mm: Convert page-writeback to XArray

Includes moving mapping_tagged() to fs.h as a static inline, and
changing it to return bool.

Signed-off-by: Matthew Wilcox <willy@infradead.org>

2 files changed, 36 insertions, 53 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index d126cad0f621..e10278e4db66 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -483,15 +483,18 @@ struct block_device {
 	struct mutex		bd_fsfreeze_mutex;
 } __randomize_layout;
 
+/* XArray tags, for tagging dirty and writeback pages in the pagecache. */
+#define PAGECACHE_TAG_DIRTY	XA_MARK_0
+#define PAGECACHE_TAG_WRITEBACK	XA_MARK_1
+#define PAGECACHE_TAG_TOWRITE	XA_MARK_2
+
 /*
- * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
- * radix trees
+ * Returns true if any of the pages in the mapping are marked with the tag.
  */
-#define PAGECACHE_TAG_DIRTY	0
-#define PAGECACHE_TAG_WRITEBACK	1
-#define PAGECACHE_TAG_TOWRITE	2
-
-int mapping_tagged(struct address_space *mapping, int tag);
+static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
+{
+	return xa_marked(&mapping->i_pages, tag);
+}
 
 static inline void i_mmap_lock_write(struct address_space *mapping)
 {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 84ae9bf5858a..fc6e5743b0bf 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2097,34 +2097,25 @@ void __init page_writeback_init(void)
  * dirty pages in the file (thus it is important for this function to be quick
  * so that it can tag pages faster than a dirtying process can create them).
  */
-/*
- * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce the i_pages lock
- * latency.
- */
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end)
 {
-#define WRITEBACK_TAG_BATCH 4096
-	unsigned long tagged = 0;
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, start);
+	unsigned int tagged = 0;
+	void *page;
 
-	xa_lock_irq(&mapping->i_pages);
-	radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start,
-							PAGECACHE_TAG_DIRTY) {
-		if (iter.index > end)
-			break;
-		radix_tree_iter_tag_set(&mapping->i_pages, &iter,
-							PAGECACHE_TAG_TOWRITE);
-		tagged++;
-		if ((tagged % WRITEBACK_TAG_BATCH) != 0)
+	xas_lock_irq(&xas);
+	xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) {
+		xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE);
+		if (++tagged % XA_CHECK_SCHED)
 			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
-		xa_unlock_irq(&mapping->i_pages);
+
+		xas_pause(&xas);
+		xas_unlock_irq(&xas);
 		cond_resched();
-		xa_lock_irq(&mapping->i_pages);
+		xas_lock_irq(&xas);
 	}
-	xa_unlock_irq(&mapping->i_pages);
+	xas_unlock_irq(&xas);
 }
 EXPORT_SYMBOL(tag_pages_for_writeback);
 
@@ -2164,7 +2155,7 @@ int write_cache_pages(struct address_space *mapping,
 	pgoff_t done_index;
 	int cycled;
 	int range_whole = 0;
-	int tag;
+	xa_mark_t tag;
 
 	pagevec_init(&pvec);
 	if (wbc->range_cyclic) {
@@ -2445,7 +2436,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 
 /*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
- * its radix tree.
+ * the xarray.
  *
  * This is also used when a single buffer is being dirtied: we want to set the
  * page dirty in that case, but not all the buffers.  This is a "bottom-up"
@@ -2471,7 +2462,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 		BUG_ON(page_mapping(page) != mapping);
 		WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
-		radix_tree_tag_set(&mapping->i_pages, page_index(page),
+		__xa_set_mark(&mapping->i_pages, page_index(page),
 				   PAGECACHE_TAG_DIRTY);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		unlock_page_memcg(page);
@@ -2634,13 +2625,13 @@ EXPORT_SYMBOL(__cancel_dirty_page);
  * Returns true if the page was previously dirty.
  *
  * This is for preparing to put the page under writeout.  We leave the page
- * tagged as dirty in the radix tree so that a concurrent write-for-sync
+ * tagged as dirty in the xarray so that a concurrent write-for-sync
  * can discover it via a PAGECACHE_TAG_DIRTY walk.  The ->writepage
  * implementation will run either set_page_writeback() or set_page_dirty(),
- * at which stage we bring the page's dirty flag and radix-tree dirty tag
+ * at which stage we bring the page's dirty flag and xarray dirty tag
  * back into sync.
  *
- * This incoherency between the page's dirty flag and radix-tree tag is
+ * This incoherency between the page's dirty flag and xarray tag is
  * unfortunate, but it only exists while the page is locked.
  */
 int clear_page_dirty_for_io(struct page *page)
@@ -2721,7 +2712,7 @@ int test_clear_page_writeback(struct page *page)
 		xa_lock_irqsave(&mapping->i_pages, flags);
 		ret = TestClearPageWriteback(page);
 		if (ret) {
-			radix_tree_tag_clear(&mapping->i_pages, page_index(page),
+			__xa_clear_mark(&mapping->i_pages, page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi)) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
@@ -2761,11 +2752,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 
 	lock_page_memcg(page);
 	if (mapping && mapping_use_writeback_tags(mapping)) {
+		XA_STATE(xas, &mapping->i_pages, page_index(page));
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 		unsigned long flags;
 
-		xa_lock_irqsave(&mapping->i_pages, flags);
+		xas_lock_irqsave(&xas, flags);
+		xas_load(&xas);
 		ret = TestSetPageWriteback(page);
 		if (!ret) {
 			bool on_wblist;
@@ -2773,8 +2766,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 			on_wblist = mapping_tagged(mapping,
 						   PAGECACHE_TAG_WRITEBACK);
 
-			radix_tree_tag_set(&mapping->i_pages, page_index(page),
-						PAGECACHE_TAG_WRITEBACK);
+			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi))
 				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
@@ -2787,12 +2779,10 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 				sb_mark_inode_writeback(mapping->host);
 		}
 		if (!PageDirty(page))
-			radix_tree_tag_clear(&mapping->i_pages, page_index(page),
-						PAGECACHE_TAG_DIRTY);
+			xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
 		if (!keep_write)
-			radix_tree_tag_clear(&mapping->i_pages, page_index(page),
-						PAGECACHE_TAG_TOWRITE);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
+			xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
+		xas_unlock_irqrestore(&xas, flags);
 	} else {
 		ret = TestSetPageWriteback(page);
 	}
@@ -2806,16 +2796,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 }
 EXPORT_SYMBOL(__test_set_page_writeback);
 
-/*
- * Return true if any of the pages in the mapping are marked with the
- * passed tag.
- */
-int mapping_tagged(struct address_space *mapping, int tag)
-{
-	return radix_tree_tagged(&mapping->i_pages, tag);
-}
-EXPORT_SYMBOL(mapping_tagged);
-
 /**
  * wait_for_stable_page() - wait for writeback to finish, if necessary.
  * @page:	The page to wait on.