memcg: nmi safe memcg stats for specific archs

There are archs which have NMI but does not support this_cpu_* ops safely
in the nmi context but they support safe atomic ops in nmi context.  For
such archs, let's add infra to use atomic ops for the memcg stats which
can be updated in nmi.

At the moment, the memcg stats which get updated in the objcg charging
path are MEMCG_KMEM, NR_SLAB_RECLAIMABLE_B & NR_SLAB_UNRECLAIMABLE_B. 
Rather than adding support for all memcg stats to be nmi safe, let's just
add infra to make these three stats nmi safe which this patch is doing.

Link: https://lkml.kernel.org/r/20250519063142.111219-3-shakeel.butt@linux.dev
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 66 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f7848f73f41c..87b6688f124a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -113,6 +113,12 @@ struct mem_cgroup_per_node {
 	CACHELINE_PADDING(_pad2_);
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 	struct mem_cgroup_reclaim_iter	iter;
+
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* slab stats for nmi context */
+	atomic_t		slab_reclaimable;
+	atomic_t		slab_unreclaimable;
+#endif
 };
 
 struct mem_cgroup_threshold {
@@ -236,6 +242,10 @@ struct mem_cgroup {
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* MEMCG_KMEM for nmi context */
+	atomic_t		kmem_stat;
+#endif
 	/*
 	 * Hint of reclaim pressure for socket memroy management. Note
 	 * that this indicator should NOT be used in legacy cgroup mode
diff --git a/init/Kconfig b/init/Kconfig
index a2aa49cfb8bd..e9f47baa34e0 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1013,6 +1013,13 @@ config MEMCG_NMI_UNSAFE
 	depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !ARCH_HAVE_NMI_SAFE_CMPXCHG
 	default y
 
+config MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	bool
+	depends on MEMCG
+	depends on HAVE_NMI
+	depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && ARCH_HAVE_NMI_SAFE_CMPXCHG
+	default y
+
 config MEMCG_V1
 	bool "Legacy cgroup v1 memory controller"
 	depends on MEMCG
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2532cc2316ee..e8e8becbe926 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3966,6 +3966,53 @@ static void mem_cgroup_stat_aggregate(struct aggregate_control *ac)
 	}
 }
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent,
+			    int cpu)
+{
+	int nid;
+
+	if (atomic_read(&memcg->kmem_stat)) {
+		int kmem = atomic_xchg(&memcg->kmem_stat, 0);
+		int index = memcg_stats_index(MEMCG_KMEM);
+
+		memcg->vmstats->state[index] += kmem;
+		if (parent)
+			parent->vmstats->state_pending[index] += kmem;
+	}
+
+	for_each_node_state(nid, N_MEMORY) {
+		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
+		struct lruvec_stats *lstats = pn->lruvec_stats;
+		struct lruvec_stats *plstats = NULL;
+
+		if (parent)
+			plstats = parent->nodeinfo[nid]->lruvec_stats;
+
+		if (atomic_read(&pn->slab_reclaimable)) {
+			int slab = atomic_xchg(&pn->slab_reclaimable, 0);
+			int index = memcg_stats_index(NR_SLAB_RECLAIMABLE_B);
+
+			lstats->state[index] += slab;
+			if (plstats)
+				plstats->state_pending[index] += slab;
+		}
+		if (atomic_read(&pn->slab_unreclaimable)) {
+			int slab = atomic_xchg(&pn->slab_unreclaimable, 0);
+			int index = memcg_stats_index(NR_SLAB_UNRECLAIMABLE_B);
+
+			lstats->state[index] += slab;
+			if (plstats)
+				plstats->state_pending[index] += slab;
+		}
+	}
+}
+#else
+static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent,
+			    int cpu)
+{}
+#endif
+
 static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
@@ -3974,6 +4021,8 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 	struct aggregate_control ac;
 	int nid;
 
+	flush_nmi_stats(memcg, parent, cpu);
+
 	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
 
 	ac = (struct aggregate_control) {