Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To:     linux-mm@kvack.org, akpm@linux-foundation.org
Cc:     Wei Xu <weixugc@google.com>, Huang Ying <ying.huang@intel.com>,
        Yang Shi <shy828301@gmail.com>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Tim C Chen <tim.c.chen@intel.com>,
        Michal Hocko <mhocko@kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Hesham Almatary <hesham.almatary@huawei.com>,
        Dave Hansen <dave.hansen@intel.com>,
        Jonathan Cameron <Jonathan.Cameron@huawei.com>,
        Alistair Popple <apopple@nvidia.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Johannes Weiner <hannes@cmpxchg.org>, jvgediya.oss@gmail.com,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH v8 06/12] mm/demotion: Expose memory tier details via sysfs
Date:   Mon,  4 Jul 2022 12:36:06 +0530
Message-Id: <20220704070612.299585-7-aneesh.kumar@linux.ibm.com>
In-Reply-To: <20220704070612.299585-1-aneesh.kumar@linux.ibm.com>
References: <20220704070612.299585-1-aneesh.kumar@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This patch adds /sys/devices/system/memtier/ where all memory tier
related details can be found. All created memory tiers will be
listed there as /sys/devices/system/memtier/memtierN/

The nodes which are part of a specific memory tier can be listed
via /sys/devices/system/memtier/memtierN/nodelist

/sys/devices/system/memtier/max_tier shows the max tier ID value
supported.

/sys/devices/system/memtier/default_tier shows the memory tier to which
NUMA nodes get added by default if not assigned a specific memory tier.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 mm/memory-tiers.c | 93 ++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 87 insertions(+), 6 deletions(-)

diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 0596f0b11065..4acf7570ae1b 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -13,14 +13,15 @@
 
 struct memory_tier {
 	struct list_head list;
+	struct device dev;
 	nodemask_t nodelist;
-	int id;
 };
 
 struct demotion_nodes {
 	nodemask_t preferred;
 };
 
+#define to_memory_tier(device) container_of(device, struct memory_tier, dev)
 static void establish_migration_targets(void);
 static DEFINE_MUTEX(memory_tier_lock);
 static LIST_HEAD(memory_tiers);
@@ -86,6 +87,42 @@ static LIST_HEAD(memory_tiers);
  */
 static struct demotion_nodes *node_demotion __read_mostly;
 
+static struct bus_type memory_tier_subsys = {
+	.name = "memtier",
+	.dev_name = "memtier",
+};
+
+static ssize_t nodelist_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct memory_tier *memtier = to_memory_tier(dev);
+
+	return sysfs_emit(buf, "%*pbl\n",
+			  nodemask_pr_args(&memtier->nodelist));
+}
+static DEVICE_ATTR_RO(nodelist);
+
+static struct attribute *memory_tier_dev_attrs[] = {
+	&dev_attr_nodelist.attr,
+	NULL
+};
+
+static const struct attribute_group memory_tier_dev_group = {
+	.attrs = memory_tier_dev_attrs,
+};
+
+static const struct attribute_group *memory_tier_dev_groups[] = {
+	&memory_tier_dev_group,
+	NULL
+};
+
+static void memory_tier_device_release(struct device *dev)
+{
+	struct memory_tier *tier = to_memory_tier(dev);
+
+	kfree(tier);
+}
+
 static void insert_memory_tier(struct memory_tier *memtier)
 {
 	struct list_head *ent;
@@ -95,7 +132,7 @@ static void insert_memory_tier(struct memory_tier *memtier)
 
 	list_for_each(ent, &memory_tiers) {
 		tmp_memtier = list_entry(ent, struct memory_tier, list);
-		if (tmp_memtier->id < memtier->id) {
+		if (tmp_memtier->dev.id < memtier->dev.id) {
 			list_add_tail(&memtier->list, ent);
 			return;
 		}
@@ -105,6 +142,7 @@ static void insert_memory_tier(struct memory_tier *memtier)
 
 static struct memory_tier *register_memory_tier(unsigned int tier)
 {
+	int error;
 	struct memory_tier *memtier;
 
 	if (tier > MAX_MEMORY_TIER_ID)
@@ -114,17 +152,26 @@ static struct memory_tier *register_memory_tier(unsigned int tier)
 	if (!memtier)
 		return ERR_PTR(-ENOMEM);
 
-	memtier->id   = tier;
+	memtier->dev.id = tier;
+	memtier->dev.bus = &memory_tier_subsys;
+	memtier->dev.release = memory_tier_device_release;
+	memtier->dev.groups = memory_tier_dev_groups;
 
 	insert_memory_tier(memtier);
 
+	error = device_register(&memtier->dev);
+	if (error) {
+		list_del(&memtier->list);
+		put_device(&memtier->dev);
+		return ERR_PTR(error);
+	}
 	return memtier;
 }
 
 static void unregister_memory_tier(struct memory_tier *memtier)
 {
 	list_del(&memtier->list);
-	kfree(memtier);
+	device_unregister(&memtier->dev);
 }
 
 static struct memory_tier *__node_get_memory_tier(int node)
@@ -143,7 +190,7 @@ static struct memory_tier *__get_memory_tier_from_id(int id)
 	struct memory_tier *memtier;
 
 	list_for_each_entry(memtier, &memory_tiers, list) {
-		if (memtier->id == id)
+		if (memtier->dev.id == id)
 			return memtier;
 	}
 	return NULL;
@@ -181,7 +228,7 @@ int node_create_and_set_memory_tier(int node, int tier)
 		goto out;
 	}
 
-	if (current_tier->id == tier)
+	if (current_tier->dev.id == tier)
 		goto out;
 
 	node_clear(node, current_tier->nodelist);
@@ -426,10 +473,44 @@ static void __init migrate_on_reclaim_init(void)
 	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
 }
 
+static ssize_t
+max_tier_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", MAX_MEMORY_TIER_ID);
+}
+static DEVICE_ATTR_RO(max_tier);
+
+static ssize_t
+default_tier_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "memtier%d\n", default_memtier);
+}
+static DEVICE_ATTR_RO(default_tier);
+
+static struct attribute *memory_tier_attrs[] = {
+	&dev_attr_max_tier.attr,
+	&dev_attr_default_tier.attr,
+	NULL
+};
+
+static const struct attribute_group memory_tier_attr_group = {
+	.attrs = memory_tier_attrs,
+};
+
+static const struct attribute_group *memory_tier_attr_groups[] = {
+	&memory_tier_attr_group,
+	NULL,
+};
+
 static int __init memory_tier_init(void)
 {
+	int ret;
 	struct memory_tier *memtier;
 
+	ret = subsys_system_register(&memory_tier_subsys, memory_tier_attr_groups);
+	if (ret)
+		pr_err("%s() failed to register subsystem: %d\n", __func__, ret);
+
 	/*
 	 * Register only default memory tier to hide all empty
 	 * memory tier from sysfs. Since this is early during
-- 
2.36.1