linux-kernel - [PATCH 06/14] lru/mlock: using per lruvec lock in munlock

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: <1566294517-86418-7-git-send-email-alex.shi@linux.alibaba.com>
Date:   Tue, 20 Aug 2019 17:48:29 +0800
From:   Alex Shi <alex.shi@...ux.alibaba.com>
To:     cgroups@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Tejun Heo <tj@...nel.org>
Cc:     Alex Shi <alex.shi@...ux.alibaba.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Michal Hocko <mhocko@...e.com>,
        Andrey Ryabinin <aryabinin@...tuozzo.com>,
        swkhack <swkhack@...il.com>,
        "Potyra, Stefan" <Stefan.Potyra@...ktrobit.com>
Subject: [PATCH 06/14] lru/mlock: using per lruvec lock in munlock

This patch using sperate lruvec lock for each of pages in
__munlock_pagevec().

Also this patch pass a lruvec in __munlock_isolate_lru_page() as
parameter to reduce a repeat lruvec locating.

Signed-off-by: Alex Shi <alex.shi@...ux.alibaba.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Vlastimil Babka <vbabka@...e.cz>
Cc: Michal Hocko <mhocko@...e.com>
Cc: Mel Gorman <mgorman@...hsingularity.net>
Cc: Andrey Ryabinin <aryabinin@...tuozzo.com>
Cc: swkhack <swkhack@...il.com>
Cc: "Potyra, Stefan" <Stefan.Potyra@...ktrobit.com>
Cc: Tejun Heo <tj@...nel.org>
Cc: cgroups@...r.kernel.org
Cc: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org
---
 mm/mlock.c | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/mm/mlock.c b/mm/mlock.c
index 1279684bada0..9915968d490a 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -106,12 +106,10 @@ void mlock_vma_page(struct page *page)
  * Isolate a page from LRU with optional get_page() pin.
  * Assumes lru_lock already held and page already pinned.
  */
-static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
+static bool __munlock_isolate_lru_page(struct page *page,
+			struct lruvec *lruvec, bool getpage)
 {
 	if (PageLRU(page)) {
-		struct lruvec *lruvec;
-
-		lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
 		if (getpage)
 			get_page(page);
 		ClearPageLRU(page);
@@ -183,6 +181,9 @@ unsigned int munlock_vma_page(struct page *page)
 {
 	int nr_pages;
 	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
+
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
@@ -194,7 +195,8 @@ unsigned int munlock_vma_page(struct page *page)
 	 * might otherwise copy PageMlocked to part of the tail pages before
 	 * we clear it in the head page. It also stabilizes hpage_nr_pages().
 	 */
-	spin_lock_irq(&pgdat->lruvec.lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
+	sync_lruvec_pgdat(lruvec, pgdat);
 
 	if (!TestClearPageMlocked(page)) {
 		/* Potentially, PTE-mapped THP: do not skip the rest PTEs */
@@ -205,15 +207,15 @@ unsigned int munlock_vma_page(struct page *page)
 	nr_pages = hpage_nr_pages(page);
 	__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
 
-	if (__munlock_isolate_lru_page(page, true)) {
-		spin_unlock_irq(&pgdat->lruvec.lru_lock);
+	if (__munlock_isolate_lru_page(page, lruvec, true)) {
+		spin_unlock_irq(&lruvec->lru_lock);
 		__munlock_isolated_page(page);
 		goto out;
 	}
 	__munlock_isolation_failed(page);
 
 unlock_out:
-	spin_unlock_irq(&pgdat->lruvec.lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 out:
 	return nr_pages - 1;
@@ -291,28 +293,30 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
 	pagevec_init(&pvec_putback);
 
 	/* Phase 1: page isolation */
-	spin_lock_irq(&zone->zone_pgdat->lruvec.lru_lock);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
+		pg_data_t *pgdat = page_pgdat(page);
+		struct lruvec *lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
+		spin_lock_irq(&lruvec->lru_lock);
+		sync_lruvec_pgdat(lruvec, pgdat);
 		if (TestClearPageMlocked(page)) {
 			/*
 			 * We already have pin from follow_page_mask()
 			 * so we can spare the get_page() here.
 			 */
-			if (__munlock_isolate_lru_page(page, false))
+			if (__munlock_isolate_lru_page(page, lruvec, false)) {
+				__mod_zone_page_state(zone, NR_MLOCK,  -1);
+				spin_unlock_irq(&lruvec->lru_lock);
 				continue;
-			else
+			} else
 				__munlock_isolation_failed(page);
-		} else {
-			delta_munlocked++;
 		}
 
 		/*
@@ -323,9 +327,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		 */
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
+		spin_unlock_irq(&lruvec->lru_lock);
 	}
-	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
-	spin_unlock_irq(&zone->zone_pgdat->lruvec.lru_lock);
 
 	/* Now we can release pins of pages that we are not munlocking */
 	pagevec_release(&pvec_putback);
-- 
1.8.3.1