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
Cc: Alex Shi <alex.shi@linux.alibaba.com>,
"Kirill A. Shutemov" <kirill@shutemov.name>
Subject: [PATCH v10 10/15] mm/mlock: ClearPageLRU before get lru lock in munlock page isolation
Date: Mon, 27 Apr 2020 15:02:59 +0800 [thread overview]
Message-ID: <1587970985-21629-11-git-send-email-alex.shi@linux.alibaba.com> (raw)
In-Reply-To: <1587970985-21629-1-git-send-email-alex.shi@linux.alibaba.com>
This patch move the lru_lock after TestClearPageLRU, then prevent other
isolation elsewhere.
__split_huge_page_refcount doesn't exist, but we still have to guard
PageMlocked in __split_huge_page_tail.
Also clean up __munlock_isolate_lru_page func, which isn't needed now.
[lkp@intel.com: found a sleeping function bug ... at mm/rmap.c:1861]
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
mm/mlock.c | 93 ++++++++++++++++++++++++++++++++++----------------------------
1 file changed, 51 insertions(+), 42 deletions(-)
diff --git a/mm/mlock.c b/mm/mlock.c
index 03b3a5d99ad7..b3ab1535f162 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -103,25 +103,6 @@ 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)
-{
- if (TestClearPageLRU(page)) {
- struct lruvec *lruvec;
-
- lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
- if (getpage)
- get_page(page);
- del_page_from_lru_list(page, lruvec, page_lru(page));
- return true;
- }
-
- return false;
-}
-
-/*
* Finish munlock after successful page isolation
*
* Page must be locked. This is a wrapper for try_to_munlock()
@@ -181,6 +162,7 @@ static void __munlock_isolation_failed(struct page *page)
unsigned int munlock_vma_page(struct page *page)
{
int nr_pages;
+ bool clearlru = false;
pg_data_t *pgdat = page_pgdat(page);
/* For try_to_munlock() and to serialize with page migration */
@@ -189,32 +171,42 @@ unsigned int munlock_vma_page(struct page *page)
VM_BUG_ON_PAGE(PageTail(page), page);
/*
- * Serialize with any parallel __split_huge_page_refcount() which
+ * Serialize with any parallel __split_huge_page_tail() which
* might otherwise copy PageMlocked to part of the tail pages before
* we clear it in the head page. It also stabilizes hpage_nr_pages().
*/
+ get_page(page);
+ clearlru = TestClearPageLRU(page);
spin_lock_irq(&pgdat->lru_lock);
if (!TestClearPageMlocked(page)) {
- /* Potentially, PTE-mapped THP: do not skip the rest PTEs */
- nr_pages = 1;
- goto unlock_out;
+ if (clearlru)
+ SetPageLRU(page);
+ /*
+ * Potentially, PTE-mapped THP: do not skip the rest PTEs
+ * Reuse lock as memory barrier for release_pages racing.
+ */
+ spin_unlock_irq(&pgdat->lru_lock);
+ put_page(page);
+ return 0;
}
nr_pages = hpage_nr_pages(page);
__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
- if (__munlock_isolate_lru_page(page, true)) {
+ if (clearlru) {
+ struct lruvec *lruvec;
+
+ lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+ del_page_from_lru_list(page, lruvec, page_lru(page));
spin_unlock_irq(&pgdat->lru_lock);
__munlock_isolated_page(page);
- goto out;
+ } else {
+ spin_unlock_irq(&pgdat->lru_lock);
+ put_page(page);
+ __munlock_isolation_failed(page);
}
- __munlock_isolation_failed(page);
-
-unlock_out:
- spin_unlock_irq(&pgdat->lru_lock);
-out:
return nr_pages - 1;
}
@@ -297,34 +289,51 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
pagevec_init(&pvec_putback);
/* Phase 1: page isolation */
- spin_lock_irq(&zone->zone_pgdat->lru_lock);
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
+ struct lruvec *lruvec;
+ bool clearlru;
- 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))
- continue;
- else
- __munlock_isolation_failed(page);
- } else {
+ clearlru = TestClearPageLRU(page);
+ spin_lock_irq(&zone->zone_pgdat->lru_lock);
+
+ if (!TestClearPageMlocked(page)) {
delta_munlocked++;
+ if (clearlru)
+ SetPageLRU(page);
+ goto putback;
+ }
+
+ if (!clearlru) {
+ __munlock_isolation_failed(page);
+ goto putback;
}
/*
+ * Isolate this page.
+ * We already have pin from follow_page_mask()
+ * so we can spare the get_page() here.
+ */
+ lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+ del_page_from_lru_list(page, lruvec, page_lru(page));
+ spin_unlock_irq(&zone->zone_pgdat->lru_lock);
+ continue;
+
+ /*
* We won't be munlocking this page in the next phase
* but we still need to release the follow_page_mask()
* pin. We cannot do it under lru_lock however. If it's
* the last pin, __page_cache_release() would deadlock.
*/
+putback:
+ spin_unlock_irq(&zone->zone_pgdat->lru_lock);
pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
}
+ /* tempary disable irq, will remove later */
+ local_irq_disable();
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
- spin_unlock_irq(&zone->zone_pgdat->lru_lock);
+ local_irq_enable();
/* Now we can release pins of pages that we are not munlocking */
pagevec_release(&pvec_putback);
--
1.8.3.1
next prev parent reply other threads:[~2020-04-27 7:04 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-27 7:02 [PATCH v10 00/15] per memcg lru lock Alex Shi
2020-04-27 7:02 ` [PATCH v10 01/15] mm/swap: use vmf clean up swapin funcs parameters Alex Shi
2020-04-27 7:02 ` [PATCH v10 02/15] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-04-27 7:02 ` [PATCH v10 03/15] mm/page_idle: no unlikely double check for idle page counting Alex Shi
2020-04-27 7:02 ` [PATCH v10 04/15] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-04-27 7:02 ` [PATCH v10 05/15] mm/thp: clean up lru_add_page_tail Alex Shi
2020-04-27 7:02 ` [PATCH v10 06/15] mm/thp: narrow lru locking Alex Shi
2020-04-27 7:02 ` [PATCH v10 07/15] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-04-27 7:02 ` [PATCH v10 08/15] mm/lru: introduce TestClearPageLRU Alex Shi
2020-04-27 7:02 ` [PATCH v10 09/15] mm/compaction: do page isolation first in compaction Alex Shi
2020-04-27 7:02 ` Alex Shi [this message]
2020-04-27 7:03 ` [PATCH v10 10/15] mm/mlock: isolation page before get lru lock in munlock Alex Shi
2020-04-27 7:03 ` [PATCH v10 11/15] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-04-27 7:03 ` [PATCH v10 12/15] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-04-27 7:03 ` [PATCH v10 13/15] mm/vmscan: use relock for move_pages_to_lru Alex Shi
2020-04-27 7:03 ` [PATCH v10 14/15] mm/pgdat: remove pgdat lru_lock Alex Shi
2020-04-27 7:03 ` [PATCH v10 15/15] mm/lru: revise the comments of lru_lock 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=1587970985-21629-11-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=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=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).