From 382360d289c1e1d89df06f33c4d5b874b38ef267 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Thu, 3 Apr 2025 14:41:38 +0800 Subject: mm/hugetlb: fix nid mismatch in alloc_surplus_hugetlb_folio() It's wrong to use nid directly since the nid may be changed in allocation. Use folio_nid() to obtain the nid of folio instead. Fix: 2273dea6b1e1 ("mm/hugetlb: update nr_huge_pages and surplus_huge_pages together") Link: https://lkml.kernel.org/r/20250403064138.2867929-1-liushixin2@huawei.com Signed-off-by: Liu Shixin Acked-by: Oscar Salvador Cc: David Hildenbrand Cc: Kefeng Wang Cc: Muchun Song Cc: Nanyong Sun Signed-off-by: Andrew Morton --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 39f92aad7bd1e1..6670f9b9e07ae9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2271,7 +2271,7 @@ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, * as surplus_pages, otherwise it might confuse * persistent_huge_pages() momentarily. */ - __prep_account_new_huge_page(h, nid); + __prep_account_new_huge_page(h, folio_nid(folio)); /* * We could have raced with the pool size change. -- cgit 1.2.3-korg From aabf58bfaacedb3f54801ba09c6d50daf83b74f4 Mon Sep 17 00:00:00 2001 From: Jinjiang Tu Date: Mon, 7 Apr 2025 20:47:06 +0800 Subject: mm/hugetlb: fix set_max_huge_pages() when there are surplus pages In set_max_huge_pages(), min_count is computed taking into account surplus huge pages, which might lead in some cases to not be able to free huge pages and end up accounting them as surplus instead. One way to solve it is to subtract surplus_huge_pages directly, but we cannot do it blindly because there might be surplus pages that are also free pages, which might happen when we fail to restore the vmemmap for optimized hvo pages. So we could be subtracting the same page twice. In order to work this around, let us first compute the number of free persistent pages, and use that along with surplus pages to compute min_count. Steps to reproduce: 1) create 5 hugetlb folios in Node0 2) run a program to use all the hugetlb folios 3) echo 0 > nr_hugepages for Node0 to free the hugetlb folios. Thus the 5 hugetlb folios in Node0 are accounted as surplus. 4) create 5 hugetlb folios in Node1 5) echo 0 > nr_hugepages for Node1 to free the hugetlb folios The result: Node0 Node1 Total 5 5 Free 0 5 Surp 5 5 The result with this patch: Node0 Node1 Total 5 0 Free 0 0 Surp 5 0 Link: https://lkml.kernel.org/r/20250409055957.3774471-1-tujinjiang@huawei.com Link: https://lkml.kernel.org/r/20250407124706.2688092-1-tujinjiang@huawei.com Fixes: 9a30523066cd ("hugetlb: add per node hstate attributes") Signed-off-by: Jinjiang Tu Acked-by: Oscar Salvador Cc: David Hildenbrand Cc: Kefeng Wang Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/hugetlb.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6670f9b9e07ae9..ea065347866e2c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3825,6 +3825,7 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { + unsigned long persistent_free_count; unsigned long min_count; unsigned long allocated; struct folio *folio; @@ -3959,8 +3960,24 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. + * + * min_count is the expected number of persistent pages, we + * shouldn't calculate min_count by using + * resv_huge_pages + persistent_huge_pages() - free_huge_pages, + * because there may exist free surplus huge pages, and this will + * lead to subtracting twice. Free surplus huge pages come from HVO + * failing to restore vmemmap, see comments in the callers of + * hugetlb_vmemmap_restore_folio(). Thus, we should calculate + * persistent free count first. */ - min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; + persistent_free_count = h->free_huge_pages; + if (h->free_huge_pages > persistent_huge_pages(h)) { + if (h->free_huge_pages > h->surplus_huge_pages) + persistent_free_count -= h->surplus_huge_pages; + else + persistent_free_count = 0; + } + min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); -- cgit 1.2.3-korg From 9e2bd67773579fdd2e58de9628c2d319f3f518e7 Mon Sep 17 00:00:00 2001 From: wangxuewen Date: Mon, 7 Apr 2025 18:30:17 +0800 Subject: mm/hugetlb: add a line break at the end of the format string Missing line break at the end of the format string. Link: https://lkml.kernel.org/r/20250407103017.2979821-1-18810879172@163.com Signed-off-by: wangxuewen Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea065347866e2c..e3e6ac991b9c6b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4647,7 +4647,7 @@ static void __init hugetlb_sysfs_init(void) err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) - pr_err("HugeTLB: Unable to add hstate %s", h->name); + pr_err("HugeTLB: Unable to add hstate %s\n", h->name); } #ifdef CONFIG_NUMA -- cgit 1.2.3-korg