| 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
| ||
|
Message-Id: <20250415024532.26632-9-songmuchun@bytedance.com>
Date: Tue, 15 Apr 2025 10:45:12 +0800
From: Muchun Song <songmuchun@...edance.com>
To: hannes@...xchg.org,
mhocko@...nel.org,
roman.gushchin@...ux.dev,
shakeel.butt@...ux.dev,
muchun.song@...ux.dev,
akpm@...ux-foundation.org,
david@...morbit.com,
zhengqi.arch@...edance.com,
yosry.ahmed@...ux.dev,
nphamcs@...il.com,
chengming.zhou@...ux.dev
Cc: linux-kernel@...r.kernel.org,
cgroups@...r.kernel.org,
linux-mm@...ck.org,
hamzamahfooz@...ux.microsoft.com,
apais@...ux.microsoft.com,
Muchun Song <songmuchun@...edance.com>
Subject: [PATCH RFC 08/28] mm: vmscan: refactor move_folios_to_lru()
In a subsequent patch, we'll reparent the LRU folios. The folios that are
moved to the appropriate LRU list can undergo reparenting during the
move_folios_to_lru() process. Hence, it's incorrect for the caller to hold
a lruvec lock. Instead, we should utilize the more general interface of
folio_lruvec_relock_irq() to obtain the correct lruvec lock.
This patch involves only code refactoring and doesn't introduce any
functional changes.
Signed-off-by: Muchun Song <songmuchun@...edance.com>
---
mm/vmscan.c | 51 +++++++++++++++++++++++++--------------------------
1 file changed, 25 insertions(+), 26 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a76b3cee043d..eac5e6e70660 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1901,24 +1901,27 @@ static bool too_many_isolated(struct pglist_data *pgdat, int file,
/*
* move_folios_to_lru() moves folios from private @list to appropriate LRU list.
*
- * Returns the number of pages moved to the given lruvec.
+ * Returns the number of pages moved to the appropriate lruvec.
+ *
+ * Note: The caller must not hold any lruvec lock.
*/
-static unsigned int move_folios_to_lru(struct lruvec *lruvec,
- struct list_head *list)
+static unsigned int move_folios_to_lru(struct list_head *list)
{
int nr_pages, nr_moved = 0;
+ struct lruvec *lruvec = NULL;
struct folio_batch free_folios;
folio_batch_init(&free_folios);
while (!list_empty(list)) {
struct folio *folio = lru_to_folio(list);
+ lruvec = folio_lruvec_relock_irq(folio, lruvec);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
list_del(&folio->lru);
if (unlikely(!folio_evictable(folio))) {
- spin_unlock_irq(&lruvec->lru_lock);
+ lruvec_unlock_irq(lruvec);
folio_putback_lru(folio);
- spin_lock_irq(&lruvec->lru_lock);
+ lruvec = NULL;
continue;
}
@@ -1940,19 +1943,15 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
folio_unqueue_deferred_split(folio);
if (folio_batch_add(&free_folios, folio) == 0) {
- spin_unlock_irq(&lruvec->lru_lock);
+ lruvec_unlock_irq(lruvec);
mem_cgroup_uncharge_folios(&free_folios);
free_unref_folios(&free_folios);
- spin_lock_irq(&lruvec->lru_lock);
+ lruvec = NULL;
}
continue;
}
- /*
- * All pages were isolated from the same lruvec (and isolation
- * inhibits memcg migration).
- */
VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
lruvec_add_folio(lruvec, folio);
nr_pages = folio_nr_pages(folio);
@@ -1961,11 +1960,12 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
workingset_age_nonresident(lruvec, nr_pages);
}
+ if (lruvec)
+ lruvec_unlock_irq(lruvec);
+
if (free_folios.nr) {
- spin_unlock_irq(&lruvec->lru_lock);
mem_cgroup_uncharge_folios(&free_folios);
free_unref_folios(&free_folios);
- spin_lock_irq(&lruvec->lru_lock);
}
return nr_moved;
@@ -2033,9 +2033,9 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false);
- spin_lock_irq(&lruvec->lru_lock);
- move_folios_to_lru(lruvec, &folio_list);
+ move_folios_to_lru(&folio_list);
+ local_irq_disable();
__mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc),
stat.nr_demoted);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
@@ -2044,7 +2044,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
__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, nr_scanned - nr_reclaimed);
@@ -2183,16 +2183,15 @@ static void shrink_active_list(unsigned long nr_to_scan,
/*
* Move folios back to the lru list.
*/
- spin_lock_irq(&lruvec->lru_lock);
-
- nr_activate = move_folios_to_lru(lruvec, &l_active);
- nr_deactivate = move_folios_to_lru(lruvec, &l_inactive);
+ nr_activate = move_folios_to_lru(&l_active);
+ nr_deactivate = move_folios_to_lru(&l_inactive);
+ 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();
if (nr_rotated)
lru_note_cost(lruvec, file, 0, nr_rotated);
@@ -4723,14 +4722,15 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active));
}
- spin_lock_irq(&lruvec->lru_lock);
-
- move_folios_to_lru(lruvec, &list);
+ move_folios_to_lru(&list);
+ local_irq_disable();
walk = current->reclaim_state->mm_walk;
if (walk && walk->batched) {
walk->lruvec = lruvec;
+ spin_lock(&lruvec->lru_lock);
reset_batch_size(walk);
+ spin_unlock(&lruvec->lru_lock);
}
__mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc),
@@ -4741,8 +4741,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
__count_vm_events(item, reclaimed);
__count_memcg_events(memcg, item, reclaimed);
__count_vm_events(PGSTEAL_ANON + type, reclaimed);
-
- spin_unlock_irq(&lruvec->lru_lock);
+ local_irq_enable();
list_splice_init(&clean, &list);
--
2.20.1
Powered by blists - more mailing lists