Merge branch 'xarray' of git://git.infradead.org/users/willy/linux-dax

Pull XArray conversion from Matthew Wilcox:
 "The XArray provides an improved interface to the radix tree data
  structure, providing locking as part of the API, specifying GFP flags
  at allocation time, eliminating preloading, less re-walking the tree,
  more efficient iterations and not exposing RCU-protected pointers to
  its users.

  This patch set

   1. Introduces the XArray implementation

   2. Converts the pagecache to use it

   3. Converts memremap to use it

  The page cache is the most complex and important user of the radix
  tree, so converting it was most important. Converting the memremap
  code removes the only other user of the multiorder code, which allows
  us to remove the radix tree code that supported it.

  I have 40+ followup patches to convert many other users of the radix
  tree over to the XArray, but I'd like to get this part in first. The
  other conversions haven't been in linux-next and aren't suitable for
  applying yet, but you can see them in the xarray-conv branch if you're
  interested"

* 'xarray' of git://git.infradead.org/users/willy/linux-dax: (90 commits)
  radix tree: Remove multiorder support
  radix tree test: Convert multiorder tests to XArray
  radix tree tests: Convert item_delete_rcu to XArray
  radix tree tests: Convert item_kill_tree to XArray
  radix tree tests: Move item_insert_order
  radix tree test suite: Remove multiorder benchmarking
  radix tree test suite: Remove __item_insert
  memremap: Convert to XArray
  xarray: Add range store functionality
  xarray: Move multiorder_check to in-kernel tests
  xarray: Move multiorder_shrink to kernel tests
  xarray: Move multiorder account test in-kernel
  radix tree test suite: Convert iteration test to XArray
  radix tree test suite: Convert tag_tagged_items to XArray
  radix tree: Remove radix_tree_clear_tags
  radix tree: Remove radix_tree_maybe_preload_order
  radix tree: Remove split/join code
  radix tree: Remove radix_tree_update_node_t
  page cache: Finish XArray conversion
  dax: Convert page fault handlers to XArray
  ...

1 files changed, 26 insertions, 46 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 439a304a6c92..3f690bae6b78 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);
 
@@ -2170,7 +2161,7 @@ int write_cache_pages(struct address_space *mapping,
 	pgoff_t end;		/* Inclusive */
 	pgoff_t done_index;
 	int range_whole = 0;
-	int tag;
+	xa_mark_t tag;
 
 	pagevec_init(&pvec);
 	if (wbc->range_cyclic) {
@@ -2442,7 +2433,7 @@ 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"
@@ -2468,7 +2459,7 @@ 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);
@@ -2631,13 +2622,13 @@ 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)
@@ -2718,7 +2709,7 @@ 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);
@@ -2758,11 +2749,13 @@ 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;
@@ -2770,8 +2763,7 @@ 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);
 
@@ -2784,12 +2776,10 @@ 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);
 	}
@@ -2803,16 +2793,6 @@ 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.