[RFC PATCH v4 19/27] mm/compaction: NP_OPS_COMPACTION - private node compaction support

[Gregory Price]

Private node zones should not be compacted unless the service explicitly
opts in - as compaction requires migration and services may have
PFN-based metadata that needs updating.

Add a folio_migrate callback which fires from migrate_folio_move() for
each relocated folio before faults are unblocked.

Add zone_supports_compaction() which returns true for normal zones and
checks NP_OPS_COMPACTION for N_MEMORY_PRIVATE zones.

Filter three direct compaction zone loops:
  - compaction_zonelist_suitable() (reclaimer eligibility)
  - try_to_compact_pages()         (direct compaction)
  - compact_node()                 (proactive/manual compaction)

kcompactd paths are intentionally unfiltered -- the service is
responsible for starting kcompactd on its node.

NP_OPS_COMPACTION requires NP_OPS_MIGRATION.

Signed-off-by: Gregory Price <gourry@xxxxxxxxxx>
---
 drivers/base/node.c          |  4 ++++
 include/linux/node_private.h |  2 ++
 mm/compaction.c              | 26 ++++++++++++++++++++++++++
 3 files changed, 32 insertions(+)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 88aaac45e814..da523aca18fa 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -965,6 +965,10 @@ int node_private_set_ops(int nid, const struct node_private_ops *ops)
 	    !(ops->flags & NP_OPS_MIGRATION))
 		return -EINVAL;
 
+	if ((ops->flags & NP_OPS_COMPACTION) &&
+	    !(ops->flags & NP_OPS_MIGRATION))
+		return -EINVAL;
+
 	mutex_lock(&node_private_lock);
 	np = rcu_dereference_protected(NODE_DATA(nid)->node_private,
 				       lockdep_is_held(&node_private_lock));
diff --git a/include/linux/node_private.h b/include/linux/node_private.h
index 5ac60db1f044..fe0336773ddb 100644
--- a/include/linux/node_private.h
+++ b/include/linux/node_private.h
@@ -142,6 +142,8 @@ struct node_private_ops {
 #define NP_OPS_RECLAIM			BIT(4)
 /* Allow NUMA balancing to scan and migrate folios on this node */
 #define NP_OPS_NUMA_BALANCING		BIT(5)
+/* Allow compaction to run on the node.  Service must start kcompactd. */
+#define NP_OPS_COMPACTION		BIT(6)
 
 /* Private node is OOM-eligible: reclaim can run and pages can be demoted here */
 #define NP_OPS_OOM_ELIGIBLE		(NP_OPS_RECLAIM | NP_OPS_DEMOTION)
diff --git a/mm/compaction.c b/mm/compaction.c
index 6a65145b03d8..d8532b957ec6 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -24,9 +24,26 @@
 #include <linux/page_owner.h>
 #include <linux/psi.h>
 #include <linux/cpuset.h>
+#include <linux/node_private.h>
 #include "internal.h"
 
 #ifdef CONFIG_COMPACTION
+
+/*
+ * Private node zones require NP_OPS_COMPACTION to opt in.  Normal zones
+ * always support compaction.
+ */
+static inline bool zone_supports_compaction(struct zone *zone)
+{
+#ifdef CONFIG_NUMA
+	if (!node_state(zone_to_nid(zone), N_MEMORY_PRIVATE))
+		return true;
+	return zone_private_flags(zone, NP_OPS_COMPACTION);
+#else
+	return true;
+#endif
+}
+
 /*
  * Fragmentation score check interval for proactive compaction purposes.
  */
@@ -2443,6 +2460,9 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 				ac->highest_zoneidx, ac->nodemask) {
 		unsigned long available;
 
+		if (!zone_supports_compaction(zone))
+			continue;
+
 		/*
 		 * Do not consider all the reclaimable memory because we do not
 		 * want to trash just for a single high order allocation which
@@ -2832,6 +2852,9 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		if (!numa_zone_alloc_allowed(alloc_flags, zone, gfp_mask))
 			continue;
 
+		if (!zone_supports_compaction(zone))
+			continue;
+
 		if (prio > MIN_COMPACT_PRIORITY
 					&& compaction_deferred(zone, order)) {
 			rc = max_t(enum compact_result, COMPACT_DEFERRED, rc);
@@ -2906,6 +2929,9 @@ static int compact_node(pg_data_t *pgdat, bool proactive)
 		if (!populated_zone(zone))
 			continue;
 
+		if (!zone_supports_compaction(zone))
+			continue;
+
 		if (fatal_signal_pending(current))
 			return -EINTR;
 
-- 
2.53.0