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]
Date:   Wed, 24 Mar 2021 17:28:33 -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>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Mike Kravetz <mike.kravetz@...cle.com>
Subject: [PATCH 6/8] hugetlb: change free_pool_huge_page to remove_pool_huge_page

free_pool_huge_page was called with hugetlb_lock held.  It would remove
a hugetlb page, and then free the corresponding pages to the lower level
allocators such as buddy.  free_pool_huge_page was called in a loop to
remove hugetlb pages and these loops could hold the hugetlb_lock for a
considerable time.

Create new routine remove_pool_huge_page to replace free_pool_huge_page.
remove_pool_huge_page will remove the hugetlb page, and it must be
called with the hugetlb_lock held.  It will return the removed page and
it is the responsibility of the caller to free the page to the lower
level allocators.  The hugetlb_lock is dropped before freeing to these
allocators which results in shorter lock hold times.

Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
---
 mm/hugetlb.c | 88 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 51 insertions(+), 37 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fae7f034d1eb..a9785e73379f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1204,7 +1204,7 @@ static int hstate_next_node_to_alloc(struct hstate *h,
 }
 
 /*
- * helper for free_pool_huge_page() - return the previously saved
+ * helper for remove_pool_huge_page() - return the previously saved
  * node ["this node"] from which to free a huge page.  Advance the
  * next node id whether or not we find a free huge page to free so
  * that the next attempt to free addresses the next node.
@@ -1720,16 +1720,18 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 }
 
 /*
- * Free huge page from pool from next node to free.
- * Attempt to keep persistent huge pages more or less
- * balanced over allowed nodes.
+ * Remove huge page from pool from next node to free.  Attempt to keep
+ * persistent huge pages more or less balanced over allowed nodes.
+ * This routine only 'removes' the hugetlb page.  The caller must make
+ * an additional call to free the page to low level allocators.
  * Called with hugetlb_lock locked.
  */
-static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
-							 bool acct_surplus)
+static struct page *remove_pool_huge_page(struct hstate *h,
+						nodemask_t *nodes_allowed,
+						 bool acct_surplus)
 {
 	int nr_nodes, node;
-	int ret = 0;
+	struct page *page = NULL;
 
 	for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
 		/*
@@ -1738,23 +1740,14 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 		 */
 		if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
 		    !list_empty(&h->hugepage_freelists[node])) {
-			struct page *page =
-				list_entry(h->hugepage_freelists[node].next,
+			page = 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;
 		}
 	}
 
-	return ret;
+	return page;
 }
 
 /*
@@ -2074,17 +2067,16 @@ static int gather_surplus_pages(struct hstate *h, long delta)
  *    to the associated reservation map.
  * 2) Free any unused surplus pages that may have been allocated to satisfy
  *    the reservation.  As many as unused_resv_pages may be freed.
- *
- * Called with hugetlb_lock held.  However, the lock could be dropped (and
- * reacquired) during calls to cond_resched_lock.  Whenever dropping the lock,
- * we must make sure nobody else can claim pages we are in the process of
- * freeing.  Do this by ensuring resv_huge_page always is greater than the
- * number of huge pages we plan to free when dropping the lock.
  */
 static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
+	struct page *page, *t_page;
+	struct list_head page_list;
+
+	/* Uncommit the reservation */
+	h->resv_huge_pages -= unused_resv_pages;
 
 	/* Cannot return gigantic pages currently */
 	if (hstate_is_gigantic(h))
@@ -2101,24 +2093,27 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * evenly across all nodes with memory. Iterate across these nodes
 	 * until we can no longer free unreserved surplus pages. This occurs
 	 * when the nodes with surplus pages have no free pages.
-	 * free_pool_huge_page() will balance the freed pages across the
+	 * remove_pool_huge_page() will balance the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
-	 *
-	 * Note that we decrement resv_huge_pages as we free the pages.  If
-	 * we drop the lock, resv_huge_pages will still be sufficiently large
-	 * to cover subsequent pages we may free.
 	 */
+	INIT_LIST_HEAD(&page_list);
 	while (nr_pages--) {
-		h->resv_huge_pages--;
-		unused_resv_pages--;
-		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
+		page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1);
+		if (!page)
 			goto out;
-		cond_resched_lock(&hugetlb_lock);
+
+		INIT_LIST_HEAD(&page->lru);
+		list_add(&page->lru, &page_list);
 	}
 
 out:
-	/* Fully uncommit the reservation */
-	h->resv_huge_pages -= unused_resv_pages;
+	spin_unlock(&hugetlb_lock);
+	list_for_each_entry_safe(page, t_page, &page_list, lru) {
+		list_del(&page->lru);
+		update_and_free_page(h, page);
+		cond_resched();
+	}
+	spin_lock(&hugetlb_lock);
 }
 
 
@@ -2648,6 +2643,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 			      nodemask_t *nodes_allowed)
 {
 	unsigned long min_count, ret;
+	struct page *page, *t_page;
+	struct list_head page_list;
 	NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);
 
 	/*
@@ -2757,11 +2754,28 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
 	min_count = max(count, min_count);
 	try_to_free_low(h, min_count, nodes_allowed);
+
+	/*
+	 * Collect pages to be removed on list without dropping lock
+	 */
+	INIT_LIST_HEAD(&page_list);
 	while (min_count < persistent_huge_pages(h)) {
-		if (!free_pool_huge_page(h, nodes_allowed, 0))
+		page = remove_pool_huge_page(h, nodes_allowed, 0);
+		if (!page)
 			break;
-		cond_resched_lock(&hugetlb_lock);
+
+		INIT_LIST_HEAD(&page->lru);
+		list_add(&page->lru, &page_list);
 	}
+	/* free the pages after dropping lock */
+	spin_unlock(&hugetlb_lock);
+	list_for_each_entry_safe(page, t_page, &page_list, lru) {
+		list_del(&page->lru);
+		update_and_free_page(h, page);
+		cond_resched();
+	}
+	spin_lock(&hugetlb_lock);
+
 	while (count < persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, 1))
 			break;
-- 
2.30.2

Powered by blists - more mailing lists