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>

1 files changed, 55 insertions, 57 deletions

diff --git a/fs/dax.c b/fs/dax.c
index b68ce484e1be..ebcec36335eb 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -59,56 +59,57 @@ static int __init init_dax_wait_table(void)
 fs_initcall(init_dax_wait_table);
 
 /*
- * We use lowest available bit in exceptional entry for locking, one bit for
- * the entry size (PMD) and two more to tell us if the entry is a zero page or
- * an empty entry that is just used for locking.  In total four special bits.
+ * DAX pagecache entries use XArray value entries so they can't be mistaken
+ * for pages.  We use one bit for locking, one bit for the entry size (PMD)
+ * and two more to tell us if the entry is a zero page or an empty entry that
+ * is just used for locking.  In total four special bits.
  *
  * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
  * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
  * block allocation.
  */
-#define RADIX_DAX_SHIFT		(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
-#define RADIX_DAX_ENTRY_LOCK	(1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
-#define RADIX_DAX_PMD		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_ZERO_PAGE	(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_EMPTY		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
+#define DAX_SHIFT	(4)
+#define DAX_LOCKED	(1UL << 0)
+#define DAX_PMD		(1UL << 1)
+#define DAX_ZERO_PAGE	(1UL << 2)
+#define DAX_EMPTY	(1UL << 3)
 
 static unsigned long dax_radix_pfn(void *entry)
 {
-	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+	return xa_to_value(entry) >> DAX_SHIFT;
 }
 
 static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
 {
-	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
-			(pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
+	return xa_mk_value(flags | ((unsigned long)pfn << DAX_SHIFT) |
+			DAX_LOCKED);
 }
 
 static unsigned int dax_radix_order(void *entry)
 {
-	if ((unsigned long)entry & RADIX_DAX_PMD)
+	if (xa_to_value(entry) & DAX_PMD)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
 
 static int dax_is_pmd_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_PMD;
+	return xa_to_value(entry) & DAX_PMD;
 }
 
 static int dax_is_pte_entry(void *entry)
 {
-	return !((unsigned long)entry & RADIX_DAX_PMD);
+	return !(xa_to_value(entry) & DAX_PMD);
 }
 
 static int dax_is_zero_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
+	return xa_to_value(entry) & DAX_ZERO_PAGE;
 }
 
 static int dax_is_empty_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_EMPTY;
+	return xa_to_value(entry) & DAX_EMPTY;
 }
 
 /*
@@ -186,9 +187,9 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
  */
 static inline int slot_locked(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-	return entry & RADIX_DAX_ENTRY_LOCK;
+	unsigned long entry = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	return entry & DAX_LOCKED;
 }
 
 /*
@@ -196,12 +197,11 @@ static inline int slot_locked(struct address_space *mapping, void **slot)
  */
 static inline void *lock_slot(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
-	entry |= RADIX_DAX_ENTRY_LOCK;
-	radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
-	return (void *)entry;
+	unsigned long v = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	void *entry = xa_mk_value(v | DAX_LOCKED);
+	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
+	return entry;
 }
 
 /*
@@ -209,17 +209,16 @@ static inline void *lock_slot(struct address_space *mapping, void **slot)
  */
 static inline void *unlock_slot(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
-	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
-	radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
-	return (void *)entry;
+	unsigned long v = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	void *entry = xa_mk_value(v & ~DAX_LOCKED);
+	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
+	return entry;
 }
 
 /*
  * Lookup entry in radix tree, wait for it to become unlocked if it is
- * exceptional entry and return it. The caller must call
+ * a DAX entry and return it. The caller must call
  * put_unlocked_mapping_entry() when he decided not to lock the entry or
  * put_locked_mapping_entry() when he locked the entry and now wants to
  * unlock it.
@@ -242,7 +241,7 @@ static void *__get_unlocked_mapping_entry(struct address_space *mapping,
 		entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
 					  &slot);
 		if (!entry ||
-		    WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
+		    WARN_ON_ONCE(!xa_is_value(entry)) ||
 		    !slot_locked(mapping, slot)) {
 			if (slotp)
 				*slotp = slot;
@@ -283,7 +282,7 @@ static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
 
 	xa_lock_irq(&mapping->i_pages);
 	entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
+	if (WARN_ON_ONCE(!entry || !xa_is_value(entry) ||
 			 !slot_locked(mapping, slot))) {
 		xa_unlock_irq(&mapping->i_pages);
 		return;
@@ -472,12 +471,11 @@ void dax_unlock_mapping_entry(struct page *page)
 }
 
 /*
- * Find radix tree entry at given index. If it points to an exceptional entry,
- * return it with the radix tree entry locked. If the radix tree doesn't
- * contain given index, create an empty exceptional entry for the index and
- * return with it locked.
+ * Find radix tree entry at given index. If it is a DAX entry, return it
+ * with the radix tree entry locked. If the radix tree doesn't contain the
+ * given index, create an empty entry for the index and return with it locked.
  *
- * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
+ * When requesting an entry with size DAX_PMD, grab_mapping_entry() will
  * either return that locked entry or will return an error.  This error will
  * happen if there are any 4k entries within the 2MiB range that we are
  * requesting.
@@ -507,13 +505,13 @@ restart:
 	xa_lock_irq(&mapping->i_pages);
 	entry = get_unlocked_mapping_entry(mapping, index, &slot);
 
-	if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
+	if (WARN_ON_ONCE(entry && !xa_is_value(entry))) {
 		entry = ERR_PTR(-EIO);
 		goto out_unlock;
 	}
 
 	if (entry) {
-		if (size_flag & RADIX_DAX_PMD) {
+		if (size_flag & DAX_PMD) {
 			if (dax_is_pte_entry(entry)) {
 				put_unlocked_mapping_entry(mapping, index,
 						entry);
@@ -584,7 +582,7 @@ restart:
 					true);
 		}
 
-		entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
+		entry = dax_radix_locked_entry(0, size_flag | DAX_EMPTY);
 
 		err = __radix_tree_insert(&mapping->i_pages, index,
 				dax_radix_order(entry), entry);
@@ -673,8 +671,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (index >= end)
 				break;
 
-			if (WARN_ON_ONCE(
-			     !radix_tree_exceptional_entry(pvec_ent)))
+			if (WARN_ON_ONCE(!xa_is_value(pvec_ent)))
 				continue;
 
 			xa_lock_irq(&mapping->i_pages);
@@ -713,7 +710,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 
 	xa_lock_irq(pages);
 	entry = get_unlocked_mapping_entry(mapping, index, NULL);
-	if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
+	if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
 		goto out;
 	if (!trunc &&
 	    (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
@@ -729,8 +726,8 @@ out:
 	return ret;
 }
 /*
- * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
- * entry to get unlocked before deleting it.
+ * Delete DAX entry at @index from @mapping.  Wait for it
+ * to be unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
@@ -740,7 +737,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
 	 * radix tree (usually fs-private i_mmap_sem for writing). Since the
-	 * caller has seen exceptional entry for this index, we better find it
+	 * caller has seen a DAX entry for this index, we better find it
 	 * at that index as well...
 	 */
 	WARN_ON_ONCE(!ret);
@@ -748,7 +745,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /*
- * Invalidate exceptional DAX entry if it is clean.
+ * Invalidate DAX entry if it is clean.
  */
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index)
@@ -802,7 +799,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 	if (dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
+	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
 		/* we are replacing a zero page with block mapping */
 		if (dax_is_pmd_entry(entry))
 			unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
@@ -940,13 +937,13 @@ static int dax_writeback_one(struct dax_device *dax_dev,
 	 * A page got tagged dirty in DAX mapping? Something is seriously
 	 * wrong.
 	 */
-	if (WARN_ON(!radix_tree_exceptional_entry(entry)))
+	if (WARN_ON(!xa_is_value(entry)))
 		return -EIO;
 
 	xa_lock_irq(pages);
 	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
 	/* Entry got punched out / reallocated? */
-	if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
+	if (!entry2 || WARN_ON_ONCE(!xa_is_value(entry2)))
 		goto put_unlocked;
 	/*
 	 * Entry got reallocated elsewhere? No need to writeback. We have to
@@ -1123,8 +1120,9 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
 	vm_fault_t ret;
 
-	dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
-			false);
+	dax_insert_mapping_entry(mapping, vmf, entry, pfn,
+			DAX_ZERO_PAGE, false);
+
 	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
 	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
@@ -1514,7 +1512,7 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 
 	pfn = page_to_pfn_t(zero_page);
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
+			DAX_PMD | DAX_ZERO_PAGE, false);
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1597,7 +1595,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * is already in the tree, for instance), it will return -EEXIST and
 	 * we just fall back to 4k entries.
 	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	entry = grab_mapping_entry(mapping, pgoff, DAX_PMD);
 	if (IS_ERR(entry))
 		goto fallback;
 
@@ -1635,7 +1633,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			goto finish_iomap;
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-						RADIX_DAX_PMD, write && !sync);
+						DAX_PMD, write && !sync);
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,