linux-mm.kvack.org archive mirror
 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
Subject: [PATCH v13 13/18] mm/swap: serialize memcg changes during pagevec_lru_move_fn
Date: Fri, 19 Jun 2020 16:33:51 +0800	[thread overview]
Message-ID: <1592555636-115095-14-git-send-email-alex.shi@linux.alibaba.com> (raw)
In-Reply-To: <1592555636-115095-1-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(), then serialize
the memcg change here.

Reported-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 | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 7ff9aa6a716a..cebb25ddeee7 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -203,7 +203,7 @@ int get_kernel_page(unsigned long start, int write, struct page **pages)
 EXPORT_SYMBOL_GPL(get_kernel_page);
 
 static void pagevec_lru_move_fn(struct pagevec *pvec,
-	void (*move_fn)(struct page *page, struct lruvec *lruvec))
+	void (*move_fn)(struct page *page, struct lruvec *lruvec), bool add)
 {
 	int i;
 	struct pglist_data *pgdat = NULL;
@@ -221,8 +221,15 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 			spin_lock_irqsave(&pgdat->lru_lock, flags);
 		}
 
+		/* new page add to lru or page moving between lru */
+		if (!add && !TestClearPageLRU(page))
+			continue;
+
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		(*move_fn)(page, lruvec);
+
+		if (!add)
+			SetPageLRU(page);
 	}
 	if (pgdat)
 		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
@@ -259,7 +266,7 @@ void rotate_reclaimable_page(struct page *page)
 		local_lock_irqsave(&lru_rotate.lock, flags);
 		pvec = this_cpu_ptr(&lru_rotate.pvec);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
+			pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, false);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 }
@@ -325,7 +332,7 @@ static void activate_page_drain(int cpu)
 	struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
 
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, __activate_page);
+		pagevec_lru_move_fn(pvec, __activate_page, false);
 }
 
 static bool need_activate_page_drain(int cpu)
@@ -343,7 +350,7 @@ void activate_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.activate_page);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, __activate_page);
+			pagevec_lru_move_fn(pvec, __activate_page, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -620,21 +627,21 @@ void lru_add_drain_cpu(int cpu)
 
 		/* No harm done if a racing interrupt already did this */
 		local_lock_irqsave(&lru_rotate.lock, flags);
-		pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
+		pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, false);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
+		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, false);
 
 	pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_deactivate_fn);
+		pagevec_lru_move_fn(pvec, lru_deactivate_fn, false);
 
 	pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu);
 	if (pagevec_count(pvec))
-		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
+		pagevec_lru_move_fn(pvec, lru_lazyfree_fn, false);
 
 	activate_page_drain(cpu);
 }
@@ -663,7 +670,7 @@ void deactivate_file_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
 
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
+			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -685,7 +692,7 @@ void deactivate_page(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_deactivate_fn);
+			pagevec_lru_move_fn(pvec, lru_deactivate_fn, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -707,7 +714,7 @@ void mark_page_lazyfree(struct page *page)
 		pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
-			pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
+			pagevec_lru_move_fn(pvec, lru_lazyfree_fn, false);
 		local_unlock(&lru_pvecs.lock);
 	}
 }
@@ -975,7 +982,7 @@ 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);
+	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, true);
 }
 
 /**
-- 
1.8.3.1



  parent reply	other threads:[~2020-06-19  8:34 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-19  8:33 [PATCH v13 00/18] per memcg lru lock Alex Shi
2020-06-19  8:33 ` [PATCH v13 01/18] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-06-19  8:33 ` [PATCH v13 02/18] mm/page_idle: no unlikely double check for idle page counting Alex Shi
2020-06-19  8:33 ` [PATCH v13 03/18] mm/compaction: correct the comments of compact_defer_shift Alex Shi
2020-06-19  8:33 ` [PATCH v13 04/18] mm/compaction: rename compact_deferred as compact_should_defer Alex Shi
2020-06-19  8:33 ` [PATCH v13 05/18] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-06-19  8:33 ` [PATCH v13 06/18] mm/thp: clean up lru_add_page_tail Alex Shi
2020-06-19  8:33 ` [PATCH v13 07/18] mm/thp: narrow lru locking Alex Shi
2020-06-19  8:33 ` [PATCH v13 08/18] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-06-19  8:33 ` [PATCH v13 09/18] mm/swap: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-06-19  8:33 ` [PATCH v13 10/18] mm/lru: introduce TestClearPageLRU Alex Shi
2020-06-19  8:33 ` [PATCH v13 11/18] mm/compaction: do page isolation first in compaction Alex Shi
2020-06-19  8:33 ` [PATCH v13 12/18] mm/mlock: reorder isolation sequence during munlock Alex Shi
2020-06-19  8:33 ` Alex Shi [this message]
2020-06-19  8:33 ` [PATCH v13 14/18] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-06-19  8:33 ` [PATCH v13 15/18] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-06-19  8:33 ` [PATCH v13 16/18] mm/vmscan: use relock for move_pages_to_lru Alex Shi
2020-06-19  8:33 ` [PATCH v13 17/18] mm/pgdat: remove pgdat lru_lock Alex Shi
2020-06-19  8:33 ` [PATCH v13 18/18] mm/lru: revise the comments of lru_lock Alex Shi
2020-06-20 23:08 ` [PATCH v13 00/18] per memcg lru lock Andrew Morton
2020-06-21 15:44   ` 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=1592555636-115095-14-git-send-email-alex.shi@linux.alibaba.com \
    --to=alex.shi@linux.alibaba.com \
    --cc=akpm@linux-foundation.org \
    --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=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@intel.com \
    --cc=mgorman@techsingularity.net \
    --cc=richard.weiyang@gmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).