All of lore.kernel.org
 help / color / mirror / Atom feed
From: Muchun Song <songmuchun@bytedance.com>
To: guro@fb.com, hannes@cmpxchg.org, mhocko@kernel.org,
	akpm@linux-foundation.org, shakeelb@google.com,
	vdavydov.dev@gmail.com
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	duanxiongchun@bytedance.com, fam.zheng@bytedance.com,
	bsingharora@gmail.com, shy828301@gmail.com,
	alex.shi@linux.alibaba.com,
	Muchun Song <songmuchun@bytedance.com>
Subject: [RFC PATCH v3 02/12] mm: memcontrol: introduce compact_lock_page_lruvec_irqsave
Date: Wed, 21 Apr 2021 15:00:49 +0800	[thread overview]
Message-ID: <20210421070059.69361-3-songmuchun@bytedance.com> (raw)
In-Reply-To: <20210421070059.69361-1-songmuchun@bytedance.com>

If we reuse the objcg APIs to charge LRU pages, the page_memcg()
can be changed when the LRU pages reparented. In this case, we need
to acquire the new lruvec lock.

    lruvec = mem_cgroup_page_lruvec(page);

    // The page is reparented.

    compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);

    // Acquired the wrong lruvec lock and need to retry.

But compact_lock_irqsave() only take lruvec lock as the parameter,
we cannot aware this change. If it can take the page as parameter
to acquire the lruvec lock. When the page memcg is changed, we can
use the page_memcg() detect whether we need to reacquire the new
lruvec lock. So compact_lock_irqsave() is not suitable for us.
Similar to lock_page_lruvec_irqsave(), introduce
compact_lock_page_lruvec_irqsave() to acquire the lruvec lock in
the compaction routine.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/compaction.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 1c500e697c88..082293587cc6 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -511,6 +511,29 @@ static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags,
 	return true;
 }
 
+static struct lruvec *
+compact_lock_page_lruvec_irqsave(struct page *page, unsigned long *flags,
+				 struct compact_control *cc)
+{
+	struct lruvec *lruvec;
+
+	lruvec = mem_cgroup_page_lruvec(page);
+
+	/* Track if the lock is contended in async mode */
+	if (cc->mode == MIGRATE_ASYNC && !cc->contended) {
+		if (spin_trylock_irqsave(&lruvec->lru_lock, *flags))
+			goto out;
+
+		cc->contended = true;
+	}
+
+	spin_lock_irqsave(&lruvec->lru_lock, *flags);
+out:
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
 /*
  * Compaction requires the taking of some coarse locks that are potentially
  * very heavily contended. The lock should be periodically unlocked to avoid
@@ -1001,11 +1024,9 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (locked)
 				unlock_page_lruvec_irqrestore(locked, flags);
 
-			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
+			lruvec = compact_lock_page_lruvec_irqsave(page, &flags, cc);
 			locked = lruvec;
 
-			lruvec_memcg_debug(lruvec, page);
-
 			/* Try get exclusive access under lock */
 			if (!skip_updated) {
 				skip_updated = true;
-- 
2.11.0


  parent reply	other threads:[~2021-04-21  7:01 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-21  7:00 [RFC PATCH v3 00/12] Use obj_cgroup APIs to charge the LRU pages Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 01/12] mm: memcontrol: move the objcg infrastructure out of CONFIG_MEMCG_KMEM Muchun Song
2021-05-25 16:27   ` Roman Gushchin
2021-05-26  2:46     ` [External] " Muchun Song
2021-05-26  2:46       ` Muchun Song
2021-04-21  7:00 ` Muchun Song [this message]
2021-05-25 17:21   ` [RFC PATCH v3 02/12] mm: memcontrol: introduce compact_lock_page_lruvec_irqsave Roman Gushchin
2021-05-26  2:49     ` [External] " Muchun Song
2021-05-26  2:49       ` Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 03/12] mm: memcontrol: make lruvec lock safe when the LRU pages reparented Muchun Song
2021-05-25 17:21   ` Roman Gushchin
2021-04-21  7:00 ` [RFC PATCH v3 04/12] mm: vmscan: rework move_pages_to_lru() Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 05/12] mm: thp: introduce lock/unlock_split_queue{_irqsave}() Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 06/12] mm: thp: make deferred split queue lock safe when the LRU pages reparented Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 07/12] mm: memcontrol: make all the callers of page_memcg() safe Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 08/12] mm: memcontrol: introduce memcg_reparent_ops Muchun Song
2021-05-25 17:46   ` Roman Gushchin
2021-05-26  3:01     ` [External] " Muchun Song
2021-05-26  3:01       ` Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 09/12] mm: memcontrol: use obj_cgroup APIs to charge the LRU pages Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 10/12] mm: memcontrol: rename {un}lock_page_memcg() to {un}lock_page_objcg() Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 11/12] mm: lru: add VM_BUG_ON_PAGE to lru maintenance function Muchun Song
2021-04-21  7:00 ` [RFC PATCH v3 12/12] mm: lru: use lruvec lock to serialize memcg changes Muchun Song
2021-05-18 13:49 ` [RFC PATCH v3 00/12] Use obj_cgroup APIs to charge the LRU pages Muchun Song
2021-05-18 13:49   ` Muchun Song
2021-05-18 14:17   ` Roman Gushchin
2021-05-20  3:20     ` [External] " Muchun Song
2021-05-20  3:20       ` Muchun Song
2021-05-25 17:35       ` Roman Gushchin
2021-05-26  2:41         ` Muchun Song
2021-05-26  2:41           ` Muchun Song

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=20210421070059.69361-3-songmuchun@bytedance.com \
    --to=songmuchun@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex.shi@linux.alibaba.com \
    --cc=bsingharora@gmail.com \
    --cc=duanxiongchun@bytedance.com \
    --cc=fam.zheng@bytedance.com \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shakeelb@google.com \
    --cc=shy828301@gmail.com \
    --cc=vdavydov.dev@gmail.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.