[PATCH v5 30/36] mm: add NODE_PRIVATE_CAP_NUMA_BALANCING for private-node NUMA balancing

[Gregory Price <gourry@gourry.net>]

By default NUMA balancing does not scan or prot_none private-node
folios, so the kernel never migrates them via access sampling.

Add NODE_PRIVATE_CAP_NUMA_BALANCING to opt a private node in.

Add folio_allows_numa_balance() to gate change_prot_numa() scans on
node eligibility. Opted-in private node participate like normal.

Unlike demotion, NUMA balancing is not reclaim-driven, so this
capability stands alone and does not require CAP_RECLAIM.

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 include/linux/node_private.h | 29 +++++++++++++++++++++++++++++
 mm/internal.h                | 13 +++++++++++++
 mm/mempolicy.c               |  2 +-
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/linux/node_private.h b/include/linux/node_private.h
index 87b03444b2c97..5c3e070ed0deb 100644
--- a/include/linux/node_private.h
+++ b/include/linux/node_private.h
@@ -16,6 +16,7 @@ struct page;
 #define NODE_PRIVATE_CAP_USER_NUMA	(1UL << 1)	/* allow mempolicy */
 #define NODE_PRIVATE_CAP_HOTUNPLUG	(1UL << 2)	/* allow hot-unplug */
 #define NODE_PRIVATE_CAP_DEMOTION	(1UL << 3)	/* allow tiering demotion */
+#define NODE_PRIVATE_CAP_NUMA_BALANCING	(1UL << 4)	/* allow NUMA balancing */
 
 /**
  * struct node_private - Per-node container for N_MEMORY_PRIVATE nodes
@@ -143,6 +144,29 @@ static inline bool node_allows_demotion(int nid)
 	return ret;
 }
 
+/**
+ * node_allows_numa_balancing - may NUMA balancing scan/migrate this node?
+ * @nid: the node to test
+ *
+ * Access-based promotion/migration.  Unlike demotion this is not reclaim-driven,
+ * so CAP_NUMA_BALANCING stands alone (no CAP_RECLAIM dependency).
+ *
+ * return: true for normal nodes and private nodes opted into CAP_NUMA_BALANCING.
+ */
+static inline bool node_allows_numa_balancing(int nid)
+{
+	struct node_private *np;
+	bool ret;
+
+	if (!node_state(nid, N_MEMORY_PRIVATE))
+		return true;
+	rcu_read_lock();
+	np = rcu_dereference(NODE_DATA(nid)->node_private);
+	ret = np && (np->caps & NODE_PRIVATE_CAP_NUMA_BALANCING);
+	rcu_read_unlock();
+	return ret;
+}
+
 #else /* !CONFIG_NUMA */
 
 static inline bool folio_is_private_node(struct folio *folio)
@@ -180,6 +204,11 @@ static inline bool node_allows_demotion(int nid)
 	return true;
 }
 
+static inline bool node_allows_numa_balancing(int nid)
+{
+	return true;
+}
+
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
diff --git a/mm/internal.h b/mm/internal.h
index 62e68acae08a3..01ab8b32b0bd8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -123,6 +123,19 @@ static inline bool folio_allows_madvise(struct folio *folio)
 	       node_allows_reclaim(folio_nid(folio));
 }
 
+/*
+ * folio_allows_numa_balance() - may NUMA balancing scan/migrate this folio?
+ *
+ * NUMA balancing is access-aware tiering migration, so it follows the tiering
+ * opt-in: false for ZONE_DEVICE and for N_MEMORY_PRIVATE nodes without
+ * CAP_NUMA_BALANCING, true for all other folios.
+ */
+static inline bool folio_allows_numa_balance(struct folio *folio)
+{
+	return !folio_is_zone_device(folio) &&
+	       node_allows_numa_balancing(folio_nid(folio));
+}
+
 /*
  * folio_allows_longterm_pin() - may this folio be long-term GUP-pinned?
  *
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index fe42a510590a2..4daba81fff7c7 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -874,7 +874,7 @@ bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma,
 {
 	int nid;
 
-	if (!folio || folio_is_private_managed(folio) || folio_test_ksm(folio))
+	if (!folio || !folio_allows_numa_balance(folio) || folio_test_ksm(folio))
 		return false;
 
 	/* Also skip shared copy-on-write folios */
-- 
2.53.0-Meta