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, 41 insertions, 18 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index bd788bbe41b0..1752ef1266f3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -842,26 +842,27 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 {
 	XA_STATE(xas, &mapping->i_pages, index);
 	int huge = folio_test_hugetlb(folio);
-	int error;
 	bool charged = false;
+	long nr = 1;
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
 	mapping_set_update(&xas, mapping);
 
-	folio_get(folio);
-	folio->mapping = mapping;
-	folio->index = index;
-
 	if (!huge) {
-		error = mem_cgroup_charge(folio, NULL, gfp);
+		int error = mem_cgroup_charge(folio, NULL, gfp);
 		VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
 		if (error)
-			goto error;
+			return error;
 		charged = true;
+		xas_set_order(&xas, index, folio_order(folio));
+		nr = folio_nr_pages(folio);
 	}
 
 	gfp &= GFP_RECLAIM_MASK;
+	folio_ref_add(folio, nr);
+	folio->mapping = mapping;
+	folio->index = xas.xa_index;
 
 	do {
 		unsigned int order = xa_get_order(xas.xa, xas.xa_index);
@@ -885,6 +886,8 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 			/* entry may have been split before we acquired lock */
 			order = xa_get_order(xas.xa, xas.xa_index);
 			if (order > folio_order(folio)) {
+				/* How to handle large swap entries? */
+				BUG_ON(shmem_mapping(mapping));
 				xas_split(&xas, old, order);
 				xas_reset(&xas);
 			}
@@ -894,29 +897,31 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 		if (xas_error(&xas))
 			goto unlock;
 
-		mapping->nrpages++;
+		mapping->nrpages += nr;
 
 		/* hugetlb pages do not participate in page cache accounting */
-		if (!huge)
-			__lruvec_stat_add_folio(folio, NR_FILE_PAGES);
+		if (!huge) {
+			__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
+			if (folio_test_pmd_mappable(folio))
+				__lruvec_stat_mod_folio(folio,
+						NR_FILE_THPS, nr);
+		}
 unlock:
 		xas_unlock_irq(&xas);
 	} while (xas_nomem(&xas, gfp));
 
-	if (xas_error(&xas)) {
-		error = xas_error(&xas);
-		if (charged)
-			mem_cgroup_uncharge(folio);
+	if (xas_error(&xas))
 		goto error;
-	}
 
 	trace_mm_filemap_add_to_page_cache(folio);
 	return 0;
 error:
+	if (charged)
+		mem_cgroup_uncharge(folio);
 	folio->mapping = NULL;
 	/* Leave page->index set: truncation relies upon it */
-	folio_put(folio);
-	return error;
+	folio_put_refs(folio, nr);
+	return xas_error(&xas);
 }
 ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
 
@@ -2997,6 +3002,24 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	struct file *fpin = NULL;
 	unsigned int mmap_miss;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/* Use the readahead code, even if readahead is disabled */
+	if (vmf->vma->vm_flags & VM_HUGEPAGE) {
+		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
+		ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
+		ra->size = HPAGE_PMD_NR;
+		/*
+		 * Fetch two PMD folios, so we get the chance to actually
+		 * readahead, unless we've been told not to.
+		 */
+		if (!(vmf->vma->vm_flags & VM_RAND_READ))
+			ra->size *= 2;
+		ra->async_size = HPAGE_PMD_NR;
+		page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER);
+		return fpin;
+	}
+#endif
+
 	/* If we don't want any read-ahead, don't bother */
 	if (vmf->vma->vm_flags & VM_RAND_READ)
 		return fpin;
@@ -3029,7 +3052,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	ra->size = ra->ra_pages;
 	ra->async_size = ra->ra_pages / 4;
 	ractl._index = ra->start;
-	do_page_cache_ra(&ractl, ra->size, ra->async_size);
+	page_cache_ra_order(&ractl, ra, 0);
 	return fpin;
 }