list_lru: dynamically adjust node arrays

We currently use a compile-time constant to size the node array for the
list_lru structure.  Due to this, we don't need to allocate any memory at
initialization time.  But as a consequence, the structures that contain
embedded list_lru lists can become way too big (the superblock for
instance contains two of them).

This patch aims at ameliorating this situation by dynamically allocating
the node arrays with the firmware provided nr_node_ids.

Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: 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>

fs/super.c

@@ -195,8 +195,12 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		INIT_HLIST_NODE(&s->s_instances);
 		INIT_HLIST_BL_HEAD(&s->s_anon);
 		INIT_LIST_HEAD(&s->s_inodes);
-		list_lru_init(&s->s_dentry_lru);
-		list_lru_init(&s->s_inode_lru);
+
+		if (list_lru_init(&s->s_dentry_lru))
+			goto err_out;
+		if (list_lru_init(&s->s_inode_lru))
+			goto err_out_dentry_lru;
+
 		INIT_LIST_HEAD(&s->s_mounts);
 		init_rwsem(&s->s_umount);
 		lockdep_set_class(&s->s_umount, &type->s_umount_key);
@@ -236,6 +240,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	}
 out:
 	return s;
+
+err_out_dentry_lru:
+	list_lru_destroy(&s->s_dentry_lru);
 err_out:
 	security_sb_free(s);
 #ifdef CONFIG_SMP

fs/xfs/xfs_buf.c

@@ -1592,6 +1592,7 @@ xfs_free_buftarg(
 	struct xfs_mount	*mp,
 	struct xfs_buftarg	*btp)
 {
+	list_lru_destroy(&btp->bt_lru);
 	unregister_shrinker(&btp->bt_shrinker);
 
 	if (mp->m_flags & XFS_MOUNT_BARRIER)
@@ -1666,9 +1667,12 @@ xfs_alloc_buftarg(
 	if (!btp->bt_bdi)
 		goto error;
 
-	list_lru_init(&btp->bt_lru);
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
+
+	if (list_lru_init(&btp->bt_lru))
+		goto error;
+
 	btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
 	btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
 	btp->bt_shrinker.seeks = DEFAULT_SEEKS;

fs/xfs/xfs_qm.c

@@ -831,11 +831,18 @@ xfs_qm_init_quotainfo(
 
 	qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP);
 
+	if ((error = list_lru_init(&qinf->qi_lru))) {
+		kmem_free(qinf);
+		mp->m_quotainfo = NULL;
+		return error;
+	}
+
 	/*
 	 * See if quotainodes are setup, and if not, allocate them,
 	 * and change the superblock accordingly.
 	 */
 	if ((error = xfs_qm_init_quotainos(mp))) {
+		list_lru_destroy(&qinf->qi_lru);
 		kmem_free(qinf);
 		mp->m_quotainfo = NULL;
 		return error;
@@ -846,8 +853,6 @@ xfs_qm_init_quotainfo(
 	INIT_RADIX_TREE(&qinf->qi_pquota_tree, GFP_NOFS);
 	mutex_init(&qinf->qi_tree_lock);
 
-	list_lru_init(&qinf->qi_lru);
-
 	/* mutex used to serialize quotaoffs */
 	mutex_init(&qinf->qi_quotaofflock);
 
@@ -935,6 +940,7 @@ xfs_qm_destroy_quotainfo(
 	qi = mp->m_quotainfo;
 	ASSERT(qi != NULL);
 
+	list_lru_destroy(&qi->qi_lru);
 	unregister_shrinker(&qi->qi_shrinker);
 
 	if (qi->qi_uquotaip) {

include/linux/list_lru.h

@@ -27,20 +27,11 @@ struct list_lru_node {
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
-	/*
-	 * Because we use a fixed-size array, 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 different slab cache than the main structure holding this
-	 * structure, we may very well fail.
-	 */
-	struct list_lru_node	node[MAX_NUMNODES];
+	struct list_lru_node	*node;
 	nodemask_t		active_nodes;
 };
 
+void list_lru_destroy(struct list_lru *lru);
 int list_lru_init(struct list_lru *lru);
 
 /**

mm/list_lru.c

@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/list_lru.h>
+#include <linux/slab.h>
 
 bool list_lru_add(struct list_lru *lru, struct list_head *item)
 {
@@ -115,9 +116,14 @@ EXPORT_SYMBOL_GPL(list_lru_walk_node);
 int list_lru_init(struct list_lru *lru)
 {
 	int i;
+	size_t size = sizeof(*lru->node) * nr_node_ids;
+
+	lru->node = kzalloc(size, GFP_KERNEL);
+	if (!lru->node)
+		return -ENOMEM;
 
 	nodes_clear(lru->active_nodes);
-	for (i = 0; i < MAX_NUMNODES; i++) {
+	for (i = 0; i < nr_node_ids; i++) {
 		spin_lock_init(&lru->node[i].lock);
 		INIT_LIST_HEAD(&lru->node[i].list);
 		lru->node[i].nr_items = 0;
@@ -125,3 +131,9 @@ int list_lru_init(struct list_lru *lru)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(list_lru_init);
+
+void list_lru_destroy(struct list_lru *lru)
+{
+	kfree(lru->node);
+}
+EXPORT_SYMBOL_GPL(list_lru_destroy);