linux-kernel - [RFC PATCH 2/9] memory-tiers: create default_sysram

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251107224956.477056-3-gourry@gourry.net>
Date: Fri,  7 Nov 2025 17:49:47 -0500
From: Gregory Price <gourry@...rry.net>
To: linux-mm@...ck.org
Cc: linux-cxl@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	nvdimm@...ts.linux.dev,
	linux-fsdevel@...r.kernel.org,
	cgroups@...r.kernel.org,
	dave@...olabs.net,
	jonathan.cameron@...wei.com,
	dave.jiang@...el.com,
	alison.schofield@...el.com,
	vishal.l.verma@...el.com,
	ira.weiny@...el.com,
	dan.j.williams@...el.com,
	longman@...hat.com,
	akpm@...ux-foundation.org,
	david@...hat.com,
	lorenzo.stoakes@...cle.com,
	Liam.Howlett@...cle.com,
	vbabka@...e.cz,
	rppt@...nel.org,
	surenb@...gle.com,
	mhocko@...e.com,
	osalvador@...e.de,
	ziy@...dia.com,
	matthew.brost@...el.com,
	joshua.hahnjy@...il.com,
	rakie.kim@...com,
	byungchul@...com,
	gourry@...rry.net,
	ying.huang@...ux.alibaba.com,
	apopple@...dia.com,
	mingo@...hat.com,
	peterz@...radead.org,
	juri.lelli@...hat.com,
	vincent.guittot@...aro.org,
	dietmar.eggemann@....com,
	rostedt@...dmis.org,
	bsegall@...gle.com,
	mgorman@...e.de,
	vschneid@...hat.com,
	tj@...nel.org,
	hannes@...xchg.org,
	mkoutny@...e.com,
	kees@...nel.org,
	muchun.song@...ux.dev,
	roman.gushchin@...ux.dev,
	shakeel.butt@...ux.dev,
	rientjes@...gle.com,
	jackmanb@...gle.com,
	cl@...two.org,
	harry.yoo@...cle.com,
	axelrasmussen@...gle.com,
	yuanchu@...gle.com,
	weixugc@...gle.com,
	zhengqi.arch@...edance.com,
	yosry.ahmed@...ux.dev,
	nphamcs@...il.com,
	chengming.zhou@...ux.dev,
	fabio.m.de.francesco@...ux.intel.com,
	rrichter@....com,
	ming.li@...omail.com,
	usamaarif642@...il.com,
	brauner@...nel.org,
	oleg@...hat.com,
	namcao@...utronix.de,
	escape@...ux.alibaba.com,
	dongjoo.seo1@...sung.com
Subject: [RFC PATCH 2/9] memory-tiers: create default_sysram_nodes

Record the set of memory nodes present at __init time, so that hotplug
memory nodes can choose whether to expose themselves to the page
allocator at hotplug time.

Do not included non-sysram nodes in demotion targets.

Signed-off-by: Gregory Price <gourry@...rry.net>
---
 include/linux/memory-tiers.h |  3 +++
 mm/memory-tiers.c            | 22 ++++++++++++++++++++--
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 7a805796fcfd..3d3f3687d134 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -39,6 +39,9 @@ struct access_coordinate;
 extern bool numa_demotion_enabled;
 extern struct memory_dev_type *default_dram_type;
 extern nodemask_t default_dram_nodes;
+extern nodemask_t default_sysram_nodelist;
+#define default_sysram_nodes (nodes_empty(default_sysram_nodelist) ? NULL : \
+			      &default_sysram_nodelist)
 struct memory_dev_type *alloc_memory_type(int adistance);
 void put_memory_type(struct memory_dev_type *memtype);
 void init_node_memory_type(int node, struct memory_dev_type *default_type);
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 0ea5c13f10a2..b2ee4f73ad54 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -44,7 +44,12 @@ static LIST_HEAD(memory_tiers);
 static LIST_HEAD(default_memory_types);
 static struct node_memory_type_map node_memory_types[MAX_NUMNODES];
 struct memory_dev_type *default_dram_type;
-nodemask_t default_dram_nodes __initdata = NODE_MASK_NONE;
+
+/* default_dram_nodes is the list of nodes with both CPUs and RAM */
+nodemask_t default_dram_nodes = NODE_MASK_NONE;
+
+/* default_sysram_nodelist is the list of nodes with RAM at __init time */
+nodemask_t default_sysram_nodelist = NODE_MASK_NONE;
 
 static const struct bus_type memory_tier_subsys = {
 	.name = "memory_tiering",
@@ -427,6 +432,14 @@ static void establish_demotion_targets(void)
 	disable_all_demotion_targets();
 
 	for_each_node_state(node, N_MEMORY) {
+		/*
+		 * If this is not a sysram node, direct-demotion is not allowed
+		 * and must be managed by special logic that understands the
+		 * memory features of that particular node.
+		 */
+		if (!node_isset(node, default_sysram_nodelist))
+			continue;
+
 		best_distance = -1;
 		nd = &node_demotion[node];
 
@@ -457,7 +470,8 @@ static void establish_demotion_targets(void)
 				break;
 
 			distance = node_distance(node, target);
-			if (distance == best_distance || best_distance == -1) {
+			if ((distance == best_distance || best_distance == -1) &&
+			    node_isset(target, default_sysram_nodelist)) {
 				best_distance = distance;
 				node_set(target, nd->preferred);
 			} else {
@@ -812,6 +826,7 @@ int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 }
 EXPORT_SYMBOL_GPL(mt_perf_to_adistance);
 
+
 /**
  * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm
  * @nb: The notifier block which describe the algorithm
@@ -922,6 +937,9 @@ static int __init memory_tier_init(void)
 	nodes_and(default_dram_nodes, node_states[N_MEMORY],
 		  node_states[N_CPU]);
 
+	/* Record all nodes with non-hotplugged memory as default SYSRAM nodes */
+	default_sysram_nodelist = node_states[N_MEMORY];
+
 	hotplug_node_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRI);
 	return 0;
 }
-- 
2.51.1