From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Thu, 18 Aug 2022 18:40:35 +0530
Subject: mm/demotion: add hotplug callbacks to handle new numa node onlined
Git-commit: c6123a19c9f040e597f55f856c679651c26b31d1
Patch-mainline: v6.1-rc1
References: jsc#PED-1248
If the new NUMA node onlined doesn't have a abstract distance assigned,
the kernel adds the NUMA node to default memory tier.
[aneesh.kumar@linux.ibm.com: fix kernel error with memory hotplug]
Link: https://lkml.kernel.org/r/20220825092019.379069-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20220818131042.113280-4-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Jagdish Gediya <jvgediya.oss@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/memory-tiers.h | 1
mm/memory-tiers.c | 68 +++++++++++++++++++++++++++++++++++++++++++
2 files changed, 69 insertions(+)
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -14,6 +14,7 @@
* the same memory tier.
*/
#define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
+#define MEMTIER_HOTPLUG_PRIO 100
#ifdef CONFIG_NUMA
#include <linux/types.h>
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -5,6 +5,7 @@
#include <linux/lockdep.h>
#include <linux/sysfs.h>
#include <linux/kobject.h>
+#include <linux/memory.h>
#include <linux/memory-tiers.h>
struct memory_tier {
@@ -105,6 +106,72 @@ static struct memory_tier *set_node_memo
return memtier;
}
+static struct memory_tier *__node_get_memory_tier(int node)
+{
+ struct memory_dev_type *memtype;
+
+ memtype = node_memory_types[node];
+ if (memtype && node_isset(node, memtype->nodes))
+ return memtype->memtier;
+ return NULL;
+}
+
+static void destroy_memory_tier(struct memory_tier *memtier)
+{
+ list_del(&memtier->list);
+ kfree(memtier);
+}
+
+static bool clear_node_memory_tier(int node)
+{
+ bool cleared = false;
+ struct memory_tier *memtier;
+
+ memtier = __node_get_memory_tier(node);
+ if (memtier) {
+ struct memory_dev_type *memtype;
+
+ memtype = node_memory_types[node];
+ node_clear(node, memtype->nodes);
+ if (nodes_empty(memtype->nodes)) {
+ list_del_init(&memtype->tier_sibiling);
+ memtype->memtier = NULL;
+ if (list_empty(&memtier->memory_types))
+ destroy_memory_tier(memtier);
+ }
+ cleared = true;
+ }
+ return cleared;
+}
+
+static int __meminit memtier_hotplug_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_OFFLINE:
+ mutex_lock(&memory_tier_lock);
+ clear_node_memory_tier(arg->status_change_nid);
+ mutex_unlock(&memory_tier_lock);
+ break;
+ case MEM_ONLINE:
+ mutex_lock(&memory_tier_lock);
+ set_node_memory_tier(arg->status_change_nid);
+ mutex_unlock(&memory_tier_lock);
+ break;
+ }
+
+ return notifier_from_errno(0);
+}
+
static int __init memory_tier_init(void)
{
int node;
@@ -126,6 +193,7 @@ static int __init memory_tier_init(void)
}
mutex_unlock(&memory_tier_lock);
+ hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRIO);
return 0;
}
subsys_initcall(memory_tier_init);