mm/swap: convert lru_deactivate_file to a folio_batch

Use a folio throughout lru_deactivate_file_fn(), removing many hidden
calls to compound_head().  Shrinks the kernel by 864 bytes of text.

Link: https://lkml.kernel.org/r/20220617175020.717127-6-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/swap.c

@@ -62,7 +62,7 @@ static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = {
 struct lru_pvecs {
 	local_lock_t lock;
 	struct folio_batch lru_add;
-	struct pagevec lru_deactivate_file;
+	struct folio_batch lru_deactivate_file;
 	struct pagevec lru_deactivate;
 	struct pagevec lru_lazyfree;
 #ifdef CONFIG_SMP
@@ -562,56 +562,57 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
 }
 
 /*
- * If the page can not be invalidated, it is moved to the
+ * If the folio cannot 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.
+ * If the folio isn't mapped and dirty/writeback, the folio
+ * could be reclaimed asap using the reclaim flag.
  *
- * 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
+ * 1. active, mapped folio -> none
+ * 2. active, dirty/writeback folio -> inactive, head, reclaim
+ * 3. inactive, mapped folio -> none
+ * 4. inactive, dirty/writeback folio -> inactive, head, 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
+ * In 4, it moves to the head of the inactive list so the folio is
+ * written out by flusher threads as this is much more efficient
  * than the single-page writeout from reclaim.
  */
-static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
+static void lru_deactivate_file_fn(struct lruvec *lruvec, struct folio *folio)
 {
-	bool active = PageActive(page);
-	int nr_pages = thp_nr_pages(page);
+	bool active = folio_test_active(folio);
+	long nr_pages = folio_nr_pages(folio);
 
-	if (PageUnevictable(page))
+	if (folio_test_unevictable(folio))
 		return;
 
-	/* Some processes are using the page */
-	if (page_mapped(page))
+	/* Some processes are using the folio */
+	if (folio_mapped(folio))
 		return;
 
-	del_page_from_lru_list(page, lruvec);
-	ClearPageActive(page);
-	ClearPageReferenced(page);
+	lruvec_del_folio(lruvec, folio);
+	folio_clear_active(folio);
+	folio_clear_referenced(folio);
 
-	if (PageWriteback(page) || PageDirty(page)) {
+	if (folio_test_writeback(folio) || folio_test_dirty(folio)) {
 		/*
-		 * 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.
+		 * Setting the reclaim flag could race with
+		 * folio_end_writeback() and confuse readahead.  But the
+		 * race window is _really_ small and  it's not a critical
+		 * problem.
 		 */
-		add_page_to_lru_list(page, lruvec);
-		SetPageReclaim(page);
+		lruvec_add_folio(lruvec, folio);
+		folio_set_reclaim(folio);
 	} else {
 		/*
-		 * The page's writeback ends up during pagevec
-		 * We move that page into tail of inactive.
+		 * The folio's writeback ended while it was in the batch.
+		 * We move that folio to the tail of the inactive list.
 		 */
-		add_page_to_lru_list_tail(page, lruvec);
+		lruvec_add_folio_tail(lruvec, folio);
 		__count_vm_events(PGROTATED, nr_pages);
 	}
 
@@ -685,9 +686,9 @@ void lru_add_drain_cpu(int cpu)
 		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);
+	fbatch = &per_cpu(lru_pvecs.lru_deactivate_file, cpu);
+	if (folio_batch_count(fbatch))
+		folio_batch_move_lru(fbatch, lru_deactivate_file_fn);
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu);
 	if (pagevec_count(pvec))
@@ -701,32 +702,27 @@ void lru_add_drain_cpu(int cpu)
 }
 
 /**
- * deactivate_file_folio() - Forcefully deactivate a file folio.
+ * deactivate_file_folio() - Deactivate a file folio.
  * @folio: Folio to deactivate.
  *
  * This function hints to the VM that @folio is a good reclaim candidate,
  * for example if its invalidation fails due to the folio being dirty
  * or under writeback.
  *
- * Context: Caller holds a reference on the page.
+ * Context: Caller holds a reference on the folio.
  */
 void deactivate_file_folio(struct folio *folio)
 {
-	struct pagevec *pvec;
+	struct folio_batch *fbatch;
 
-	/*
-	 * In a workload with many unevictable pages such as mprotect,
-	 * unevictable folio deactivation for accelerating reclaim is pointless.
-	 */
+	/* Deactivating an unevictable folio will not accelerate reclaim */
 	if (folio_test_unevictable(folio))
 		return;
 
 	folio_get(folio);
 	local_lock(&lru_pvecs.lock);
-	pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
-
-	if (pagevec_add_and_need_flush(pvec, &folio->page))
-		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
+	fbatch = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
+	folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn);
 	local_unlock(&lru_pvecs.lock);
 }
 
@@ -899,7 +895,7 @@ static inline void __lru_add_drain_all(bool force_all_cpus)
 
 		if (folio_batch_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
 		    data_race(folio_batch_count(&per_cpu(lru_rotate.fbatch, cpu))) ||
-		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
+		    folio_batch_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
 		    need_activate_page_drain(cpu) ||