list_lru: per-node list infrastructure

Now that we have an LRU list API, we can start to enhance the
implementation.  This splits the single LRU list into per-node lists and
locks to enhance scalability.  Items are placed on lists according to the
node the memory belongs to.  To make scanning the lists efficient, also
track whether the per-node lists have entries in them in a active
nodemask.

Note: We use a fixed-size array for the node LRU, this struct can be very
big if MAX_NUMNODES is big.  If this becomes a problem this is fixable by
turning this into a pointer and dynamically allocating this to
nr_node_ids.  This quantity is firwmare-provided, and still would provide
room for all nodes at the cost of a pointer lookup and an extra
allocation.  Because that allocation will most likely come from a may very
well fail.

[glommer@openvz.org: fix warnings, added note about node lru]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Greg Thelen <gthelen@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Carlos Maiolino <cmaiolino@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Rientjes <rientjes@google.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: J. Bruce Fields <bfields@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Kent Overstreet <koverstreet@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 111 insertions, 35 deletions

diff --git a/mm/list_lru.c b/mm/list_lru.c
index dd74c5434cd8..1efe4ecc02b1 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -6,41 +6,73 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mm.h>
 #include <linux/list_lru.h>
 
 bool list_lru_add(struct list_lru *lru, struct list_head *item)
 {
-	spin_lock(&lru->lock);
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+
+	spin_lock(&nlru->lock);
+	WARN_ON_ONCE(nlru->nr_items < 0);
 	if (list_empty(item)) {
-		list_add_tail(item, &lru->list);
-		lru->nr_items++;
-		spin_unlock(&lru->lock);
+		list_add_tail(item, &nlru->list);
+		if (nlru->nr_items++ == 0)
+			node_set(nid, lru->active_nodes);
+		spin_unlock(&nlru->lock);
 		return true;
 	}
-	spin_unlock(&lru->lock);
+	spin_unlock(&nlru->lock);
 	return false;
 }
 EXPORT_SYMBOL_GPL(list_lru_add);
 
 bool list_lru_del(struct list_lru *lru, struct list_head *item)
 {
-	spin_lock(&lru->lock);
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+
+	spin_lock(&nlru->lock);
 	if (!list_empty(item)) {
 		list_del_init(item);
-		lru->nr_items--;
-		spin_unlock(&lru->lock);
+		if (--nlru->nr_items == 0)
+			node_clear(nid, lru->active_nodes);
+		WARN_ON_ONCE(nlru->nr_items < 0);
+		spin_unlock(&nlru->lock);
 		return true;
 	}
-	spin_unlock(&lru->lock);
+	spin_unlock(&nlru->lock);
 	return false;
 }
 EXPORT_SYMBOL_GPL(list_lru_del);
 
-unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
-			    void *cb_arg, unsigned long nr_to_walk)
+unsigned long list_lru_count(struct list_lru *lru)
 {
+	unsigned long count = 0;
+	int nid;
+
+	for_each_node_mask(nid, lru->active_nodes) {
+		struct list_lru_node *nlru = &lru->node[nid];
+
+		spin_lock(&nlru->lock);
+		WARN_ON_ONCE(nlru->nr_items < 0);
+		count += nlru->nr_items;
+		spin_unlock(&nlru->lock);
+	}
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(list_lru_count);
+
+static unsigned long
+list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
+		   void *cb_arg, unsigned long *nr_to_walk)
+{
+
+	struct list_lru_node	*nlru = &lru->node[nid];
 	struct list_head *item, *n;
-	unsigned long removed = 0;
+	unsigned long isolated = 0;
 	/*
 	 * If we don't keep state of at which pass we are, we can loop at
 	 * LRU_RETRY, since we have no guarantees that the caller will be able
@@ -50,18 +82,20 @@ unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
 	 */
 	bool first_pass = true;
 
-	spin_lock(&lru->lock);
+	spin_lock(&nlru->lock);
 restart:
-	list_for_each_safe(item, n, &lru->list) {
+	list_for_each_safe(item, n, &nlru->list) {
 		enum lru_status ret;
-		ret = isolate(item, &lru->lock, cb_arg);
+		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
 		case LRU_REMOVED:
-			lru->nr_items--;
-			removed++;
+			if (--nlru->nr_items == 0)
+				node_clear(nid, lru->active_nodes);
+			WARN_ON_ONCE(nlru->nr_items < 0);
+			isolated++;
 			break;
 		case LRU_ROTATE:
-			list_move_tail(item, &lru->list);
+			list_move_tail(item, &nlru->list);
 			break;
 		case LRU_SKIP:
 			break;
@@ -76,42 +110,84 @@ restart:
 			BUG();
 		}
 
-		if (nr_to_walk-- == 0)
+		if ((*nr_to_walk)-- == 0)
 			break;
 
 	}
-	spin_unlock(&lru->lock);
-	return removed;
+
+	spin_unlock(&nlru->lock);
+	return isolated;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_node);
+
+unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
+			    void *cb_arg, unsigned long nr_to_walk)
+{
+	unsigned long isolated = 0;
+	int nid;
+
+	for_each_node_mask(nid, lru->active_nodes) {
+		isolated += list_lru_walk_node(lru, nid, isolate,
+					       cb_arg, &nr_to_walk);
+		if (nr_to_walk <= 0)
+			break;
+	}
+	return isolated;
 }
 EXPORT_SYMBOL_GPL(list_lru_walk);
 
-unsigned long list_lru_dispose_all(struct list_lru *lru,
-				   list_lru_dispose_cb dispose)
+static unsigned long list_lru_dispose_all_node(struct list_lru *lru, int nid,
+					       list_lru_dispose_cb dispose)
 {
-	unsigned long disposed = 0;
+	struct list_lru_node	*nlru = &lru->node[nid];
 	LIST_HEAD(dispose_list);
+	unsigned long disposed = 0;
 
-	spin_lock(&lru->lock);
-	while (!list_empty(&lru->list)) {
-		list_splice_init(&lru->list, &dispose_list);
-		disposed += lru->nr_items;
-		lru->nr_items = 0;
-		spin_unlock(&lru->lock);
+	spin_lock(&nlru->lock);
+	while (!list_empty(&nlru->list)) {
+		list_splice_init(&nlru->list, &dispose_list);
+		disposed += nlru->nr_items;
+		nlru->nr_items = 0;
+		node_clear(nid, lru->active_nodes);
+		spin_unlock(&nlru->lock);
 
 		dispose(&dispose_list);
 
-		spin_lock(&lru->lock);
+		spin_lock(&nlru->lock);
 	}
-	spin_unlock(&lru->lock);
+	spin_unlock(&nlru->lock);
 	return disposed;
 }
 
+unsigned long list_lru_dispose_all(struct list_lru *lru,
+				   list_lru_dispose_cb dispose)
+{
+	unsigned long disposed;
+	unsigned long total = 0;
+	int nid;
+
+	do {
+		disposed = 0;
+		for_each_node_mask(nid, lru->active_nodes) {
+			disposed += list_lru_dispose_all_node(lru, nid,
+							      dispose);
+		}
+		total += disposed;
+	} while (disposed != 0);
+
+	return total;
+}
+
 int list_lru_init(struct list_lru *lru)
 {
-	spin_lock_init(&lru->lock);
-	INIT_LIST_HEAD(&lru->list);
-	lru->nr_items = 0;
+	int i;
 
+	nodes_clear(lru->active_nodes);
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		spin_lock_init(&lru->node[i].lock);
+		INIT_LIST_HEAD(&lru->node[i].list);
+		lru->node[i].nr_items = 0;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(list_lru_init);