mm/swap: use nr_node_ids for avail_lists in swap_info_struct

Since a2468cc9bfdf ("swap: choose swap device according to numa node"),
avail_lists field of swap_info_struct is changed to an array with
MAX_NUMNODES elements.  This made swap_info_struct size increased to 40KiB
and needs an order-4 page to hold it.

This is not optimal in that:
1 Most systems have way less than MAX_NUMNODES(1024) nodes so it
  is a waste of memory;
2 It could cause swapon failure if the swap device is swapped on
  after system has been running for a while, due to no order-4
  page is available as pointed out by Vasily Averin.

Solve the above two issues by using nr_node_ids(which is the actual
possible node number the running system has) for avail_lists instead of
MAX_NUMNODES.

nr_node_ids is unknown at compile time so can't be directly used when
declaring this array.  What I did here is to declare avail_lists as zero
element array and allocate space for it when allocating space for
swap_info_struct.  The reason why keep using array but not pointer is
plist_for_each_entry needs the field to be part of the struct, so pointer
will not work.

This patch is on top of Vasily Averin's fix commit.  I think the use of
kvzalloc for swap_info_struct is still needed in case nr_node_ids is
really big on some systems.

Link: http://lkml.kernel.org/r/20181115083847.GA11129@intel.com
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vasily Averin <vvs@virtuozzo.com>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 12 insertions, 2 deletions

diff --git a/include/linux/swap.h b/include/linux/swap.h
index f9e576a2c188..622025ac1461 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -235,7 +235,6 @@ struct swap_info_struct {
 	unsigned long	flags;		/* SWP_USED etc: see above */
 	signed short	prio;		/* swap priority of this type */
 	struct plist_node list;		/* entry in swap_active_head */
-	struct plist_node avail_lists[MAX_NUMNODES];/* entry in swap_avail_heads */
 	signed char	type;		/* strange name for an index */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
@@ -276,6 +275,16 @@ struct swap_info_struct {
 					 */
 	struct work_struct discard_work; /* discard worker */
 	struct swap_cluster_list discard_clusters; /* discard clusters list */
+	struct plist_node avail_lists[0]; /*
+					   * entries in swap_avail_heads, one
+					   * entry per node.
+					   * Must be last as the number of the
+					   * array is nr_node_ids, which is not
+					   * a fixed value so have to allocate
+					   * dynamically.
+					   * And it has to be an array so that
+					   * plist_for_each_* can work.
+					   */
 };
 
 #ifdef CONFIG_64BIT
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8688ae65ef58..6e06821623f6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2812,8 +2812,9 @@ static struct swap_info_struct *alloc_swap_info(void)
 	struct swap_info_struct *p;
 	unsigned int type;
 	int i;
+	int size = sizeof(*p) + nr_node_ids * sizeof(struct plist_node);
 
-	p = kvzalloc(sizeof(*p), GFP_KERNEL);
+	p = kvzalloc(size, GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);