1 files changed, 83 insertions, 125 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 16a525296960..2cca7141470c 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -79,16 +79,14 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
 static void __page_cache_release(struct page *page)
 {
 	if (PageLRU(page)) {
-		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 		unsigned long flags;
 
-		spin_lock_irqsave(&pgdat->lru_lock, flags);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		lruvec = lock_page_lruvec_irqsave(page, &flags);
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 		__ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	}
 	__ClearPageWaiters(page);
 }
@@ -204,63 +202,46 @@ int get_kernel_page(unsigned long start, int write, struct page **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)
+	void (*move_fn)(struct page *page, struct lruvec *lruvec))
 {
 	int i;
-	struct pglist_data *pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
 
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			pgdat = pagepgdat;
-			spin_lock_irqsave(&pgdat->lru_lock, flags);
-		}
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
+			continue;
 
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-		(*move_fn)(page, lruvec, arg);
+		lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
+		(*move_fn)(page, lruvec);
+
+		SetPageLRU(page);
 	}
-	if (pgdat)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	release_pages(pvec->pages, pvec->nr);
 	pagevec_reinit(pvec);
 }
 
-static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec,
-				 void *arg)
+static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
 {
-	int *pgmoved = arg;
-
-	if (PageLRU(page) && !PageUnevictable(page)) {
+	if (!PageUnevictable(page)) {
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		ClearPageActive(page);
 		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
-		(*pgmoved) += thp_nr_pages(page);
+		__count_vm_events(PGROTATED, thp_nr_pages(page));
 	}
 }
 
 /*
- * 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.
+ *
+ * rotate_reclaimable_page() must disable IRQs, to prevent nasty races.
  */
 void rotate_reclaimable_page(struct page *page)
 {
@@ -273,7 +254,7 @@ void rotate_reclaimable_page(struct page *page)
 		local_lock_irqsave(&lru_rotate.lock, flags);
 		pvec = this_cpu_ptr(&lru_rotate.pvec);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_move_tail(pvec);
+			pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 }
@@ -283,6 +264,14 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 	do {
 		unsigned long lrusize;
 
+		/*
+		 * Hold lruvec->lru_lock is safe here, since
+		 * 1) The pinned lruvec in reclaim, or
+		 * 2) From a pre-LRU page during refault (which also holds the
+		 *    rcu lock, so would be safe even if the page was on the LRU
+		 *    and could move simultaneously to a new lruvec).
+		 */
+		spin_lock_irq(&lruvec->lru_lock);
 		/* Record cost event */
 		if (file)
 			lruvec->file_cost += nr_pages;
@@ -306,6 +295,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 			lruvec->file_cost /= 2;
 			lruvec->anon_cost /= 2;
 		}
+		spin_unlock_irq(&lruvec->lru_lock);
 	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
@@ -315,10 +305,9 @@ void lru_note_cost_page(struct page *page)
 		      page_is_file_lru(page), thp_nr_pages(page));
 }
 
-static void __activate_page(struct page *page, struct lruvec *lruvec,
-			    void *arg)
+static void __activate_page(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+	if (!PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
@@ -340,7 +329,7 @@ static void activate_page_drain(int cpu)
 	struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
 
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, __activate_page, NULL);
+		pagevec_lru_move_fn(pvec, __activate_page);
 }
 
 static bool need_activate_page_drain(int cpu)
@@ -358,7 +347,7 @@ static void activate_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.activate_page);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, __activate_page, NULL);
+			pagevec_lru_move_fn(pvec, __activate_page);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -370,12 +359,15 @@ static inline void activate_page_drain(int cpu)
 
 static void activate_page(struct page *page)
 {
-	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
 
 	page = compound_head(page);
-	spin_lock_irq(&pgdat->lru_lock);
-	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL);
-	spin_unlock_irq(&pgdat->lru_lock);
+	if (TestClearPageLRU(page)) {
+		lruvec = lock_page_lruvec_irq(page);
+		__activate_page(page, lruvec);
+		unlock_page_lruvec_irq(lruvec);
+		SetPageLRU(page);
+	}
 }
 #endif
 
@@ -525,16 +517,12 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
  * be write it out by flusher threads as this is much more effective
  * than the single-page writeout from reclaim.
  */
-static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
-			      void *arg)
+static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 {
 	int lru;
 	bool active;
 	int nr_pages = thp_nr_pages(page);
 
-	if (!PageLRU(page))
-		return;
-
 	if (PageUnevictable(page))
 		return;
 
@@ -573,10 +561,9 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
 	}
 }
 
-static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
-			    void *arg)
+static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+	if (PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
@@ -591,10 +578,9 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
 	}
 }
 
-static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
-			    void *arg)
+static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
+	if (PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
 		int nr_pages = thp_nr_pages(page);
@@ -636,21 +622,21 @@ void lru_add_drain_cpu(int cpu)
 
 		/* No harm done if a racing interrupt already did this */
 		local_lock_irqsave(&lru_rotate.lock, flags);
-		pagevec_move_tail(pvec);
+		pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
+		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+		pagevec_lru_move_fn(pvec, lru_deactivate_fn);
 
 	pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
+		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
 
 	activate_page_drain(cpu);
 }
@@ -679,7 +665,7 @@ void deactivate_file_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
 
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
+			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -701,7 +687,7 @@ void deactivate_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+			pagevec_lru_move_fn(pvec, lru_deactivate_fn);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -723,7 +709,7 @@ void mark_page_lazyfree(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
+			pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -871,8 +857,7 @@ void release_pages(struct page **pages, int nr)
 {
 	int i;
 	LIST_HEAD(pages_to_free);
-	struct pglist_data *locked_pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags;
 	unsigned int lock_batch;
 
@@ -882,11 +867,11 @@ void release_pages(struct page **pages, int nr)
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get
 		 * excessive with a continuous string of pages from the
-		 * same pgdat. The lock is held only if pgdat != NULL.
+		 * same lruvec. The lock is held only if lruvec != NULL.
 		 */
-		if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) {
-			spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
-			locked_pgdat = NULL;
+		if (lruvec && ++lock_batch == SWAP_CLUSTER_MAX) {
+			unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = NULL;
 		}
 
 		page = compound_head(page);
@@ -894,10 +879,9 @@ void release_pages(struct page **pages, int nr)
 			continue;
 
 		if (is_zone_device_page(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock,
-						       flags);
-				locked_pgdat = NULL;
+			if (lruvec) {
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+				lruvec = NULL;
 			}
 			/*
 			 * ZONE_DEVICE pages that return 'false' from
@@ -918,27 +902,22 @@ void release_pages(struct page **pages, int nr)
 			continue;
 
 		if (PageCompound(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
-				locked_pgdat = NULL;
+			if (lruvec) {
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+				lruvec = NULL;
 			}
 			__put_compound_page(page);
 			continue;
 		}
 
 		if (PageLRU(page)) {
-			struct pglist_data *pgdat = page_pgdat(page);
+			struct lruvec *prev_lruvec = lruvec;
 
-			if (pgdat != locked_pgdat) {
-				if (locked_pgdat)
-					spin_unlock_irqrestore(&locked_pgdat->lru_lock,
-									flags);
+			lruvec = relock_page_lruvec_irqsave(page, lruvec,
+									&flags);
+			if (prev_lruvec != lruvec)
 				lock_batch = 0;
-				locked_pgdat = pgdat;
-				spin_lock_irqsave(&locked_pgdat->lru_lock, flags);
-			}
 
-			lruvec = mem_cgroup_page_lruvec(page, locked_pgdat);
 			VM_BUG_ON_PAGE(!PageLRU(page), page);
 			__ClearPageLRU(page);
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
@@ -948,8 +927,8 @@ void release_pages(struct page **pages, int nr)
 
 		list_add(&page->lru, &pages_to_free);
 	}
-	if (locked_pgdat)
-		spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 
 	mem_cgroup_uncharge_list(&pages_to_free);
 	free_unref_page_list(&pages_to_free);
@@ -977,41 +956,7 @@ void __pagevec_release(struct pagevec *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)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
-	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
-	lockdep_assert_held(&lruvec_pgdat(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 {
-		/*
-		 * Head page has not yet been counted, as an hpage,
-		 * so we must account for each subpage individually.
-		 *
-		 * Put page_tail on the list at the correct position
-		 * so they all end up in order.
-		 */
-		add_page_to_lru_list_tail(page_tail, lruvec,
-					  page_lru(page_tail));
-	}
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
-static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
-				 void *arg)
+static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 {
 	enum lru_list lru;
 	int was_unevictable = TestClearPageUnevictable(page);
@@ -1070,7 +1015,20 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
  */
 void __pagevec_lru_add(struct pagevec *pvec)
 {
-	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL);
+	int i;
+	struct lruvec *lruvec = NULL;
+	unsigned long flags = 0;
+
+	for (i = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+
+		lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
+		__pagevec_lru_add_fn(page, lruvec);
+	}
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
+	release_pages(pvec->pages, pvec->nr);
+	pagevec_reinit(pvec);
 }
 
 /**