linux-kernel - [PATCH v3 5/8] hugetlb: call update_and_free_page without hugetlb

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210331034148.112624-6-mike.kravetz@oracle.com>
Date:   Tue, 30 Mar 2021 20:41:45 -0700
From:   Mike Kravetz <mike.kravetz@...cle.com>
To:     linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc:     Roman Gushchin <guro@...com>, Michal Hocko <mhocko@...e.com>,
        Shakeel Butt <shakeelb@...gle.com>,
        Oscar Salvador <osalvador@...e.de>,
        David Hildenbrand <david@...hat.com>,
        Muchun Song <songmuchun@...edance.com>,
        David Rientjes <rientjes@...gle.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Matthew Wilcox <willy@...radead.org>,
        HORIGUCHI NAOYA <naoya.horiguchi@....com>,
        "Aneesh Kumar K . V" <aneesh.kumar@...ux.ibm.com>,
        Waiman Long <longman@...hat.com>, Peter Xu <peterx@...hat.com>,
        Mina Almasry <almasrymina@...gle.com>,
        Hillf Danton <hdanton@...a.com>,
        Joonsoo Kim <iamjoonsoo.kim@....com>,
        Barry Song <song.bao.hua@...ilicon.com>,
        Will Deacon <will@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Mike Kravetz <mike.kravetz@...cle.com>
Subject: [PATCH v3 5/8] 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.

Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
Acked-by: Michal Hocko <mhocko@...e.com>
Reviewed-by: Muchun Song <songmuchun@...edance.com>
Reviewed-by: Miaohe Lin <linmiaohe@...wei.com>
---
 mm/hugetlb.c | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 16beabbbbe49..ac4be941a3e5 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 @@ int dissolve_free_huge_page(struct page *page)
 		}
 		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);
@@ -2674,22 +2683,34 @@ 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,
-- 
2.30.2