From 1121828a0c213caa55ddd5ee23ee78e99cbdd33e Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Tue, 4 May 2021 18:34:59 -0700
Subject: [PATCH] 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@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Barry Song <song.bao.hua@hisilicon.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9a263a1c200e..5425936a4590 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1451,16 +1451,18 @@ static void __free_huge_page(struct page *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 hstate *h, nodemask_t *nodes_allowed,
 				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 hstate *h, unsigned long count,
 						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,
-- 
2.20.1