[PATCH 02/25] mm/fbatch: allow folios_put_refs() to skip xa_is_value() entries

[Hugh Dickins <hughd@google.com>]

Let folios_put_refs() (hence folio_batch_release()) skip xa_is_value()
entries, and therefore remove unneeded folio_batch_remove_exceptionals().

It made some sense when introduced in 3.1 for shmem swap entries only,
but workingset shadows popularized exceptional entries in 3.15, and it's
silly for so many sites to be squashing exceptionals out of the fbatch,
merely to suit an inadequacy in folios_put_refs().

But remove exceptionals on leaving truncate_folio_batch_exceptionals(),
one of whose callers then passes the fbatch on to others less tolerant.

No longer essential to this series, since 7.2 commit 9669b87065a6
("mm/lruvec: preemptively free dead folios during lru_add drain")
allowed folios_put_refs() to skip NULLs; but still an improvement.

Signed-off-by: Hugh Dickins <hughd@google.com>
---
 include/linux/folio_batch.h |  5 +----
 mm/folio.c                  | 25 ++++---------------------
 mm/shmem.c                  |  2 --
 mm/truncate.c               | 16 ++++++++++------
 4 files changed, 15 insertions(+), 33 deletions(-)

diff --git a/include/linux/folio_batch.h b/include/linux/folio_batch.h
index b45946adc50b..e1cc8ae023f1 100644
--- a/include/linux/folio_batch.h
+++ b/include/linux/folio_batch.h
@@ -22,8 +22,7 @@ struct folio;
  * The folio_batch is used to amortise the cost of retrieving and
  * operating on a set of folios.  The order of folios in the batch may be
  * significant (eg delete_from_page_cache_batch()).  Some users of the
- * folio_batch store "exceptional" entries in it which can be removed
- * by calling folio_batch_remove_exceptionals().
+ * folio_batch store "exceptional" (xa_is_value) entries in it too.
  */
 struct folio_batch {
 	unsigned char nr;
@@ -100,6 +99,4 @@ static inline void folio_batch_release(struct folio_batch *fbatch)
 	if (folio_batch_count(fbatch))
 		__folio_batch_release(fbatch);
 }
-
-void folio_batch_remove_exceptionals(struct folio_batch *fbatch);
 #endif /* _LINUX_FOLIO_BATCH_H */
diff --git a/mm/folio.c b/mm/folio.c
index 62b96c9ce19e..b2bce6b77498 100644
--- a/mm/folio.c
+++ b/mm/folio.c
@@ -983,6 +983,10 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs)
 		if (!folio)
 			continue;
 
+		/* Skip any "exceptional" (workingset or shmem swap) entry. */
+		if (xa_is_value(folio))
+			continue;
+
 		if (is_huge_zero_folio(folio))
 			continue;
 
@@ -1088,27 +1092,6 @@ void __folio_batch_release(struct folio_batch *fbatch)
 }
 EXPORT_SYMBOL(__folio_batch_release);
 
-/**
- * folio_batch_remove_exceptionals() - Prune non-folios from a batch.
- * @fbatch: The batch to prune
- *
- * find_get_entries() fills a batch with both folios and shadow/swap/DAX
- * entries.  This function prunes all the non-folio entries from @fbatch
- * without leaving holes, so that it can be passed on to folio-only batch
- * operations.
- */
-void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
-{
-	unsigned int i, j;
-
-	for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) {
-		struct folio *folio = fbatch->folios[i];
-		if (!xa_is_value(folio))
-			fbatch->folios[j++] = folio;
-	}
-	fbatch->nr = j;
-}
-
 #ifdef CONFIG_MEMCG
 static void lruvec_reparent_lru(struct lruvec *child_lruvec,
 				struct lruvec *parent_lruvec,
diff --git a/mm/shmem.c b/mm/shmem.c
index 89a1495e55f7..3911721e1e55 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1156,7 +1156,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, uoff_t lend,
 				truncate_inode_folio(mapping, folio);
 			folio_unlock(folio);
 		}
-		folio_batch_remove_exceptionals(&fbatch);
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
@@ -1276,7 +1275,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, uoff_t lend,
 			}
 			folio_unlock(folio);
 		}
-		folio_batch_remove_exceptionals(&fbatch);
 		folio_batch_release(&fbatch);
 	}
 
diff --git a/mm/truncate.c b/mm/truncate.c
index b58ba940be47..4151f7a167e3 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -53,7 +53,7 @@ static void clear_shadow_entries(struct address_space *mapping,
 /*
  * Unconditionally remove exceptional entries. Usually called from truncate
  * path. Note that the folio_batch may be altered by this function by removing
- * exceptional entries similar to what folio_batch_remove_exceptionals() does.
+ * exceptional entries.
  * Please note that indices[] has entries in ascending order as guaranteed by
  * either find_get_entries() or find_lock_entries().
  */
@@ -95,7 +95,7 @@ static void truncate_folio_batch_exceptionals(struct address_space *mapping,
 				dax_delete_mapping_entry(mapping, indices[i]);
 			}
 		}
-		goto out;
+		goto squash;
 	}
 
 	xas_set(&xas, indices[j]);
@@ -113,8 +113,14 @@ static void truncate_folio_batch_exceptionals(struct address_space *mapping,
 	if (mapping_shrinkable(mapping))
 		inode_lru_list_add(mapping->host);
 	spin_unlock(&mapping->host->i_lock);
-out:
-	folio_batch_remove_exceptionals(fbatch);
+
+squash:
+	for (i = j + 1; i < nr; i++) {
+		folio = fbatch->folios[i];
+		if (!xa_is_value(folio))
+			fbatch->folios[j++] = folio;
+	}
+	fbatch->nr = j;
 }
 
 /**
@@ -575,7 +581,6 @@ unsigned long mapping_try_invalidate(struct address_space *mapping,
 		if (xa_has_values)
 			clear_shadow_entries(mapping, indices[0], indices[nr-1]);
 
-		folio_batch_remove_exceptionals(&fbatch);
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
@@ -732,7 +737,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		if (xa_has_values)
 			clear_shadow_entries(mapping, indices[0], indices[nr-1]);
 
-		folio_batch_remove_exceptionals(&fbatch);
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
-- 
2.51.0