summaryrefslogtreecommitdiff
path: root/mm/mlock.c
diff options
context:
space:
mode:
authorAlex Shi <alex.shi@linux.alibaba.com>2020-12-15 23:34:29 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-12-16 01:48:04 +0300
commit6168d0da2b479ce25a4647de194045de1bdd1f1d (patch)
treed3a8a1d484d5ca32097347ca9b314483b6186fbd /mm/mlock.c
parentfc574c23558c63799dd99a9bb1d62e33708abaf5 (diff)
downloadlinux-6168d0da2b479ce25a4647de194045de1bdd1f1d.tar.xz
mm/lru: replace pgdat lru_lock with lruvec lock
This patch moves per node lru_lock into lruvec, thus bring a lru_lock for each of memcg per node. So on a large machine, each of memcg don't have to suffer from per node pgdat->lru_lock competition. They could go fast with their self lru_lock. After move memcg charge before lru inserting, page isolation could serialize page's memcg, then per memcg lruvec lock is stable and could replace per node lru lock. In isolate_migratepages_block(), compact_unlock_should_abort and lock_page_lruvec_irqsave are open coded to work with compact_control. Also add a debug func in locking which may give some clues if there are sth out of hands. Daniel Jordan's testing show 62% improvement on modified readtwice case on his 2P * 10 core * 2 HT broadwell box. https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/ Hugh Dickins helped on the patch polish, thanks! [alex.shi@linux.alibaba.com: fix comment typo] Link: https://lkml.kernel.org/r/5b085715-292a-4b43-50b3-d73dc90d1de5@linux.alibaba.com [alex.shi@linux.alibaba.com: use page_memcg()] Link: https://lkml.kernel.org/r/5a4c2b72-7ee8-2478-fc0e-85eb83aafec4@linux.alibaba.com Link: https://lkml.kernel.org/r/1604566549-62481-18-git-send-email-alex.shi@linux.alibaba.com Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Rong Chen <rong.a.chen@intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Alexander Duyck <alexander.duyck@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Jann Horn <jannh@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mika Penttilä <mika.penttila@nextfour.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richard.weiyang@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mlock.c')
-rw-r--r--mm/mlock.c22
1 files changed, 16 insertions, 6 deletions
diff --git a/mm/mlock.c b/mm/mlock.c
index 7b0e6334be6f..ab164a675c25 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -262,12 +262,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
int nr = pagevec_count(pvec);
int delta_munlocked = -nr;
struct pagevec pvec_putback;
+ struct lruvec *lruvec = NULL;
int pgrescued = 0;
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];
@@ -277,10 +277,16 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
* so we can spare the get_page() here.
*/
if (TestClearPageLRU(page)) {
- struct lruvec *lruvec;
+ struct lruvec *new_lruvec;
+
+ new_lruvec = mem_cgroup_page_lruvec(page,
+ page_pgdat(page));
+ if (new_lruvec != lruvec) {
+ if (lruvec)
+ unlock_page_lruvec_irq(lruvec);
+ lruvec = lock_page_lruvec_irq(page);
+ }
- lruvec = mem_cgroup_page_lruvec(page,
- page_pgdat(page));
del_page_from_lru_list(page, lruvec,
page_lru(page));
continue;
@@ -299,8 +305,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
}
- __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
- spin_unlock_irq(&zone->zone_pgdat->lru_lock);
+ if (lruvec) {
+ __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+ unlock_page_lruvec_irq(lruvec);
+ } else if (delta_munlocked) {
+ mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+ }
/* Now we can release pins of pages that we are not munlocking */
pagevec_release(&pvec_putback);