Merge tag 'folio-5.18c' of git://git.infradead.org/users/willy/pagecache

Pull folio updates from Matthew Wilcox:

 - Rewrite how munlock works to massively reduce the contention on
   i_mmap_rwsem (Hugh Dickins):

     https://lore.kernel.org/linux-mm/8e4356d-9622-a7f0-b2c-f116b5f2efea@google.com/

 - Sort out the page refcount mess for ZONE_DEVICE pages (Christoph
   Hellwig):

     https://lore.kernel.org/linux-mm/20220210072828.2930359-1-hch@lst.de/

 - Convert GUP to use folios and make pincount available for order-1
   pages. (Matthew Wilcox)

 - Convert a few more truncation functions to use folios (Matthew
   Wilcox)

 - Convert page_vma_mapped_walk to use PFNs instead of pages (Matthew
   Wilcox)

 - Convert rmap_walk to use folios (Matthew Wilcox)

 - Convert most of shrink_page_list() to use a folio (Matthew Wilcox)

 - Add support for creating large folios in readahead (Matthew Wilcox)

* tag 'folio-5.18c' of git://git.infradead.org/users/willy/pagecache: (114 commits)
  mm/damon: minor cleanup for damon_pa_young
  selftests/vm/transhuge-stress: Support file-backed PMD folios
  mm/filemap: Support VM_HUGEPAGE for file mappings
  mm/readahead: Switch to page_cache_ra_order
  mm/readahead: Align file mappings for non-DAX
  mm/readahead: Add large folio readahead
  mm: Support arbitrary THP sizes
  mm: Make large folios depend on THP
  mm: Fix READ_ONLY_THP warning
  mm/filemap: Allow large folios to be added to the page cache
  mm: Turn can_split_huge_page() into can_split_folio()
  mm/vmscan: Convert pageout() to take a folio
  mm/vmscan: Turn page_check_references() into folio_check_references()
  mm/vmscan: Account large folios correctly
  mm/vmscan: Optimise shrink_page_list for non-PMD-sized folios
  mm/vmscan: Free non-shmem folios without splitting them
  mm/rmap: Constify the rmap_walk_control argument
  mm/rmap: Convert rmap_walk() to take a folio
  mm: Turn page_anon_vma() into folio_anon_vma()
  mm/rmap: Turn page_lock_anon_vma_read() into folio_lock_anon_vma_read()
  ...

1 files changed, 68 insertions, 105 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 754520bab299..5b30045207e1 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -74,8 +74,8 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
 };
 
 /*
- * This path almost never happens for VM activity - pages are normally
- * freed via pagevecs.  But it gets used by networking.
+ * This path almost never happens for VM activity - pages are normally freed
+ * via pagevecs.  But it gets used by networking - and for compound pages.
  */
 static void __page_cache_release(struct page *page)
 {
@@ -89,6 +89,14 @@ static void __page_cache_release(struct page *page)
 		__clear_page_lru_flags(page);
 		unlock_page_lruvec_irqrestore(lruvec, flags);
 	}
+	/* See comment on PageMlocked in release_pages() */
+	if (unlikely(PageMlocked(page))) {
+		int nr_pages = thp_nr_pages(page);
+
+		__ClearPageMlocked(page);
+		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
+		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
+	}
 	__ClearPageWaiters(page);
 }
 
@@ -114,17 +122,9 @@ static void __put_compound_page(struct page *page)
 
 void __put_page(struct page *page)
 {
-	if (is_zone_device_page(page)) {
-		put_dev_pagemap(page->pgmap);
-
-		/*
-		 * The page belongs to the device that created pgmap. Do
-		 * not return it to page allocator.
-		 */
-		return;
-	}
-
-	if (unlikely(PageCompound(page)))
+	if (unlikely(is_zone_device_page(page)))
+		free_zone_device_page(page);
+	else if (unlikely(PageCompound(page)))
 		__put_compound_page(page);
 	else
 		__put_single_page(page);
@@ -482,22 +482,12 @@ EXPORT_SYMBOL(folio_add_lru);
 void lru_cache_add_inactive_or_unevictable(struct page *page,
 					 struct vm_area_struct *vma)
 {
-	bool unevictable;
-
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
-	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
-		int nr_pages = thp_nr_pages(page);
-		/*
-		 * We use the irq-unsafe __mod_zone_page_state 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, nr_pages);
-		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
-	}
-	lru_cache_add(page);
+	if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED))
+		mlock_new_page(page);
+	else
+		lru_cache_add(page);
 }
 
 /*
@@ -636,35 +626,37 @@ void lru_add_drain_cpu(int cpu)
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
 
 	activate_page_drain(cpu);
+	mlock_page_drain(cpu);
 }
 
 /**
- * deactivate_file_page - forcefully deactivate a file page
- * @page: page to deactivate
+ * deactivate_file_folio() - Forcefully deactivate a file folio.
+ * @folio: Folio 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
+ * 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.
  */
-void deactivate_file_page(struct page *page)
+void deactivate_file_folio(struct folio *folio)
 {
+	struct pagevec *pvec;
+
 	/*
-	 * In a workload with many unevictable page such as mprotect,
-	 * unevictable page deactivation for accelerating reclaim is pointless.
+	 * In a workload with many unevictable pages such as mprotect,
+	 * unevictable folio deactivation for accelerating reclaim is pointless.
 	 */
-	if (PageUnevictable(page))
+	if (folio_test_unevictable(folio))
 		return;
 
-	if (likely(get_page_unless_zero(page))) {
-		struct pagevec *pvec;
-
-		local_lock(&lru_pvecs.lock);
-		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
+	folio_get(folio);
+	local_lock(&lru_pvecs.lock);
+	pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
 
-		if (pagevec_add_and_need_flush(pvec, page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
-		local_unlock(&lru_pvecs.lock);
-	}
+	if (pagevec_add_and_need_flush(pvec, &folio->page))
+		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
+	local_unlock(&lru_pvecs.lock);
 }
 
 /*
@@ -837,6 +829,7 @@ inline void __lru_add_drain_all(bool force_all_cpus)
 		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
 		    need_activate_page_drain(cpu) ||
+		    need_mlock_page_drain(cpu) ||
 		    has_bh_in_lru(cpu, NULL)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
@@ -935,18 +928,10 @@ void release_pages(struct page **pages, int nr)
 				unlock_page_lruvec_irqrestore(lruvec, flags);
 				lruvec = NULL;
 			}
-			/*
-			 * ZONE_DEVICE pages that return 'false' from
-			 * page_is_devmap_managed() do not require special
-			 * processing, and instead, expect a call to
-			 * put_page_testzero().
-			 */
-			if (page_is_devmap_managed(page)) {
-				put_devmap_managed_page(page);
+			if (put_devmap_managed_page(page))
 				continue;
-			}
 			if (put_page_testzero(page))
-				put_dev_pagemap(page->pgmap);
+				free_zone_device_page(page);
 			continue;
 		}
 
@@ -974,6 +959,18 @@ void release_pages(struct page **pages, int nr)
 			__clear_page_lru_flags(page);
 		}
 
+		/*
+		 * In rare cases, when truncation or holepunching raced with
+		 * munlock after VM_LOCKED was cleared, Mlocked may still be
+		 * found set here.  This does not indicate a problem, unless
+		 * "unevictable_pgs_cleared" appears worryingly large.
+		 */
+		if (unlikely(PageMlocked(page))) {
+			__ClearPageMlocked(page);
+			dec_zone_page_state(page, NR_MLOCK);
+			count_vm_event(UNEVICTABLE_PGCLEARED);
+		}
+
 		__ClearPageWaiters(page);
 
 		list_add(&page->lru, &pages_to_free);
@@ -1014,43 +1011,32 @@ static void __pagevec_lru_add_fn(struct folio *folio, struct lruvec *lruvec)
 
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
+	folio_set_lru(folio);
 	/*
-	 * A folio becomes evictable in two ways:
-	 * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()].
-	 * 2) Before acquiring LRU lock to put the folio on the correct LRU
-	 *    and then
-	 *   a) do PageLRU check with lock [check_move_unevictable_pages]
-	 *   b) do PageLRU check before lock [clear_page_mlock]
-	 *
-	 * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need
-	 * following strict ordering:
-	 *
-	 * #0: __pagevec_lru_add_fn		#1: clear_page_mlock
+	 * Is an smp_mb__after_atomic() still required here, before
+	 * folio_evictable() tests PageMlocked, to rule out the possibility
+	 * of stranding an evictable folio on an unevictable LRU?  I think
+	 * not, because __munlock_page() only clears PageMlocked while the LRU
+	 * lock is held.
 	 *
-	 * folio_set_lru()			folio_test_clear_mlocked()
-	 * smp_mb() // explicit ordering	// above provides strict
-	 *					// ordering
-	 * folio_test_mlocked()			folio_test_lru()
-	 *
-	 *
-	 * if '#1' does not observe setting of PG_lru by '#0' and
-	 * fails isolation, the explicit barrier will make sure that
-	 * folio_evictable check will put the folio on the correct
-	 * LRU. Without smp_mb(), folio_set_lru() can be reordered
-	 * after folio_test_mlocked() check and can make '#1' fail the
-	 * isolation of the folio whose mlocked bit is cleared (#0 is
-	 * also looking at the same folio) and the evictable folio will
-	 * be stranded on an unevictable LRU.
+	 * (That is not true of __page_cache_release(), and not necessarily
+	 * true of release_pages(): but those only clear PageMlocked after
+	 * put_page_testzero() has excluded any other users of the page.)
 	 */
-	folio_set_lru(folio);
-	smp_mb__after_atomic();
-
 	if (folio_evictable(folio)) {
 		if (was_unevictable)
 			__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
 	} else {
 		folio_clear_active(folio);
 		folio_set_unevictable(folio);
+		/*
+		 * folio->mlock_count = !!folio_test_mlocked(folio)?
+		 * But that leaves __mlock_page() in doubt whether another
+		 * actor has already counted the mlock or not.  Err on the
+		 * safe side, underestimate, let page reclaim fix it, rather
+		 * than leaving a page on the unevictable LRU indefinitely.
+		 */
+		folio->mlock_count = 0;
 		if (!was_unevictable)
 			__count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
 	}
@@ -1158,26 +1144,3 @@ void __init swap_setup(void)
 	 * _really_ don't want to cluster much more
 	 */
 }
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-void put_devmap_managed_page(struct page *page)
-{
-	int count;
-
-	if (WARN_ON_ONCE(!page_is_devmap_managed(page)))
-		return;
-
-	count = page_ref_dec_return(page);
-
-	/*
-	 * devmap page refcounts are 1-based, rather than 0-based: if
-	 * refcount is 1, then the page is free and the refcount is
-	 * stable because nobody holds a reference on the page.
-	 */
-	if (count == 1)
-		free_devmap_managed_page(page);
-	else if (!count)
-		__put_page(page);
-}
-EXPORT_SYMBOL(put_devmap_managed_page);
-#endif