[PATCH v4 07/10] mm: shmem: support large folio allocation for shmem_replace_folio()

[Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>]

To support large folio swapin for shmem in the following patches, add
large folio allocation for the new replacement folio in shmem_replace_folio().
Moreover large folios occupy N consecutive entries in the swap cache
instead of using multi-index entries like the page cache, therefore
we should replace each consecutive entries in the swap cache instead
of using the shmem_replace_entry().

As well as updating statistics and folio reference count using the number
of pages in the folio.

Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
---
 mm/shmem.c | 54 +++++++++++++++++++++++++++++++-----------------------
 1 file changed, 31 insertions(+), 23 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index f6bab42180ea..d94f02ad7bd1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1889,28 +1889,24 @@ static bool shmem_should_replace_folio(struct folio *folio, gfp_t gfp)
 static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
 				struct shmem_inode_info *info, pgoff_t index)
 {
-	struct folio *old, *new;
-	struct address_space *swap_mapping;
-	swp_entry_t entry;
-	pgoff_t swap_index;
-	int error;
-
-	old = *foliop;
-	entry = old->swap;
-	swap_index = swap_cache_index(entry);
-	swap_mapping = swap_address_space(entry);
+	struct folio *new, *old = *foliop;
+	swp_entry_t entry = old->swap;
+	struct address_space *swap_mapping = swap_address_space(entry);
+	pgoff_t swap_index = swap_cache_index(entry);
+	XA_STATE(xas, &swap_mapping->i_pages, swap_index);
+	int nr_pages = folio_nr_pages(old);
+	int error = 0, i;
 
 	/*
 	 * We have arrived here because our zones are constrained, so don't
 	 * limit chance of success by further cpuset and node constraints.
 	 */
 	gfp &= ~GFP_CONSTRAINT_MASK;
-	VM_BUG_ON_FOLIO(folio_test_large(old), old);
-	new = shmem_alloc_folio(gfp, 0, info, index);
+	new = shmem_alloc_folio(gfp, folio_order(old), info, index);
 	if (!new)
 		return -ENOMEM;
 
-	folio_get(new);
+	folio_ref_add(new, nr_pages);
 	folio_copy(new, old);
 	flush_dcache_folio(new);
 
@@ -1920,18 +1916,25 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
 	new->swap = entry;
 	folio_set_swapcache(new);
 
-	/*
-	 * Our caller will very soon move newpage out of swapcache, but it's
-	 * a nice clean interface for us to replace oldpage by newpage there.
-	 */
+	/* Swap cache still stores N entries instead of a high-order entry */
 	xa_lock_irq(&swap_mapping->i_pages);
-	error = shmem_replace_entry(swap_mapping, swap_index, old, new);
+	for (i = 0; i < nr_pages; i++) {
+		void *item = xas_load(&xas);
+
+		if (item != old) {
+			error = -ENOENT;
+			break;
+		}
+
+		xas_store(&xas, new);
+		xas_next(&xas);
+	}
 	if (!error) {
 		mem_cgroup_replace_folio(old, new);
-		__lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1);
-		__lruvec_stat_mod_folio(new, NR_SHMEM, 1);
-		__lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1);
-		__lruvec_stat_mod_folio(old, NR_SHMEM, -1);
+		__lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages);
+		__lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages);
+		__lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages);
+		__lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages);
 	}
 	xa_unlock_irq(&swap_mapping->i_pages);
 
@@ -1951,7 +1954,12 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
 	old->private = NULL;
 
 	folio_unlock(old);
-	folio_put_refs(old, 2);
+	/*
+	 * The old folio are removed from swap cache, drop the 'nr_pages'
+	 * reference, as well as one temporary reference getting from swap
+	 * cache.
+	 */
+	folio_put_refs(old, nr_pages + 1);
 	return error;
 }
 
-- 
2.39.3