All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alex Shi <alex.shi@linux.alibaba.com>
To: akpm@linux-foundation.org, mgorman@techsingularity.net,
	tj@kernel.org, hughd@google.com, khlebnikov@yandex-team.ru,
	daniel.m.jordan@oracle.com, yang.shi@linux.alibaba.com,
	willy@infradead.org, hannes@cmpxchg.org, lkp@intel.com,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	cgroups@vger.kernel.org, shakeelb@google.com,
	iamjoonsoo.kim@lge.com, richard.weiyang@gmail.com,
	kirill@shutemov.name, alexander.duyck@gmail.com,
	rong.a.chen@intel.com
Subject: [PATCH v17 16/21] mm/swap: serialize memcg changes in pagevec_lru_move_fn
Date: Sat, 25 Jul 2020 20:59:53 +0800	[thread overview]
Message-ID: <1595681998-19193-17-git-send-email-alex.shi@linux.alibaba.com> (raw)
In-Reply-To: <1595681998-19193-1-git-send-email-alex.shi@linux.alibaba.com>

Hugh Dickins' found a memcg change bug on original version:
If we want to change the pgdat->lru_lock to memcg's lruvec lock, we have
to serialize mem_cgroup_move_account during pagevec_lru_move_fn. The
possible bad scenario would like:

	cpu 0					cpu 1
lruvec = mem_cgroup_page_lruvec()
					if (!isolate_lru_page())
						mem_cgroup_move_account

spin_lock_irqsave(&lruvec->lru_lock <== wrong lock.

So we need the ClearPageLRU to block isolate_lru_page(), that serializes
the memcg change. and then removing the PageLRU check in move_fn callee
as the consequence.

Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/swap.c | 46 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 36 insertions(+), 10 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 5092fe9c8c47..3029b3f74811 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -221,8 +221,14 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 			spin_lock_irqsave(&pgdat->lru_lock, flags);
 		}
 
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
+			continue;
+
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		(*move_fn)(page, lruvec);
+
+		SetPageLRU(page);
 	}
 	if (pgdat)
 		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
@@ -232,7 +238,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 
 static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageUnevictable(page)) {
+	if (!PageUnevictable(page)) {
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		ClearPageActive(page);
 		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
@@ -306,7 +312,7 @@ void lru_note_cost_page(struct page *page)
 
 static void __activate_page(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+	if (!PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = hpage_nr_pages(page);
 
@@ -362,7 +368,8 @@ void activate_page(struct page *page)
 
 	page = compound_head(page);
 	spin_lock_irq(&pgdat->lru_lock);
-	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
+	if (PageLRU(page))
+		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
 	spin_unlock_irq(&pgdat->lru_lock);
 }
 #endif
@@ -520,9 +527,6 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 	bool active;
 	int nr_pages = hpage_nr_pages(page);
 
-	if (!PageLRU(page))
-		return;
-
 	if (PageUnevictable(page))
 		return;
 
@@ -563,7 +567,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 
 static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+	if (PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = hpage_nr_pages(page);
 
@@ -580,7 +584,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 
 static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
+	if (PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
 		int nr_pages = hpage_nr_pages(page);
@@ -654,7 +658,7 @@ void deactivate_file_page(struct page *page)
 	 * In a workload with many unevictable page such as mprotect,
 	 * unevictable page deactivation for accelerating reclaim is pointless.
 	 */
-	if (PageUnevictable(page))
+	if (PageUnevictable(page) || !PageLRU(page))
 		return;
 
 	if (likely(get_page_unless_zero(page))) {
@@ -976,7 +980,29 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
  */
 void __pagevec_lru_add(struct pagevec *pvec)
 {
-	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn);
+	int i;
+	struct pglist_data *pgdat = NULL;
+	struct lruvec *lruvec;
+	unsigned long flags = 0;
+
+	for (i = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		struct pglist_data *pagepgdat = page_pgdat(page);
+
+		if (pagepgdat != pgdat) {
+			if (pgdat)
+				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+			pgdat = pagepgdat;
+			spin_lock_irqsave(&pgdat->lru_lock, flags);
+		}
+
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		__pagevec_lru_add_fn(page, lruvec);
+	}
+	if (pgdat)
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	release_pages(pvec->pages, pvec->nr);
+	pagevec_reinit(pvec);
 }
 
 /**
-- 
1.8.3.1


  parent reply	other threads:[~2020-07-25 13:00 UTC|newest]

Thread overview: 209+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-25 12:59 [PATCH v17 00/21] per memcg lru lock Alex Shi
2020-07-25 12:59 ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 01/21] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-08-06  3:47   ` Alex Shi
2020-08-06  3:47     ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 02/21] mm/page_idle: no unlikely double check for idle page counting Alex Shi
2020-07-25 12:59 ` [PATCH v17 03/21] mm/compaction: correct the comments of compact_defer_shift Alex Shi
2020-07-27 17:29   ` Alexander Duyck
2020-07-27 17:29     ` Alexander Duyck
2020-07-28 11:59     ` Alex Shi
2020-07-28 11:59       ` Alex Shi
2020-07-28 14:17       ` Alexander Duyck
2020-07-28 14:17         ` Alexander Duyck
2020-07-28 14:17         ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 04/21] mm/compaction: rename compact_deferred as compact_should_defer Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 05/21] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 06/21] mm/thp: clean up lru_add_page_tail Alex Shi
2020-07-25 12:59 ` [PATCH v17 07/21] mm/thp: remove code path which never got into Alex Shi
2020-07-25 12:59 ` [PATCH v17 08/21] mm/thp: narrow lru locking Alex Shi
2020-07-25 12:59 ` [PATCH v17 09/21] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 10/21] mm/swap: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-07-25 12:59 ` [PATCH v17 11/21] mm/lru: move lru_lock holding in func lru_note_cost_page Alex Shi
2020-08-05 21:18   ` Alexander Duyck
2020-08-05 21:18     ` Alexander Duyck
2020-08-05 21:18     ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 12/21] mm/lru: move lock into lru_note_cost Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 13/21] mm/lru: introduce TestClearPageLRU Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-29  3:53   ` Alex Shi
2020-07-29  3:53     ` Alex Shi
2020-08-05 22:43     ` Alexander Duyck
2020-08-05 22:43       ` Alexander Duyck
2020-08-06  1:54       ` Alex Shi
2020-08-06  1:54         ` Alex Shi
2020-08-06 14:41         ` Alexander Duyck
2020-08-06 14:41           ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 14/21] mm/compaction: do page isolation first in compaction Alex Shi
2020-08-04 21:35   ` Alexander Duyck
2020-08-04 21:35     ` Alexander Duyck
2020-08-04 21:35     ` Alexander Duyck
2020-08-06 18:38   ` Alexander Duyck
2020-08-06 18:38     ` Alexander Duyck
2020-08-06 18:38     ` Alexander Duyck
2020-08-07  3:24     ` Alex Shi
2020-08-07  3:24       ` Alex Shi
2020-08-07 14:51       ` Alexander Duyck
2020-08-07 14:51         ` Alexander Duyck
2020-08-07 14:51         ` Alexander Duyck
2020-08-10 13:10         ` Alex Shi
2020-08-10 13:10           ` Alex Shi
2020-08-10 14:41           ` Alexander Duyck
2020-08-10 14:41             ` Alexander Duyck
2020-08-10 14:41             ` Alexander Duyck
2020-08-11  8:22             ` Alex Shi
2020-08-11 14:47               ` Alexander Duyck
2020-08-11 14:47                 ` Alexander Duyck
2020-08-11 14:47                 ` Alexander Duyck
2020-08-12 11:43                 ` Alex Shi
2020-08-12 12:16                   ` Alex Shi
2020-08-12 12:16                     ` Alex Shi
2020-08-12 16:51                   ` Alexander Duyck
2020-08-12 16:51                     ` Alexander Duyck
2020-08-12 16:51                     ` Alexander Duyck
2020-08-13  1:46                     ` Alex Shi
2020-08-13  2:17                       ` Alexander Duyck
2020-08-13  2:17                         ` Alexander Duyck
2020-08-13  2:17                         ` Alexander Duyck
2020-08-13  3:52                         ` Alex Shi
2020-08-13  3:52                           ` Alex Shi
2020-08-13  4:02                       ` [RFC PATCH 0/3] " Alexander Duyck
2020-08-13  4:02                         ` Alexander Duyck
2020-08-13  4:02                         ` [RFC PATCH 1/3] mm: Drop locked from isolate_migratepages_block Alexander Duyck
2020-08-13  4:02                           ` Alexander Duyck
2020-08-13  6:56                           ` Alex Shi
2020-08-13  6:56                             ` Alex Shi
2020-08-13 14:32                             ` Alexander Duyck
2020-08-13 14:32                               ` Alexander Duyck
2020-08-13 14:32                               ` Alexander Duyck
2020-08-14  7:25                               ` Alex Shi
2020-08-14  7:25                                 ` Alex Shi
2020-08-13  7:44                           ` Alex Shi
2020-08-13  7:44                             ` Alex Shi
2020-08-13 14:26                             ` Alexander Duyck
2020-08-13 14:26                               ` Alexander Duyck
2020-08-13  4:02                         ` [RFC PATCH 2/3] mm: Drop use of test_and_set_skip in favor of just setting skip Alexander Duyck
2020-08-13  4:02                           ` Alexander Duyck
2020-08-14  7:19                           ` Alex Shi
2020-08-14  7:19                             ` Alex Shi
2020-08-14 14:24                             ` Alexander Duyck
2020-08-14 14:24                               ` Alexander Duyck
2020-08-14 14:24                               ` Alexander Duyck
2020-08-14 21:15                               ` Alexander Duyck
2020-08-14 21:15                                 ` Alexander Duyck
2020-08-14 21:15                                 ` Alexander Duyck
2020-08-15  9:49                                 ` Alex Shi
2020-08-17 15:38                                   ` Alexander Duyck
2020-08-17 15:38                                     ` Alexander Duyck
2020-08-17 15:38                                     ` Alexander Duyck
2020-08-18  6:50                           ` Alex Shi
2020-08-18  6:50                             ` Alex Shi
2020-08-13  4:02                         ` [RFC PATCH 3/3] mm: Identify compound pages sooner in isolate_migratepages_block Alexander Duyck
2020-08-13  4:02                           ` Alexander Duyck
2020-08-14  7:20                           ` Alex Shi
2020-08-14  7:20                             ` Alex Shi
2020-08-17 22:58   ` [PATCH v17 14/21] mm/compaction: do page isolation first in compaction Alexander Duyck
2020-08-17 22:58     ` Alexander Duyck
2020-08-17 22:58     ` Alexander Duyck
2020-07-25 12:59 ` [PATCH v17 15/21] mm/thp: add tail pages into lru anyway in split_huge_page() Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-25 12:59 ` Alex Shi [this message]
2020-07-25 12:59 ` [PATCH v17 17/21] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-07-25 12:59   ` Alex Shi
2020-07-27 23:34   ` Alexander Duyck
2020-07-27 23:34     ` Alexander Duyck
2020-07-27 23:34     ` Alexander Duyck
2020-07-28  7:15     ` Alex Shi
2020-07-28  7:15       ` Alex Shi
2020-07-28 11:19     ` Alex Shi
2020-07-28 11:19       ` Alex Shi
2020-07-28 14:54       ` Alexander Duyck
2020-07-28 14:54         ` Alexander Duyck
2020-07-28 14:54         ` Alexander Duyck
2020-07-29  1:00         ` Alex Shi
2020-07-29  1:27           ` Alexander Duyck
2020-07-29  1:27             ` Alexander Duyck
2020-07-29  1:27             ` Alexander Duyck
2020-07-29  2:27             ` Alex Shi
2020-07-29  2:27               ` Alex Shi
2020-07-28 15:39     ` Alex Shi
2020-07-28 15:39       ` Alex Shi
2020-07-28 15:55       ` Alexander Duyck
2020-07-28 15:55         ` Alexander Duyck
2020-07-28 15:55         ` Alexander Duyck
2020-07-29  0:48         ` Alex Shi
2020-07-29  3:54   ` Alex Shi
2020-08-06  7:41   ` Alex Shi
2020-08-06  7:41     ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 18/21] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-07-29 17:52   ` Alexander Duyck
2020-07-29 17:52     ` Alexander Duyck
2020-07-29 17:52     ` Alexander Duyck
2020-07-30  6:08     ` Alex Shi
2020-07-30  6:08       ` Alex Shi
2020-07-31 14:20       ` Alexander Duyck
2020-07-31 14:20         ` Alexander Duyck
2020-07-31 14:20         ` Alexander Duyck
2020-07-31 21:14   ` [PATCH RFC] mm: Add function for testing if the current lruvec lock is valid alexander.h.duyck
2020-07-31 21:14     ` alexander.h.duyck-ral2JQCrhuEAvxtiuMwx3w
2020-07-31 23:54     ` Alex Shi
2020-07-31 23:54       ` Alex Shi
2020-08-02 18:20       ` Alexander Duyck
2020-08-02 18:20         ` Alexander Duyck
2020-08-02 18:20         ` Alexander Duyck
2020-08-04  6:13         ` Alex Shi
2020-08-04  6:13           ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 19/21] mm/vmscan: use relock for move_pages_to_lru Alex Shi
2020-08-03 22:49   ` Alexander Duyck
2020-08-03 22:49     ` Alexander Duyck
2020-08-04  6:23     ` Alex Shi
2020-08-04  6:23       ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 20/21] mm/pgdat: remove pgdat lru_lock Alex Shi
2020-08-03 22:42   ` Alexander Duyck
2020-08-03 22:42     ` Alexander Duyck
2020-08-03 22:42     ` Alexander Duyck
2020-08-03 22:45     ` Alexander Duyck
2020-08-03 22:45       ` Alexander Duyck
2020-08-03 22:45       ` Alexander Duyck
2020-08-04  6:22       ` Alex Shi
2020-08-04  6:22         ` Alex Shi
2020-07-25 12:59 ` [PATCH v17 21/21] mm/lru: revise the comments of lru_lock Alex Shi
2020-08-03 22:37   ` Alexander Duyck
2020-08-03 22:37     ` Alexander Duyck
2020-08-04 10:04     ` Alex Shi
2020-08-04 10:04       ` Alex Shi
2020-08-04 14:29       ` Alexander Duyck
2020-08-04 14:29         ` Alexander Duyck
2020-08-04 14:29         ` Alexander Duyck
2020-08-06  1:39         ` Alex Shi
2020-08-06  1:39           ` Alex Shi
2020-08-06 16:27           ` Alexander Duyck
2020-08-06 16:27             ` Alexander Duyck
2020-08-06 16:27             ` Alexander Duyck
2020-07-27  5:40 ` [PATCH v17 00/21] per memcg lru lock Alex Shi
2020-07-27  5:40   ` Alex Shi
2020-07-29 14:49   ` Alex Shi
2020-07-29 14:49     ` Alex Shi
2020-07-29 18:06     ` Hugh Dickins
2020-07-29 18:06       ` Hugh Dickins
2020-07-30  2:16       ` Alex Shi
2020-07-30  2:16         ` Alex Shi
2020-08-03 15:07         ` Michal Hocko
2020-08-03 15:07           ` Michal Hocko
2020-08-04  6:14           ` Alex Shi
2020-08-04  6:14             ` Alex Shi
2020-07-31 21:31 ` Alexander Duyck
2020-07-31 21:31   ` Alexander Duyck
2020-07-31 21:31   ` Alexander Duyck
2020-08-04  8:36 ` Alex Shi
2020-08-04  8:36   ` Alex Shi
2020-08-04  8:36 ` Alex Shi
2020-08-04  8:36   ` Alex Shi
2020-08-04  8:37 ` Alex Shi
2020-08-04  8:37   ` Alex Shi
2020-08-04  8:37 ` Alex Shi
2020-08-04  8:37   ` Alex Shi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1595681998-19193-17-git-send-email-alex.shi@linux.alibaba.com \
    --to=alex.shi@linux.alibaba.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=cgroups@vger.kernel.org \
    --cc=daniel.m.jordan@oracle.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=khlebnikov@yandex-team.ru \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@intel.com \
    --cc=mgorman@techsingularity.net \
    --cc=richard.weiyang@gmail.com \
    --cc=rong.a.chen@intel.com \
    --cc=shakeelb@google.com \
    --cc=tj@kernel.org \
    --cc=willy@infradead.org \
    --cc=yang.shi@linux.alibaba.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.