[RFC PATCH v3 11/13] mm/damon/vaddr: Use damos->migrate_dests in migrate_{hot,cold}

[Bijan Tabatabai <bijan311@gmail.com>]

From: Bijan Tabatabai <bijantabatab@micron.com>

damos->migrate_dests provides a list of nodes the migrate_{hot,cold}
actions should migrate to, as well as the weights which specify the
ratio pages should be migrated to each destination node.

This patch interleaves pages in the migrate_{hot,cold} actions according
to the information provided in damos->migrate_dests if it is used. The
interleaving algorithm used is similar to the one used in
weighted_interleave_nid(). If damos->migration_dests is not provided, the
actions migrate pages to the node specified in damos->target_nid as
before.

Co-developed-by: Ravi Shankar Jonnalagadda <ravis.opensrc@micron.com>
Signed-off-by: Ravi Shankar Jonnalagadda <ravis.opensrc@micron.com>
Signed-off-by: Bijan Tabatabai <bijantabatab@micron.com>
---
 mm/damon/vaddr.c | 114 ++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 97 insertions(+), 17 deletions(-)

diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 5cdfdc47c5ff..5f230a427fdc 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -611,11 +611,76 @@ static unsigned int damon_va_check_accesses(struct damon_ctx *ctx)
 	return max_nr_accesses;
 }
 
+struct damos_va_migrate_private {
+	struct list_head *migration_lists;
+	struct damos *scheme;
+};
+
+/*
+ * Place the given folio in the migration_list corresponding to where the folio
+ * should be migrated.
+ *
+ * The algorithm used here is similar to weighted_interleave_nid()
+ */
+static void damos_va_migrate_folio(struct folio *folio,
+		struct vm_area_struct *vma, unsigned long addr,
+		struct damos_migrate_dests *dests,
+		struct list_head *migration_lists)
+{
+	pgoff_t ilx;
+	int order;
+	unsigned int target;
+	unsigned int weight_total = 0;
+	int i;
+
+	/*
+	 * If dests is empty, there is only one migration list corresponding
+	 * to s->target_nid.
+	 */
+	if (!dests->nr_dests) {
+		i = 0;
+		goto isolate;
+	}
+
+	order = folio_order(folio);
+	ilx = vma->vm_pgoff >> order;
+	ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order);
+
+	for (i = 0; i < dests->nr_dests; i++)
+		weight_total += dests->weight_arr[i];
+
+	/* If the total weights are somehow 0, don't migrate at all */
+	if (!weight_total)
+		return;
+
+	target = ilx % weight_total;
+	for (i = 0; i < dests->nr_dests; i++) {
+		if (target < dests->weight_arr[i])
+			break;
+		target -= dests->weight_arr[i];
+	}
+
+	/* No index being chosen indicates a mistake in the algorithm */
+	if (i == dests->nr_dests) {
+		WARN_ONCE(1, "Error determining target interleave node");
+		return;
+	}
+
+isolate:
+	if (!folio_isolate_lru(folio))
+		return;
+
+	list_add(&folio->lru, &migration_lists[i]);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
 		unsigned long next, struct mm_walk *walk)
 {
-	struct list_head *migration_list = walk->private;
+	struct damos_va_migrate_private *priv = walk->private;
+	struct damos *s = priv->scheme;
+	struct list_head *migration_lists = priv->migration_lists;
+	struct damos_migrate_dests *dests = &s->migrate_dests;
 	struct folio *folio;
 	spinlock_t *ptl;
 	pmd_t pmde;
@@ -630,12 +695,8 @@ static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
 	if (!folio)
 		goto unlock;
 
-	if (!folio_isolate_lru(folio))
-		goto put_folio;
-
-	list_add(&folio->lru, migration_list);
+	damos_va_migrate_folio(folio, walk->vma, addr, dests, migration_lists);
 
-put_folio:
 	folio_put(folio);
 unlock:
 	spin_unlock(ptl);
@@ -648,7 +709,10 @@ static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int damos_va_migrate_pte_entry(pte_t *pte, unsigned long addr,
 		unsigned long enxt, struct mm_walk *walk)
 {
-	struct list_head *migration_list = walk->private;
+	struct damos_va_migrate_private *priv = walk->private;
+	struct damos *s = priv->scheme;
+	struct list_head *migration_lists = priv->migration_lists;
+	struct damos_migrate_dests *dests = &s->migrate_dests;
 	struct folio *folio;
 	pte_t ptent;
 
@@ -660,12 +724,8 @@ static int damos_va_migrate_pte_entry(pte_t *pte, unsigned long addr,
 	if (!folio)
 		return 0;
 
-	if (!folio_isolate_lru(folio))
-		goto out;
-
-	list_add(&folio->lru, migration_list);
+	damos_va_migrate_folio(folio, walk->vma, addr, dests, migration_lists);
 
-out:
 	folio_put(folio);
 	return 0;
 }
@@ -717,34 +777,54 @@ static unsigned long damos_va_migrate(struct damon_target *target,
 		struct damon_region *r, struct damos *s,
 		unsigned long *sz_filter_passed)
 {
-	LIST_HEAD(folio_list);
+	struct damos_va_migrate_private priv;
 	struct task_struct *task;
 	struct mm_struct *mm;
+	int nr_dests;
+	int nid;
+	bool use_target_nid;
 	unsigned long applied = 0;
+	struct damos_migrate_dests *dests = &s->migrate_dests;
 	struct mm_walk_ops walk_ops = {
 		.pmd_entry = damos_va_migrate_pmd_entry,
 		.pte_entry = damos_va_migrate_pte_entry,
 		.walk_lock = PGWALK_RDLOCK,
 	};
 
+	use_target_nid = dests->nr_dests == 0;
+	nr_dests = use_target_nid ? 1 : dests->nr_dests;
+	priv.scheme = s;
+	priv.migration_lists = kmalloc_array(nr_dests,
+		sizeof(struct list_head), GFP_KERNEL);
+	if (!priv.migration_lists)
+		return 0;
+
+	for (int i = 0; i < nr_dests; i++)
+		INIT_LIST_HEAD(&priv.migration_lists[i]);
+
 	task = damon_get_task_struct(target);
 	if (!task)
-		return 0;
+		goto free_lists;
 
 	mm = damon_get_mm(target);
 	if (!mm)
 		goto put_task;
 
 	mmap_read_lock(mm);
-	walk_page_range(mm, r->ar.start, r->ar.end, &walk_ops, &folio_list);
+	walk_page_range(mm, r->ar.start, r->ar.end, &walk_ops, &priv);
 	mmap_read_unlock(mm);
 	mmput(mm);
 
-	applied = damon_migrate_pages(&folio_list, s->target_nid);
-	cond_resched();
+	for (int i = 0; i < nr_dests; i++) {
+		nid = use_target_nid ? s->target_nid : dests->node_id_arr[i];
+		applied += damon_migrate_pages(&priv.migration_lists[i], nid);
+		cond_resched();
+	}
 
 put_task:
 	put_task_struct(task);
+free_lists:
+	kfree(priv.migration_lists);
 	return applied * PAGE_SIZE;
 }
 
-- 
2.43.5