[RFC 4/6] mm, thp: introduce a controller to trigger zero subpages reclaim

[Ning Zhang <ningzhang@xxxxxxxxxxxxxxxxx>]

Add a new controller named "reclaim" for memory.thp_reclaim_ctrl
to trigger thp reclaim immediately:

  echo "reclaim 1" > memory.thp_reclaim_ctrl
  echo "reclaim 2" > memory.thp_reclaim_ctrl

"reclaim 1" means triggering reclaim only for current memcg.
"reclaim 2" means triggering reclaim for current memcg and it's
children memcgs.

Signed-off-by: Ning Zhang <ningzhang@xxxxxxxxxxxxxxxxx>
---
 include/linux/huge_mm.h |  1 +
 mm/huge_memory.c        | 29 +++++++++++++++++++++++++++++
 mm/memcontrol.c         | 27 +++++++++++++++++++++++++++
 3 files changed, 57 insertions(+)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 304e3df..f792433 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -190,6 +190,7 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 int zsr_get_hpage(struct hpage_reclaim *hr_queue, struct page **reclaim_page,
 		  int threshold);
 unsigned long zsr_reclaim_hpage(struct lruvec *lruvec, struct page *page);
+void zsr_reclaim_memcg(struct mem_cgroup *memcg);
 static inline struct list_head *hpage_reclaim_list(struct page *page)
 {
 	return &page[3].hpage_reclaim_list;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 40a9879..633fd0f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3541,4 +3541,33 @@ unsigned long zsr_reclaim_hpage(struct lruvec *lruvec, struct page *page)
 
 	return reclaimed;
 }
+
+void zsr_reclaim_memcg(struct mem_cgroup *memcg)
+{
+	struct lruvec *lruvec;
+	struct hpage_reclaim *hr_queue;
+	int threshold, nid;
+
+	if (get_thp_reclaim_mode(memcg) == THP_RECLAIM_DISABLE)
+		return;
+
+	threshold = READ_ONCE(memcg->thp_reclaim_threshold);
+	for_each_online_node(nid) {
+		lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+		hr_queue = &memcg->nodeinfo[nid]->hpage_reclaim_queue;
+		for ( ; ; ) {
+			struct page *page = NULL;
+
+			if (zsr_get_hpage(hr_queue, &page, threshold))
+				break;
+
+			if (!page)
+				continue;
+
+			zsr_reclaim_hpage(lruvec, page);
+
+			cond_resched();
+		}
+	}
+}
 #endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7ba3c69..a8e3ca1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4521,6 +4521,8 @@ static int memcg_thp_reclaim_ctrl_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+#define CTRL_RECLAIM_MEMCG 1 /* only relciam current memcg */
+#define CTRL_RECLAIM_ALL   2 /* reclaim current memcg and all the children memcgs */
 static ssize_t memcg_thp_reclaim_ctrl_write(struct kernfs_open_file *of,
 					    char *buf, size_t nbytes,
 					    loff_t off)
@@ -4548,6 +4550,31 @@ static ssize_t memcg_thp_reclaim_ctrl_write(struct kernfs_open_file *of,
 			return -EINVAL;
 
 		xchg(&memcg->thp_reclaim_threshold, threshold);
+	} else if (!strcmp(key, "reclaim")) {
+		struct mem_cgroup *iter;
+		int mode;
+
+		value = strsep_s(&buf, " \t\n");
+		if (!value)
+			return -EINVAL;
+
+		ret = kstrtouint(value, 0, &mode);
+		if (ret)
+			return ret;
+
+		switch (mode) {
+		case CTRL_RECLAIM_MEMCG:
+			zsr_reclaim_memcg(memcg);
+			break;
+		case CTRL_RECLAIM_ALL:
+			iter = mem_cgroup_iter(memcg, NULL, NULL);
+			do {
+				zsr_reclaim_memcg(iter);
+			} while ((iter = mem_cgroup_iter(memcg, iter, NULL)));
+			break;
+		default:
+			return -EINVAL;
+		}
 	} else
 		return -EINVAL;
 
-- 
1.8.3.1