linux-kernel - [PATCH v1 1/2] mm:vmscan: fix workingset eviction memcg issue

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240111122451.682-2-justinjiang@vivo.com>
Date: Thu, 11 Jan 2024 20:24:50 +0800
From: Zhiguo Jiang <justinjiang@...o.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
	David Hildenbrand <david@...hat.com>,
	Matthew Wilcox <willy@...radead.org>,
	Chris Li <chrisl@...nel.org>,
	Michal Hocko <mhocko@...e.com>,
	Kefeng Wang <wangkefeng.wang@...wei.com>,
	Dan Schatzberg <schatzberg.dan@...il.com>,
	Yosry Ahmed <yosryahmed@...gle.com>,
	Yue Zhao <findns94@...il.com>,
	Hugh Dickins <hughd@...gle.com>,
	Johannes Weiner <hannes@...xchg.org>,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org
Cc: opensource.kernel@...o.com,
	Zhiguo Jiang <justinjiang@...o.com>
Subject: [PATCH v1 1/2] mm:vmscan: fix workingset eviction memcg issue

The parameter of target_memcg is NULL in workingset_eviction(), and
the lruvec obtained by mem_cgroup_lruvec(target_memcg, pgdat) is always
root_mem_cgroup->lruvec, rather than the lruvec of mem_cgroup where
folio is actually located.

Fix target_memcg to the memcg obtained by folio_memcg(folio).

Signed-off-by: Zhiguo Jiang <justinjiang@...o.com>
---
 include/linux/swap.h |  2 +-
 mm/vmscan.c          | 11 +++++------
 mm/workingset.c      |  6 +++---
 3 files changed, 9 insertions(+), 10 deletions(-)
 mode change 100644 => 100755 include/linux/swap.h
 mode change 100644 => 100755 mm/vmscan.c
 mode change 100644 => 100755 mm/workingset.c

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 41e4b484bc34..4de61f158903
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -346,7 +346,7 @@ static inline swp_entry_t page_swap_entry(struct page *page)
 /* linux/mm/workingset.c */
 bool workingset_test_recent(void *shadow, bool file, bool *workingset);
 void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
-void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
+void *workingset_eviction(struct folio *folio);
 void workingset_refault(struct folio *folio, void *shadow);
 void workingset_activation(struct folio *folio);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 91e7d334a7ca..8a1fbdaca042
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -693,7 +693,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
  * gets returned with a refcount of 0.
  */
 static int __remove_mapping(struct address_space *mapping, struct folio *folio,
-			    bool reclaimed, struct mem_cgroup *target_memcg)
+			    bool reclaimed)
 {
 	int refcount;
 	void *shadow = NULL;
@@ -742,7 +742,7 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 		swp_entry_t swap = folio->swap;
 
 		if (reclaimed && !mapping_exiting(mapping))
-			shadow = workingset_eviction(folio, target_memcg);
+			shadow = workingset_eviction(folio);
 		__delete_from_swap_cache(folio, swap, shadow);
 		mem_cgroup_swapout(folio, swap);
 		xa_unlock_irq(&mapping->i_pages);
@@ -769,7 +769,7 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 		 */
 		if (reclaimed && folio_is_file_lru(folio) &&
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
-			shadow = workingset_eviction(folio, target_memcg);
+			shadow = workingset_eviction(folio);
 		__filemap_remove_folio(folio, shadow);
 		xa_unlock_irq(&mapping->i_pages);
 		if (mapping_shrinkable(mapping))
@@ -803,7 +803,7 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
  */
 long remove_mapping(struct address_space *mapping, struct folio *folio)
 {
-	if (__remove_mapping(mapping, folio, false, NULL)) {
+	if (__remove_mapping(mapping, folio, false)) {
 		/*
 		 * Unfreezing the refcount with 1 effectively
 		 * drops the pagecache ref for us without requiring another
@@ -1417,8 +1417,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 			 */
 			count_vm_events(PGLAZYFREED, nr_pages);
 			count_memcg_folio_events(folio, PGLAZYFREED, nr_pages);
-		} else if (!mapping || !__remove_mapping(mapping, folio, true,
-							 sc->target_mem_cgroup))
+		} else if (!mapping || !__remove_mapping(mapping, folio, true))
 			goto keep_locked;
 
 		folio_unlock(folio);
diff --git a/mm/workingset.c b/mm/workingset.c
index 226012974328..f29396d4bf75
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -372,15 +372,15 @@ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
 
 /**
  * workingset_eviction - note the eviction of a folio from memory
- * @target_memcg: the cgroup that is causing the reclaim
  * @folio: the folio being evicted
  *
  * Return: a shadow entry to be stored in @folio->mapping->i_pages in place
  * of the evicted @folio so that a later refault can be detected.
  */
-void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
+void *workingset_eviction(struct folio *folio)
 {
 	struct pglist_data *pgdat = folio_pgdat(folio);
+	struct mem_cgroup *memcg = folio_memcg(folio);
 	unsigned long eviction;
 	struct lruvec *lruvec;
 	int memcgid;
@@ -393,7 +393,7 @@ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
 	if (lru_gen_enabled())
 		return lru_gen_eviction(folio);
 
-	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	/* XXX: target_memcg can be NULL, go through lruvec */
 	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
 	eviction = atomic_long_read(&lruvec->nonresident_age);
-- 
2.39.0