Add support for Specific Purpose Memory (SPM) NUMA nodes.

A SPM node is managed by the page allocator, but can only allocated
by using the __GFP_SP_NODE flag with an appropriate nodemask.

Check/Set the node type (SysRAM vs SPM) at hotplug time.
Disallow SPM from being added to SysRAM nodes and vice-versa.

This prevents normal allocation paths (page faults, kmalloc, etc)
from being directly exposed to these memories, and provides a clear
integration point for buddy-allocation of SPM memory.

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 include/linux/memory_hotplug.h | 10 ++++++++++
 mm/memory_hotplug.c            |  7 +++++++
 2 files changed, 17 insertions(+)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 23f038a16231..a50c467951ba 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -74,6 +74,16 @@ typedef int __bitwise mhp_t;
  * helpful in low-memory situations.
  */
 #define MHP_OFFLINE_INACCESSIBLE	((__force mhp_t)BIT(3))
+/*
+ * The hotplugged memory can only be added to a "Specific Purpose Memory"
+ * NUMA node.  SPM Nodes are not generally accessible by the page allocator
+ * by way of userland configuration - as most nodemask interfaces
+ * (mempolicy, cpusets) restrict nodes to SysRAM nodes.
+ *
+ * Hotplugging SPM into a SysRAM Node results in -EINVAL.
+ * Hotplugging SysRAM into a SPM Node results in -EINVAL.
+ */
+#define MHP_SPM_NODE	((__force mhp_t)BIT(4))
 
 /*
  * Extended parameters for memory hotplug:
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0be83039c3b5..488cdd8e5f6f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -20,6 +20,7 @@
 #include <linux/memory.h>
 #include <linux/memremap.h>
 #include <linux/memory_hotplug.h>
+#include <linux/memory-tiers.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
 #include <linux/delay.h>
@@ -1529,6 +1530,12 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 
 	mem_hotplug_begin();
 
+	/* Set the NUMA node type and bail out if the type is wrong */
+	ret = mt_set_node_type(nid, (mhp_flags & MHP_SPM_NODE) ?
+				    MT_NODE_TYPE_SPM : MT_NODE_TYPE_SYSRAM);
+	if (ret)
+		goto error_mem_hotplug_end;
+
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
 		if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
 			memblock_flags = MEMBLOCK_DRIVER_MANAGED;
-- 
2.51.1

mt_set_node_type should be static

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 include/linux/memory-tiers.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 59443cbfaec3..aed9dc9e0c82 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -194,7 +194,7 @@ static inline void mt_put_memory_types(struct list_head *memory_types)
 {
 }
 
-int mt_set_node_type(int node, int type)
+static int mt_set_node_type(int node, int type)
 {
 	return 0;
 }
-- 
2.51.1

Hi Gregory,

kernel test robot noticed the following build warnings:



url:    https://github.com/intel-lab-lkp/linux/commits/UPDATE-20251113-230036/Gregory-Price/mm-constify-oom_control-scan_control-and-alloc_context-nodemask/20251113-033247
base:   the 8th patch of https://lore.kernel.org/r/20251112192936.2574429-9-gourry%40gourry.net
patch link:    https://lore.kernel.org/r/20251113145815.2926823-1-gourry%40gourry.net
patch subject: [PATCH] memory-tiers: multi-definition fixup
config: m68k-allnoconfig (https://download.01.org/0day-ci/archive/20251114/202511140039.XVfj2ju0-lkp@intel.com/config)
compiler: m68k-linux-gcc (GCC) 15.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251114/202511140039.XVfj2ju0-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511140039.XVfj2ju0-lkp@intel.com/

All warnings (new ones prefixed by >>):

   In file included from mm/oom_kill.c:37:
>> include/linux/memory-tiers.h:197:12: warning: 'mt_set_node_type' defined but not used [-Wunused-function]
     197 | static int mt_set_node_type(int node, int type)
         |            ^~~~~~~~~~~~~~~~


vim +/mt_set_node_type +197 include/linux/memory-tiers.h

   196	
 > 197	static int mt_set_node_type(int node, int type)

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Since this protection may break userspace tools, it should
be an opt-in until those tools have time to update to the
new daxN.M/hotplug interface instead of memory blocks.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Gregory Price <gourry@gourry.net>
---
 drivers/dax/Kconfig | 18 ++++++++++++++++++
 drivers/dax/kmem.c  | 29 ++++++++++++++++++++---------
 2 files changed, 38 insertions(+), 9 deletions(-)

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index d656e4c0eb84..cc13c22eb8f8 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -78,4 +78,22 @@ config DEV_DAX_KMEM
 
 	  Say N if unsure.
 
+config DEV_DAX_KMEM_PROTECTED
+	bool "Protect DAX_KMEM memory blocks being changed"
+	depends on DEV_DAX_KMEM
+	default n
+	help
+	  Prevents actions from outside the KMEM DAX driver from changing
+	  DAX KMEM memory block states. For example, the memory block
+	  sysfs functions (online, state) will return -EBUSY, and normal
+	  calls to memory_hotplug functions from other drivers and kernel
+	  sources will fail.
+
+	  This may break existing memory block management patterns that
+	  depend on offlining DAX KMEM blocks from userland before unbinding
+	  the driver.  Use this only if your tools have been updated to use
+	  the daxN.M/hotplug interface.
+
+	  Say N if unsure.
+
 endif
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index f3562f65376c..094b8a51099e 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -184,6 +184,21 @@ static int dax_kmem_memory_notifier_cb(struct notifier_block *nb,
 	return NOTIFY_BAD;
 }
 
+static int dax_kmem_register_notifier(struct dax_kmem_data *data)
+{
+	if (!IS_ENABLED(DEV_DAX_KMEM_PROTECTED))
+		return 0;
+	data->mem_nb.notifier_call = dax_kmem_memory_notifier_cb;
+	return register_memory_notifier(&data->mem_nb);
+}
+
+static void dax_kmem_unregister_notifier(struct dax_kmem_data *data)
+{
+	if (!IS_ENABLED(DEV_DAX_KMEM_PROTECTED))
+		return;
+	unregister_memory_notifier(&data->mem_nb);
+}
+
 /**
  * dax_kmem_do_hotplug - hotplug memory for dax kmem device
  * @dev_dax: the dev_dax instance
@@ -563,13 +578,9 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	if (rc < 0)
 		goto err_resources;
 
-	/* Register memory notifier to block external operations */
-	data->mem_nb.notifier_call = dax_kmem_memory_notifier_cb;
-	rc = register_memory_notifier(&data->mem_nb);
-	if (rc) {
-		dev_warn(dev, "failed to register memory notifier\n");
+	rc = dax_kmem_register_notifier(data);
+	if (rc)
 		goto err_notifier;
-	}
 
 	/*
 	 * Hotplug using the system default policy - this preserves backwards
@@ -595,7 +606,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	return 0;
 
 err_hotplug:
-	unregister_memory_notifier(&data->mem_nb);
+	dax_kmem_unregister_notifier(data);
 err_notifier:
 	dax_kmem_cleanup_resources(dev_dax, data);
 err_resources:
@@ -619,7 +630,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 
 	device_remove_file(dev, &dev_attr_hotplug);
 	dax_kmem_cleanup_resources(dev_dax, data);
-	unregister_memory_notifier(&data->mem_nb);
+	dax_kmem_unregister_notifier(data);
 	memory_group_unregister(data->mgid);
 	kfree(data->res_name);
 	kfree(data);
@@ -640,7 +651,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 	struct dax_kmem_data *data = dev_get_drvdata(dev);
 
 	device_remove_file(dev, &dev_attr_hotplug);
-	unregister_memory_notifier(&data->mem_nb);
+	dax_kmem_unregister_notifier(data);
 
 	/*
 	 * Without hotremove purposely leak the request_mem_region() for the
-- 
2.52.0