Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   Li Zhijian <lizhijian@fujitsu.com>
To:     Andrew Morton <akpm@linux-foundation.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        rafael@kernel.org, linux-mm@kvack.org
Cc:     ying.huang@intel.com, y-goto@fujitsu.com,
        linux-kernel@vger.kernel.org, Li Zhijian <lizhijian@fujitsu.com>
Subject: [PATCH RFC 1/4] drivers/base/node: Add demotion_nodes sys infterface
Date:   Thu,  2 Nov 2023 10:56:45 +0800
Message-Id: <20231102025648.1285477-2-lizhijian@fujitsu.com>
In-Reply-To: <20231102025648.1285477-1-lizhijian@fujitsu.com>
References: <20231102025648.1285477-1-lizhijian@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

It shows the demotion target nodes of a node. Export this information to
user directly.

Below is an example where node0 node1 are DRAM, node3 is a PMEM node.
- Before PMEM is online, no demotion_nodes for node0 and node1.
$ cat /sys/devices/system/node/node0/demotion_nodes
 <show nothing>
- After node3 is online as kmem
$ daxctl reconfigure-device --mode=system-ram --no-online dax0.0 && daxctl online-memory dax0.0
[
  {
    "chardev":"dax0.0",
    "size":1054867456,
    "target_node":3,
    "align":2097152,
    "mode":"system-ram",
    "online_memblocks":0,
    "total_memblocks":7
  }
]
$ cat /sys/devices/system/node/node0/demotion_nodes
3
$ cat /sys/devices/system/node/node1/demotion_nodes
3
$ cat /sys/devices/system/node/node3/demotion_nodes
 <show nothing>

Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
 drivers/base/node.c          | 13 +++++++++++++
 include/linux/memory-tiers.h |  6 ++++++
 mm/memory-tiers.c            |  8 ++++++++
 3 files changed, 27 insertions(+)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 493d533f8375..27e8502548a7 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
+#include <linux/memory-tiers.h>
 #include <linux/vmstat.h>
 #include <linux/notifier.h>
 #include <linux/node.h>
@@ -569,11 +570,23 @@ static ssize_t node_read_distance(struct device *dev,
 }
 static DEVICE_ATTR(distance, 0444, node_read_distance, NULL);
 
+static ssize_t demotion_nodes_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int ret;
+	nodemask_t nmask = next_demotion_nodes(dev->id);
+
+	ret = sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&nmask));
+	return ret;
+}
+static DEVICE_ATTR_RO(demotion_nodes);
+
 static struct attribute *node_dev_attrs[] = {
 	&dev_attr_meminfo.attr,
 	&dev_attr_numastat.attr,
 	&dev_attr_distance.attr,
 	&dev_attr_vmstat.attr,
+	&dev_attr_demotion_nodes.attr,
 	NULL
 };
 
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 437441cdf78f..8eb04923f965 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -38,6 +38,7 @@ void init_node_memory_type(int node, struct memory_dev_type *default_type);
 void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
+nodemask_t next_demotion_nodes(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
 bool node_is_toptier(int node);
 #else
@@ -46,6 +47,11 @@ static inline int next_demotion_node(int node)
 	return NUMA_NO_NODE;
 }
 
+static inline next_demotion_nodes next_demotion_nodes(int node)
+{
+	return NODE_MASK_NONE;
+}
+
 static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
 {
 	*targets = NODE_MASK_NONE;
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 37a4f59d9585..90047f37d98a 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -282,6 +282,14 @@ void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
 	rcu_read_unlock();
 }
 
+nodemask_t next_demotion_nodes(int node)
+{
+	if (!node_demotion)
+		return NODE_MASK_NONE;
+
+	return node_demotion[node].preferred;
+}
+
 /**
  * next_demotion_node() - Get the next node in the demotion path
  * @node: The starting node to lookup the next node
-- 
2.29.2