From: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
The per-CPU counter are modified with the non-atomic modifier. The
consistency is ensured by disabling interrupts for the update.
On non PREEMPT_RT configuration this works because acquiring a
spinlock_t typed lock with the _irq() suffix disables interrupts. On
PREEMPT_RT configurations the RMW operation can be interrupted.
Another problem is that mem_cgroup_swapout() expects to be invoked with
disabled interrupts because the caller has to acquire a spinlock_t which
is acquired with disabled interrupts. Since spinlock_t never disables
interrupts on PREEMPT_RT the interrupts are never disabled at this
point.
The code is never called from in_irq() context on PREEMPT_RT therefore
disabling preemption during the update is sufficient on PREEMPT_RT.
The sections which explicitly disable interrupts can remain on
PREEMPT_RT because the sections remain short and they don't involve
sleeping locks (memcg_check_events() is doing nothing on PREEMPT_RT).
Disable preemption during update of the per-CPU variables which do not
explicitly disable interrupts.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Acked-by: Roman Gushchin <guro@xxxxxx>
[do: backported to v5.15]
Signed-off-by: David Oberhollenzer <goliath@xxxxxxxxxxxx>
---
mm/memcontrol.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 48 insertions(+), 1 deletion(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6078d57aee0f..e566c34466a1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -654,6 +654,35 @@ static u64 flush_next_time;
#define FLUSH_TIME (2UL*HZ)
+/*
+ * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
+ * not rely on this as part of an acquired spinlock_t lock. These functions are
+ * never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
+ * is sufficient.
+ */
+static void memcg_stats_lock(void)
+{
+#ifdef CONFIG_PREEMPT_RT
+ preempt_disable();
+#else
+ VM_BUG_ON(!irqs_disabled());
+#endif
+}
+
+static void __memcg_stats_lock(void)
+{
+#ifdef CONFIG_PREEMPT_RT
+ preempt_disable();
+#endif
+}
+
+static void memcg_stats_unlock(void)
+{
+#ifdef CONFIG_PREEMPT_RT
+ preempt_enable();
+#endif
+}
+
static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
{
unsigned int x;
@@ -737,6 +766,20 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
memcg = pn->memcg;
+ /*
+ * The caller from rmap relay on disabled preemption becase they never
+ * update their counter from in-interrupt context. For these two
+ * counters we check that the update is never performed from an
+ * interrupt context while other caller need to have disabled interrupt.
+ */
+ __memcg_stats_lock();
+ if (IS_ENABLED(CONFIG_DEBUG_VM)) {
+ if (idx == NR_ANON_MAPPED || idx == NR_FILE_MAPPED)
+ WARN_ON_ONCE(!in_task());
+ else
+ WARN_ON_ONCE(!irqs_disabled());
+ }
+
/* Update memcg */
__this_cpu_add(memcg->vmstats_percpu->state[idx], val);
@@ -744,6 +787,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
memcg_rstat_updated(memcg, val);
+ memcg_stats_unlock();
}
/**
@@ -844,8 +888,10 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
if (mem_cgroup_disabled())
return;
+ memcg_stats_lock();
__this_cpu_add(memcg->vmstats_percpu->events[idx], count);
memcg_rstat_updated(memcg, count);
+ memcg_stats_unlock();
}
static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
@@ -7211,8 +7257,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
* important here to have the interrupts disabled because it is the
* only synchronisation we have for updating the per-CPU variables.
*/
- VM_BUG_ON(!irqs_disabled());
+ memcg_stats_lock();
mem_cgroup_charge_statistics(memcg, page, -nr_entries);
+ memcg_stats_unlock();
memcg_check_events(memcg, page);
css_put(&memcg->css);
--
2.37.1
