diff options
authorAaron Lu <aaron.lu@intel.com>2018-12-28 00:34:39 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2019-01-26 09:37:06 +0100
commit4fb12a087a80dbedf56e4157b755bdea958aae7e (patch)
parent694c20fe01729c6b96f5fb7dbeb8bb85b7c9af91 (diff)
mm/swap: use nr_node_ids for avail_lists in swap_info_struct
[ Upstream commit 66f71da9dd38af17dc17209cdde7987d4679a699 ] 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> Signed-off-by: Sasha Levin <sashal@kernel.org>
2 files changed, 12 insertions, 2 deletions
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f02fb5db8914..4fd1ab9565ba 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -231,7 +231,6 @@ 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 */
@@ -272,6 +271,16 @@ 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 af3c4c5a0b4e..4f9e522643a2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2830,8 +2830,9 @@ 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);