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>
Subject: [PATCH v7 04/12] mm/demotion: Add hotplug callbacks to handle new numa node onlined
Date:   Wed, 22 Jun 2022 13:55:05 +0530
Message-Id: <20220622082513.467538-5-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

If the new NUMA node onlined doesn't have a memory tier assigned,
the kernel adds the NUMA node to default memory tier.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 mm/memory-tiers.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index fc404fcff7ff..2147112981a6 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -5,6 +5,7 @@
 #include <linux/slab.h>
 #include <linux/lockdep.h>
 #include <linux/moduleparam.h>
+#include <linux/memory.h>
 #include <linux/memory-tiers.h>
 
 struct memory_tier {
@@ -130,8 +131,73 @@ int node_create_and_set_memory_tier(int node, int tier)
 }
 EXPORT_SYMBOL_GPL(node_create_and_set_memory_tier);
 
+static int __node_set_memory_tier(int node, int tier)
+{
+	int ret = 0;
+	struct memory_tier *memtier;
+
+	memtier = __get_memory_tier_from_id(tier);
+	if (!memtier) {
+		ret = -EINVAL;
+		goto out;
+	}
+	node_set(node, memtier->nodelist);
+out:
+	return ret;
+}
+
+static int node_set_memory_tier(int node, int tier)
+{
+	struct memory_tier *memtier;
+	int ret = 0;
+
+	mutex_lock(&memory_tier_lock);
+	memtier = __node_get_memory_tier(node);
+	if (!memtier)
+		ret = __node_set_memory_tier(node, tier);
+
+	mutex_unlock(&memory_tier_lock);
+
+	return ret;
+}
+
 static unsigned int default_memtier = DEFAULT_MEMORY_TIER;
 core_param(default_memory_tier, default_memtier, uint, 0644);
+/*
+ * This runs whether reclaim-based migration is enabled or not,
+ * which ensures that the user can turn reclaim-based migration
+ * at any time without needing to recalculate migration targets.
+ */
+static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
+						 unsigned long action, void *_arg)
+{
+	struct memory_notify *arg = _arg;
+
+	/*
+	 * Only update the node migration order when a node is
+	 * changing status, like online->offline.
+	 */
+	if (arg->status_change_nid < 0)
+		return notifier_from_errno(0);
+
+	switch (action) {
+	case MEM_ONLINE:
+		/*
+		 * We ignore the error here, if the node already have the tier
+		 * registered, we will continue to use that for the new memory
+		 * we are adding here.
+		 */
+		node_set_memory_tier(arg->status_change_nid, default_memtier);
+		break;
+	}
+
+	return notifier_from_errno(0);
+}
+
+static void __init migrate_on_reclaim_init(void)
+{
+	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
+}
 
 static int __init memory_tier_init(void)
 {
@@ -153,6 +219,8 @@ static int __init memory_tier_init(void)
 	/* CPU only nodes are not part of memory tiers. */
 	memtier->nodelist = node_states[N_MEMORY];
 	mutex_unlock(&memory_tier_lock);
+
+	migrate_on_reclaim_init();
 	return 0;
 }
 subsys_initcall(memory_tier_init);
-- 
2.36.1