From: Mike Kravetz <mike.kravetz@xxxxxxxxxx> Subject: hugetlb: call update_and_free_page without hugetlb_lock With the introduction of remove_hugetlb_page(), there is no need for update_and_free_page to hold the hugetlb lock. Change all callers to drop the lock before calling. With additional code modifications, this will allow loops which decrease the huge page pool to drop the hugetlb_lock with each page to reduce long hold times. The ugly unlock/lock cycle in free_pool_huge_page will be removed in a subsequent patch which restructures free_pool_huge_page. Link: https://lkml.kernel.org/r/20210409205254.242291-6-mike.kravetz@xxxxxxxxxx Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx> Acked-by: Michal Hocko <mhocko@xxxxxxxx> Reviewed-by: Muchun Song <songmuchun@xxxxxxxxxxxxx> Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx> Reviewed-by: Oscar Salvador <osalvador@xxxxxxx> Cc: "Aneesh Kumar K . V" <aneesh.kumar@xxxxxxxxxxxxx> Cc: Barry Song <song.bao.hua@xxxxxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Hillf Danton <hdanton@xxxxxxxx> Cc: HORIGUCHI NAOYA <naoya.horiguchi@xxxxxxx> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Mina Almasry <almasrymina@xxxxxxxxxx> Cc: Peter Xu <peterx@xxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Roman Gushchin <guro@xxxxxx> Cc: Shakeel Butt <shakeelb@xxxxxxxxxx> Cc: Waiman Long <longman@xxxxxxxxxx> Cc: Will Deacon <will@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/hugetlb.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) --- a/mm/hugetlb.c~hugetlb-call-update_and_free_page-without-hugetlb_lock +++ a/mm/hugetlb.c @@ -1451,16 +1451,18 @@ static void __free_huge_page(struct page if (HPageTemporary(page)) { remove_hugetlb_page(h, page, false); + spin_unlock(&hugetlb_lock); update_and_free_page(h, page); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_page(h, page, true); + spin_unlock(&hugetlb_lock); update_and_free_page(h, page); } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); + spin_unlock(&hugetlb_lock); } - spin_unlock(&hugetlb_lock); } /* @@ -1741,7 +1743,13 @@ static int free_pool_huge_page(struct hs list_entry(h->hugepage_freelists[node].next, struct page, lru); remove_hugetlb_page(h, page, acct_surplus); + /* + * unlock/lock around update_and_free_page is temporary + * and will be removed with subsequent patch. + */ + spin_unlock(&hugetlb_lock); update_and_free_page(h, page); + spin_lock(&hugetlb_lock); ret = 1; break; } @@ -1810,8 +1818,9 @@ retry: } remove_hugetlb_page(h, page, false); h->max_huge_pages--; + spin_unlock(&hugetlb_lock); update_and_free_page(h, head); - rc = 0; + return 0; } out: spin_unlock(&hugetlb_lock); @@ -2563,22 +2572,34 @@ static void try_to_free_low(struct hstat nodemask_t *nodes_allowed) { int i; + struct page *page, *next; + LIST_HEAD(page_list); if (hstate_is_gigantic(h)) return; + /* + * Collect pages to be freed on a list, and free after dropping lock + */ for_each_node_mask(i, *nodes_allowed) { - struct page *page, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(page, next, freel, lru) { if (count >= h->nr_huge_pages) - return; + goto out; if (PageHighMem(page)) continue; remove_hugetlb_page(h, page, false); - update_and_free_page(h, page); + list_add(&page->lru, &page_list); } } + +out: + spin_unlock(&hugetlb_lock); + list_for_each_entry_safe(page, next, &page_list, lru) { + update_and_free_page(h, page); + cond_resched(); + } + spin_lock(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, _
