LKML Archive on 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, alexs@kernel.org,
	smuchun@gmail.com, zhengqi.arch@bytedance.com,
	Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v1 04/12] mm: vmscan: rework move_pages_to_lru()
Date: Sat, 14 Aug 2021 13:25:11 +0800	[thread overview]
Message-ID: <20210814052519.86679-5-songmuchun@bytedance.com> (raw)
In-Reply-To: <20210814052519.86679-1-songmuchun@bytedance.com>

In the later patch, we will reparent the LRU pages. The pages moved to
appropriate LRU list can be reparented during the process of the
move_pages_to_lru(). So holding a lruvec lock by the caller is wrong, we
should use the more general interface of folio_lruvec_relock_irq() to
acquire the correct lruvec lock.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/mm.h |  1 +
 mm/vmscan.c        | 49 +++++++++++++++++++++++++------------------------
 2 files changed, 26 insertions(+), 24 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ce8fc0fd6d6e..1e7f06bc5f2d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -227,6 +227,7 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 #define PAGE_ALIGNED(addr)	IS_ALIGNED((unsigned long)(addr), PAGE_SIZE)
 
 #define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
+#define lru_to_folio(head) (list_entry((head)->prev, struct folio, lru))
 
 void setup_initial_init_mm(void *start_code, void *end_code,
 			   void *end_data, void *brk);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 403a175a720f..8ce42858ad5d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2153,23 +2153,28 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
  * move_pages_to_lru() moves pages from private @list to appropriate LRU list.
  * On return, @list is reused as a list of pages to be freed by the caller.
  *
- * Returns the number of pages moved to the given lruvec.
+ * Returns the number of pages moved to the appropriate LRU list.
+ *
+ * Note: The caller must not hold any lruvec lock.
  */
-static unsigned int move_pages_to_lru(struct lruvec *lruvec,
-				      struct list_head *list)
+static unsigned int move_pages_to_lru(struct list_head *list)
 {
-	int nr_pages, nr_moved = 0;
+	int nr_moved = 0;
+	struct lruvec *lruvec = NULL;
 	LIST_HEAD(pages_to_free);
-	struct page *page;
 
 	while (!list_empty(list)) {
-		page = lru_to_page(list);
+		int nr_pages;
+		struct folio *folio = lru_to_folio(list);
+		struct page *page = &folio->page;
+
+		lruvec = folio_lruvec_relock_irq(folio, lruvec);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&lruvec->lru_lock);
+			unlock_page_lruvec_irq(lruvec);
 			putback_lru_page(page);
-			spin_lock_irq(&lruvec->lru_lock);
+			lruvec = NULL;
 			continue;
 		}
 
@@ -2190,20 +2195,16 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 			__clear_page_lru_flags(page);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&lruvec->lru_lock);
+				unlock_page_lruvec_irq(lruvec);
 				destroy_compound_page(page);
-				spin_lock_irq(&lruvec->lru_lock);
+				lruvec = NULL;
 			} else
 				list_add(&page->lru, &pages_to_free);
 
 			continue;
 		}
 
-		/*
-		 * All pages were isolated from the same lruvec (and isolation
-		 * inhibits memcg migration).
-		 */
-		VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page);
+		VM_BUG_ON_PAGE(!folio_matches_lruvec(folio, lruvec), page);
 		add_page_to_lru_list(page, lruvec);
 		nr_pages = thp_nr_pages(page);
 		nr_moved += nr_pages;
@@ -2211,6 +2212,8 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 			workingset_age_nonresident(lruvec, nr_pages);
 	}
 
+	if (lruvec)
+		unlock_page_lruvec_irq(lruvec);
 	/*
 	 * To save our caller's stack, now use input list for pages to free.
 	 */
@@ -2284,16 +2287,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
-	spin_lock_irq(&lruvec->lru_lock);
-	move_pages_to_lru(lruvec, &page_list);
+	move_pages_to_lru(&page_list);
 
+	local_irq_disable();
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
-	spin_unlock_irq(&lruvec->lru_lock);
+	local_irq_enable();
 
 	lru_note_cost(lruvec, file, stat.nr_pageout);
 	mem_cgroup_uncharge_list(&page_list);
@@ -2420,18 +2423,16 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&lruvec->lru_lock);
-
-	nr_activate = move_pages_to_lru(lruvec, &l_active);
-	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
+	nr_activate = move_pages_to_lru(&l_active);
+	nr_deactivate = move_pages_to_lru(&l_inactive);
 	/* Keep all free pages in l_active list */
 	list_splice(&l_inactive, &l_active);
 
+	local_irq_disable();
 	__count_vm_events(PGDEACTIVATE, nr_deactivate);
 	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
-
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&lruvec->lru_lock);
+	local_irq_enable();
 
 	mem_cgroup_uncharge_list(&l_active);
 	free_unref_page_list(&l_active);
-- 
2.11.0


  parent reply	other threads:[~2021-08-14  5:25 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-14  5:25 [PATCH v1 00/12] Use obj_cgroup APIs to charge the LRU pages Muchun Song
2021-08-14  5:25 ` [PATCH v1 01/12] mm: memcontrol: prepare objcg API for non-kmem usage Muchun Song
2021-08-14 22:23   ` kernel test robot
2021-08-18  3:01   ` Roman Gushchin
2021-08-20  6:44     ` Muchun Song
2021-08-14  5:25 ` [PATCH v1 02/12] mm: memcontrol: introduce compact_folio_lruvec_lock_irqsave Muchun Song
2021-08-14  5:25 ` [PATCH v1 03/12] mm: memcontrol: make lruvec lock safe when LRU pages are reparented Muchun Song
2021-08-18  3:18   ` Roman Gushchin
2021-08-18  4:28     ` Muchun Song
2021-08-18  4:47       ` Roman Gushchin
2021-08-14  5:25 ` Muchun Song [this message]
2021-08-14  5:25 ` [PATCH v1 05/12] mm: thp: introduce folio_split_queue_lock{_irqsave}() Muchun Song
2021-08-14  8:22   ` kernel test robot
2021-08-14 10:38   ` kernel test robot
2021-08-14  5:25 ` [PATCH v1 06/12] mm: thp: make split queue lock safe when LRU pages are reparented Muchun Song
2021-08-14  5:25 ` [PATCH v1 07/12] mm: memcontrol: make all the callers of {folio,page}_memcg() safe Muchun Song
2021-08-14  5:25 ` [PATCH v1 08/12] mm: memcontrol: introduce memcg_reparent_ops Muchun Song
2021-08-14  5:25 ` [PATCH v1 09/12] mm: memcontrol: use obj_cgroup APIs to charge the LRU pages Muchun Song
2021-08-14 14:08   ` kernel test robot
2021-08-14  5:25 ` [PATCH v1 10/12] mm: memcontrol: rename {un}lock_page_memcg() to {un}lock_page_objcg() Muchun Song
2021-08-14  5:25 ` [PATCH v1 11/12] mm: lru: add VM_BUG_ON_FOLIO to lru maintenance function Muchun Song
2021-08-14  5:25 ` [PATCH v1 12/12] mm: lru: use lruvec lock to serialize memcg changes 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=20210814052519.86679-5-songmuchun@bytedance.com \
    --to=songmuchun@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexs@kernel.org \
    --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=smuchun@gmail.com \
    --cc=vdavydov.dev@gmail.com \
    --cc=zhengqi.arch@bytedance.com \
    --subject='Re: [PATCH v1 04/12] mm: vmscan: rework move_pages_to_lru()' \
    /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

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).