xarray: Replace exceptional entries

Introduce xarray value entries and tagged pointers to replace radix
tree exceptional entries.  This is a slight change in encoding to allow
the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a
value entry).  It is also a change in emphasis; exceptional entries are
intimidating and different.  As the comment explains, you can choose
to store values or pointers in the xarray and they are both first-class
citizens.
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>

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

@@ -723,9 +723,7 @@ static inline bool pte_user(pte_t pte)
 	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

@@ -313,9 +313,7 @@ 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/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

@@ -440,7 +440,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, pg_index);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		if (page && !xa_is_value(page)) {
 			misses++;
 			if (misses > 4)
 				break;

fs/proc/task_mmu.c

@@ -521,7 +521,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		if (!page)
 			return;
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			mss->swap += PAGE_SIZE;
 		else
 			put_page(page);

include/linux/radix-tree.h

@@ -28,34 +28,26 @@
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
  *
  * 00 - data pointer
- * 01 - internal entry
- * 10 - exceptional entry
- * 11 - this bit combination is currently unused/reserved
+ * 10 - internal entry
+ * x1 - value entry
  *
  * The internal entry may be a pointer to the next level in the tree, a
  * sibling entry, or an indicator that the entry in this slot has been moved
  * to another location in the tree and the lookup should be restarted.  While
  * NULL fits the 'data pointer' pattern, it means that there is no entry in
  * the tree for this index (no matter what level of the tree it is found at).
- * This means that you cannot store NULL in the tree as a value for the index.
+ * This means that storing a NULL entry in the tree is the same as deleting
+ * the entry from the tree.
  */
 #define RADIX_TREE_ENTRY_MASK		3UL
-#define RADIX_TREE_INTERNAL_NODE	1UL
-
-/*
- * Most users of the radix tree store pointers but shmem/tmpfs stores swap
- * entries in the same tree.  They are marked as exceptional entries to
- * distinguish them from pointers to struct page.
- * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it.
- */
-#define RADIX_TREE_EXCEPTIONAL_ENTRY	2
-#define RADIX_TREE_EXCEPTIONAL_SHIFT	2
+#define RADIX_TREE_INTERNAL_NODE	2UL
 
 static inline bool radix_tree_is_internal_node(void *ptr)
 {
@@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 /*
  * @count is the count of every non-NULL element in the ->slots array
- * whether that is an exceptional entry, a retry entry, a user pointer,
+ * whether that is a value entry, a retry entry, a user pointer,
  * a sibling entry or a pointer to the next level of the tree.
  * @exceptional is the count of every element in ->slots which is
- * either radix_tree_exceptional_entry() or is a sibling entry for an
- * exceptional entry.
+ * either a value entry or a sibling of a value entry.
  */
 struct radix_tree_node {
 	unsigned char	shift;		/* Bits remaining in each slot */
@@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg)
 	return unlikely(radix_tree_is_internal_node(arg));
 }
 
-/**
- * radix_tree_exceptional_entry	- radix_tree_deref_slot gave exceptional entry?
- * @arg:	value returned by radix_tree_deref_slot
- * Returns:	0 if well-aligned pointer, non-0 if exceptional entry.
- */
-static inline int radix_tree_exceptional_entry(void *arg)
-{
-	/* Not unlikely because radix_tree_exception often tested first */
-	return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY;
-}
-
 /**
  * radix_tree_exception	- radix_tree_deref_slot returned either exception?
  * @arg:	value returned by radix_tree_deref_slot

include/linux/swapops.h

@@ -18,9 +18,8 @@
  *
  * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
  */
-#define SWP_TYPE_SHIFT(e)	((sizeof(e.val) * 8) - \
-			(MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT))
-#define SWP_OFFSET_MASK(e)	((1UL << SWP_TYPE_SHIFT(e)) - 1)
+#define SWP_TYPE_SHIFT	(BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
+#define SWP_OFFSET_MASK	((1UL << SWP_TYPE_SHIFT) - 1)
 
 /*
  * Store a type+offset into a swp_entry_t in an arch-independent format
@@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
 {
 	swp_entry_t ret;
 
-	ret.val = (type << SWP_TYPE_SHIFT(ret)) |
-			(offset & SWP_OFFSET_MASK(ret));
+	ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK);
 	return ret;
 }
 
@@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
  */
 static inline unsigned swp_type(swp_entry_t entry)
 {
-	return (entry.val >> SWP_TYPE_SHIFT(entry));
+	return (entry.val >> SWP_TYPE_SHIFT);
 }
 
 /*
@@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry)
  */
 static inline pgoff_t swp_offset(swp_entry_t entry)
 {
-	return entry.val & SWP_OFFSET_MASK(entry);
+	return entry.val & SWP_OFFSET_MASK;
 }
 
 #ifdef CONFIG_MMU
@@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg)
 {
 	swp_entry_t entry;
 
-	entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+	entry.val = xa_to_value(arg);
 	return entry;
 }
 
 static inline void *swp_to_radix_entry(swp_entry_t entry)
 {
-	unsigned long value;
-
-	value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT;
-	return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY);
+	return xa_mk_value(entry.val);
 }
 
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)

include/linux/xarray.h

@@ -5,9 +5,111 @@
  * eXtensible Arrays
  * Copyright (c) 2017 Microsoft Corporation
  * Author: Matthew Wilcox <willy@infradead.org>
+ *
+ * See Documentation/core-api/xarray.rst for how to use the XArray.
  */
 
+#include <linux/bug.h>
 #include <linux/spinlock.h>
+#include <linux/types.h>
+
+/*
+ * The bottom two bits of the entry determine how the XArray interprets
+ * the contents:
+ *
+ * 00: Pointer entry
+ * 10: Internal entry
+ * x1: Value entry or tagged pointer
+ *
+ * Attempting to store internal entries in the XArray is a bug.
+ */
+
+#define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
+
+/**
+ * xa_mk_value() - Create an XArray entry from an integer.
+ * @v: Value to store in XArray.
+ *
+ * Context: Any context.
+ * Return: An entry suitable for storing in the XArray.
+ */
+static inline void *xa_mk_value(unsigned long v)
+{
+	WARN_ON((long)v < 0);
+	return (void *)((v << 1) | 1);
+}
+
+/**
+ * xa_to_value() - Get value stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: The value stored in the XArray entry.
+ */
+static inline unsigned long xa_to_value(const void *entry)
+{
+	return (unsigned long)entry >> 1;
+}
+
+/**
+ * xa_is_value() - Determine if an entry is a value.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: True if the entry is a value, false if it is a pointer.
+ */
+static inline bool xa_is_value(const void *entry)
+{
+	return (unsigned long)entry & 1;
+}
+
+/**
+ * xa_tag_pointer() - Create an XArray entry for a tagged pointer.
+ * @p: Plain pointer.
+ * @tag: Tag value (0, 1 or 3).
+ *
+ * If the user of the XArray prefers, they can tag their pointers instead
+ * of storing value entries.  Three tags are available (0, 1 and 3).
+ * These are distinct from the xa_mark_t as they are not replicated up
+ * through the array and cannot be searched for.
+ *
+ * Context: Any context.
+ * Return: An XArray entry.
+ */
+static inline void *xa_tag_pointer(void *p, unsigned long tag)
+{
+	return (void *)((unsigned long)p | tag);
+}
+
+/**
+ * xa_untag_pointer() - Turn an XArray entry into a plain pointer.
+ * @entry: XArray entry.
+ *
+ * If you have stored a tagged pointer in the XArray, call this function
+ * to get the untagged version of the pointer.
+ *
+ * Context: Any context.
+ * Return: A pointer.
+ */
+static inline void *xa_untag_pointer(void *entry)
+{
+	return (void *)((unsigned long)entry & ~3UL);
+}
+
+/**
+ * xa_pointer_tag() - Get the tag stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * If you have stored a tagged pointer in the XArray, call this function
+ * to get the tag of that pointer.
+ *
+ * Context: Any context.
+ * Return: A tag.
+ */
+static inline unsigned int xa_pointer_tag(void *entry)
+{
+	return (unsigned long)entry & 3UL;
+}
 
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)

lib/idr.c

@@ -338,11 +338,8 @@ EXPORT_SYMBOL(idr_replace);
  * by the number of bits in the leaf bitmap before doing a radix tree lookup.
  *
  * As an optimisation, if there are only a few low bits set in any given
- * leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional
- * entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits
- * directly in the entry.  By being really tricksy, we could store
- * BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising
- * for 0-3 allocated IDs.
+ * leaf, instead of allocating a 128-byte bitmap, we store the bits
+ * directly in the entry.
  *
  * We allow the radix tree 'exceptional' count to get out of date.  Nothing
  * in the IDA nor the radix tree code checks it.  If it becomes important
@@ -366,12 +363,11 @@ static int ida_get_new_above(struct ida *ida, int start)
 	struct radix_tree_iter iter;
 	struct ida_bitmap *bitmap;
 	unsigned long index;
-	unsigned bit, ebit;
+	unsigned bit;
 	int new;
 
 	index = start / IDA_BITMAP_BITS;
 	bit = start % IDA_BITMAP_BITS;
-	ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT;
 
 	slot = radix_tree_iter_init(&iter, index);
 	for (;;) {
@@ -386,25 +382,23 @@ static int ida_get_new_above(struct ida *ida, int start)
 				return PTR_ERR(slot);
 			}
 		}
-		if (iter.index > index) {
+		if (iter.index > index)
 			bit = 0;
-			ebit = RADIX_TREE_EXCEPTIONAL_SHIFT;
-		}
 		new = iter.index * IDA_BITMAP_BITS;
 		bitmap = rcu_dereference_raw(*slot);
-		if (radix_tree_exception(bitmap)) {
-			unsigned long tmp = (unsigned long)bitmap;
-			ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit);
-			if (ebit < BITS_PER_LONG) {
-				tmp |= 1UL << ebit;
-				rcu_assign_pointer(*slot, (void *)tmp);
-				return new + ebit -
-					RADIX_TREE_EXCEPTIONAL_SHIFT;
+		if (xa_is_value(bitmap)) {
+			unsigned long tmp = xa_to_value(bitmap);
+			int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE,
+							bit);
+			if (vbit < BITS_PER_XA_VALUE) {
+				tmp |= 1UL << vbit;
+				rcu_assign_pointer(*slot, xa_mk_value(tmp));
+				return new + vbit;
 			}
 			bitmap = this_cpu_xchg(ida_bitmap, NULL);
 			if (!bitmap)
 				return -EAGAIN;
-			bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+			bitmap->bitmap[0] = tmp;
 			rcu_assign_pointer(*slot, bitmap);
 		}
 
@@ -425,17 +419,14 @@ static int ida_get_new_above(struct ida *ida, int start)
 			new += bit;
 			if (new < 0)
 				return -ENOSPC;
-			if (ebit < BITS_PER_LONG) {
-				bitmap = (void *)((1UL << ebit) |
-						RADIX_TREE_EXCEPTIONAL_ENTRY);
-				radix_tree_iter_replace(root, &iter, slot,
-						bitmap);
-				return new;
+			if (bit < BITS_PER_XA_VALUE) {
+				bitmap = xa_mk_value(1UL << bit);
+			} else {
+				bitmap = this_cpu_xchg(ida_bitmap, NULL);
+				if (!bitmap)
+					return -EAGAIN;
+				__set_bit(bit, bitmap->bitmap);
 			}
-			bitmap = this_cpu_xchg(ida_bitmap, NULL);
-			if (!bitmap)
-				return -EAGAIN;
-			__set_bit(bit, bitmap->bitmap);
 			radix_tree_iter_replace(root, &iter, slot, bitmap);
 		}
 
@@ -457,9 +448,9 @@ static void ida_remove(struct ida *ida, int id)
 		goto err;
 
 	bitmap = rcu_dereference_raw(*slot);
-	if (radix_tree_exception(bitmap)) {
+	if (xa_is_value(bitmap)) {
 		btmp = (unsigned long *)slot;
-		offset += RADIX_TREE_EXCEPTIONAL_SHIFT;
+		offset += 1; /* Intimate knowledge of the value encoding */
 		if (offset >= BITS_PER_LONG)
 			goto err;
 	} else {
@@ -470,9 +461,8 @@ static void ida_remove(struct ida *ida, int id)
 
 	__clear_bit(offset, btmp);
 	radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE);
-	if (radix_tree_exception(bitmap)) {
-		if (rcu_dereference_raw(*slot) ==
-					(void *)RADIX_TREE_EXCEPTIONAL_ENTRY)
+	if (xa_is_value(bitmap)) {
+		if (xa_to_value(rcu_dereference_raw(*slot)) == 0)
 			radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
 	} else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) {
 		kfree(bitmap);
@@ -503,7 +493,7 @@ void ida_destroy(struct ida *ida)
 	xa_lock_irqsave(&ida->ida_rt, flags);
 	radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) {
 		struct ida_bitmap *bitmap = rcu_dereference_raw(*slot);
-		if (!radix_tree_exception(bitmap))
+		if (!xa_is_value(bitmap))
 			kfree(bitmap);
 		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
 	}

lib/radix-tree.c

@@ -340,14 +340,12 @@ static void dump_ida_node(void *entry, unsigned long index)
 		for (i = 0; i < RADIX_TREE_MAP_SIZE; i++)
 			dump_ida_node(node->slots[i],
 					index | (i << node->shift));
-	} else if (radix_tree_exceptional_entry(entry)) {
+	} else if (xa_is_value(entry)) {
 		pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n",
 				entry, (int)(index & RADIX_TREE_MAP_MASK),
 				index * IDA_BITMAP_BITS,
-				index * IDA_BITMAP_BITS + BITS_PER_LONG -
-					RADIX_TREE_EXCEPTIONAL_SHIFT,
-				(unsigned long)entry >>
-					RADIX_TREE_EXCEPTIONAL_SHIFT);
+				index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE,
+				xa_to_value(entry));
 	} else {
 		struct ida_bitmap *bitmap = entry;
 
@@ -656,7 +654,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		BUG_ON(shift > BITS_PER_LONG);
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
-		} else if (radix_tree_exceptional_entry(entry)) {
+		} else if (xa_is_value(entry)) {
 			/* Moving an exceptional root->rnode to a node */
 			node->exceptional = 1;
 		}
@@ -955,12 +953,12 @@ static inline int insert_entries(struct radix_tree_node *node,
 					!is_sibling_entry(node, old) &&
 					(old != RADIX_TREE_RETRY))
 			radix_tree_free_nodes(old);
-		if (radix_tree_exceptional_entry(old))
+		if (xa_is_value(old))
 			node->exceptional--;
 	}
 	if (node) {
 		node->count += n;
-		if (radix_tree_exceptional_entry(item))
+		if (xa_is_value(item))
 			node->exceptional += n;
 	}
 	return n;
@@ -974,7 +972,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	rcu_assign_pointer(*slot, item);
 	if (node) {
 		node->count++;
-		if (radix_tree_exceptional_entry(item))
+		if (xa_is_value(item))
 			node->exceptional++;
 	}
 	return 1;
@@ -1190,8 +1188,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 			  radix_tree_update_node_t update_node)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = !!radix_tree_exceptional_entry(item) -
-				!!radix_tree_exceptional_entry(old);
+	int exceptional = !!xa_is_value(item) - !!xa_is_value(old);
 	int count = calculate_count(root, node, slot, item, old);
 
 	/*
@@ -1992,7 +1989,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0;
+	int exceptional = xa_is_value(old) ? -1 : 0;
 	unsigned offset = get_slot_offset(node, slot);
 	int tag;
 

mm/filemap.c

@@ -127,7 +127,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 
 		p = radix_tree_deref_slot_protected(slot,
 						    &mapping->i_pages.xa_lock);
-		if (!radix_tree_exceptional_entry(p))
+		if (!xa_is_value(p))
 			return -EEXIST;
 
 		mapping->nrexceptional--;
@@ -336,7 +336,7 @@ page_cache_tree_delete_batch(struct address_space *mapping,
 			break;
 		page = radix_tree_deref_slot_protected(slot,
 						       &mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			continue;
 		if (!tail_pages) {
 			/*
@@ -1355,7 +1355,7 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 		struct page *page;
 
 		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+		if (!page || xa_is_value(page))
 			break;
 		index++;
 		if (index == 0)
@@ -1396,7 +1396,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 		struct page *page;
 
 		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+		if (!page || xa_is_value(page))
 			break;
 		index--;
 		if (index == ULONG_MAX)
@@ -1539,7 +1539,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 
 repeat:
 	page = find_get_entry(mapping, offset);
-	if (radix_tree_exceptional_entry(page))
+	if (xa_is_value(page))
 		page = NULL;
 	if (!page)
 		goto no_page;

mm/khugepaged.c

@@ -1369,7 +1369,7 @@ static void collapse_shmem(struct mm_struct *mm,
 
 		page = radix_tree_deref_slot_protected(slot,
 				&mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) {
+		if (xa_is_value(page) || !PageUptodate(page)) {
 			xa_unlock_irq(&mapping->i_pages);
 			/* swap in or instantiate fallocated page */
 			if (shmem_getpage(mapping->host, index, &page,

mm/madvise.c

@@ -251,7 +251,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 		page = find_get_entry(mapping, index);
-		if (!radix_tree_exceptional_entry(page)) {
+		if (!xa_is_value(page)) {
 			if (page)
 				put_page(page);
 			continue;

mm/memcontrol.c

@@ -4750,7 +4750,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 	/* shmem/tmpfs may report page out on swap: account for that too. */
 	if (shmem_mapping(mapping)) {
 		page = find_get_entry(mapping, pgoff);
-		if (radix_tree_exceptional_entry(page)) {
+		if (xa_is_value(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
 			if (do_memsw_account())
 				*entry = swp;

mm/mincore.c

@@ -66,7 +66,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 		 * shmem/tmpfs may return swap: account for swapcache
 		 * page too.
 		 */
-		if (radix_tree_exceptional_entry(page)) {
+		if (xa_is_value(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
 			page = find_get_page(swap_address_space(swp),
 					     swp_offset(swp));

mm/readahead.c

@@ -179,7 +179,7 @@ unsigned int __do_page_cache_readahead(struct address_space *mapping,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, page_offset);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		if (page && !xa_is_value(page)) {
 			/*
 			 * Page already present?  Kick off the current batch of
 			 * contiguous pages before continuing with the next

mm/shmem.c

@@ -709,7 +709,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 			continue;
 		}
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			swapped++;
 
 		if (need_resched()) {
@@ -824,7 +824,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
@@ -921,7 +921,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				if (shmem_free_swap(mapping, index, page)) {
@@ -1643,7 +1643,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 repeat:
 	swap.val = 0;
 	page = find_lock_entry(mapping, index);
-	if (radix_tree_exceptional_entry(page)) {
+	if (xa_is_value(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
 	}
@@ -2578,7 +2578,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				index = indices[i];
 			}
 			page = pvec.pages[i];
-			if (page && !radix_tree_exceptional_entry(page)) {
+			if (page && !xa_is_value(page)) {
 				if (!PageUptodate(page))
 					page = NULL;
 			}

mm/swap.c

@@ -965,7 +965,7 @@ void pagevec_remove_exceptionals(struct pagevec *pvec)
 
 	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
+		if (!xa_is_value(page))
 			pvec->pages[j++] = page;
 	}
 	pvec->nr = j;

mm/truncate.c

@@ -70,7 +70,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping,
 		return;
 
 	for (j = 0; j < pagevec_count(pvec); j++)
-		if (radix_tree_exceptional_entry(pvec->pages[j]))
+		if (xa_is_value(pvec->pages[j]))
 			break;
 
 	if (j == pagevec_count(pvec))
@@ -85,7 +85,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping,
 		struct page *page = pvec->pages[i];
 		pgoff_t index = indices[i];
 
-		if (!radix_tree_exceptional_entry(page)) {
+		if (!xa_is_value(page)) {
 			pvec->pages[j++] = page;
 			continue;
 		}
@@ -347,7 +347,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page))
+			if (xa_is_value(page))
 				continue;
 
 			if (!trylock_page(page))
@@ -442,7 +442,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 			}
 
-			if (radix_tree_exceptional_entry(page))
+			if (xa_is_value(page))
 				continue;
 
 			lock_page(page);
@@ -561,7 +561,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (index > end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				invalidate_exceptional_entry(mapping, index,
 							     page);
 				continue;
@@ -692,7 +692,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			if (index > end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (!invalidate_exceptional_entry2(mapping,
 								   index, page))
 					ret = -EBUSY;

mm/workingset.c

@@ -155,8 +155,8 @@
  * refault distance will immediately activate the refaulting page.
  */
 
-#define EVICTION_SHIFT	(RADIX_TREE_EXCEPTIONAL_ENTRY + \
-			 NODES_SHIFT +	\
+#define EVICTION_SHIFT	((BITS_PER_LONG - BITS_PER_XA_VALUE) +	\
+			 NODES_SHIFT +				\
 			 MEM_CGROUP_ID_SHIFT)
 #define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)
 
@@ -173,20 +173,19 @@ static unsigned int bucket_order __read_mostly;
 static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
 {
 	eviction >>= bucket_order;
+	eviction &= EVICTION_MASK;
 	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
 	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
-	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
 
-	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+	return xa_mk_value(eviction);
 }
 
 static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
 			  unsigned long *evictionp)
 {
-	unsigned long entry = (unsigned long)shadow;
+	unsigned long entry = xa_to_value(shadow);
 	int memcgid, nid;
 
-	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
 	entry >>= NODES_SHIFT;
 	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
@@ -453,7 +452,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		goto out_invalid;
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
-			if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i])))
+			if (WARN_ON_ONCE(!xa_is_value(node->slots[i])))
 				goto out_invalid;
 			if (WARN_ON_ONCE(!node->exceptional))
 				goto out_invalid;

tools/testing/radix-tree/idr-test.c

@@ -19,7 +19,7 @@
 
 #include "test.h"
 
-#define DUMMY_PTR	((void *)0x12)
+#define DUMMY_PTR	((void *)0x10)
 
 int item_idr_free(int id, void *p, void *data)
 {
@@ -411,11 +411,11 @@ void ida_check_conv_user(void)
 		int id = ida_alloc(&ida, GFP_NOWAIT);
 		if (id == -ENOMEM) {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) !=
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 			id = ida_alloc(&ida, GFP_KERNEL);
 		} else {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) ==
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 		}
 		IDA_BUG_ON(&ida, id != i);
 	}

tools/testing/radix-tree/linux/radix-tree.h

@@ -2,7 +2,6 @@
 #ifndef _TEST_RADIX_TREE_H
 #define _TEST_RADIX_TREE_H
 
-#include "generated/map-shift.h"
 #include "../../../../include/linux/radix-tree.h"
 
 extern int kmalloc_verbose;

tools/testing/radix-tree/multiorder.c

@@ -39,12 +39,11 @@ static void __multiorder_tag_test(int index, int order)
 
 	/*
 	 * Verify we get collisions for covered indices.  We try and fail to
-	 * insert an exceptional entry so we don't leak memory via
+	 * insert a value entry so we don't leak memory via
 	 * item_insert_order().
 	 */
 	for_each_index(i, base, order) {
-		err = __radix_tree_insert(&tree, i, order,
-				(void *)(0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY));
+		err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0));
 		assert(err == -EEXIST);
 	}
 
@@ -380,8 +379,8 @@ static void multiorder_join1(unsigned long index,
 }
 
 /*
- * Check that the accounting of exceptional entries is handled correctly
- * by joining an exceptional entry to a normal pointer.
+ * Check that the accounting of value entries is handled correctly
+ * by joining a value entry to a normal pointer.
  */
 static void multiorder_join2(unsigned order1, unsigned order2)
 {
@@ -391,9 +390,9 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	void *item2;
 
 	item_insert_order(&tree, 0, order2);
-	radix_tree_insert(&tree, 1 << order2, (void *)0x12UL);
+	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == (void *)0x12UL);
+	assert(item2 == xa_mk_value(5));
 	assert(node->exceptional == 1);
 
 	item2 = radix_tree_lookup(&tree, 0);
@@ -407,7 +406,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 }
 
 /*
- * This test revealed an accounting bug for exceptional entries at one point.
+ * This test revealed an accounting bug for value entries at one point.
  * Nodes were being freed back into the pool with an elevated exception count
  * by radix_tree_join() and then radix_tree_split() was failing to zero the
  * count of exceptional entries.
@@ -421,16 +420,16 @@ static void multiorder_join3(unsigned int order)
 	unsigned long i;
 
 	for (i = 0; i < (1 << order); i++) {
-		radix_tree_insert(&tree, i, (void *)0x12UL);
+		radix_tree_insert(&tree, i, xa_mk_value(5));
 	}
 
-	radix_tree_join(&tree, 0, order, (void *)0x16UL);
+	radix_tree_join(&tree, 0, order, xa_mk_value(7));
 	rcu_barrier();
 
 	radix_tree_split(&tree, 0, 0);
 
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, (void *)0x12UL);
+		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5));
 	}
 
 	__radix_tree_lookup(&tree, 0, &node, NULL);
@@ -517,10 +516,10 @@ static void __multiorder_split2(int old_order, int new_order)
 	struct radix_tree_node *node;
 	void *item;
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
@@ -530,7 +529,7 @@ static void __multiorder_split2(int old_order, int new_order)
 	}
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item != (void *)0x12);
+	assert(item != xa_mk_value(5));
 	assert(node->exceptional == 0);
 
 	item_kill_tree(&tree);
@@ -544,40 +543,40 @@ static void __multiorder_split3(int old_order, int new_order)
 	struct radix_tree_node *node;
 	void *item;
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, (void *)0x16);
+		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7));
 	}
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x16);
+	assert(item == xa_mk_value(7));
 	assert(node->exceptional > 0);
 
 	item_kill_tree(&tree);
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
 		if (iter.index == (1 << new_order))
 			radix_tree_iter_replace(&tree, &iter, slot,
-						(void *)0x16);
+						xa_mk_value(7));
 		else
 			radix_tree_iter_replace(&tree, &iter, slot, NULL);
 	}
 
 	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
-	assert(item == (void *)0x16);
+	assert(item == xa_mk_value(7));
 	assert(node->count == node->exceptional);
 	do {
 		node = node->parent;
@@ -610,13 +609,13 @@ static void multiorder_account(void)
 
 	item_insert_order(&tree, 0, 5);
 
-	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
+	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(node->count == node->exceptional * 2);
 	radix_tree_delete(&tree, 1 << 5);
 	assert(node->exceptional == 0);
 
-	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
+	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
 	assert(node->count == node->exceptional * 2);
 	__radix_tree_replace(&tree, node, slot, NULL, NULL);

tools/testing/radix-tree/test.c

@@ -295,7 +295,7 @@ void item_kill_tree(struct radix_tree_root *root)
 	int nfound;
 
 	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (radix_tree_exceptional_entry(*slot))
+		if (xa_is_value(*slot))
 			radix_tree_delete(root, iter.index);
 	}