From 00ccf40ae298262feb13b3ad56b4428647f3aafa Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 15 Apr 2025 14:15:03 +0200 Subject: [PATCH] mm, hugetlb: avoid passing a null nodemask when there is mbind policy Before trying to allocate a page, gather_surplus_pages() sets up a nodemask for the nodes we can allocate from, but instead of passing the nodemask down the road to the page allocator, it iterates over the nodes within that nodemask right there, meaning that the page allocator will receive a preferred_nid and a null nodemask. This is a problem when using a memory policy, because it might be that the page allocator ends up using a node as a fallback which is not represented in the policy. Avoid that by passing the nodemask directly to the page allocator, so it can filter out fallback nodes that are not part of the nodemask. Link: https://lkml.kernel.org/r/20250415121503.376811-1-osalvador@suse.de Signed-off-by: Oscar Salvador Reviewed-by: Vlastimil Babka Cc: David Hildenbrand Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/hugetlb.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a2c111447812..38738293e6b6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2419,7 +2419,6 @@ static int gather_surplus_pages(struct hstate *h, long delta) long i; long needed, allocated; bool alloc_ok = true; - int node; nodemask_t *mbind_nodemask, alloc_nodemask; mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); @@ -2443,21 +2442,12 @@ retry: for (i = 0; i < needed; i++) { folio = NULL; - /* Prioritize current node */ - if (node_isset(numa_mem_id(), alloc_nodemask)) - folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), - numa_mem_id(), NULL); - - if (!folio) { - for_each_node_mask(node, alloc_nodemask) { - if (node == numa_mem_id()) - continue; - folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), - node, NULL); - if (folio) - break; - } - } + /* + * It is okay to use NUMA_NO_NODE because we use numa_mem_id() + * down the road to pick the current node if that is the case. + */ + folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), + NUMA_NO_NODE, &alloc_nodemask); if (!folio) { alloc_ok = false; break; -- 2.25.1