mm/demotion: demote pages according to allocation fallback order

Currently, a higher tier node can only be demoted to selected nodes on the
next lower tier as defined by the demotion path.  This strict demotion
order does not work in all use cases (e.g.  some use cases may want to
allow cross-socket demotion to another node in the same demotion tier as a
fallback when the preferred demotion node is out of space).  This demotion
order is also inconsistent with the page allocation fallback order when
all the nodes in a higher tier are out of space: The page allocation can
fall back to any node from any lower tier, whereas the demotion order
doesn't allow that currently.

This patch adds support to get all the allowed demotion targets for a
memory tier.  demote_page_list() function is now modified to utilize this
allowed node mask as the fallback allocation mask.

Link: https://lkml.kernel.org/r/20220818131042.113280-9-aneesh.kumar@linux.ibm.com
Signed-off-by: Jagdish Gediya <jvgediya.oss@gmail.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 43 insertions, 15 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index b7e9d8f8f649..809df16c7c0d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1533,21 +1533,34 @@ static void folio_check_dirty_writeback(struct folio *folio,
 		mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
 }
 
-static struct page *alloc_demote_page(struct page *page, unsigned long node)
+static struct page *alloc_demote_page(struct page *page, unsigned long private)
 {
-	struct migration_target_control mtc = {
-		/*
-		 * Allocate from 'node', or fail quickly and quietly.
-		 * When this happens, 'page' will likely just be discarded
-		 * instead of migrated.
-		 */
-		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
-			    __GFP_THISNODE  | __GFP_NOWARN |
-			    __GFP_NOMEMALLOC | GFP_NOWAIT,
-		.nid = node
-	};
+	struct page *target_page;
+	nodemask_t *allowed_mask;
+	struct migration_target_control *mtc;
+
+	mtc = (struct migration_target_control *)private;
+
+	allowed_mask = mtc->nmask;
+	/*
+	 * make sure we allocate from the target node first also trying to
+	 * demote or reclaim pages from the target node via kswapd if we are
+	 * low on free memory on target node. If we don't do this and if
+	 * we have free memory on the slower(lower) memtier, we would start
+	 * allocating pages from slower(lower) memory tiers without even forcing
+	 * a demotion of cold pages from the target memtier. This can result
+	 * in the kernel placing hot pages in slower(lower) memory tiers.
+	 */
+	mtc->nmask = NULL;
+	mtc->gfp_mask |= __GFP_THISNODE;
+	target_page = alloc_migration_target(page, (unsigned long)mtc);
+	if (target_page)
+		return target_page;
 
-	return alloc_migration_target(page, (unsigned long)&mtc);
+	mtc->gfp_mask &= ~__GFP_THISNODE;
+	mtc->nmask = allowed_mask;
+
+	return alloc_migration_target(page, (unsigned long)mtc);
 }
 
 /*
@@ -1560,6 +1573,19 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
 {
 	int target_nid = next_demotion_node(pgdat->node_id);
 	unsigned int nr_succeeded;
+	nodemask_t allowed_mask;
+
+	struct migration_target_control mtc = {
+		/*
+		 * Allocate from 'node', or fail quickly and quietly.
+		 * When this happens, 'page' will likely just be discarded
+		 * instead of migrated.
+		 */
+		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN |
+			__GFP_NOMEMALLOC | GFP_NOWAIT,
+		.nid = target_nid,
+		.nmask = &allowed_mask
+	};
 
 	if (list_empty(demote_pages))
 		return 0;
@@ -1567,10 +1593,12 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
 	if (target_nid == NUMA_NO_NODE)
 		return 0;
 
+	node_get_allowed_targets(pgdat, &allowed_mask);
+
 	/* Demotion ignores all cpuset and mempolicy settings */
 	migrate_pages(demote_pages, alloc_demote_page, NULL,
-			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
-			    &nr_succeeded);
+		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
+		      &nr_succeeded);
 
 	if (current_is_kswapd())
 		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);