1 files changed, 117 insertions, 38 deletions

diff --git a/mm/truncate.c b/mm/truncate.c
index 7c304d2f0052..12467c1bd711 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -46,7 +46,7 @@ static void clear_shadow_entries(struct address_space *mapping,
 
 	xas_unlock_irq(&xas);
 	if (mapping_shrinkable(mapping))
-		inode_add_lru(mapping->host);
+		inode_lru_list_add(mapping->host);
 	spin_unlock(&mapping->host->i_lock);
 }
 
@@ -78,8 +78,22 @@ static void truncate_folio_batch_exceptionals(struct address_space *mapping,
 
 	if (dax_mapping(mapping)) {
 		for (i = j; i < nr; i++) {
-			if (xa_is_value(fbatch->folios[i]))
+			if (xa_is_value(fbatch->folios[i])) {
+				/*
+				 * File systems should already have called
+				 * dax_break_layout_entry() to remove all DAX
+				 * entries while holding a lock to prevent
+				 * establishing new entries. Therefore we
+				 * shouldn't find any here.
+				 */
+				WARN_ON_ONCE(1);
+
+				/*
+				 * Delete the mapping so truncate_pagecache()
+				 * doesn't loop forever.
+				 */
 				dax_delete_mapping_entry(mapping, indices[i]);
+			}
 		}
 		goto out;
 	}
@@ -97,7 +111,7 @@ static void truncate_folio_batch_exceptionals(struct address_space *mapping,
 
 	xas_unlock_irq(&xas);
 	if (mapping_shrinkable(mapping))
-		inode_add_lru(mapping->host);
+		inode_lru_list_add(mapping->host);
 	spin_unlock(&mapping->host->i_lock);
 out:
 	folio_batch_remove_exceptionals(fbatch);
@@ -163,6 +177,32 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
 	return 0;
 }
 
+static int try_folio_split_or_unmap(struct folio *folio, struct page *split_at,
+				    unsigned long min_order)
+{
+	enum ttu_flags ttu_flags =
+		TTU_SYNC |
+		TTU_SPLIT_HUGE_PMD |
+		TTU_IGNORE_MLOCK;
+	int ret;
+
+	ret = try_folio_split_to_order(folio, split_at, min_order);
+
+	/*
+	 * If the split fails, unmap the folio, so it will be refaulted
+	 * with PTEs to respect SIGBUS semantics.
+	 *
+	 * Make an exception for shmem/tmpfs that for long time
+	 * intentionally mapped with PMDs across i_size.
+	 */
+	if (ret && !shmem_mapping(folio->mapping)) {
+		try_to_unmap(folio, ttu_flags);
+		WARN_ON(folio_mapped(folio));
+	}
+
+	return ret;
+}
+
 /*
  * Handle partial folios.  The folio may be entirely within the
  * range if a split has raced with us.  If not, we zero the part of the
@@ -177,20 +217,22 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
 bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 {
 	loff_t pos = folio_pos(folio);
+	size_t size = folio_size(folio);
 	unsigned int offset, length;
+	struct page *split_at, *split_at2;
+	unsigned int min_order;
 
 	if (pos < start)
 		offset = start - pos;
 	else
 		offset = 0;
-	length = folio_size(folio);
-	if (pos + length <= (u64)end)
-		length = length - offset;
+	if (pos + size <= (u64)end)
+		length = size - offset;
 	else
 		length = end + 1 - pos - offset;
 
 	folio_wait_writeback(folio);
-	if (length == folio_size(folio)) {
+	if (length == size) {
 		truncate_inode_folio(folio->mapping, folio);
 		return true;
 	}
@@ -207,8 +249,44 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 		folio_invalidate(folio, offset, length);
 	if (!folio_test_large(folio))
 		return true;
-	if (split_folio(folio) == 0)
+
+	min_order = mapping_min_folio_order(folio->mapping);
+	split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE);
+	if (!try_folio_split_or_unmap(folio, split_at, min_order)) {
+		/*
+		 * try to split at offset + length to make sure folios within
+		 * the range can be dropped, especially to avoid memory waste
+		 * for shmem truncate
+		 */
+		struct folio *folio2;
+
+		if (offset + length == size)
+			goto no_split;
+
+		split_at2 = folio_page(folio,
+				PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE);
+		folio2 = page_folio(split_at2);
+
+		if (!folio_try_get(folio2))
+			goto no_split;
+
+		if (!folio_test_large(folio2))
+			goto out;
+
+		if (!folio_trylock(folio2))
+			goto out;
+
+		/* make sure folio2 is large and does not change its mapping */
+		if (folio_test_large(folio2) &&
+		    folio2->mapping == folio->mapping)
+			try_folio_split_or_unmap(folio2, split_at2, min_order);
+
+		folio_unlock(folio2);
+out:
+		folio_put(folio2);
+no_split:
 		return true;
+	}
 	if (folio_test_dirty(folio))
 		return false;
 	truncate_inode_folio(folio->mapping, folio);
@@ -286,7 +364,7 @@ long mapping_evict_folio(struct address_space *mapping, struct folio *folio)
  * page aligned properly.
  */
 void truncate_inode_pages_range(struct address_space *mapping,
-				loff_t lstart, loff_t lend)
+				loff_t lstart, uoff_t lend)
 {
 	pgoff_t		start;		/* inclusive */
 	pgoff_t		end;		/* exclusive */
@@ -334,7 +412,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
 	folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0);
 	if (!IS_ERR(folio)) {
-		same_folio = lend < folio_pos(folio) + folio_size(folio);
+		same_folio = lend < folio_next_pos(folio);
 		if (!truncate_inode_partial_folio(folio, lstart, lend)) {
 			start = folio_next_index(folio);
 			if (same_folio)
@@ -372,7 +450,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		for (i = 0; i < folio_batch_count(&fbatch); i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			/* We rely upon deletion not changing page->index */
+			/* We rely upon deletion not changing folio->index */
 
 			if (xa_is_value(folio))
 				continue;
@@ -525,6 +603,15 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 }
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
+static int folio_launder(struct address_space *mapping, struct folio *folio)
+{
+	if (!folio_test_dirty(folio))
+		return 0;
+	if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
+		return 0;
+	return mapping->a_ops->launder_folio(folio);
+}
+
 /*
  * This is like mapping_evict_folio(), except it ignores the folio's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
@@ -532,14 +619,24 @@ EXPORT_SYMBOL(invalidate_mapping_pages);
  * shrink_folio_list() has a temp ref on them, or because they're transiently
  * sitting in the folio_add_lru() caches.
  */
-static int invalidate_complete_folio2(struct address_space *mapping,
-					struct folio *folio)
+int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
+			   gfp_t gfp)
 {
-	if (folio->mapping != mapping)
-		return 0;
+	int ret;
 
-	if (!filemap_release_folio(folio, GFP_KERNEL))
-		return 0;
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+
+	if (folio_mapped(folio))
+		unmap_mapping_folio(folio);
+	BUG_ON(folio_mapped(folio));
+
+	ret = folio_launder(mapping, folio);
+	if (ret)
+		return ret;
+	if (folio->mapping != mapping)
+		return -EBUSY;
+	if (!filemap_release_folio(folio, gfp))
+		return -EBUSY;
 
 	spin_lock(&mapping->host->i_lock);
 	xa_lock_irq(&mapping->i_pages);
@@ -550,7 +647,7 @@ static int invalidate_complete_folio2(struct address_space *mapping,
 	__filemap_remove_folio(folio, NULL);
 	xa_unlock_irq(&mapping->i_pages);
 	if (mapping_shrinkable(mapping))
-		inode_add_lru(mapping->host);
+		inode_lru_list_add(mapping->host);
 	spin_unlock(&mapping->host->i_lock);
 
 	filemap_free_folio(mapping, folio);
@@ -558,16 +655,7 @@ static int invalidate_complete_folio2(struct address_space *mapping,
 failed:
 	xa_unlock_irq(&mapping->i_pages);
 	spin_unlock(&mapping->host->i_lock);
-	return 0;
-}
-
-static int folio_launder(struct address_space *mapping, struct folio *folio)
-{
-	if (!folio_test_dirty(folio))
-		return 0;
-	if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
-		return 0;
-	return mapping->a_ops->launder_folio(folio);
+	return -EBUSY;
 }
 
 /**
@@ -631,16 +719,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			}
 			VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio);
 			folio_wait_writeback(folio);
-
-			if (folio_mapped(folio))
-				unmap_mapping_folio(folio);
-			BUG_ON(folio_mapped(folio));
-
-			ret2 = folio_launder(mapping, folio);
-			if (ret2 == 0) {
-				if (!invalidate_complete_folio2(mapping, folio))
-					ret2 = -EBUSY;
-			}
+			ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL);
 			if (ret2 < 0)
 				ret = ret2;
 			folio_unlock(folio);