Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zi Yan <zi.yan@sent.com>
To:     Dave Hansen <dave.hansen@linux.intel.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        Keith Busch <keith.busch@intel.com>,
        Fengguang Wu <fengguang.wu@intel.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Cc:     Daniel Jordan <daniel.m.jordan@oracle.com>,
        Michal Hocko <mhocko@kernel.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Mel Gorman <mgorman@techsingularity.net>,
        John Hubbard <jhubbard@nvidia.com>,
        Mark Hairgrove <mhairgrove@nvidia.com>,
        Nitin Gupta <nigupta@nvidia.com>,
        Javier Cabezas <jcabezas@nvidia.com>,
        David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 18/25] memcg: Add per node memory usage&max stats in memcg.
Date:   Wed,  3 Apr 2019 19:00:39 -0700
Message-Id: <20190404020046.32741-19-zi.yan@sent.com>
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>
References: <20190404020046.32741-1-zi.yan@sent.com>
Reply-To: ziy@nvidia.com
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Zi Yan <ziy@nvidia.com>

It prepares for the following patches to enable memcg-based NUMA
node page migration. We are going to limit memory usage in each node
on a per-memcg basis.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/cgroup-defs.h |  1 +
 include/linux/memcontrol.h  | 67 +++++++++++++++++++++++++++++++++++++
 mm/memcontrol.c             | 80 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 148 insertions(+)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 1c70803..7e87f5e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -531,6 +531,7 @@ struct cftype {
 	struct cgroup_subsys *ss;	/* NULL for cgroup core files */
 	struct list_head node;		/* anchored at ss->cfts */
 	struct kernfs_ops *kf_ops;
+	int numa_node_id;
 
 	int (*open)(struct kernfs_open_file *of);
 	void (*release)(struct kernfs_open_file *of);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1f3d880..3e40321 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -130,6 +130,7 @@ struct mem_cgroup_per_node {
 	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
+	unsigned long		max_nr_base_pages;
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
 
@@ -797,6 +798,51 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
+static inline unsigned long lruvec_size_memcg_node(enum lru_list lru,
+	struct mem_cgroup *memcg, int nid)
+{
+	if (nid == MAX_NUMNODES)
+		return 0;
+
+	VM_BUG_ON(lru < 0 || lru >= NR_LRU_LISTS);
+	return mem_cgroup_node_nr_lru_pages(memcg, nid, BIT(lru));
+}
+
+static inline unsigned long active_inactive_size_memcg_node(struct mem_cgroup *memcg, int nid, bool active)
+{
+	unsigned long val = 0;
+	enum lru_list lru;
+
+	for_each_evictable_lru(lru) {
+		if ((active  && is_active_lru(lru)) ||
+			(!active && !is_active_lru(lru)))
+			val += mem_cgroup_node_nr_lru_pages(memcg, nid, BIT(lru));
+	}
+
+	return val;
+}
+
+static inline unsigned long memcg_size_node(struct mem_cgroup *memcg, int nid)
+{
+	unsigned long val = 0;
+	int i;
+
+	if (nid == MAX_NUMNODES)
+		return val;
+
+	for (i = 0; i < NR_LRU_LISTS; i++)
+		val += mem_cgroup_node_nr_lru_pages(memcg, nid, BIT(i));
+
+	return val;
+}
+
+static inline unsigned long memcg_max_size_node(struct mem_cgroup *memcg, int nid)
+{
+	if (nid == MAX_NUMNODES)
+		return 0;
+	return memcg->nodeinfo[nid]->max_nr_base_pages;
+}
+
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
@@ -1123,6 +1169,27 @@ static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+
+static inline unsigned long lruvec_size_memcg_node(enum lru_list lru,
+	struct mem_cgroup *memcg, int nid)
+{
+	return 0;
+}
+
+static inline unsigned long active_inactive_size_memcg_node(struct mem_cgroup *memcg, int nid, bool active)
+{
+	return 0;
+}
+
+static inline unsigned long memcg_size_node(struct mem_cgroup *memcg, int nid)
+{
+	return 0;
+}
+static inline unsigned long memcg_max_size_node(struct mem_cgroup *memcg, int nid)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MEMCG */
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 532e0e2..478d216 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4394,6 +4394,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	pn->usage_in_excess = 0;
 	pn->on_tree = false;
 	pn->memcg = memcg;
+	pn->max_nr_base_pages = PAGE_COUNTER_MAX;
 
 	memcg->nodeinfo[node] = pn;
 	return 0;
@@ -6700,4 +6701,83 @@ static int __init mem_cgroup_swap_init(void)
 }
 subsys_initcall(mem_cgroup_swap_init);
 
+static int memory_per_node_stat_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct cftype *cur_file = seq_cft(m);
+	int nid = cur_file->numa_node_id;
+	unsigned long val = 0;
+	int i;
+
+	for (i = 0; i < NR_LRU_LISTS; i++)
+		val += mem_cgroup_node_nr_lru_pages(memcg, nid, BIT(i));
+
+	seq_printf(m, "%llu\n", (u64)val * PAGE_SIZE);
+
+	return 0;
+}
+
+static int memory_per_node_max_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct cftype *cur_file = seq_cft(m);
+	int nid = cur_file->numa_node_id;
+	unsigned long max = READ_ONCE(memcg->nodeinfo[nid]->max_nr_base_pages);
+
+	if (max == PAGE_COUNTER_MAX)
+		seq_puts(m, "max\n");
+	else
+		seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
+
+	return 0;
+}
+
+static ssize_t memory_per_node_max_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	struct cftype *cur_file = of_cft(of);
+	int nid = cur_file->numa_node_id;
+	unsigned long max;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "max", &max);
+	if (err)
+		return err;
+
+	xchg(&memcg->nodeinfo[nid]->max_nr_base_pages, max);
+
+	return nbytes;
+}
+
+static struct cftype memcg_per_node_stats_files[N_MEMORY];
+static struct cftype memcg_per_node_max_files[N_MEMORY];
+
+static int __init mem_cgroup_per_node_init(void)
+{
+	int nid;
+
+	for_each_node_state(nid, N_MEMORY) {
+		snprintf(memcg_per_node_stats_files[nid].name, MAX_CFTYPE_NAME,
+				"size_at_node:%d", nid);
+		memcg_per_node_stats_files[nid].flags = CFTYPE_NOT_ON_ROOT;
+		memcg_per_node_stats_files[nid].seq_show = memory_per_node_stat_show;
+		memcg_per_node_stats_files[nid].numa_node_id = nid;
+
+		snprintf(memcg_per_node_max_files[nid].name, MAX_CFTYPE_NAME,
+				"max_at_node:%d", nid);
+		memcg_per_node_max_files[nid].flags = CFTYPE_NOT_ON_ROOT;
+		memcg_per_node_max_files[nid].seq_show = memory_per_node_max_show;
+		memcg_per_node_max_files[nid].write = memory_per_node_max_write;
+		memcg_per_node_max_files[nid].numa_node_id = nid;
+	}
+	WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys,
+				memcg_per_node_stats_files));
+	WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys,
+				memcg_per_node_max_files));
+	return 0;
+}
+subsys_initcall(mem_cgroup_per_node_init);
+
 #endif /* CONFIG_MEMCG_SWAP */
-- 
2.7.4