Commit 14b46879 authored by Johannes Weiner's avatar Johannes Weiner Committed by Linus Torvalds
Browse files

mm: workingset: move shadow entry tracking to radix tree exceptional tracking 

Currently, we track the shadow entries in the page cache in the upper
bits of the radix_tree_node->count, behind the back of the radix tree
implementation.  Because the radix tree code has no awareness of them,
we rely on random subtleties throughout the implementation (such as the
node->count != 1 check in the shrinking code, which is meant to exclude
multi-entry nodes but also happens to skip nodes with only one shadow
entry, as that's accounted in the upper bits).  This is error prone and
has, in fact, caused the bug fixed in d3798ae8 ("mm: filemap: don't
plant shadow entries without radix tree node").

To remove these subtleties, this patch moves shadow entry tracking from
the upper bits of node->count to the existing counter for exceptional
entries.  node->count goes back to being a simple counter of valid
entries in the tree node and can be shrunk to a single byte.

This vastly simplifies the page cache code.  All accounting happens
natively inside the radix tree implementation, and maintaining the LRU
linkage of shadow nodes is consolidated into a single function in the
workingset code that is called for leaf nodes affected by a change in
the page cache tree.

This also removes the last user of the __radix_delete_node() return
value.  Eliminate it.

Link: http://lkml.kernel.org/r/20161117193211.GE23430@cmpxchg.org


Signed-off-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Reviewed-by: default avatarJan Kara <jack@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <mawilcox@linuxonhyperv.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 4d693d08

include/linux/radix-tree.h

+2 −6
Original line number Diff line number Diff line
@@ -80,14 +80,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) 
#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \

					  RADIX_TREE_MAP_SHIFT))



/* Internally used bits of node->count */

#define RADIX_TREE_COUNT_SHIFT	(RADIX_TREE_MAP_SHIFT + 1)

#define RADIX_TREE_COUNT_MASK	((1UL << RADIX_TREE_COUNT_SHIFT) - 1)



struct radix_tree_node {

	unsigned char	shift;		/* Bits remaining in each slot */

	unsigned char	offset;		/* Slot offset in parent */

	unsigned int	count;		/* Total entry count */

	unsigned char	count;		/* Total entry count */

	unsigned char	exceptional;	/* Exceptional entry count */

	union {

		struct {
@@ -270,7 +266,7 @@ void __radix_tree_replace(struct radix_tree_root *root, 
			  radix_tree_update_node_t update_node, void *private);

void radix_tree_replace_slot(struct radix_tree_root *root,

			     void **slot, void *item);

bool __radix_tree_delete_node(struct radix_tree_root *root,

void __radix_tree_delete_node(struct radix_tree_root *root,

			      struct radix_tree_node *node);

void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);

void *radix_tree_delete(struct radix_tree_root *, unsigned long);

include/linux/swap.h

+1 −33
Original line number Diff line number Diff line
@@ -246,39 +246,7 @@ struct swap_info_struct { 
void *workingset_eviction(struct address_space *mapping, struct page *page);

bool workingset_refault(void *shadow);

void workingset_activation(struct page *page);

extern struct list_lru workingset_shadow_nodes;



static inline unsigned int workingset_node_pages(struct radix_tree_node *node)

{

	return node->count & RADIX_TREE_COUNT_MASK;

}



static inline void workingset_node_pages_inc(struct radix_tree_node *node)

{

	node->count++;

}



static inline void workingset_node_pages_dec(struct radix_tree_node *node)

{

	VM_WARN_ON_ONCE(!workingset_node_pages(node));

	node->count--;

}



static inline unsigned int workingset_node_shadows(struct radix_tree_node *node)

{

	return node->count >> RADIX_TREE_COUNT_SHIFT;

}



static inline void workingset_node_shadows_inc(struct radix_tree_node *node)

{

	node->count += 1U << RADIX_TREE_COUNT_SHIFT;

}



static inline void workingset_node_shadows_dec(struct radix_tree_node *node)

{

	VM_WARN_ON_ONCE(!workingset_node_shadows(node));

	node->count -= 1U << RADIX_TREE_COUNT_SHIFT;

}

void workingset_update_node(struct radix_tree_node *node, void *private);



/* linux/mm/page_alloc.c */

extern unsigned long totalram_pages;

lib/radix-tree.c

+6 −19
Original line number Diff line number Diff line
@@ -541,12 +541,10 @@ out: 
 *	radix_tree_shrink    -    shrink radix tree to minimum height

 *	@root		radix tree root

 */

static inline bool radix_tree_shrink(struct radix_tree_root *root,

static inline void radix_tree_shrink(struct radix_tree_root *root,

				     radix_tree_update_node_t update_node,

				     void *private)

{

	bool shrunk = false;



	for (;;) {

		struct radix_tree_node *node = root->rnode;

		struct radix_tree_node *child;
@@ -606,26 +604,20 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root, 
		}



		radix_tree_node_free(node);

		shrunk = true;

	}



	return shrunk;

}



static bool delete_node(struct radix_tree_root *root,

static void delete_node(struct radix_tree_root *root,

			struct radix_tree_node *node,

			radix_tree_update_node_t update_node, void *private)

{

	bool deleted = false;



	do {

		struct radix_tree_node *parent;



		if (node->count) {

			if (node == entry_to_node(root->rnode))

				deleted |= radix_tree_shrink(root, update_node,

							     private);

			return deleted;

				radix_tree_shrink(root, update_node, private);

			return;

		}



		parent = node->parent;
@@ -638,12 +630,9 @@ static bool delete_node(struct radix_tree_root *root, 
		}



		radix_tree_node_free(node);

		deleted = true;



		node = parent;

	} while (node);



	return deleted;

}



/**
@@ -1595,13 +1584,11 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) 
 *	After clearing the slot at @index in @node from radix tree

 *	rooted at @root, call this function to attempt freeing the

 *	node and shrinking the tree.

 *

 *	Returns %true if @node was freed, %false otherwise.

 */

bool __radix_tree_delete_node(struct radix_tree_root *root,

void __radix_tree_delete_node(struct radix_tree_root *root,

			      struct radix_tree_node *node)

{

	return delete_node(root, node, NULL, NULL);

	delete_node(root, node, NULL, NULL);

}



static inline void delete_sibling_entries(struct radix_tree_node *node,

mm/filemap.c

+5 −49
Original line number Diff line number Diff line
@@ -132,37 +132,19 @@ static int page_cache_tree_insert(struct address_space *mapping, 
		if (!dax_mapping(mapping)) {

			if (shadowp)

				*shadowp = p;

			if (node)

				workingset_node_shadows_dec(node);

		} else {

			/* DAX can replace empty locked entry with a hole */

			WARN_ON_ONCE(p !=

				(void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |

					 RADIX_DAX_ENTRY_LOCK));

			/* DAX accounts exceptional entries as normal pages */

			if (node)

				workingset_node_pages_dec(node);

			/* Wakeup waiters for exceptional entry lock */

			dax_wake_mapping_entry_waiter(mapping, page->index,

						      false);

		}

	}

	radix_tree_replace_slot(&mapping->page_tree, slot, page);

	__radix_tree_replace(&mapping->page_tree, node, slot, page,

			     workingset_update_node, mapping);

	mapping->nrpages++;

	if (node) {

		workingset_node_pages_inc(node);

		/*

		 * Don't track node that contains actual pages.

		 *

		 * Avoid acquiring the list_lru lock if already

		 * untracked.  The list_empty() test is safe as

		 * node->private_list is protected by

		 * mapping->tree_lock.

		 */

		if (!list_empty(&node->private_list))

			list_lru_del(&workingset_shadow_nodes,

				     &node->private_list);

	}

	return 0;

}
@@ -185,8 +167,6 @@ static void page_cache_tree_delete(struct address_space *mapping, 
		__radix_tree_lookup(&mapping->page_tree, page->index + i,

				    &node, &slot);



		radix_tree_clear_tags(&mapping->page_tree, node, slot);



		if (!node) {

			VM_BUG_ON_PAGE(nr != 1, page);

			/*
@@ -196,33 +176,9 @@ static void page_cache_tree_delete(struct address_space *mapping, 
			shadow = NULL;

		}



		radix_tree_replace_slot(&mapping->page_tree, slot, shadow);



		if (!node)

			break;



		workingset_node_pages_dec(node);

		if (shadow)

			workingset_node_shadows_inc(node);

		else

			if (__radix_tree_delete_node(&mapping->page_tree, node))

				continue;



		/*

		 * Track node that only contains shadow entries. DAX mappings

		 * contain no shadow entries and may contain other exceptional

		 * entries so skip those.

		 *

		 * Avoid acquiring the list_lru lock if already tracked.

		 * The list_empty() test is safe as node->private_list is

		 * protected by mapping->tree_lock.

		 */

		if (!dax_mapping(mapping) && !workingset_node_pages(node) &&

				list_empty(&node->private_list)) {

			node->private_data = mapping;

			list_lru_add(&workingset_shadow_nodes,

					&node->private_list);

		}

		radix_tree_clear_tags(&mapping->page_tree, node, slot);

		__radix_tree_replace(&mapping->page_tree, node, slot, shadow,

				     workingset_update_node, mapping);

	}



	if (shadow) {

mm/truncate.c

+3 −18
Original line number Diff line number Diff line
@@ -44,28 +44,13 @@ static void clear_exceptional_entry(struct address_space *mapping, 
	 * without the tree itself locked.  These unlocked entries

	 * need verification under the tree lock.

	 */

	if (!__radix_tree_lookup(&mapping->page_tree, index, &node,

				&slot))

	if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot))

		goto unlock;

	if (*slot != entry)

		goto unlock;

	radix_tree_replace_slot(&mapping->page_tree, slot, NULL);

	__radix_tree_replace(&mapping->page_tree, node, slot, NULL,

			     workingset_update_node, mapping);

	mapping->nrexceptional--;

	if (!node)

		goto unlock;

	workingset_node_shadows_dec(node);

	/*

	 * Don't track node without shadow entries.

	 *

	 * Avoid acquiring the list_lru lock if already untracked.

	 * The list_empty() test is safe as node->private_list is

	 * protected by mapping->tree_lock.

	 */

	if (!workingset_node_shadows(node) &&

	    !list_empty(&node->private_list))

		list_lru_del(&workingset_shadow_nodes,

				&node->private_list);

	__radix_tree_delete_node(&mapping->page_tree, node);

unlock:

	spin_unlock_irq(&mapping->tree_lock);

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE