#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>
{
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.
+ * 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.
*/
- 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.
- */
- 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
}
EXPORT_SYMBOL(put_pages_list);
-/*
- * pagevec_move_tail() must be called with IRQ disabled.
- * Otherwise this may cause nasty races.
- */
-static void pagevec_move_tail(struct pagevec *pvec)
+static void pagevec_lru_move_fn(struct pagevec *pvec,
+ void (*move_fn)(struct page *page, void *arg),
+ void *arg)
{
int i;
- int pgmoved = 0;
struct zone *zone = NULL;
+ unsigned long flags = 0;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
if (pagezone != zone) {
if (zone)
- spin_unlock(&zone->lru_lock);
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = pagezone;
- spin_lock(&zone->lru_lock);
- }
- if (PageLRU(page) && !PageActive(page) && !PageUnevictable(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++;
+ spin_lock_irqsave(&zone->lru_lock, flags);
}
+
+ (*move_fn)(page, arg);
}
if (zone)
- spin_unlock(&zone->lru_lock);
- __count_vm_events(PGROTATED, pgmoved);
+ 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, void *arg)
+{
+ int *pgmoved = arg;
+ struct zone *zone = page_zone(page);
+
+ if (PageLRU(page) && !PageActive(page) && !PageUnevictable(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)++;
+ }
+}
+
+/*
+ * 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)
+void rotate_reclaimable_page(struct page *page)
{
if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
!PageUnevictable(page) && PageLRU(page)) {
memcg_reclaim_stat->recent_rotated[file]++;
}
-/*
- * FIXME: speed this up?
- */
-void activate_page(struct page *page)
+static void __activate_page(struct page *page, void *arg)
{
struct zone *zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
int file = page_is_file_cache(page);
int lru = page_lru_base_type(page);
update_page_reclaim_stat(zone, page, 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);
+}
+
+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)
+{
+}
+
+void activate_page(struct page *page)
+{
+ struct zone *zone = page_zone(page);
+
+ spin_lock_irq(&zone->lru_lock);
+ __activate_page(page, NULL);
spin_unlock_irq(&zone->lru_lock);
}
+#endif
/*
* Mark a page as having seen activity.
* 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(struct page *page, struct zone *zone)
+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 (!PageLRU(page) || !PageActive(page))
+ 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 + LRU_ACTIVE);
+ del_page_from_lru_list(zone, page, lru + active);
ClearPageActive(page);
ClearPageReferenced(page);
add_page_to_lru_list(zone, page, lru);
- __count_vm_event(PGDEACTIVATE);
- update_page_reclaim_stat(zone, page, file, 0);
-}
-
-static void ____pagevec_lru_deactivate(struct pagevec *pvec)
-{
- int i;
- struct zone *zone = NULL;
-
- 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_irq(&zone->lru_lock);
- zone = pagezone;
- spin_lock_irq(&zone->lru_lock);
- }
- lru_deactivate(page, zone);
+ 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 (zone)
- spin_unlock_irq(&zone->lru_lock);
- release_pages(pvec->pages, pvec->nr, pvec->cold);
- pagevec_reinit(pvec);
+ 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
pvec = &per_cpu(lru_deactivate_pvecs, cpu);
if (pagevec_count(pvec))
- ____pagevec_lru_deactivate(pvec);
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
+ activate_page_drain(cpu);
}
/**
*/
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_deactivate(pvec);
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
put_cpu_var(lru_deactivate_pvecs);
}
}
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);
}
}
+static void ____pagevec_lru_add_fn(struct page *page, void *arg)
+{
+ enum lru_list lru = (enum lru_list)arg;
+ struct zone *zone = page_zone(page);
+ int file = is_file_lru(lru);
+ int active = is_active_lru(lru);
+
+ VM_BUG_ON(PageActive(page));
+ VM_BUG_ON(PageUnevictable(page));
+ VM_BUG_ON(PageLRU(page));
+
+ SetPageLRU(page);
+ if (active)
+ SetPageActive(page);
+ update_page_reclaim_stat(zone, page, file, active);
+ add_page_to_lru_list(zone, 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)
{
- int i;
- struct zone *zone = NULL;
-
VM_BUG_ON(is_unevictable_lru(lru));
- for (i = 0; i < pagevec_count(pvec); i++) {
- struct page *page = pvec->pages[i];
- struct zone *pagezone = page_zone(page);
- int file;
- int active;
-
- if (pagezone != zone) {
- if (zone)
- spin_unlock_irq(&zone->lru_lock);
- zone = pagezone;
- spin_lock_irq(&zone->lru_lock);
- }
- VM_BUG_ON(PageActive(page));
- VM_BUG_ON(PageUnevictable(page));
- VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
- active = is_active_lru(lru);
- file = is_file_lru(lru);
- if (active)
- SetPageActive(page);
- update_page_reclaim_stat(zone, page, file, active);
- add_page_to_lru_list(zone, page, lru);
- }
- if (zone)
- spin_unlock_irq(&zone->lru_lock);
- release_pages(pvec->pages, pvec->nr, pvec->cold);
- pagevec_reinit(pvec);
+ pagevec_lru_move_fn(pvec, ____pagevec_lru_add_fn, (void *)lru);
}
EXPORT_SYMBOL(____pagevec_lru_add);