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
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Andrey Ryabinin <aryabinin@virtuozzo.com>
Subject: [PATCH v21 18/19] mm/lru: introduce the relock_page_lruvec function
Date: Thu, 5 Nov 2020 16:55:48 +0800 [thread overview]
Message-ID: <1604566549-62481-19-git-send-email-alex.shi@linux.alibaba.com> (raw)
In-Reply-To: <1604566549-62481-1-git-send-email-alex.shi@linux.alibaba.com>
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Use this new function to replace repeated same code, no func change.
When testing for relock we can avoid the need for RCU locking if we simply
compare the page pgdat and memcg pointers versus those that the lruvec is
holding. By doing this we can avoid the extra pointer walks and accesses of
the memory cgroup.
In addition we can avoid the checks entirely if lruvec is currently NULL.
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.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: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: cgroups@vger.kernel.org
Cc: linux-mm@kvack.org
---
include/linux/memcontrol.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++
mm/mlock.c | 11 +---------
mm/swap.c | 33 +++++++----------------------
mm/vmscan.c | 12 ++---------
4 files changed, 62 insertions(+), 46 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6ecb08ff4ad1..ba4050154fea 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -660,6 +660,22 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
+static inline bool lruvec_holds_page_lru_lock(struct page *page,
+ struct lruvec *lruvec)
+{
+ pg_data_t *pgdat = page_pgdat(page);
+ const struct mem_cgroup *memcg;
+ struct mem_cgroup_per_node *mz;
+
+ if (mem_cgroup_disabled())
+ return lruvec == &pgdat->__lruvec;
+
+ mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+ memcg = page->mem_cgroup ? : root_mem_cgroup;
+
+ return lruvec->pgdat == pgdat && mz->memcg == memcg;
+}
+
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
@@ -1221,6 +1237,14 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
return &pgdat->__lruvec;
}
+static inline bool lruvec_holds_page_lru_lock(struct page *page,
+ struct lruvec *lruvec)
+{
+ pg_data_t *pgdat = page_pgdat(page);
+
+ return lruvec == &pgdat->__lruvec;
+}
+
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
return NULL;
@@ -1663,6 +1687,34 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
spin_unlock_irqrestore(&lruvec->lru_lock, flags);
}
+/* Don't lock again iff page's lruvec locked */
+static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
+ struct lruvec *locked_lruvec)
+{
+ if (locked_lruvec) {
+ if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+ return locked_lruvec;
+
+ unlock_page_lruvec_irq(locked_lruvec);
+ }
+
+ return lock_page_lruvec_irq(page);
+}
+
+/* Don't lock again iff page's lruvec locked */
+static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
+ struct lruvec *locked_lruvec, unsigned long *flags)
+{
+ if (locked_lruvec) {
+ if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+ return locked_lruvec;
+
+ unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
+ }
+
+ return lock_page_lruvec_irqsave(page, flags);
+}
+
#ifdef CONFIG_CGROUP_WRITEBACK
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
diff --git a/mm/mlock.c b/mm/mlock.c
index ab164a675c25..55b3b3672977 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -277,16 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
* so we can spare the get_page() here.
*/
if (TestClearPageLRU(page)) {
- 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 = relock_page_lruvec_irq(page, lruvec);
del_page_from_lru_list(page, lruvec,
page_lru(page));
continue;
diff --git a/mm/swap.c b/mm/swap.c
index ed033f7c4f2d..c593ba596dea 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -210,19 +210,12 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
- struct lruvec *new_lruvec;
/* block memcg migration during page moving between lru */
if (!TestClearPageLRU(page))
continue;
- new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
- if (lruvec != new_lruvec) {
- if (lruvec)
- unlock_page_lruvec_irqrestore(lruvec, flags);
- lruvec = lock_page_lruvec_irqsave(page, &flags);
- }
-
+ lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
(*move_fn)(page, lruvec);
SetPageLRU(page);
@@ -918,17 +911,12 @@ void release_pages(struct page **pages, int nr)
}
if (PageLRU(page)) {
- struct lruvec *new_lruvec;
-
- new_lruvec = mem_cgroup_page_lruvec(page,
- page_pgdat(page));
- if (new_lruvec != lruvec) {
- if (lruvec)
- unlock_page_lruvec_irqrestore(lruvec,
- flags);
+ struct lruvec *prev_lruvec = lruvec;
+
+ lruvec = relock_page_lruvec_irqsave(page, lruvec,
+ &flags);
+ if (prev_lruvec != lruvec)
lock_batch = 0;
- lruvec = lock_page_lruvec_irqsave(page, &flags);
- }
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
@@ -1033,15 +1021,8 @@ void __pagevec_lru_add(struct pagevec *pvec)
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
- struct lruvec *new_lruvec;
-
- new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
- if (lruvec != new_lruvec) {
- if (lruvec)
- unlock_page_lruvec_irqrestore(lruvec, flags);
- lruvec = lock_page_lruvec_irqsave(page, &flags);
- }
+ lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
__pagevec_lru_add_fn(page, lruvec);
}
if (lruvec)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2953ddec88a0..3b09a39de8cd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1884,8 +1884,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
* All pages were isolated from the same lruvec (and isolation
* inhibits memcg migration).
*/
- VM_BUG_ON_PAGE(mem_cgroup_page_lruvec(page, page_pgdat(page))
- != lruvec, page);
+ VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page);
lru = page_lru(page);
nr_pages = thp_nr_pages(page);
@@ -4277,7 +4276,6 @@ void check_move_unevictable_pages(struct pagevec *pvec)
for (i = 0; i < pvec->nr; i++) {
struct page *page = pvec->pages[i];
int nr_pages;
- struct lruvec *new_lruvec;
if (PageTransTail(page))
continue;
@@ -4289,13 +4287,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
if (!TestClearPageLRU(page))
continue;
- new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
- if (lruvec != new_lruvec) {
- if (lruvec)
- unlock_page_lruvec_irq(lruvec);
- lruvec = lock_page_lruvec_irq(page);
- }
-
+ lruvec = relock_page_lruvec_irq(page, lruvec);
if (page_evictable(page) && PageUnevictable(page)) {
enum lru_list lru = page_lru_base_type(page);
--
1.8.3.1
next prev parent reply other threads:[~2020-11-05 8:57 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-05 8:55 [PATCH v21 00/19] per memcg lru lock Alex Shi
2020-11-05 8:55 ` [PATCH v21 01/19] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-11-05 8:55 ` [PATCH v21 02/19] mm/thp: use head for head page in lru_add_page_tail Alex Shi
2020-11-05 8:55 ` [PATCH v21 03/19] mm/thp: Simplify lru_add_page_tail() Alex Shi
2020-11-05 8:55 ` [PATCH v21 04/19] mm/thp: narrow lru locking Alex Shi
2020-11-05 8:55 ` [PATCH v21 05/19] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-11-11 12:36 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 06/19] mm/rmap: stop store reordering issue on page->mapping Alex Shi
2020-11-06 1:20 ` Alex Shi
2020-11-10 19:06 ` Johannes Weiner
2020-11-11 7:41 ` Hugh Dickins
2020-11-05 8:55 ` [PATCH v21 07/19] mm: page_idle_get_page() does not need lru_lock Alex Shi
2020-11-10 19:01 ` Johannes Weiner
2020-11-11 8:17 ` huang ying
2020-11-11 12:52 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 08/19] mm/memcg: add debug checking in lock_page_memcg Alex Shi
2020-11-05 8:55 ` [PATCH v21 09/19] mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn Alex Shi
2020-11-05 8:55 ` [PATCH v21 10/19] mm/lru: move lock into lru_note_cost Alex Shi
2020-11-05 8:55 ` [PATCH v21 11/19] mm/vmscan: remove lruvec reget in move_pages_to_lru Alex Shi
2020-11-05 8:55 ` [PATCH v21 12/19] mm/mlock: remove lru_lock on TestClearPageMlocked Alex Shi
2020-11-11 13:03 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 13/19] mm/mlock: remove __munlock_isolate_lru_page Alex Shi
2020-11-11 13:07 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 14/19] mm/lru: introduce TestClearPageLRU Alex Shi
2020-11-11 13:36 ` Vlastimil Babka
2020-11-12 2:03 ` Hugh Dickins
2020-11-12 11:24 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 15/19] mm/compaction: do page isolation first in compaction Alex Shi
2020-11-11 17:12 ` Vlastimil Babka
2020-11-12 2:28 ` Hugh Dickins
2020-11-12 3:35 ` Alex Shi
2020-11-12 11:25 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 16/19] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn Alex Shi
2020-11-11 18:00 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 17/19] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-11-05 13:43 ` Alex Shi
2020-11-06 7:48 ` Alex Shi
2020-11-10 18:54 ` Johannes Weiner
2020-11-11 17:46 ` Vlastimil Babka
2020-11-11 17:59 ` Vlastimil Babka
2020-11-12 12:19 ` Vlastimil Babka
2020-11-12 14:19 ` Alex Shi
2020-11-05 8:55 ` Alex Shi [this message]
2020-11-06 7:50 ` [PATCH v21 18/19] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-11-10 18:59 ` Johannes Weiner
2020-11-12 12:31 ` Vlastimil Babka
2020-11-05 8:55 ` [PATCH v21 19/19] mm/lru: revise the comments of lru_lock Alex Shi
2020-11-12 12:37 ` Vlastimil Babka
2020-11-10 12:14 ` [PATCH v21 00/19] per memcg lru lock Alex Shi
2020-11-16 3:45 ` Alex Shi
2020-12-15 0:47 ` Andrew Morton
2020-12-15 2:16 ` Hugh Dickins
2020-12-15 2:28 ` Andrew Morton
2021-01-05 19:30 ` Qian Cai
2021-01-05 19:42 ` Shakeel Butt
2021-01-05 20:11 ` Qian Cai
2021-01-05 21:35 ` Hugh Dickins
2021-01-05 22:01 ` Qian Cai
2021-01-06 3:10 ` Hugh Dickins
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=1604566549-62481-19-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=alexander.h.duyck@linux.intel.com \
--cc=aryabinin@virtuozzo.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=tglx@linutronix.de \
--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).