[PATCH v13 134/137] mm/filemap: Allow multi-page folios to be added to the page cache

[Matthew Wilcox (Oracle)]

We return -EEXIST if there are any non-shadow entries in the page
cache in the range covered by the folio.  If there are multiple
shadow entries in the range, we set *shadowp to one of them (currently
the one at the highest index).  If that turns out to be the wrong
answer, we can implement something more complex.  This is mostly
modelled after the equivalent function in the shmem code.

Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
 mm/filemap.c | 40 +++++++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index c8fc0d07fa92..57dd01c5060c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -848,26 +848,27 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 {
 	XA_STATE(xas, &mapping->i_pages, index);
 	int huge = folio_hugetlb(folio);
-	int error;
 	bool charged = false;
+	unsigned int nr = 1;
 
 	VM_BUG_ON_FOLIO(!folio_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_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);
@@ -891,6 +892,8 @@ 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);
 			}
@@ -900,29 +903,32 @@ 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 (nr > 1)
+				__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->page);
 	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_ref_sub(folio, nr);
+	VM_BUG_ON_FOLIO(folio_ref_count(folio) <= 0, folio);
+	return xas_error(&xas);
 }
 ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
 
-- 
2.30.2