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
  ...

.clang-format

@@ -323,7 +323,6 @@ ForEachMacros:
   - 'protocol_for_each_card'
   - 'protocol_for_each_dev'
   - 'queue_for_each_hw_ctx'
-  - 'radix_tree_for_each_contig'
   - 'radix_tree_for_each_slot'
   - 'radix_tree_for_each_tagged'
   - 'rbtree_postorder_for_each_entry_safe'

.mailmap

@@ -119,6 +119,13 @@ Mark Brown <[email protected]>
 Mark Yao <[email protected]> <[email protected]>
 Martin Kepplinger <[email protected]> <[email protected]>
 Martin Kepplinger <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
+Matthew Wilcox <[email protected]> <[email protected]>
 Matthieu CASTET <[email protected]>
 Mauro Carvalho Chehab <[email protected]> <[email protected]>
 Mauro Carvalho Chehab <[email protected]> <[email protected]>

Documentation/core-api/index.rst

@@ -21,6 +21,7 @@ Core utilities
    local_ops
    workqueue
    genericirq
+   xarray
    flexible-arrays
    librs
    genalloc

MAINTAINERS

@@ -535,7 +535,7 @@ F:	Documentation/hwmon/adt7475
 F:	drivers/hwmon/adt7475.c
 
 ADVANSYS SCSI DRIVER
-M:	Matthew Wilcox <[email protected]>
+M:	Matthew Wilcox <[email protected]>
 M:	Hannes Reinecke <[email protected]>
 L:	[email protected]
 S:	Maintained
@@ -4393,7 +4393,7 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-diolan-u2c.c
 
 FILESYSTEM DIRECT ACCESS (DAX)
-M:	Matthew Wilcox <[email protected]>
+M:	Matthew Wilcox <[email protected]>
 M:	Ross Zwisler <[email protected]>
 M:	Jan Kara <[email protected]>
 L:	[email protected]
@@ -8697,7 +8697,7 @@ F:	drivers/message/fusion/
 F:	drivers/scsi/mpt3sas/
 
 LSILOGIC/SYMBIOS/NCR 53C8XX and 53C1010 PCI-SCSI drivers
-M:	Matthew Wilcox <[email protected]>
+M:	Matthew Wilcox <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/scsi/sym53c8xx_2/
@@ -16137,6 +16137,17 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
 S:	Maintained
 F:	arch/x86/entry/vdso/
 
+XARRAY
+M:	Matthew Wilcox <[email protected]>
+L:	[email protected]
+S:	Supported
+F:	Documentation/core-api/xarray.rst
+F:	lib/idr.c
+F:	lib/xarray.c
+F:	include/linux/idr.h
+F:	include/linux/xarray.h
+F:	tools/testing/radix-tree
+
 XC2028/3028 TUNER DRIVER
 M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]

arch/parisc/kernel/syscall.S

@@ -2,7 +2,7 @@
  * Linux/PA-RISC Project (http://www.parisc-linux.org/)
  * 
  * System call entry code / Linux gateway page
- * Copyright (c) Matthew Wilcox 1999 <willy@bofh.ai>
+ * Copyright (c) Matthew Wilcox 1999 <willy@infradead.org>
  * Licensed under the GNU GPL.
  * thanks to Philipp Rumpf, Mike Shaver and various others
  * sorry about the wall, puffin..

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -716,9 +716,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))

arch/powerpc/include/asm/nohash/64/pgtable.h

@@ -350,9 +350,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define MAX_SWAPFILES_CHECK() do { \
 	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))

drivers/gpu/drm/i915/i915_gem.c

@@ -5996,7 +5996,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 	count = __sg_page_count(sg);
 
 	while (idx + count <= n) {
-		unsigned long exception, i;
+		void *entry;
+		unsigned long i;
 		int ret;
 
 		/* If we cannot allocate and insert this entry, or the
@@ -6011,12 +6012,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 		if (ret && ret != -EEXIST)
 			goto scan;
 
-		exception =
-			RADIX_TREE_EXCEPTIONAL_ENTRY |
-			idx << RADIX_TREE_EXCEPTIONAL_SHIFT;
+		entry = xa_mk_value(idx);
 		for (i = 1; i < count; i++) {
-			ret = radix_tree_insert(&iter->radix, idx + i,
-						(void *)exception);
+			ret = radix_tree_insert(&iter->radix, idx + i, entry);
 			if (ret && ret != -EEXIST)
 				goto scan;
 		}
@@ -6054,15 +6052,14 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 	GEM_BUG_ON(!sg);
 
 	/* If this index is in the middle of multi-page sg entry,
-	 * the radixtree will contain an exceptional entry that points
+	 * the radix tree will contain a value entry that points
 	 * to the start of that range. We will return the pointer to
 	 * the base page and the offset of this page within the
 	 * sg entry's range.
 	 */
 	*offset = 0;
-	if (unlikely(radix_tree_exception(sg))) {
-		unsigned long base =
-			(unsigned long)sg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+	if (unlikely(xa_is_value(sg))) {
+		unsigned long base = xa_to_value(sg);
 
 		sg = radix_tree_lookup(&iter->radix, base);
 		GEM_BUG_ON(!sg);

drivers/input/keyboard/hilkbd.c

@@ -2,7 +2,7 @@
  *  linux/drivers/hil/hilkbd.c
  *
  *  Copyright (C) 1998 Philip Blundell <[email protected]>
- *  Copyright (C) 1999 Matthew Wilcox <willy@bofh.ai>
+ *  Copyright (C) 1999 Matthew Wilcox <willy@infradead.org>
  *  Copyright (C) 1999-2007 Helge Deller <[email protected]>
  *
  *  Very basic HP Human Interface Loop (HIL) driver.

drivers/pci/hotplug/acpiphp.h

@@ -8,7 +8,7 @@
  * Copyright (C) 2002 Hiroshi Aono ([email protected])
  * Copyright (C) 2002,2003 Takayoshi Kochi ([email protected])
  * Copyright (C) 2002,2003 NEC Corporation
- * Copyright (C) 2003-2005 Matthew Wilcox ([email protected])
+ * Copyright (C) 2003-2005 Matthew Wilcox ([email protected])
  * Copyright (C) 2003-2005 Hewlett Packard
  *
  * All rights reserved.

drivers/pci/hotplug/acpiphp_core.c

@@ -8,7 +8,7 @@
  * Copyright (C) 2002 Hiroshi Aono ([email protected])
  * Copyright (C) 2002,2003 Takayoshi Kochi ([email protected])
  * Copyright (C) 2002,2003 NEC Corporation
- * Copyright (C) 2003-2005 Matthew Wilcox ([email protected])
+ * Copyright (C) 2003-2005 Matthew Wilcox ([email protected])
  * Copyright (C) 2003-2005 Hewlett Packard
  *
  * All rights reserved.
@@ -40,7 +40,7 @@ bool acpiphp_disabled;
 static struct acpiphp_attention_info *attention_info;
 
 #define DRIVER_VERSION	"0.5"
-#define DRIVER_AUTHOR	"Greg Kroah-Hartman <[email protected]>, Takayoshi Kochi <[email protected]>, Matthew Wilcox <willy@hp.com>"
+#define DRIVER_AUTHOR	"Greg Kroah-Hartman <[email protected]>, Takayoshi Kochi <[email protected]>, Matthew Wilcox <willy@infradead.org>"
 #define DRIVER_DESC	"ACPI Hot Plug PCI Controller Driver"
 
 MODULE_AUTHOR(DRIVER_AUTHOR);

drivers/pci/hotplug/acpiphp_glue.c

@@ -5,7 +5,7 @@
  * Copyright (C) 2002,2003 Takayoshi Kochi ([email protected])
  * Copyright (C) 2002 Hiroshi Aono ([email protected])
  * Copyright (C) 2002,2003 NEC Corporation
- * Copyright (C) 2003-2005 Matthew Wilcox ([email protected])
+ * Copyright (C) 2003-2005 Matthew Wilcox ([email protected])
  * Copyright (C) 2003-2005 Hewlett Packard
  * Copyright (C) 2005 Rajesh Shah ([email protected])
  * Copyright (C) 2005 Intel Corporation

drivers/staging/erofs/utils.c

@@ -35,7 +35,6 @@ static atomic_long_t erofs_global_shrink_cnt;
 
 #ifdef CONFIG_EROFS_FS_ZIP
 
-/* radix_tree and the future XArray both don't use tagptr_t yet */
 struct erofs_workgroup *erofs_find_workgroup(
 	struct super_block *sb, pgoff_t index, bool *tag)
 {
@@ -47,9 +46,8 @@ struct erofs_workgroup *erofs_find_workgroup(
 	rcu_read_lock();
 	grp = radix_tree_lookup(&sbi->workstn_tree, index);
 	if (grp != NULL) {
-		*tag = radix_tree_exceptional_entry(grp);
-		grp = (void *)((unsigned long)grp &
-			~RADIX_TREE_EXCEPTIONAL_ENTRY);
+		*tag = xa_pointer_tag(grp);
+		grp = xa_untag_pointer(grp);
 
 		if (erofs_workgroup_get(grp, &oldcount)) {
 			/* prefer to relax rcu read side */
@@ -83,9 +81,7 @@ int erofs_register_workgroup(struct super_block *sb,
 	sbi = EROFS_SB(sb);
 	erofs_workstn_lock(sbi);
 
-	if (tag)
-		grp = (void *)((unsigned long)grp |
-			1UL << RADIX_TREE_EXCEPTIONAL_SHIFT);
+	grp = xa_tag_pointer(grp, tag);
 
 	err = radix_tree_insert(&sbi->workstn_tree,
 		grp->index, grp);
@@ -131,9 +127,7 @@ unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
 
 	for (i = 0; i < found; ++i) {
 		int cnt;
-		struct erofs_workgroup *grp = (void *)
-			((unsigned long)batch[i] &
-				~RADIX_TREE_EXCEPTIONAL_ENTRY);
+		struct erofs_workgroup *grp = xa_untag_pointer(batch[i]);
 
 		first_index = grp->index + 1;
 
@@ -150,8 +144,8 @@ unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
 #endif
 			continue;
 
-		if (radix_tree_delete(&sbi->workstn_tree,
-			grp->index) != grp) {
+		if (xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree,
+			grp->index)) != grp) {
 #ifdef EROFS_FS_HAS_MANAGED_CACHE
 skip:
 			erofs_workgroup_unfreeze(grp, 1);

fs/btrfs/compression.c

@@ -437,10 +437,8 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		if (pg_index > end_index)
 			break;
 
-		rcu_read_lock();
-		page = radix_tree_lookup(&mapping->i_pages, pg_index);
-		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		page = xa_load(&mapping->i_pages, pg_index);
+		if (page && !xa_is_value(page)) {
 			misses++;
 			if (misses > 4)
 				break;

fs/btrfs/extent_io.c

@@ -3784,7 +3784,7 @@ int btree_write_cache_pages(struct address_space *mapping,
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
 	int scanned = 0;
-	int tag;
+	xa_mark_t tag;
 
 	pagevec_init(&pvec);
 	if (wbc->range_cyclic) {
@@ -3909,7 +3909,7 @@ static int extent_write_cache_pages(struct address_space *mapping,
 	pgoff_t done_index;
 	int range_whole = 0;
 	int scanned = 0;
-	int tag;
+	xa_mark_t tag;
 
 	/*
 	 * We have to hold onto the inode so that ordered extents can do their
@@ -5159,11 +5159,9 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 
 		clear_page_dirty_for_io(page);
 		xa_lock_irq(&page->mapping->i_pages);
-		if (!PageDirty(page)) {
-			radix_tree_tag_clear(&page->mapping->i_pages,
-						page_index(page),
-						PAGECACHE_TAG_DIRTY);
-		}
+		if (!PageDirty(page))
+			__xa_clear_mark(&page->mapping->i_pages,
+					page_index(page), PAGECACHE_TAG_DIRTY);
 		xa_unlock_irq(&page->mapping->i_pages);
 		ClearPageError(page);
 		unlock_page(page);

fs/buffer.c

@@ -562,7 +562,7 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
 EXPORT_SYMBOL(mark_buffer_dirty_inode);
 
 /*
- * Mark the page dirty, and set it dirty in the radix tree, and mark the inode
+ * Mark the page dirty, and set it dirty in the page cache, and mark the inode
  * dirty.
  *
  * If warn is true, then emit a warning if the page is not uptodate and has
@@ -579,8 +579,8 @@ void __set_page_dirty(struct page *page, struct address_space *mapping,
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
-		radix_tree_tag_set(&mapping->i_pages,
-				page_index(page), PAGECACHE_TAG_DIRTY);
+		__xa_set_mark(&mapping->i_pages, page_index(page),
+				PAGECACHE_TAG_DIRTY);
 	}
 	xa_unlock_irqrestore(&mapping->i_pages, flags);
 }
@@ -1050,7 +1050,7 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * The relationship between dirty buffers and dirty pages:
  *
  * Whenever a page has any dirty buffers, the page's dirty bit is set, and
- * the page is tagged dirty in its radix tree.
+ * the page is tagged dirty in the page cache.
  *
  * At all times, the dirtiness of the buffers represents the dirtiness of
  * subsections of the page.  If the page has buffers, the page dirty bit is
@@ -1073,9 +1073,9 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * mark_buffer_dirty - mark a buffer_head as needing writeout
  * @bh: the buffer_head to mark dirty
  *
- * mark_buffer_dirty() will set the dirty bit against the buffer, then set its
- * backing page dirty, then tag the page as dirty in its address_space's radix
- * tree and then attach the address_space's inode to its superblock's dirty
+ * mark_buffer_dirty() will set the dirty bit against the buffer, then set
+ * its backing page dirty, then tag the page as dirty in the page cache
+ * and then attach the address_space's inode to its superblock's dirty
  * inode list.
  *
  * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,