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 <[email protected]>
Reviewed-by: Josef Bacik <[email protected]>

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;