Message-ID: <20251112192936.2574429-5-gourry@gourry.net>
Date: Wed, 12 Nov 2025 14:29:20 -0500
From: Gregory Price <gourry@...rry.net>
To: linux-mm@...ck.org
Cc: kernel-team@...a.com,
	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 v2 04/11] memory-tiers: Introduce SysRAM and Specific Purpose Memory Nodes

Create Memory Node "types" (SysRAM and Specific Purpose) which can be
set at memory hotplug time.

SysRAM nodes present at __init time are added to the mt_sysram_nodelist
and memory hotplug will decide whether hotplugged nodes will be placed
in mt_sysram_nodelist or mt_spm_nodelist.

SPM nodes are not included in demotion targets.

Setting a node type is permanent and cannot be switched once set, this
prevents type-change race conditions on the global mt_sysram_nodelist.

Signed-off-by: Gregory Price <gourry@...rry.net>
---
 include/linux/memory-tiers.h | 47 +++++++++++++++++++++++++
 mm/memory-tiers.c            | 66 ++++++++++++++++++++++++++++++++++--
 2 files changed, 111 insertions(+), 2 deletions(-)

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 7a805796fcfd..59443cbfaec3 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -35,10 +35,44 @@ struct memory_dev_type {
 
 struct access_coordinate;
 
+enum {
+	MT_NODE_TYPE_SYSRAM,
+	MT_NODE_TYPE_SPM
+};
+
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
 extern struct memory_dev_type *default_dram_type;
 extern nodemask_t default_dram_nodes;
+extern nodemask_t mt_sysram_nodelist;
+extern nodemask_t mt_spm_nodelist;
+static inline nodemask_t *mt_sysram_nodemask(void)
+{
+	if (nodes_empty(mt_sysram_nodelist))
+		return NULL;
+	return &mt_sysram_nodelist;
+}
+static inline void mt_nodemask_sysram_mask(nodemask_t *dst, nodemask_t *mask)
+{
+	/* If the sysram filter isn't available, this allows all */
+	if (nodes_empty(mt_sysram_nodelist)) {
+		nodes_or(*dst, *mask, NODE_MASK_NONE);
+		return;
+	}
+	nodes_and(*dst, *mask, mt_sysram_nodelist);
+}
+static inline bool mt_node_is_sysram(int nid)
+{
+	/* if sysram filter isn't setup, this allows all */
+	return nodes_empty(mt_sysram_nodelist) ||
+	       node_isset(nid, mt_sysram_nodelist);
+}
+static inline bool mt_node_allowed(int nid, gfp_t gfp_mask)
+{
+	if (gfp_mask & __GFP_SPM_NODE)
+		return true;
+	return mt_node_is_sysram(nid);
+}
 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);
@@ -73,11 +107,19 @@ static inline bool node_is_toptier(int node)
 }
 #endif
 
+int mt_set_node_type(int node, int type);
+
 #else
 
 #define numa_demotion_enabled	false
 #define default_dram_type	NULL
 #define default_dram_nodes	NODE_MASK_NONE
+#define mt_sysram_nodelist	NODE_MASK_NONE
+#define mt_spm_nodelist		NODE_MASK_NONE
+static inline nodemask_t *mt_sysram_nodemask(void) { return NULL; }
+static inline void mt_nodemask_sysram_mask(nodemask_t *dst, nodemask_t *mask) {}
+static inline bool mt_node_is_sysram(int nid) { return true; }
+static inline bool mt_node_allowed(int nid, gfp_t gfp_mask) { return true; }
 /*
  * CONFIG_NUMA implementation returns non NULL error.
  */
@@ -151,5 +193,10 @@ static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist,
 static inline void mt_put_memory_types(struct list_head *memory_types)
 {
 }
+
+int mt_set_node_type(int node, int type)
+{
+	return 0;
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 0ea5c13f10a2..dd6cfaa4c667 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -44,7 +44,15 @@ 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;
+
+/* mt_sysram_nodelist is the list of nodes with SysramRAM */
+nodemask_t mt_sysram_nodelist = NODE_MASK_NONE;
+
+/* mt_spm_nodelist is the list of nodes with Specific Purpose Memory */
+nodemask_t mt_spm_nodelist = NODE_MASK_NONE;
 
 static const struct bus_type memory_tier_subsys = {
 	.name = "memory_tiering",
@@ -427,6 +435,14 @@ 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, mt_sysram_nodelist))
+			continue;
+
 		best_distance = -1;
 		nd = &node_demotion[node];
 
@@ -457,7 +473,8 @@ 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, mt_sysram_nodelist)) {
 				best_distance = distance;
 				node_set(target, nd->preferred);
 			} else {
@@ -689,6 +706,48 @@ void mt_put_memory_types(struct list_head *memory_types)
 }
 EXPORT_SYMBOL_GPL(mt_put_memory_types);
 
+/**
+ * mt_set_node_type() - Set a NUMA Node's Memory type.
+ * @node: The node type to set
+ * @type: The type to set
+ *
+ * This is a one-way setting, once a type is assigned it cannot be cleared
+ * without resetting the system.  This is to avoid race conditions associated
+ * with moving nodes from one type to another during memory hotplug.
+ *
+ * Once a node is added as a SysRAM node, it will be used by default in
+ * the page allocator as a valid target when the calling does not provide
+ * a node or nodemask.  This is safe as the page allocator iterates through
+ * zones and uses this nodemask to filter zones - if a node is present but
+ * has no zones the node is ignored.
+ *
+ * Return: 0 if the node type is set successfully (or it's already set)
+ *         -EBUSY if the node has a different type already
+ *         -ENODEV if the type is invalid
+ */
+int mt_set_node_type(int node, int type)
+{
+	int err;
+
+	mutex_lock(&memory_tier_lock);
+	if (type == MT_NODE_TYPE_SYSRAM)
+		err = node_isset(node, mt_spm_nodelist) ? -EBUSY : 0;
+	else if (type == MT_NODE_TYPE_SPM)
+		err = node_isset(node, mt_sysram_nodelist) ? -EBUSY : 0;
+	if (err)
+		goto out;
+
+	if (type == MT_NODE_TYPE_SYSRAM)
+		node_set(node, mt_sysram_nodelist);
+	else if (type == MT_NODE_TYPE_SPM)
+		node_set(node, mt_spm_nodelist);
+	else
+		err = -ENODEV;
+out:
+	mutex_unlock(&memory_tier_lock);
+	return err;
+}
+
 /*
  * This is invoked via `late_initcall()` to initialize memory tiers for
  * memory nodes, both with and without CPUs. After the initialization of
@@ -922,6 +981,9 @@ 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 */
+	mt_sysram_nodelist = node_states[N_MEMORY];
+
 	hotplug_node_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRI);
 	return 0;
 }
-- 
2.51.1

Powered by blists - more mailing lists