * 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);
-skip_lock:
- if (put_page_testzero(page_head))
- __put_single_page(page_head);
-out_put_single:
- if (put_page_testzero(page))
- __put_single_page(page);
- return;
- }
- VM_BUG_ON(page_head != page->first_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);
+ if (put_page_testzero(page_head)) {
/*
- * We can release the refcount taken by
- * get_page_unless_zero() now that
- * __split_huge_page_refcount() is blocked on
- * the compound_lock.
+ * 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.
*/
- if (put_page_testzero(page_head))
- VM_BUG_ON(1);
- /* __split_huge_page_refcount will wait now */
- VM_BUG_ON(page_mapcount(page) <= 0);
- atomic_dec(&page->_mapcount);
- VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
- VM_BUG_ON(atomic_read(&page->_count) != 0);
- compound_unlock_irqrestore(page_head, flags);
+ 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);
+}
-skip_lock_tail:
+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);
}
- } else {
- /* page_head is a dangling pointer */
- VM_BUG_ON(PageTail(page));
- goto out_put_single;
+out_put_single:
+ if (put_page_testzero(page))
+ __put_single_page(page);
+ return;
}
- } else if (put_page_testzero(page)) {
- if (PageHead(page))
- __put_compound_page(page);
- else
- __put_single_page(page);
+ VM_BUG_ON_PAGE(page_head != compound_head(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(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)))
* split_huge_page().
*/
unsigned long flags;
- bool got = false;
- struct page *page_head = compound_trans_head(page);
-
- if (likely(page != page_head && get_page_unless_zero(page_head))) {
+ bool got;
+ struct page *page_head = compound_head(page);
- /* Ref to put_compound_page() comment. */
- if (PageSlab(page_head)) {
- if (likely(PageTail(page))) {
- __get_page_tail_foll(page, false);
- return true;
- } else {
- put_page(page_head);
- return false;
- }
+ /* 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
page_cache_get(page);
local_irq_save(flags);
- pvec = &__get_cpu_var(lru_rotate_pvecs);
+ pvec = this_cpu_ptr(&lru_rotate_pvecs);
if (!pagevec_add(pvec, page))
pagevec_move_tail(pvec);
local_irq_restore(flags);
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);
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)) {
{
}
+static bool need_activate_page_drain(int cpu)
+{
+ return false;
+}
+
void activate_page(struct page *page)
{
struct zone *zone = page_zone(page);
}
#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) && PageLRU(page)) {
- activate_page(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);
}
+ if (page_is_idle(page))
+ clear_page_idle(page);
}
EXPORT_SYMBOL(mark_page_accessed);
-/*
- * Order of operations is important: flush the pagevec when it's already
- * full, not when adding the last page, to make sure that last page is
- * not added to the LRU directly when passed to this function. Because
- * mark_page_accessed() (called after this when writing) only activates
- * pages that are on the LRU, linear writes in subpage chunks would see
- * every PAGEVEC_SIZE page activated, which is unexpected.
- */
-void __lru_cache_add(struct page *page, enum lru_list lru)
+static void __lru_cache_add(struct page *page)
{
- struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];
+ struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
page_cache_get(page);
if (!pagevec_space(pvec))
- __pagevec_lru_add(pvec, lru);
+ __pagevec_lru_add(pvec);
pagevec_add(pvec, page);
- put_cpu_var(lru_add_pvecs);
+ put_cpu_var(lru_add_pvec);
}
-EXPORT_SYMBOL(__lru_cache_add);
/**
- * lru_cache_add_lru - add a page to a page list
- * @page: the page to be added to the LRU.
- * @lru: the LRU list to which the page is added.
+ * lru_cache_add: add a page to the page lists
+ * @page: the page to add
*/
-void lru_cache_add_lru(struct page *page, enum lru_list lru)
+void lru_cache_add_anon(struct page *page)
{
- if (PageActive(page)) {
- VM_BUG_ON(PageUnevictable(page));
+ if (PageActive(page))
ClearPageActive(page);
- } else if (PageUnevictable(page)) {
- VM_BUG_ON(PageActive(page));
- ClearPageUnevictable(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);
- VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page));
- __lru_cache_add(page, lru);
+/**
+ * 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);
}
/**
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
* 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,
+static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
void *arg)
{
int lru, file;
*/
void lru_add_drain_cpu(int cpu)
{
- struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu);
- struct pagevec *pvec;
- int lru;
+ struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
- for_each_lru(lru) {
- pvec = &pvecs[lru - LRU_BASE];
- if (pagevec_count(pvec))
- __pagevec_lru_add(pvec, lru);
- }
+ if (pagevec_count(pvec))
+ __pagevec_lru_add(pvec);
pvec = &per_cpu(lru_rotate_pvecs, cpu);
if (pagevec_count(pvec)) {
local_irq_restore(flags);
}
- pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+ pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
if (pagevec_count(pvec))
- pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+ pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
activate_page_drain(cpu);
}
/**
- * deactivate_page - forcefully deactivate a page
+ * deactivate_file_page - forcefully deactivate a file 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)
+void deactivate_file_page(struct page *page)
{
/*
- * In a workload with many unevictable page such as mprotect, unevictable
- * page deactivation for accelerating reclaim is pointless.
+ * 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);
+ struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
if (!pagevec_add(pvec, page))
- pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
- put_cpu_var(lru_deactivate_pvecs);
+ pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
+ put_cpu_var(lru_deactivate_file_pvecs);
}
}
lru_add_drain();
}
-/*
- * Returns 0 for success
- */
-int lru_add_drain_all(void)
+static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
+
+void lru_add_drain_all(void)
{
- return schedule_on_each_cpu(lru_add_drain_per_cpu);
+ 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_file_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.
+/**
+ * release_pages - batched page_cache_release()
+ * @pages: array of pages to release
+ * @nr: number of pages
+ * @cold: whether the pages are cache cold
*
- * 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.
+ * Decrement the reference count on all the pages in @pages. If it
+ * fell to zero, remove the page from the LRU and free it.
*/
-void release_pages(struct page **pages, int nr, int cold)
+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);
+ unsigned int uninitialized_var(lock_batch);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
continue;
}
+ /*
+ * Make sure the IRQ-safe lock-holding time does not get
+ * excessive with a continuous string of pages from the
+ * same zone. The lock is held only if zone != NULL.
+ */
+ if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
+ zone = NULL;
+ }
+
if (!put_page_testzero(page))
continue;
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
+ lock_batch = 0;
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
- VM_BUG_ON(!PageLRU(page));
+ VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(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_list(&pages_to_free);
free_hot_cold_page_list(&pages_to_free, cold);
}
EXPORT_SYMBOL(release_pages);
void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *list)
{
- int uninitialized_var(active);
- enum lru_list lru;
const int file = 0;
- VM_BUG_ON(!PageHead(page));
- VM_BUG_ON(PageCompound(page_tail));
- VM_BUG_ON(PageLRU(page_tail));
+ 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 (page_evictable(page_tail)) {
- if (PageActive(page)) {
- SetPageActive(page_tail);
- active = 1;
- lru = LRU_ACTIVE_ANON;
- } else {
- active = 0;
- lru = LRU_INACTIVE_ANON;
- }
- } else {
- SetPageUnevictable(page_tail);
- lru = LRU_UNEVICTABLE;
- }
-
if (likely(PageLRU(page)))
list_add_tail(&page_tail->lru, &page->lru);
else if (list) {
* 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, lru);
+ 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, active);
+ 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)
{
- enum lru_list lru = (enum lru_list)arg;
- int file = is_file_lru(lru);
- int active = is_active_lru(lru);
+ int file = page_is_file_cache(page);
+ int active = PageActive(page);
+ enum lru_list lru = page_lru(page);
- VM_BUG_ON(PageActive(page));
- VM_BUG_ON(PageUnevictable(page));
- VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON_PAGE(PageLRU(page), page);
SetPageLRU(page);
- if (active)
- SetPageActive(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, enum lru_list lru)
+void __pagevec_lru_add(struct pagevec *pvec)
{
- VM_BUG_ON(is_unevictable_lru(lru));
-
- pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, (void *)lru);
+ 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
#ifdef CONFIG_SWAP
int i;
- bdi_init(swapper_spaces[0].backing_dev_info);
- for (i = 0; i < MAX_SWAPFILES; i++) {
+ 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 */