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, 29 insertions, 39 deletions

diff --git a/mm/workingset.c b/mm/workingset.c
index cbc13d4dfa79..d46f8c92aa2f 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -160,20 +160,20 @@
  * and activations is maintained (node->inactive_age).
  *
  * On eviction, a snapshot of this counter (along with some bits to
- * identify the node) is stored in the now empty page cache radix tree
+ * identify the node) is stored in the now empty page cache
  * slot of the evicted page.  This is called a shadow entry.
  *
  * On cache misses for which there are shadow entries, an eligible
  * refault distance will immediately activate the refaulting page.
  */
 
-#define EVICTION_SHIFT	(RADIX_TREE_EXCEPTIONAL_ENTRY + \
+#define EVICTION_SHIFT	((BITS_PER_LONG - BITS_PER_XA_VALUE) +	\
 			 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT)
 #define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)
 
 /*
  * Eviction timestamps need to be able to cover the full range of
- * actionable refaults. However, bits are tight in the radix tree
+ * actionable refaults. However, bits are tight in the xarray
  * entry, and after storing the identifier for the lruvec there might
  * not be enough left to represent every single actionable refault. In
  * that case, we have to sacrifice granularity for distance, and group
@@ -185,22 +185,21 @@ static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
 			 bool workingset)
 {
 	eviction >>= bucket_order;
+	eviction &= EVICTION_MASK;
 	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
 	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
 	eviction = (eviction << 1) | workingset;
-	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, bool *workingsetp)
 {
-	unsigned long entry = (unsigned long)shadow;
+	unsigned long entry = xa_to_value(shadow);
 	int memcgid, nid;
 	bool workingset;
 
-	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
 	workingset = entry & 1;
 	entry >>= 1;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
@@ -367,7 +366,7 @@ out:
 
 static struct list_lru shadow_nodes;
 
-void workingset_update_node(struct radix_tree_node *node)
+void workingset_update_node(struct xa_node *node)
 {
 	/*
 	 * Track non-empty nodes that contain only shadow entries;
@@ -379,7 +378,7 @@ void workingset_update_node(struct radix_tree_node *node)
 	 */
 	VM_WARN_ON_ONCE(!irqs_disabled());  /* For __inc_lruvec_page_state */
 
-	if (node->count && node->count == node->exceptional) {
+	if (node->count && node->count == node->nr_values) {
 		if (list_empty(&node->private_list)) {
 			list_lru_add(&shadow_nodes, &node->private_list);
 			__inc_lruvec_page_state(virt_to_page(node),
@@ -404,7 +403,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	nodes = list_lru_shrink_count(&shadow_nodes, sc);
 
 	/*
-	 * Approximate a reasonable limit for the radix tree nodes
+	 * Approximate a reasonable limit for the nodes
 	 * containing shadow entries. We don't need to keep more
 	 * shadow entries than possible pages on the active list,
 	 * since refault distances bigger than that are dismissed.
@@ -419,11 +418,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	 * worst-case density of 1/8th. Below that, not all eligible
 	 * refaults can be detected anymore.
 	 *
-	 * On 64-bit with 7 radix_tree_nodes per page and 64 slots
+	 * On 64-bit with 7 xa_nodes per page and 64 slots
 	 * each, this will reclaim shadow entries when they consume
 	 * ~1.8% of available memory:
 	 *
-	 * PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE
+	 * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
 	 */
 #ifdef CONFIG_MEMCG
 	if (sc->memcg) {
@@ -438,7 +437,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 #endif
 		pages = node_present_pages(sc->nid);
 
-	max_nodes = pages >> (RADIX_TREE_MAP_SHIFT - 3);
+	max_nodes = pages >> (XA_CHUNK_SHIFT - 3);
 
 	if (!nodes)
 		return SHRINK_EMPTY;
@@ -451,11 +450,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 static enum lru_status shadow_lru_isolate(struct list_head *item,
 					  struct list_lru_one *lru,
 					  spinlock_t *lru_lock,
-					  void *arg)
+					  void *arg) __must_hold(lru_lock)
 {
+	struct xa_node *node = container_of(item, struct xa_node, private_list);
+	XA_STATE(xas, node->array, 0);
 	struct address_space *mapping;
-	struct radix_tree_node *node;
-	unsigned int i;
 	int ret;
 
 	/*
@@ -463,15 +462,14 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * the shadow node LRU under the i_pages lock and the
 	 * lru_lock.  Because the page cache tree is emptied before
 	 * the inode can be destroyed, holding the lru_lock pins any
-	 * address_space that has radix tree nodes on the LRU.
+	 * address_space that has nodes on the LRU.
 	 *
 	 * We can then safely transition to the i_pages lock to
 	 * pin only the address_space of the particular node we want
 	 * to reclaim, take the node off-LRU, and drop the lru_lock.
 	 */
 
-	node = container_of(item, struct radix_tree_node, private_list);
-	mapping = container_of(node->root, struct address_space, i_pages);
+	mapping = container_of(node->array, struct address_space, i_pages);
 
 	/* Coming from the list, invert the lock order */
 	if (!xa_trylock(&mapping->i_pages)) {
@@ -490,29 +488,21 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * no pages, so we expect to be able to remove them all and
 	 * delete and free the empty node afterwards.
 	 */
-	if (WARN_ON_ONCE(!node->exceptional))
+	if (WARN_ON_ONCE(!node->nr_values))
 		goto out_invalid;
-	if (WARN_ON_ONCE(node->count != node->exceptional))
-		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])))
-				goto out_invalid;
-			if (WARN_ON_ONCE(!node->exceptional))
-				goto out_invalid;
-			if (WARN_ON_ONCE(!mapping->nrexceptional))
-				goto out_invalid;
-			node->slots[i] = NULL;
-			node->exceptional--;
-			node->count--;
-			mapping->nrexceptional--;
-		}
-	}
-	if (WARN_ON_ONCE(node->exceptional))
+	if (WARN_ON_ONCE(node->count != node->nr_values))
 		goto out_invalid;
+	mapping->nrexceptional -= node->nr_values;
+	xas.xa_node = xa_parent_locked(&mapping->i_pages, node);
+	xas.xa_offset = node->offset;
+	xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
+	xas_set_update(&xas, workingset_update_node);
+	/*
+	 * We could store a shadow entry here which was the minimum of the
+	 * shadow entries we were tracking ...
+	 */
+	xas_store(&xas, NULL);
 	__inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
-	__radix_tree_delete_node(&mapping->i_pages, node,
-				 workingset_lookup_update(mapping));
 
 out_invalid:
 	xa_unlock_irq(&mapping->i_pages);