| 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: <20250513031316.2147548-5-shakeel.butt@linux.dev>
Date: Mon, 12 May 2025 20:13:13 -0700
From: Shakeel Butt <shakeel.butt@...ux.dev>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Muchun Song <muchun.song@...ux.dev>,
Vlastimil Babka <vbabka@...e.cz>,
Alexei Starovoitov <ast@...nel.org>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Harry Yoo <harry.yoo@...cle.com>,
Yosry Ahmed <yosry.ahmed@...ux.dev>,
bpf@...r.kernel.org,
linux-mm@...ck.org,
cgroups@...r.kernel.org,
linux-kernel@...r.kernel.org,
Meta kernel team <kernel-team@...a.com>
Subject: [RFC PATCH 4/7] memcg: make count_memcg_events re-entrant safe against irqs
Let's make count_memcg_events re-entrant safe against irqs. The only
thing needed is to convert the usage of __this_cpu_add() to
this_cpu_add(). In addition, with re-entrant safety, there is no need
to disable irqs. Also add warnings for in_nmi() as it is not safe
against nmi context.
Signed-off-by: Shakeel Butt <shakeel.butt@...ux.dev>
---
include/linux/memcontrol.h | 21 ++-------------------
mm/memcontrol-v1.c | 6 +++---
mm/memcontrol.c | 10 +++++++---
mm/swap.c | 8 ++++----
mm/vmscan.c | 14 +++++++-------
5 files changed, 23 insertions(+), 36 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 84e2cea7e666..31b9ab93d4e1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -952,19 +952,8 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
local_irq_restore(flags);
}
-void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
- unsigned long count);
-
-static inline void count_memcg_events(struct mem_cgroup *memcg,
- enum vm_event_item idx,
- unsigned long count)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __count_memcg_events(memcg, idx, count);
- local_irq_restore(flags);
-}
+void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
+ unsigned long count);
static inline void count_memcg_folio_events(struct folio *folio,
enum vm_event_item idx, unsigned long nr)
@@ -1438,12 +1427,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
}
static inline void count_memcg_events(struct mem_cgroup *memcg,
- enum vm_event_item idx,
- unsigned long count)
-{
-}
-
-static inline void __count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
unsigned long count)
{
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 3852f0713ad2..581c960ba19b 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -512,9 +512,9 @@ static void memcg1_charge_statistics(struct mem_cgroup *memcg, int nr_pages)
{
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
- __count_memcg_events(memcg, PGPGIN, 1);
+ count_memcg_events(memcg, PGPGIN, 1);
else {
- __count_memcg_events(memcg, PGPGOUT, 1);
+ count_memcg_events(memcg, PGPGOUT, 1);
nr_pages = -nr_pages; /* for event */
}
@@ -689,7 +689,7 @@ void memcg1_uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
unsigned long flags;
local_irq_save(flags);
- __count_memcg_events(memcg, PGPGOUT, pgpgout);
+ count_memcg_events(memcg, PGPGOUT, pgpgout);
__this_cpu_add(memcg->events_percpu->nr_page_events, nr_memory);
memcg1_check_events(memcg, nid);
local_irq_restore(flags);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 373d36cae069..9e7dc90cc460 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -829,12 +829,12 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
}
/**
- * __count_memcg_events - account VM events in a cgroup
+ * count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
* @idx: the event item
* @count: the number of events that occurred
*/
-void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
+void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
unsigned long count)
{
int i = memcg_events_index(idx);
@@ -846,9 +846,13 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
return;
+ if (WARN_ONCE(in_nmi(), "%s: called in nmi context for stat item %d\n",
+ __func__, idx))
+ return;
+
cpu = get_cpu();
- __this_cpu_add(memcg->vmstats_percpu->events[i], count);
+ this_cpu_add(memcg->vmstats_percpu->events[i], count);
memcg_rstat_updated(memcg, count, cpu);
trace_count_memcg_events(memcg, idx, count);
diff --git a/mm/swap.c b/mm/swap.c
index 77b2d5997873..4fc322f7111a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -309,7 +309,7 @@ static void lru_activate(struct lruvec *lruvec, struct folio *folio)
trace_mm_lru_activate(folio);
__count_vm_events(PGACTIVATE, nr_pages);
- __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages);
+ count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages);
}
#ifdef CONFIG_SMP
@@ -581,7 +581,7 @@ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio)
if (active) {
__count_vm_events(PGDEACTIVATE, nr_pages);
- __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
+ count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
nr_pages);
}
}
@@ -599,7 +599,7 @@ static void lru_deactivate(struct lruvec *lruvec, struct folio *folio)
lruvec_add_folio(lruvec, folio);
__count_vm_events(PGDEACTIVATE, nr_pages);
- __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages);
+ count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages);
}
static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
@@ -625,7 +625,7 @@ static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
lruvec_add_folio(lruvec, folio);
__count_vm_events(PGLAZYFREE, nr_pages);
- __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages);
+ count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages);
}
/*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5efd939d8c76..f86d264558f5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2028,7 +2028,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
item = PGSCAN_KSWAPD + reclaimer_offset(sc);
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_scanned);
- __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
+ count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
__count_vm_events(PGSCAN_ANON + file, nr_scanned);
spin_unlock_irq(&lruvec->lru_lock);
@@ -2048,7 +2048,7 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
item = PGSTEAL_KSWAPD + reclaimer_offset(sc);
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_reclaimed);
- __count_memcg_events(lruvec_memcg(lruvec), 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);
@@ -2138,7 +2138,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
if (!cgroup_reclaim(sc))
__count_vm_events(PGREFILL, nr_scanned);
- __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
+ count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
spin_unlock_irq(&lruvec->lru_lock);
@@ -2195,7 +2195,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
nr_deactivate = move_folios_to_lru(lruvec, &l_inactive);
__count_vm_events(PGDEACTIVATE, nr_deactivate);
- __count_memcg_events(lruvec_memcg(lruvec), 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);
@@ -4616,8 +4616,8 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
__count_vm_events(item, isolated);
__count_vm_events(PGREFILL, sorted);
}
- __count_memcg_events(memcg, item, isolated);
- __count_memcg_events(memcg, PGREFILL, sorted);
+ count_memcg_events(memcg, item, isolated);
+ count_memcg_events(memcg, PGREFILL, sorted);
__count_vm_events(PGSCAN_ANON + type, isolated);
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH,
scanned, skipped, isolated,
@@ -4769,7 +4769,7 @@ static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
item = PGSTEAL_KSWAPD + reclaimer_offset(sc);
if (!cgroup_reclaim(sc))
__count_vm_events(item, reclaimed);
- __count_memcg_events(memcg, item, reclaimed);
+ count_memcg_events(memcg, item, reclaimed);
__count_vm_events(PGSTEAL_ANON + type, reclaimed);
spin_unlock_irq(&lruvec->lru_lock);
--
2.47.1
Powered by blists - more mailing lists