1 files changed, 47 insertions, 1 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2929c24c22b7..71cb253368cb 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2301,6 +2301,35 @@ static void sp_free(struct sp_node *n)
         kmem_cache_free(sn_cache, n);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
+{
+        /* Never defer a private fault */
+        if (cpupid_match_pid(p, last_cpupid))
+                return false;
+
+        if (p->numa_migrate_deferred) {
+                p->numa_migrate_deferred--;
+                return true;
+        }
+        return false;
+}
+
+static inline void defer_numa_migrate(struct task_struct *p)
+{
+        p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
+}
+#else
+static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
+{
+        return false;
+}
+
+static inline void defer_numa_migrate(struct task_struct *p)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2402,7 +2431,24 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
                  * relation.
                  */
                 last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
-                if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid)
+                if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
+
+                        /* See sysctl_numa_balancing_migrate_deferred comment */
+                        if (!cpupid_match_pid(current, last_cpupid))
+                                defer_numa_migrate(current);
+
+                        goto out;
+                }
+
+                /*
+                 * The quadratic filter above reduces extraneous migration
+                 * of shared pages somewhat. This code reduces it even more,
+                 * reducing the overhead of page migrations of shared pages.
+                 * This makes workloads with shared pages rely more on
+                 * "move task near its memory", and less on "move memory
+                 * towards its task", which is exactly what we want.
+                 */
+                if (numa_migrate_deferred(current, last_cpupid))
                         goto out;
         }