Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:2 as permitted sender) client-ip=2620:137:e000::3:2;
Received-SPF: Pass (protection.outlook.com: domain of micron.com designates
 137.201.242.130 as permitted sender) receiver=protection.outlook.com;
 client-ip=137.201.242.130; helo=mail.micron.com; pr=C
From:   <sthanneeru.opensrc@micron.com>
To:     <aneesh.kumar@linux.ibm.com>, <hannes@cmpxchg.org>,
        <hasanalmaruf@fb.com>, <haowang3@fb.com>, <ying.huang@intel.com>,
        <gregory.price@memverge.com>, <dan.j.williams@intel.com>,
        <mhocko@suse.com>, <tj@kernel.org>, <hezhongkun.hzk@bytedance.com>,
        <fvdl@google.com>, <john@jagalactic.com>, <mirakhur@micron.com>,
        <vtavarespetr@micron.com>, <Ravis.OpenSrc@micron.com>,
        <Jonathan.Cameron@huawei.com>, <linux-kernel@vger.kernel.org>,
        <linux-api@vger.kernel.org>
CC:     Srinivasulu Thanneeru <sthanneeru.opensrc@micron.com>,
        Ravi Jonnalagadda <ravis.opensrc@micron.com>
Subject: [RFC PATCH 1/2] base/node: Add sysfs for adistance_offset
Date:   Fri, 1 Dec 2023 03:18:57 +0530
Message-ID: <20231130214858.1887-2-sthanneeru.opensrc@micron.com>
In-Reply-To: <20231130214858.1887-1-sthanneeru.opensrc@micron.com>
References: <20231130214858.1887-1-sthanneeru.opensrc@micron.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 30 Nov 2023 21:49:19.3672
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 92c3c0dd-af63-4856-bc6c-08dbf1ee34e8
X-MS-Exchange-CrossTenant-Id: f38a5ecd-2813-4862-b11b-ac1d563c806f
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=f38a5ecd-2813-4862-b11b-ac1d563c806f;Ip=[137.201.242.130];Helo=[mail.micron.com]
X-MS-Exchange-CrossTenant-AuthSource: BL6PEPF0001AB51.namprd04.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SA2PR08MB6523
X-Spam-Status: No, score=-0.9 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,
	DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,
	SPF_HELO_NONE,SPF_PASS,T_SCC_BODY_TEXT_LINE autolearn=unavailable
	autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on agentk.vger.email
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (agentk.vger.email [0.0.0.0]); Thu, 30 Nov 2023 13:49:59 -0800 (PST)

From: Srinivasulu Thanneeru <sthanneeru.opensrc@micron.com>

This patch introduces a new attribute called adistance_offset to the
node_devices structure.
Using adistance_offset, a node can be migrated to a targeted tier.
Target tier's adjacent distance(adistance) is calculated by taking the
adistance offset into account.

Signed-off-by: Srinivasulu Thanneeru <sthanneeru.opensrc@micron.com>
Signed-off-by: Ravi Jonnalagadda <ravis.opensrc@micron.com>
---
 drivers/base/node.c          | 45 ++++++++++++++++++++++++++++++++++++
 include/linux/memory-tiers.h |  6 +++++
 include/linux/node.h         |  1 +
 mm/memory-tiers.c            | 14 +++++++++++
 4 files changed, 66 insertions(+)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 493d533f8375..1e63c692977b 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 +570,54 @@ static ssize_t node_read_distance(struct device *dev,
 }
 static DEVICE_ATTR(distance, 0444, node_read_distance, NULL);
 
+static ssize_t adistance_offset_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	int nid = dev->id;
+	int len = 0;
+
+	/*
+	 * buf is currently PAGE_SIZE in length and each node needs 4 chars
+	 * at the most (distance + space or newline).
+	 */
+	BUILD_BUG_ON(MAX_NUMNODES * 4 > PAGE_SIZE);
+
+	len += sysfs_emit(buf, "%d\n", node_devices[nid]->adistance_offset);
+	return len;
+}
+
+static ssize_t adistance_offset_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t size)
+{
+	int nid = dev->id;
+	int value, ret;
+
+	ret = kstrtoint(buf, 0, &value);
+
+	if (ret)
+		return ret;
+	if (node_devices[nid]->adistance_offset == value)
+		return size;
+	/*
+	 * Request from a node to migrate to a memtier with negative
+	 * adistance is not valid.
+	 */
+	ret = get_target_memtier_adistance(nid, value);
+	if (ret < 0)
+		return -EINVAL;
+
+	node_devices[nid]->adistance_offset = value;
+	return size;
+}
+static DEVICE_ATTR_RW(adistance_offset);
+
 static struct attribute *node_dev_attrs[] = {
 	&dev_attr_meminfo.attr,
 	&dev_attr_numastat.attr,
 	&dev_attr_distance.attr,
 	&dev_attr_vmstat.attr,
+	&dev_attr_adistance_offset.attr,
 	NULL
 };
 
@@ -883,6 +927,7 @@ int __register_one_node(int nid)
 
 	INIT_LIST_HEAD(&node_devices[nid]->access_list);
 	node_init_caches(nid);
+	node_devices[nid]->adistance_offset = 0;
 
 	return error;
 }
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 1e39d27bee41..ff4e7136ab40 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -48,6 +48,7 @@ int mt_calc_adistance(int node, int *adist);
 int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
 			     const char *source);
 int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
+int get_target_memtier_adistance(int node, int adistance_offset);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -136,5 +137,10 @@ static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
 {
 	return -EIO;
 }
+
+static int get_target_memtier_adistance(int node, int adistance_offset)
+{
+	return 0;
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/include/linux/node.h b/include/linux/node.h
index 427a5975cf40..fd0f4f3177f8 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -83,6 +83,7 @@ static inline void node_set_perf_attrs(unsigned int nid,
 struct node {
 	struct device	dev;
 	struct list_head access_list;
+	int adistance_offset;
 #ifdef CONFIG_HMEM_REPORTING
 	struct list_head cache_attrs;
 	struct device *cache_dev;
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 8d5291add2bc..a40d4d4383d7 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -167,6 +167,20 @@ static const struct attribute_group *memtier_dev_groups[] = {
 	NULL
 };
 
+int get_target_memtier_adistance(int node, int adistance_offset)
+{
+	struct memory_dev_type *memtype;
+	int node_adistance;
+
+	memtype = node_memory_types[node].memtype;
+	/*
+	 * Calculate the targeted memtier abstract distance from
+	 * memtype adistance and node adistance offset.
+	 */
+	node_adistance = memtype->adistance + adistance_offset;
+	return node_adistance;
+}
+
 static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype)
 {
 	int ret;
-- 
2.25.1