Received-SPF: pass (google.com: domain of linux-kernel+bounces-70702-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Byungchul Park <byungchul@sk.com>
To: mingo@redhat.com,
	peterz@infradead.org,
	juri.lelli@redhat.com,
	vincent.guittot@linaro.org,
	dietmar.eggemann@arm.com,
	rostedt@goodmis.org,
	bsegall@google.com,
	mgorman@suse.de,
	bristot@redhat.com,
	vschneid@redhat.com
Cc: linux-kernel@vger.kernel.org,
	linux-mm@kvack.org,
	kernel_team@skhynix.com,
	akpm@linux-foundation.org
Subject: [PATCH v4] sched/numa, mm: do not try to migrate memory to memoryless nodes
Date: Mon, 19 Feb 2024 13:19:20 +0900
Message-Id: <20240219041920.1183-1-byungchul@sk.com>
Precedence: bulk

Changes from v3:
	1. Rewrite the comment in code and the commit message to make it
	   more clear. (feedbacked by Oscar Salvador)
	2. Add "Reviewed-by: Oscar Salvador <osalvador@suse.de>"

Changes from v2:
	1. Rewrite the comment in code and the commit message becasue it
	   turns out that this patch is not the real fix for the oops
	   descriped. The real fix goes in another patch below:

	   https://lore.kernel.org/lkml/20240216111502.79759-1-byungchul@sk.com/

Changes from v1:
	1. Trim the verbose oops in the commit message. (feedbacked by
	   Phil Auld)
	2. Rewrite a comment in code. (feedbacked by Phil Auld)

--->8---
From 98f5d472c08e3ed5b9b6543290d392a2e50fcf3c Mon Sep 17 00:00:00 2001
From: Byungchul Park <byungchul@sk.com>
Date: Mon, 19 Feb 2024 13:10:47 +0900
Subject: [PATCH v4] sched/numa, mm: do not try to migrate memory to memoryless nodes

Memoryless nodes do not have any memory to migrate to, so stop trying
it.

Signed-off-by: Byungchul Park <byungchul@sk.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
---
 kernel/sched/fair.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d7a3c63a2171..3e3b44ae72d1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1828,6 +1828,12 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
 	int dst_nid = cpu_to_node(dst_cpu);
 	int last_cpupid, this_cpupid;
 
+	/*
+	 * Cannot migrate to memoryless nodes.
+	 */
+	if (!node_state(dst_nid, N_MEMORY))
+		return false;
+
 	/*
 	 * The pages in slow memory node should be migrated according
 	 * to hot/cold instead of private/shared.
-- 
2.17.1