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, 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,
mhocko@suse.com, vdavydov.dev@gmail.com, shy828301@gmail.com
Subject: [PATCH v20 17/20] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn
Date: Thu, 29 Oct 2020 18:45:02 +0800 [thread overview]
Message-ID: <1603968305-8026-18-git-send-email-alex.shi@linux.alibaba.com> (raw)
In-Reply-To: <1603968305-8026-1-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 TestClearPageLRU to block isolate_lru_page(), that serializes
the memcg change. and then removing the PageLRU check in move_fn callee
as the consequence.
__pagevec_lru_add_fn() is different from the others, because the pages
it deals with are, by definition, not yet on the lru. TestClearPageLRU
is not needed and would not work, so __pagevec_lru_add() goes its own
way.
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
mm/swap.c | 44 +++++++++++++++++++++++++++++++++++---------
1 file changed, 35 insertions(+), 9 deletions(-)
diff --git a/mm/swap.c b/mm/swap.c
index 8798bd899db0..9e30f096309b 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -222,8 +222,14 @@ 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);
@@ -233,7 +239,7 @@ 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 = thp_nr_pages(page);
@@ -362,7 +368,8 @@ static 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
@@ -519,9 +526,6 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
bool active;
int nr_pages = thp_nr_pages(page);
- if (!PageLRU(page))
- return;
-
if (PageUnevictable(page))
return;
@@ -562,7 +566,7 @@ 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 = thp_nr_pages(page);
@@ -579,7 +583,7 @@ 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 = thp_nr_pages(page);
@@ -1018,7 +1022,29 @@ 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
next prev parent reply other threads:[~2020-10-29 10:46 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-29 10:44 [PATCH v20 00/20] per memcg lru lock Alex Shi
2020-10-29 10:44 ` [PATCH v20 01/20] mm/memcg: warning on !memcg after readahead page charged Alex Shi
2020-10-29 13:43 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 02/20] mm/memcg: bail early from swap accounting if memcg disabled Alex Shi
2020-10-29 13:46 ` Johannes Weiner
2020-10-30 2:27 ` Alex Shi
2020-10-30 14:04 ` Johannes Weiner
2020-10-31 1:13 ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 03/20] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-10-29 13:47 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 04/20] mm/thp: use head for head page in lru_add_page_tail Alex Shi
2020-10-29 13:50 ` Johannes Weiner
2020-10-30 2:46 ` Alex Shi
2020-10-30 13:52 ` Johannes Weiner
2020-10-31 1:14 ` Alex Shi
2020-11-02 16:03 ` Matthew Wilcox
2020-11-03 2:43 ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 05/20] mm/thp: Simplify lru_add_page_tail() Alex Shi
2020-10-29 14:00 ` Johannes Weiner
2020-10-30 2:48 ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 06/20] mm/thp: narrow lru locking Alex Shi
2020-10-29 10:44 ` [PATCH v20 07/20] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-11-02 14:20 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 08/20] mm: page_idle_get_page() does not need lru_lock Alex Shi
2020-11-02 14:41 ` Johannes Weiner
2020-11-02 14:49 ` Matthew Wilcox
2020-11-02 20:20 ` Johannes Weiner
2020-11-04 11:27 ` Alex Shi
2020-11-04 17:46 ` Johannes Weiner
2020-11-05 4:52 ` Alex Shi
2020-11-05 4:57 ` Matthew Wilcox
2020-11-05 5:03 ` Alex Shi
2020-11-05 15:36 ` Johannes Weiner
2020-11-05 15:43 ` Matthew Wilcox
2020-11-06 1:11 ` Alex Shi
2020-11-11 7:27 ` Hugh Dickins
2020-10-29 10:44 ` [PATCH v20 09/20] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-11-02 14:45 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 10/20] mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-11-02 14:48 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 11/20] mm/lru: move lock into lru_note_cost Alex Shi
2020-10-29 13:42 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 12/20] mm/vmscan: remove lruvec reget in move_pages_to_lru Alex Shi
2020-11-02 14:52 ` Johannes Weiner
2020-11-03 2:51 ` Alex Shi
2020-10-29 10:44 ` [PATCH v20 13/20] mm/mlock: remove lru_lock on TestClearPageMlocked Alex Shi
2020-11-02 14:55 ` Johannes Weiner
2020-10-29 10:44 ` [PATCH v20 14/20] mm/mlock: remove __munlock_isolate_lru_page Alex Shi
2020-11-02 14:56 ` Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 15/20] mm/lru: introduce TestClearPageLRU Alex Shi
2020-11-02 15:10 ` Johannes Weiner
2020-11-03 3:02 ` Alex Shi
2020-10-29 10:45 ` [PATCH v20 16/20] mm/compaction: do page isolation first in compaction Alex Shi
2020-11-02 15:18 ` Johannes Weiner
2020-10-29 10:45 ` Alex Shi [this message]
2020-11-02 15:20 ` [PATCH v20 17/20] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 18/20] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-10-30 2:49 ` Alex Shi
2020-11-02 20:41 ` Johannes Weiner
2020-11-03 4:58 ` Alex Shi
2020-10-29 10:45 ` [PATCH v20 19/20] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-11-02 20:44 ` Johannes Weiner
2020-10-29 10:45 ` [PATCH v20 20/20] mm/lru: revise the comments of lru_lock Alex Shi
2020-11-02 20:46 ` Johannes Weiner
2020-11-04 11:55 ` [PATCH v20 00/20] per memcg lru lock Alex Shi
2020-11-04 16:59 ` Johannes Weiner
2020-11-05 5:07 ` 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=1603968305-8026-18-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=mhocko@suse.com \
--cc=richard.weiyang@gmail.com \
--cc=rong.a.chen@intel.com \
--cc=shakeelb@google.com \
--cc=shy828301@gmail.com \
--cc=tj@kernel.org \
--cc=vdavydov.dev@gmail.com \
--cc=willy@infradead.org \
/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).