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>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
        Jagdish Gediya <jvgediya@linux.ibm.com>
Subject: [PATCH v7 03/12] mm/demotion/dax/kmem: Set node's memory tier to MEMORY_TIER_PMEM
Date:   Wed, 22 Jun 2022 13:55:04 +0530
Message-Id: <20220622082513.467538-4-aneesh.kumar@linux.ibm.com>
In-Reply-To: <20220622082513.467538-1-aneesh.kumar@linux.ibm.com>
References: <20220622082513.467538-1-aneesh.kumar@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

By default, all nodes are assigned to DEFAULT_MEMORY_TIER which
is the memory tier designated for nodes with DRAM

Set dax kmem device node's tier to MEMORY_TIER_PMEM. MEMORY_TIER_PMEM
appears below DEFAULT_MEMORY_TIER in demotion order.

Signed-off-by: Jagdish Gediya <jvgediya@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/dax/kmem.c           |  6 ++-
 include/linux/memory-tiers.h |  5 +++
 mm/memory-tiers.c            | 79 ++++++++++++++++++++++++++++++++++++
 3 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index a37622060fff..0c03889286ac 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -11,6 +11,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/memory-tiers.h>
 #include "dax-private.h"
 #include "bus.h"
 
@@ -41,6 +42,9 @@ struct dax_kmem_data {
 	struct resource *res[];
 };
 
+static unsigned int dax_kmem_memtier = MEMORY_TIER_PMEM;
+module_param(dax_kmem_memtier, uint, 0644);
+
 static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 {
 	struct device *dev = &dev_dax->dev;
@@ -146,7 +150,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	}
 
 	dev_set_drvdata(dev, data);
-
+	node_create_and_set_memory_tier(numa_node, dax_kmem_memtier);
 	return 0;
 
 err_request_mem:
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index c47dbe381089..9d36ff13c954 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -14,9 +14,14 @@
 #define MAX_MEMORY_TIER_ID	400
 
 extern bool numa_demotion_enabled;
+int node_create_and_set_memory_tier(int node, int tier);
 
 #else
 
 #define numa_demotion_enabled	false
+static inline int node_create_and_set_memory_tier(int node, int tier)
+{
+	return 0;
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 2dcf70802661..fc404fcff7ff 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -51,6 +51,85 @@ static struct memory_tier *register_memory_tier(unsigned int tier)
 	return memtier;
 }
 
+static void unregister_memory_tier(struct memory_tier *memtier)
+{
+	list_del(&memtier->list);
+	kfree(memtier);
+}
+
+static struct memory_tier *__node_get_memory_tier(int node)
+{
+	struct memory_tier *memtier;
+
+	list_for_each_entry(memtier, &memory_tiers, list) {
+		if (node_isset(node, memtier->nodelist))
+			return memtier;
+	}
+	return NULL;
+}
+
+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)
+			return memtier;
+	}
+	return NULL;
+}
+
+static int __node_create_and_set_memory_tier(int node, int tier)
+{
+	int ret = 0;
+	struct memory_tier *memtier;
+
+	memtier = __get_memory_tier_from_id(tier);
+	if (!memtier) {
+		memtier = register_memory_tier(tier);
+		if (IS_ERR(memtier)) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+	node_set(node, memtier->nodelist);
+out:
+	return ret;
+}
+
+int node_create_and_set_memory_tier(int node, int tier)
+{
+	struct memory_tier *current_tier;
+	int ret = 0;
+
+	mutex_lock(&memory_tier_lock);
+
+	current_tier = __node_get_memory_tier(node);
+	if (!current_tier) {
+		ret = __node_create_and_set_memory_tier(node, tier);
+		goto out;
+	}
+
+	if (current_tier->id == tier)
+		goto out;
+
+	node_clear(node, current_tier->nodelist);
+
+	ret = __node_create_and_set_memory_tier(node, tier);
+	if (ret) {
+		/* reset it back to older tier */
+		node_set(node, current_tier->nodelist);
+		goto out;
+	}
+	if (nodes_empty(current_tier->nodelist))
+		unregister_memory_tier(current_tier);
+out:
+	mutex_unlock(&memory_tier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(node_create_and_set_memory_tier);
+
 static unsigned int default_memtier = DEFAULT_MEMORY_TIER;
 core_param(default_memory_tier, default_memtier, uint, 0644);
 
-- 
2.36.1