2 files changed, 59 insertions, 13 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6831abb..0a349dd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -780,10 +780,13 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_NUMA_BALANCING
 /*
- * numa task sample period in ms: 5s
+ * numa task sample period in ms
  */
-unsigned int sysctl_numa_balancing_scan_period_min = 5000;
-unsigned int sysctl_numa_balancing_scan_period_max = 5000*16;
+unsigned int sysctl_numa_balancing_scan_period_min = 100;
+unsigned int sysctl_numa_balancing_scan_period_max = 100*16;
+
+/* Portion of address space to scan in MB */
+unsigned int sysctl_numa_balancing_scan_size = 256;
 
 static void task_numa_placement(struct task_struct *p)
 {
@@ -808,6 +811,12 @@ void task_numa_fault(int node, int pages)
 	task_numa_placement(p);
 }
 
+static void reset_ptenuma_scan(struct task_struct *p)
+{
+	ACCESS_ONCE(p->mm->numa_scan_seq)++;
+	p->mm->numa_scan_offset = 0;
+}
+
 /*
  * The expensive part of numa migration is done from task_work context.
  * Triggered from task_tick_numa().
@@ -817,6 +826,9 @@ void task_numa_work(struct callback_head *work)
 	unsigned long migrate, next_scan, now = jiffies;
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
+	struct vm_area_struct *vma;
+	unsigned long offset, end;
+	long length;
 
 	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
 
@@ -846,18 +858,45 @@ void task_numa_work(struct callback_head *work)
 	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
 		return;
 
-	ACCESS_ONCE(mm->numa_scan_seq)++;
-	{
-		struct vm_area_struct *vma;
+	offset = mm->numa_scan_offset;
+	length = sysctl_numa_balancing_scan_size;
+	length <<= 20;
 
-		down_read(&mm->mmap_sem);
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			if (!vma_migratable(vma))
-				continue;
-			change_prot_numa(vma, vma->vm_start, vma->vm_end);
-		}
-		up_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, offset);
+	if (!vma) {
+		reset_ptenuma_scan(p);
+		offset = 0;
+		vma = mm->mmap;
+	}
+	for (; vma && length > 0; vma = vma->vm_next) {
+		if (!vma_migratable(vma))
+			continue;
+
+		/* Skip small VMAs. They are not likely to be of relevance */
+		if (((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < HPAGE_PMD_NR)
+			continue;
+
+		offset = max(offset, vma->vm_start);
+		end = min(ALIGN(offset + length, HPAGE_SIZE), vma->vm_end);
+		length -= end - offset;
+
+		change_prot_numa(vma, offset, end);
+
+		offset = end;
 	}
+
+	/*
+	 * It is possible to reach the end of the VMA list but the last few VMAs are
+	 * not guaranteed to the vma_migratable. If they are not, we would find the
+	 * !migratable VMA on the next scan but not reset the scanner to the start
+	 * so check it now.
+	 */
+	if (vma)
+		mm->numa_scan_offset = offset;
+	else
+		reset_ptenuma_scan(p);
+	up_read(&mm->mmap_sem);
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 025e1ae..7d3a2e0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -366,6 +366,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing_scan_size_mb",
+		.data		= &sysctl_numa_balancing_scan_size,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{