#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm_inline.h>
#include <linux/buffer_head.h> /* for try_to_release_page() */
#include <linux/percpu_counter.h>
static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
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
{
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
- struct page *page_head = page->first_page;
- smp_rmb();
- /*
- * If PageTail is still set after smp_rmb() we can be sure
- * that the page->first_page we read wasn't a dangling pointer.
- * See __split_huge_page_refcount() smp_wmb().
- */
- if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+ struct page *page_head = compound_trans_head(page);
+
+ if (likely(page != page_head &&
+ get_page_unless_zero(page_head))) {
unsigned long flags;
/*
- * Verify that our page_head wasn't converted
- * to a a regular page before we got a
- * reference on it.
- */
- if (unlikely(!PageHead(page_head))) {
- /* PageHead is cleared after PageTail */
- smp_rmb();
- VM_BUG_ON(PageTail(page));
- goto out_put_head;
- }
- /*
- * Only run compound_lock on a valid PageHead,
- * after having it pinned with
- * get_page_unless_zero() above.
+ * 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.
*/
- smp_mb();
- /* page_head wasn't a dangling pointer */
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
VM_BUG_ON(PageHead(page_head));
- out_put_head:
if (put_page_testzero(page_head))
__put_single_page(page_head);
out_put_single:
VM_BUG_ON(page_head != page->first_page);
/*
* We can release the refcount taken by
- * get_page_unless_zero now that
- * split_huge_page_refcount is blocked on the
- * compound_lock.
+ * 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(1);
/* __split_huge_page_refcount will wait now */
- VM_BUG_ON(atomic_read(&page->_count) <= 0);
- atomic_dec(&page->_count);
+ 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);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
}
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 = false;
+ struct page *page_head = compound_trans_head(page);
+
+ 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
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
- release_pages(pvec->pages, pagevec_count(pvec), pvec->cold);
+ release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
struct zone *zone = page_zone(page);
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
- int lru = page_lru_base_type(page);
+ enum lru_list lru = page_lru_base_type(page);
list_move_tail(&page->lru, &zone->lru[lru].list);
+ mem_cgroup_rotate_reclaimable_page(page);
(*pgmoved)++;
}
}
memcg_reclaim_stat->recent_rotated[file]++;
}
-/*
- * A page will go to active list either by activate_page or putback_lru_page.
- * In the activate_page case, the page hasn't active bit set. The page might
- * not in LRU list because it's isolated before it gets a chance to be moved to
- * active list. The window is small because pagevec just stores several pages.
- * For such case, we do nothing for such page.
- * In the putback_lru_page case, the page isn't in lru list but has active
- * bit set
- */
static void __activate_page(struct page *page, void *arg)
{
struct zone *zone = page_zone(page);
- int file = page_is_file_cache(page);
- int lru = page_lru_base_type(page);
- bool putback = !PageLRU(page);
- /* The page is isolated before it's moved to active list */
- if (!PageLRU(page) && !PageActive(page))
- return;
- if ((PageLRU(page) && PageActive(page)) || PageUnevictable(page))
- return;
-
- if (!putback)
+ 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(zone, page, lru);
- else
- SetPageLRU(page);
- SetPageActive(page);
- lru += LRU_ACTIVE;
- add_page_to_lru_list(zone, page, lru);
+ SetPageActive(page);
+ lru += LRU_ACTIVE;
+ add_page_to_lru_list(zone, page, lru);
+ __count_vm_event(PGACTIVATE);
- if (putback)
- return;
- __count_vm_event(PGACTIVATE);
- update_page_reclaim_stat(zone, page, file, 1);
+ update_page_reclaim_stat(zone, page, file, 1);
+ }
}
#ifdef CONFIG_SMP
}
}
-/* Caller should hold zone->lru_lock */
-int putback_active_lru_page(struct zone *zone, struct page *page)
-{
- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
-
- if (!pagevec_add(pvec, page)) {
- spin_unlock_irq(&zone->lru_lock);
- pagevec_lru_move_fn(pvec, __activate_page, NULL);
- spin_lock_irq(&zone->lru_lock);
- }
- put_cpu_var(activate_page_pvecs);
- return 1;
-}
-
#else
static inline void activate_page_drain(int cpu)
{
struct zone *zone = page_zone(page);
spin_lock_irq(&zone->lru_lock);
- if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page))
- __activate_page(page, NULL);
+ __activate_page(page, NULL);
spin_unlock_irq(&zone->lru_lock);
}
#endif
}
/*
+ * 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, void *arg)
+{
+ int lru, file;
+ bool active;
+ struct zone *zone = page_zone(page);
+
+ 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(zone, page, lru + active);
+ ClearPageActive(page);
+ ClearPageReferenced(page);
+ add_page_to_lru_list(zone, page, 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, &zone->lru[lru].list);
+ mem_cgroup_rotate_reclaimable_page(page);
+ __count_vm_event(PGROTATED);
+ }
+
+ if (active)
+ __count_vm_event(PGDEACTIVATE);
+ update_page_reclaim_stat(zone, page, 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.
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)
{
drain_cpu_pagevecs(get_cpu());
VM_BUG_ON(!PageHead(page));
VM_BUG_ON(PageCompound(page_tail));
VM_BUG_ON(PageLRU(page_tail));
- VM_BUG_ON(!spin_is_locked(&zone->lru_lock));
+ VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&zone->lru_lock));
SetPageLRU(page_tail);